Nuova ricerca

FEDERICO BOLELLI

Ricercatore Legge 240/10 - t.det.
Dipartimento di Ingegneria "Enzo Ferrari"

Home | Curriculum(pdf) | Didattica |


Pubblicazioni

2024 - A Graph-Based Multi-Scale Approach with Knowledge Distillation for WSI Classification [Articolo su rivista]
Bontempo, Gianpaolo; Bolelli, Federico; Porrello, Angelo; Calderara, Simone; Ficarra, Elisa
abstract

The usage of Multi Instance Learning (MIL) for classifying Whole Slide Images (WSIs) has recently increased. Due to their gigapixel size, the pixel-level annotation of such data is extremely expensive and time-consuming, practically unfeasible. For this reason, multiple automatic approaches have been raised in the last years to support clinical practice and diagnosis. Unfortunately, most state-of-the-art proposals apply attention mechanisms without considering the spatial instance correlation and usually work on a single-scale resolution. To leverage the full potential of pyramidal structured WSI, we propose a graph-based multi-scale MIL approach, DAS-MIL. Our model comprises three modules: i) a self-supervised feature extractor, ii) a graph-based architecture that precedes the MIL mechanism and aims at creating a more contextualized representation of the WSI structure by considering the mutual (spatial) instance correlation both inter and intra-scale. Finally, iii) a (self) distillation loss between resolutions is introduced to compensate for their informative gap and significantly improve the final prediction. The effectiveness of the proposed framework is demonstrated on two well-known datasets, where we outperform SOTA on WSI classification, gaining a +2.7% AUC and +3.7% accuracy on the popular Camelyon16 benchmark.

2024 - ClusterFix: A Cluster-Based Debiasing Approach without Protected-Group Supervision [Relazione in Atti di Convegno]
Capitani, Giacomo; Bolelli, Federico; Porrello, Angelo; Calderara, Simone; Ficarra, Elisa
abstract

The failures of Deep Networks can sometimes be ascribed to biases in the data or algorithmic choices. Existing debiasing approaches exploit prior knowledge to avoid unintended solutions; we acknowledge that, in real-world settings, it could be unfeasible to gather enough prior information to characterize the bias, or it could even raise ethical considerations. We hence propose a novel debiasing approach, termed ClusterFix, which does not require any external hint about the nature of biases. Such an approach alters the standard empirical risk minimization and introduces a per-example weight, encoding how critical and far from the majority an example is. Notably, the weights consider how difficult it is for the model to infer the correct pseudo-label, which is obtained in a self-supervised manner by dividing examples into multiple clusters. Extensive experiments show that the misclassification error incurred in identifying the correct cluster allows for identifying examples prone to bias-related issues. As a result, our approach outperforms existing methods on standard benchmarks for bias removal and fairness.

2023 - Annotating the Inferior Alveolar Canal: the Ultimate Tool [Relazione in Atti di Convegno]
Lumetti, Luca; Pipoli, Vittorio; Bolelli, Federico; Grana, Costantino
abstract

The Inferior Alveolar Nerve (IAN) is of main interest in the maxillofacial field, as an accurate localization of such nerve reduces the risks of injury during surgical procedures. Although recent literature has focused on developing novel deep learning techniques to produce accurate segmentation masks of the canal containing the IAN, there are still strong limitations due to the scarce amount of publicly available 3D maxillofacial datasets. In this paper, we present an improved version of a previously released tool, IACAT (Inferior Alveolar Canal Annotation Tool), today used by medical experts to produce 3D ground truth annotation. In addition, we release a new dataset, ToothFairy, which is part of the homonymous MICCAI2023 challenge hosted by the Grand-Challenge platform, as an extension of the previously released Maxillo dataset, which was the only publicly available. With ToothFairy, the number of annotations has been increased as well as the quality of existing data.

2023 - Artificial intelligence evaluation of confocal microscope prostate images: our preliminary experience [Articolo su rivista]
Bianchi, G.; Puliatti, S.; Rodriguez, N.; Micali, S.; Bertoni, L.; Reggiani Bonetti, L.; Caramaschi, S.; Bolelli, F.; Pinamonti, M.; Rozze, D.; Grana, C.
abstract

2023 - Buffer-MIL: Robust Multi-instance Learning with a Buffer-Based Approach [Relazione in Atti di Convegno]
Bontempo, G.; Lumetti, L.; Porrello, A.; Bolelli, F.; Calderara, S.; Ficarra, E.
abstract

Histopathological image analysis is a critical area of research with the potential to aid pathologists in faster and more accurate diagnoses. However, Whole-Slide Images (WSIs) present challenges for deep learning frameworks due to their large size and lack of pixel-level annotations. Multi-Instance Learning (MIL) is a popular approach that can be employed for handling WSIs, treating each slide as a bag composed of multiple patches or instances. In this work we propose Buffer-MIL, which aims at tackling the covariate shift and class imbalance characterizing most of the existing histopathological datasets. With this goal, a buffer containing the most representative instances of each disease-positive slide of the training set is incorporated into our model. An attention mechanism is then used to compare all the instances against the buffer, to find the most critical ones in a given slide. We evaluate Buffer-MIL on two publicly available WSI datasets, Camelyon16 and TCGA lung cancer, outperforming current state-of-the-art models by 2.2% of accuracy on Camelyon16.

2023 - DAS-MIL: Distilling Across Scales for MILClassification of Histological WSIs [Relazione in Atti di Convegno]
Bontempo, Gianpaolo; Porrello, Angelo; Bolelli, Federico; Calderara, Simone; Ficarra, Elisa
abstract

The adoption of Multi-Instance Learning (MIL) for classifying Whole-Slide Images (WSIs) has increased in recent years. Indeed, pixel-level annotation of gigapixel WSI is mostly unfeasible and time-consuming in practice. For this reason, MIL approaches have been profitably integrated with the most recent deep-learning solutions for WSI classification to support clinical practice and diagnosis. Nevertheless, the majority of such approaches overlook the multi-scale nature of the WSIs; the few existing hierarchical MIL proposals simply flatten the multi-scale representations by concatenation or summation of features vectors, neglecting the spatial structure of the WSI. Our work aims to unleash the full potential of pyramidal structured WSI; to do so, we propose a graph-based multi-scale MIL approach, termed DAS-MIL, that exploits message passing to let information flows across multiple scales. By means of a knowledge distillation schema, the alignment between the latent space representation at different resolutions is encouraged while preserving the diversity in the informative content. The effectiveness of the proposed framework is demonstrated on two well-known datasets, where we outperform SOTA on WSI classification, gaining a +1.9% AUC and +3.3¬curacy on the popular Camelyon16 benchmark.

2023 - Enhancing PFI Prediction with GDS-MIL: A Graph-based Dual Stream MIL Approach [Relazione in Atti di Convegno]
Bontempo, Gianpaolo; Bartolini, Nicola; Lovino, Marta; Bolelli, Federico; Virtanen, Anni; Ficarra, Elisa
abstract

Whole-Slide Images (WSI) are emerging as a promising resource for studying biological tissues, demonstrating a great potential in aiding cancer diagnosis and improving patient treatment. However, the manual pixel-level annotation of WSIs is extremely time-consuming and practically unfeasible in real-world scenarios. Multi-Instance Learning (MIL) have gained attention as a weakly supervised approach able to address lack of annotation tasks. MIL models aggregate patches (e.g., cropping of a WSI) into bag-level representations (e.g., WSI label), but neglect spatial information of the WSIs, crucial for histological analysis. In the High-Grade Serous Ovarian Cancer (HGSOC) context, spatial information is essential to predict a prognosis indicator (the Platinum-Free Interval, PFI) from WSIs. Such a prediction would bring highly valuable insights both for patient treatment and prognosis of chemotherapy resistance. Indeed, NeoAdjuvant ChemoTherapy (NACT) induces changes in tumor tissue morphology and composition, making the prediction of PFI from WSIs extremely challenging. In this paper, we propose GDS-MIL, a method that integrates a state-of-the-art MIL model with a Graph ATtention layer (GAT in short) to inject a local context into each instance before MIL aggregation. Our approach achieves a significant improvement in accuracy on the ``Ome18'' PFI dataset. In summary, this paper presents a novel solution for enhancing PFI prediction in HGSOC, with the potential of significantly improving treatment decisions and patient outcomes.

2023 - Inferior Alveolar Canal Automatic Detection with Deep Learning CNNs on CBCTs: Development of a Novel Model and Release of Open-Source Dataset and Algorithm [Articolo su rivista]
Di Bartolomeo, Mattia; Pellacani, Arrigo; Bolelli, Federico; Cipriano, Marco; Lumetti, Luca; Negrello, Sara; Allegretti, Stefano; Minafra, Paolo; Pollastri, Federico; Nocini, Riccardo; Colletti, Giacomo; Chiarini, Luigi; Grana, Costantino; Anesi, Alexandre
abstract

Introduction: The need of accurate three-dimensional data of anatomical structures is increasing in the surgical field. The development of convolutional neural networks (CNNs) has been helping to fill this gap by trying to provide efficient tools to clinicians. Nonetheless, the lack of a fully accessible datasets and open-source algorithms is slowing the improvements in this field. In this paper, we focus on the fully automatic segmentation of the Inferior Alveolar Canal (IAC), which is of immense interest in the dental and maxillo-facial surgeries. Conventionally, only a bidimensional annotation of the IAC is used in common clinical practice. A reliable convolutional neural network (CNNs) might be timesaving in daily practice and improve the quality of assistance. Materials and methods: Cone Beam Computed Tomography (CBCT) volumes obtained from a single radiological center using the same machine were gathered and annotated. The course of the IAC was annotated on the CBCT volumes. A secondary dataset with sparse annotations and a primary dataset with both dense and sparse annotations were generated. Three separate experiments were conducted in order to evaluate the CNN. The IoU and Dice scores of every experiment were recorded as the primary endpoint, while the time needed to achieve the annotation was assessed as the secondary end-point. Results: A total of 347 CBCT volumes were collected, then divided into primary and secondary datasets. Among the three experiments, an IoU score of 0.64 and a Dice score of 0.79 were obtained thanks to the pre-training of the CNN on the secondary dataset and the creation of a novel deep label propagation model, followed by proper training on the primary dataset. To the best of our knowledge, these results are the best ever published in the segmentation of the IAC. The datasets is publicly available and algorithm is published as open-source software. On average, the CNN could produce a 3D annotation of the IAC in 6.33 s, compared to 87.3 s needed by the radiology technician to produce a bidimensional annotation. Conclusions: To resume, the following achievements have been reached. A new state of the art in terms of Dice score was achieved, overcoming the threshold commonly considered of 0.75 for the use in clinical practice. The CNN could fully automatically produce accurate three-dimensional segmentation of the IAC in a rapid setting, compared to the bidimensional annotations commonly used in the clinical practice and generated in a time-consuming manner. We introduced our innovative deep label propagation method to optimize the performance of the CNN in the segmentation of the IAC. For the first time in this field, the datasets and the source codes used were publicly released, granting reproducibility of the experiments and helping in the improvement of IAC segmentation.

2022 - Applications of AI and HPC in the Health Domain [Capitolo/Saggio]
Oniga, D.; Cantalupo, B.; Tartaglione, E.; Perlo, D.; Grangetto, M.; Aldinucci, M.; Bolelli, F.; Pollastri, F.; Cancilla, M.; Canalini, L.; Grana, C.; Alcalde, C. M.; Cardillo, F. A.; Florea, M.
abstract

2022 - Automated Prediction of Kidney Failure in IgA Nephropathy with Deep Learning from Biopsy Images [Articolo su rivista]
Testa, F.; Fontana, F.; Pollastri, F.; Chester, J.; Leonelli, M.; Giaroni, F.; Gualtieri, F.; Bolelli, F.; Mancini, E.; Nordio, M.; Sacco, P.; Ligabue, G.; Giovanella, S.; Ferri, M.; Alfano, G.; Gesualdo, L.; Cimino, S.; Donati, G.; Grana, C.; Magistroni, R.
abstract

Background and objectives Digital pathology and artificial intelligence offer new opportunities for automatic histologic scoring. We applied a deep learning approach to IgA nephropathy biopsy images to develop an automatic histologic prognostic score, assessed against ground truth (kidney failure) among patients with IgA nephropathy who were treated over 39 years. We assessed noninferiority in comparison with the histologic component of currently validated predictive tools. We correlated additional histologic features with our deep learning predictive score to identify potential additional predictive features. Design, setting, participants, & measurements Training for deep learning was performed with randomly selected, digitalized, cortical Periodic acid–Schiff–stained sections images (363 kidney biopsy specimens) to develop our deep learning predictive score. We estimated noninferiority using the area under the receiver operating characteristic curve (AUC) in a randomly selected group (95 biopsy specimens) against the gold standard Oxford classification (MEST-C) scores used by the International IgA Nephropathy Prediction Tool and the clinical decision supporting system for estimating the risk of kidney failure in IgA nephropathy. We assessed additional potential predictive histologic features against a subset (20 kidney biopsy specimens) with the strongest and weakest deep learning predictive scores. Results We enrolled 442 patients; the 10-year kidney survival was 78%, and the study median follow-up was 6.7 years. Manual MEST-C showed no prognostic relationship for the endocapillary parameter only. The deep learning predictive score was not inferior to MEST-C applied using the International IgA Nephropathy Prediction Tool and the clinical decision supporting system (AUC of 0.84 versus 0.77 and 0.74, respectively) and confirmed a good correlation with the tubolointerstitial score (r50.41, P,0.01). We observed no correlations between the deep learning prognostic score and the mesangial, endocapillary, segmental sclerosis, and crescent parameters. Additional potential predictive histopathologic features incorporated by the deep learning predictive score included (1)inflammation within areas of interstitial fibrosis and tubular atrophy and (2) hyaline casts. Conclusions The deep learning approach was noninferior to manual histopathologic reporting and considered prognostic features not currently included in MEST-C assessment.

2022 - Connected Components Labeling on Bitonal Images [Relazione in Atti di Convegno]
Bolelli, Federico; Allegretti, Stefano; Grana, Costantino
abstract

2022 - Deep Segmentation of the Mandibular Canal: a New 3D Annotated Dataset of CBCT Volumes [Articolo su rivista]
Cipriano, Marco; Allegretti, Stefano; Bolelli, Federico; Di Bartolomeo, Mattia; Pollastri, Federico; Pellacani, Arrigo; Minafra, Paolo; Anesi, Alexandre; Grana, Costantino
abstract

Inferior Alveolar Nerve (IAN) canal detection has been the focus of multiple recent works in dentistry and maxillofacial imaging. Deep learning-based techniques have reached interesting results in this research field, although the small size of 3D maxillofacial datasets has strongly limited the performance of these algorithms. Researchers have been forced to build their own private datasets, thus precluding any opportunity for reproducing results and fairly comparing proposals. This work describes a novel, large, and publicly available mandibular Cone Beam Computed Tomography (CBCT) dataset, with 2D and 3D manual annotations, provided by expert clinicians. Leveraging this dataset and employing deep learning techniques, we are able to improve the state of the art on the 3D mandibular canal segmentation. The source code which allows to exactly reproduce all the reported experiments is released as an open-source project, along with this article.

2022 - Improving Segmentation of the Inferior Alveolar Nerve through Deep Label Propagation [Relazione in Atti di Convegno]
Cipriano, Marco; Allegretti, Stefano; Bolelli, Federico; Pollastri, Federico; Grana, Costantino
abstract

2022 - Long-Range 3D Self-Attention for MRI Prostate Segmentation [Relazione in Atti di Convegno]
Pollastri, Federico; Cipriano, Marco; Bolelli, Federico; Grana, Costantino
abstract

The problem of prostate segmentation from Magnetic Resonance Imaging (MRI) is an intense research area, due to the increased use of MRI in the diagnosis and treatment planning of prostate cancer. The lack of clear boundaries and huge variation of texture and shapes between patients makes the task very challenging, and the 3D nature of the data makes 2D segmentation algorithms suboptimal for the task. With this paper, we propose a novel architecture to fill the gap between the most recent advances in 2D computer vision and 3D semantic segmentation. In particular, the designed model retrieves multi-scale 3D features with dilated convolutions and makes use of a self-attention transformer to gain a global field of view. The proposed Long-Range 3D Self-Attention block allows the convolutional neural network to build significant features by merging together contextual information collected at various scales. Experimental results show that the proposed method improves the state-of-the-art segmentation accuracy on MRI prostate segmentation.

2022 - One DAG to Rule Them All [Articolo su rivista]
Bolelli, Federico; Allegretti, Stefano; Grana, Costantino
abstract

In this paper, we present novel strategies for optimizing the performance of many binary image processing algorithms. These strategies are collected in an open-source framework, GRAPHGEN, that is able to automatically generate optimized C++ source code implementing the desired optimizations. Simply starting from a set of rules, the algorithms introduced with the GRAPHGEN framework can generate decision trees with minimum average path-length, possibly considering image pattern frequencies, apply state prediction and code compression by the use of Directed Rooted Acyclic Graphs (DRAGs). Moreover, the proposed algorithmic solutions allow to combine different optimization techniques and significantly improve performance. Our proposal is showcased on three classical and widely employed algorithms (namely Connected Components Labeling, Thinning, and Contour Tracing). When compared to existing approaches —in 2D and 3D—, implementations using the generated optimal DRAGs perform significantly better than previous state-of-the-art algorithms, both on CPU and GPU.

2022 - Quest for Speed: The Epic Saga of Record-Breaking on OpenCV Connected Components Extraction [Relazione in Atti di Convegno]
Bolelli, Federico; Allegretti, Stefano; Grana, Costantino
abstract

Connected Components Labeling (CCL) represents an essential part of many Image Processing and Computer Vision pipelines. Given its relevance on the field, it has been part of most cutting-edge Computer Vision libraries. In this paper, all the algorithms included in the OpenCV during the years are reviewed, from sequential to parallel/GPU-based implementations. Our goal is to provide a better understanding of what has changed and why one algorithm should be preferred to another both in terms of memory usage and execution speed.

2021 - A Cone Beam Computed Tomography Annotation Tool for Automatic Detection of the Inferior Alveolar Nerve Canal [Relazione in Atti di Convegno]
Mercadante, Cristian; Cipriano, Marco; Bolelli, Federico; Pollastri, Federico; Di Bartolomeo, Mattia; Anesi, Alexandre; Grana, Costantino
abstract

In recent years, deep learning has been employed in several medical fields, achieving impressive results. Unfortunately, these algorithms require a huge amount of annotated data to ensure the correct learning process. When dealing with medical imaging, collecting and annotating data can be cumbersome and expensive. This is mainly related to the nature of data, often three-dimensional, and to the need for well-trained expert technicians. In maxillofacial imagery, recent works have been focused on the detection of the Inferior Alveolar Nerve (IAN), since its position is of great relevance for avoiding severe injuries during surgery operations such as third molar extraction or implant installation. In this work, we introduce a novel tool for analyzing and labeling the alveolar nerve from Cone Beam Computed Tomography (CBCT) 3D volumes.

2021 - A Deep Analysis on High Resolution Dermoscopic Image Classification [Articolo su rivista]
Pollastri, Federico; Parreño, Mario; Maroñas, Juan; Bolelli, Federico; Paredes, Roberto; Ramos, Daniel; Grana, Costantino
abstract

Convolutional Neural Networks (CNNs) have been broadly employed in dermoscopic image analysis, mainly as a result of the large amount of data gathered by the International Skin Imaging Collaboration (ISIC). Like in many other medical imaging domains, state-of-the-art methods take advantage of architectures developed for other tasks, frequently assuming full transferability between enormous sets of natural images (eg{} ImageNet) and dermoscopic images, which is not always the case. With this paper we provide a comprehensive analysis on the effectiveness of state-of-the-art deep learning techniques when applied to dermoscopic image analysis. In order to achieve this goal, we consider several CNNs architectures and analyze how their performance is affected by the size of the network, image resolution, data augmentation process, amount of available data, and model calibration. Moreover, taking advantage of the analysis performed, we design a novel ensemble method to further increase the classification accuracy. The proposed solution achieved the third best result in the 2019 official ISIC challenge, with an accuracy of 0.593.

2021 - A Heuristic-Based Decision Tree for Connected Components Labeling of 3D Volumes [Relazione in Atti di Convegno]
Söchting, Maximilian; Allegretti, Stefano; Bolelli, Federico; Grana, Costantino
abstract

Connected Components Labeling represents a fundamental step for many Computer Vision and Image Processing pipelines. Since the first appearance of the task in the sixties, many algorithmic solutions to optimize the computational load needed to label an image have been proposed. Among them, block-based scan approaches and decision trees revealed to be some of the most valuable strategies. However, due to the cost of the manual construction of optimal decision trees and the computational limitations of automatic strategies employed in the past, the application of blocks and decision trees has been restricted to small masks, and thus to 2D algorithms. With this paper we present a novel heuristic algorithm based on decision tree learning methodology, called Entropy Partitioning Decision Tree (EPDT). It allows to compute near-optimal decision trees for large scan masks. Experimental results demonstrate that algorithms based on the generated decision trees outperform state-of-the-art competitors.

2021 - A Heuristic-Based Decision Tree for Connected Components Labeling of 3D Volumes: Implementation and Reproducibility Notes [Relazione in Atti di Convegno]
Bolelli, Federico; Allegretti, Stefano; Grana, Costantino
abstract

This paper provides a detailed description of how to install, setup, and use the YACCLAB benchmark to test the algorithms published in "A Heuristic-Based Decision Tree for Connected Components Labeling of 3D Volumes," underlying how the parameters affect and influence experimental results.

2021 - Confidence Calibration for Deep Renal Biopsy Immunofluorescence Image Classification [Relazione in Atti di Convegno]
Pollastri, Federico; Maroñas, Juan; Bolelli, Federico; Ligabue, Giulia; Paredes, Roberto; Magistroni, Riccardo; Grana, Costantino
abstract

With this work we tackle immunofluorescence classification in renal biopsy, employing state-of-the-art Convolutional Neural Networks. In this setting, the aim of the probabilistic model is to assist an expert practitioner towards identifying the location pattern of antibody deposits within a glomerulus. Since modern neural networks often provide overconfident outputs, we stress the importance of having a reliable prediction, demonstrating that Temperature Scaling (TS), a recently introduced re-calibration technique, can be successfully applied to immunofluorescence classification in renal biopsy. Experimental results demonstrate that the designed model yields good accuracy on the specific task, and that TS is able to provide reliable probabilities, which are highly valuable for such a task given the low inter-rater agreement.

2021 - Fast Run-Based Connected Components Labeling for Bitonal Images [Relazione in Atti di Convegno]
Wonsang, Lee; Allegretti, Stefano; Bolelli, Federico; Grana, Costantino
abstract

Connected Components Labeling (CCL) is a fundamental task in binary image processing. Since its introduction in the sixties, several algorithmic strategies have been proposed to optimize its execution time. Most CCL algorithms in literature, including the current state-of-the-art, are designed to work on an input stored with 1-byte per pixel, even if the most memory-efficient format for a binary input only uses 1-bit per pixel. This paper deals with connected components labeling on 1-bit per pixel images, also known as 1bpp or bitonal images. An existing run-based CCL strategy is adapted to this input format, and optimized with Find First Set hardware operations and a smart management of provisional labels, giving birth to an efficient solution called Bit-Run Two Scan (BRTS). Then, BRTS is further optimized by merging pairs of consecutive lines through bitwise OR, and finding runs on this reduced data. This modification is the basis for another new algorithm on bitonal images, Bit-Merge-Run Scan (BMRS). When evaluated on a public benchmark, the two proposals outperform all the fastest competitors in literature, and therefore represent the new state-of-the-art for connected components labeling on bitonal images.

2021 - Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval [Relazione in Atti di Convegno]
Allegretti, Stefano; Bolelli, Federico; Pollastri, Federico; Longhitano, Sabrina; Pellacani, Giovanni; Grana, Costantino
abstract

In recent years, many attempts have been dedicated to the creation of automated devices that could assist both expert and beginner dermatologists towards fast and early diagnosis of skin lesions. Tasks such as skin lesion classification and segmentation have been extensively addressed with deep learning algorithms, which in some cases reach a diagnostic accuracy comparable to that of expert physicians. However, the general lack of interpretability and reliability severely hinders the ability of those approaches to actually support dermatologists in the diagnosis process. In this paper a novel skin image retrieval system is presented, which exploits features extracted by Convolutional Neural Networks to gather similar images from a publicly available dataset, in order to assist the diagnosis process of both expert and novice practitioners. In the proposed framework, ResNet-50 is initially trained for the classification of dermoscopic images; then, the feature extraction part is isolated, and an embedding network is built on top of it. The embedding learns an alternative representation, which allows to check image similarity by means of a distance measure. Experimental results reveal that the proposed method is able to select meaningful images, which can effectively boost the classification accuracy of human dermatologists.

2021 - The DeepHealth Toolkit: A Key European Free and Open-Source Software for Deep Learning and Computer Vision Ready to Exploit Heterogeneous HPC and Cloud Architectures [Capitolo/Saggio]
Aldinucci, Marco; Atienza, David; Bolelli, Federico; Caballero, Mónica; Colonnelli, Iacopo; Flich, José; Gómez, Jon A.; González, David; Grana, Costantino; Grangetto, Marco; Leo, Simone; López, Pedro; Oniga, Dana; Paredes, Roberto; Pireddu, Luca; Quiñones, Eduardo; Silva, Tatiana; Tartaglione, Enzo; Zapater, Marina
abstract

At the present time, we are immersed in the convergence between Big Data, High-Performance Computing and Artificial Intelligence. Technological progress in these three areas has accelerated in recent years, forcing different players like software companies and stakeholders to move quicky. The European Union is dedicating a lot of resources to maintain its relevant position in this scenario, funding projects to implement large-scale pilot testbeds that combine the latest advances in Artificial Intelligence, High-Performance Computing, Cloud and Big Data technologies. The DeepHealth project is an example focused on the health sector whose main outcome is the DeepHealth toolkit, a European unified framework that offers deep learning and computer vision capabilities, completely adapted to exploit underlying heterogeneous High-Performance Computing, Big Data and cloud architectures, and ready to be integrated into any software platform to facilitate the development and deployment of new applications for specific problems in any sector. This toolkit is intended to be one of the European contributions to the field of AI. This chapter introduces the toolkit with its main components and complementary tools; providing a clear view to facilitate and encourage its adoption and wide use by the European community of developers of AI-based solutions and data scientists working in the healthcare sector and others.

2021 - The DeepHealth Toolkit: A Unified Framework to Boost Biomedical Applications [Relazione in Atti di Convegno]
Cancilla, Michele; Canalini, Laura; Bolelli, Federico; Allegretti, Stefano; Carrión, Salvador; Paredes, Roberto; Ander Gómez, Jon; Leo, Simone; Enrico Piras, Marco; Pireddu, Luca; Badouh, Asaf; Marco-Sola, Santiago; Alvarez, Lluc; Moreto, Miquel; Grana, Costantino
abstract

Given the overwhelming impact of machine learning on the last decade, several libraries and frameworks have been developed in recent years to simplify the design and training of neural networks, providing array-based programming, automatic differentiation and user-friendly access to hardware accelerators. None of those tools, however, was designed with native and transparent support for Cloud Computing or heterogeneous High-Performance Computing (HPC). The DeepHealth Toolkit is an open source Deep Learning toolkit aimed at boosting productivity of data scientists operating in the medical field by providing a unified framework for the distributed training of neural networks, which is able to leverage hybrid HPC and cloud environments in a transparent way for the user. The toolkit is composed of a Computer Vision library, a Deep Learning library, and a front-end for non-expert users; all of the components are focused on the medical domain, but they are general purpose and can be applied to any other field. In this paper, the principles driving the design of the DeepHealth libraries are described, along with details about the implementation and the interaction between the different elements composing the toolkit. Finally, experiments on common benchmarks prove the efficiency of each separate component and of the DeepHealth Toolkit overall.

2020 - A Warp Speed Chain-Code Algorithm Based on Binary Decision Trees [Relazione in Atti di Convegno]
Allegretti, Stefano; Bolelli, Federico; Grana, Costantino
abstract

Contours extraction, also known as chain-code extraction, is one of the most common algorithms of binary image processing. Despite being the raster way the most cache friendly and, consequently, fast way to scan an image, most commonly used chain-code algorithms perform contours tracing, and therefore tend to be fairly inefficient. In this paper, we took a rarely used algorithm that extracts contours in raster scan, and optimized its execution time through template functions, look-up tables and decision trees, in order to reduce code branches and the average number of load/store operations required. The result is a very fast solution that outspeeds the state-of-the-art contours extraction algorithm implemented in OpenCV, on a collection of real case datasets. Contribution: This paper significantly improves the performance of existing chain-code algorithms, by smartly introducing decision trees to reduce code branches and the average number of load/store operations required.

2020 - Augmenting data with GANs to segment melanoma skin lesions [Articolo su rivista]
Pollastri, Federico; Bolelli, Federico; Paredes Palacios, Roberto; Grana, Costantino
abstract

This paper presents a novel strategy that employs Generative Adversarial Networks (GANs) to augment data in the skin lesion segmentation task, which is a fundamental first step in the automated melanoma detection process. The proposed framework generates both skin lesion images and their segmentation masks, making the data augmentation process extremely straightforward. In order to thoroughly analyze how the quality and diversity of synthetic images impact the efficiency of the method, we remodel two different well known GANs: a Deep Convolutional GAN (DCGAN) and a Laplacian GAN (LAPGAN). Experimental results reveal that, by introducing such kind of synthetic data into the training process, the overall accuracy of a state-of-the-art Convolutional/Deconvolutional Neural Network for melanoma skin lesion segmentation is increased.

2020 - Evaluation of the Classification Accuracy of the Kidney Biopsy Direct Immunofluorescence through Convolutional Neural Networks [Articolo su rivista]
Ligabue, Giulia; Pollastri, Federico; Fontana, Francesco; Leonelli, Marco; Furci, Luciana; Giovanella, Silvia; Alfano, Gaetano; Cappelli, Gianni; Testa, Francesca; Bolelli, Federico; Grana, Costantino; Magistroni, Riccardo
abstract

Background and objectives: Immunohistopathology is an essential technique in the diagnostic workflow of a kidney biopsy. Deep learning is an effective tool in the elaboration of medical imaging. We wanted to evaluate the role of a convolutional neural network as a support tool for kidney immunofluorescence reporting. Design, setting, participants, & measurements: High-magnification (×400) immunofluorescence images of kidney biopsies performed from the year 2001 to 2018 were collected. The report, adopted at the Division of Nephrology of the AOU Policlinico di Modena, describes the specimen in terms of “appearance,” “distribution,” “location,” and “intensity” of the glomerular deposits identified with fluorescent antibodies against IgG, IgA, IgM, C1q and C3 complement fractions, fibrinogen, and κ- and λ-light chains. The report was used as ground truth for the training of the convolutional neural networks. Results: In total, 12,259 immunofluorescence images of 2542 subjects undergoing kidney biopsy were collected. The test set analysis showed accuracy values between 0.79 (“irregular capillary wall” feature) and 0.94 (“fine granular” feature). The agreement test of the results obtained by the convolutional neural networks with respect to the ground truth showed similar values to three pathologists of our center. Convolutional neural networks were 117 times faster than human evaluators in analyzing 180 test images. A web platform, where it is possible to upload digitized images of immunofluorescence specimens, is available to evaluate the potential of our approach. Conclusions: The data showed that the accuracy of convolutional neural networks is comparable with that of pathologists experienced in the field.

2020 - Optimized Block-Based Algorithms to Label Connected Components on GPUs [Articolo su rivista]
Allegretti, Stefano; Bolelli, Federico; Grana, Costantino
abstract

Connected Components Labeling (CCL) is a crucial step of several image processing and computer vision pipelines. Many efficient sequential strategies exist, among which one of the most effective is the use of a block-based mask to drastically cut the number of memory accesses. In the last decade, aided by the fast development of Graphics Processing Units (GPUs), a lot of data parallel CCL algorithms have been proposed along with sequential ones. Applications that entirely run in GPU can benefit from parallel implementations of CCL that allow to avoid expensive memory transfers between host and device. In this paper, two new eight-connectivity CCL algorithms are proposed, namely Block-based Union Find (BUF) and Block-based Komura Equivalence (BKE). These algorithms optimize existing GPU solutions introducing a block-based approach. Extensions for three-dimensional datasets are also discussed. In order to produce a fair comparison with previously proposed alternatives, YACCLAB, a public CCL benchmarking framework, has been extended and made suitable for evaluating also GPU algorithms. Moreover, three-dimensional datasets have been added to its collection. Experimental results on real cases and synthetically generated datasets demonstrate the superiority of the new proposals with respect to state-of-the-art, both on 2D and 3D scenarios.

2020 - Spaghetti Labeling: Directed Acyclic Graphs for Block-Based Connected Components Labeling [Articolo su rivista]
Bolelli, Federico; Allegretti, Stefano; Baraldi, Lorenzo; Grana, Costantino
abstract

Connected Components Labeling is an essential step of many Image Processing and Computer Vision tasks. Since the first proposal of a labeling algorithm, which dates back to the sixties, many approaches have optimized the computational load needed to label an image. In particular, the use of decision forests and state prediction have recently appeared as valuable strategies to improve performance. However, due to the overhead of the manual construction of prediction states and the size of the resulting machine code, the application of these strategies has been restricted to small masks, thus ignoring the benefit of using a block-based approach. In this paper, we combine a block-based mask with state prediction and code compression: the resulting algorithm is modeled as a Directed Rooted Acyclic Graph with multiple entry points, which is automatically generated without manual intervention. When tested on synthetic and real datasets, in comparison with optimized implementations of state-of-the-art algorithms, the proposed approach shows superior performance, surpassing the results obtained by all compared approaches in all settings.

2020 - Towards Reliable Experiments on the Performance of Connected Components Labeling Algorithms [Articolo su rivista]
Bolelli, Federico; Cancilla, Michele; Baraldi, Lorenzo; Grana, Costantino
abstract

The problem of labeling the connected components of a binary image is well-defined and several proposals have been presented in the past. Since an exact solution to the problem exists, algorithms mainly differ on their execution speed. In this paper, we propose and describe YACCLAB, Yet Another Connected Components Labeling Benchmark. Together with a rich and varied dataset, YACCLAB contains an open source platform to test new proposals and to compare them with publicly available competitors. Textual and graphical outputs are automatically generated for many kinds of tests, which analyze the methods from different perspectives. An extensive set of experiments among state-of-the-art techniques is reported and discussed.

2019 - A Block-Based Union-Find Algorithm to Label Connected Components on GPUs [Relazione in Atti di Convegno]
Allegretti, Stefano; Bolelli, Federico; Cancilla, Michele; Grana, Costantino
abstract

In this paper, we introduce a novel GPU-based Connected Components Labeling algorithm: the Block-based Union Find. The proposed strategy significantly improves an existing GPU algorithm, taking advantage of a block-based approach. Experimental results on real cases and synthetically generated datasets demonstrate the superiority of the new proposal with respect to state-of-the-art.

2019 - Connected Components Labeling on DRAGs: Implementation and Reproducibility Notes [Relazione in Atti di Convegno]
Bolelli, Federico; Cancilla, Michele; Baraldi, Lorenzo; Grana, Costantino
abstract

In this paper we describe the algorithmic implementation details of "Connected Components Labeling on DRAGs'' (Directed Rooted Acyclic Graphs), studying the influence of parameters on the results. Moreover, a detailed description of how to install, setup and use YACCLAB (Yet Another Connected Components LAbeling Benchmark) to test DRAG is provided.

2019 - How does Connected Components Labeling with Decision Trees perform on GPUs? [Relazione in Atti di Convegno]
Allegretti, Stefano; Bolelli, Federico; Cancilla, Michele; Pollastri, Federico; Canalini, Laura; Grana, Costantino
abstract

In this paper the problem of Connected Components Labeling (CCL) in binary images using Graphic Processing Units (GPUs) is tackled by a different perspective. In the last decade, many novel algorithms have been released, specifically designed for GPUs. Because CCL literature concerning sequential algorithms is very rich, and includes many efficient solutions, designers of parallel algorithms were often inspired by techniques that had already proved successful in a sequential environment, such as the Union-Find paradigm for solving equivalences between provisional labels. However, the use of decision trees to minimize memory accesses, which is one of the main feature of the best performing sequential algorithms, was never taken into account when designing parallel CCL solutions. In fact, branches in the code tend to cause thread divergence, which usually leads to inefficiency. Anyway, this consideration does not necessarily apply to every possible scenario. Are we sure that the advantages of decision trees do not compensate for the cost of thread divergence? In order to answer this question, we chose three well-known sequential CCL algorithms, which employ decision trees as the cornerstone of their strategy, and we built a data-parallel version of each of them. Experimental tests on real case datasets show that, in most cases, these solutions outperform state-of-the-art algorithms, thus demonstrating the effectiveness of decision trees also in a parallel environment.

2019 - Improving the Performance of Thinning Algorithms with Directed Rooted Acyclic Graphs [Relazione in Atti di Convegno]
Bolelli, Federico; Grana, Costantino
abstract

In this paper we propose a strategy to optimize the performance of thinning algorithms. This solution is obtained by combining three proven strategies for binary images neighborhood exploration, namely modeling the problem with an optimal decision tree, reusing pixels from the previous step of the algorithm, and reducing the code footprint by means of Directed Rooted Acyclic Graphs. A complete and open-source benchmarking suite is also provided. Experimental results confirm that the proposed algorithms clearly outperform classical implementations.

2019 - M-VAD Names: a Dataset for Video Captioning with Naming [Articolo su rivista]
Pini, Stefano; Cornia, Marcella; Bolelli, Federico; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Current movie captioning architectures are not capable of mentioning characters with their proper name, replacing them with a generic "someone" tag. The lack of movie description datasets with characters' visual annotations surely plays a relevant role in this shortage. Recently, we proposed to extend the M-VAD dataset by introducing such information. In this paper, we present an improved version of the dataset, namely M-VAD Names, and its semi-automatic annotation procedure. The resulting dataset contains 63k visual tracks and 34k textual mentions, all associated with character identities. To showcase the features of the dataset and quantify the complexity of the naming task, we investigate multimodal architectures to replace the "someone" tags with proper character names in existing video captions. The evaluation is further extended by testing this application on videos outside of the M-VAD Names dataset.

2019 - Skin Lesion Segmentation Ensemble with Diverse Training Strategies [Relazione in Atti di Convegno]
Canalini, Laura; Pollastri, Federico; Bolelli, Federico; Cancilla, Michele; Allegretti, Stefano; Grana, Costantino
abstract

This paper presents a novel strategy to perform skin lesion segmentation from dermoscopic images. We design an effective segmentation pipeline, and explore several pre-training methods to initialize the features extractor, highlighting how different procedures lead the Convolutional Neural Network (CNN) to focus on different features. An encoder-decoder segmentation CNN is employed to take advantage of each pre-trained features extractor. Experimental results reveal how multiple initialization strategies can be exploited, by means of an ensemble method, to obtain state-of-the-art skin lesion segmentation accuracy.

2018 - A Hierarchical Quasi-Recurrent approach to Video Captioning [Relazione in Atti di Convegno]
Bolelli, Federico; Baraldi, Lorenzo; Grana, Costantino
abstract

Video captioning has picked up a considerable measure of attention thanks to the use of Recurrent Neural Networks, since they can be utilized to both encode the input video and to create the corresponding description. In this paper, we present a recurrent video encoding scheme which can find and exploit the layered structure of the video. Differently from the established encoder-decoder approach, in which a video is encoded continuously by a recurrent layer, we propose to employ Quasi-Recurrent Neural Networks, further extending their basic cell with a boundary detector which can recognize discontinuity points between frames or segments and likewise modify the temporal connections of the encoding layer. We assess our approach on a large scale dataset, the Montreal Video Annotation dataset. Experiments demonstrate that our approach can find suitable levels of representation of the input information, while reducing the computational requirements.

2018 - Connected Components Labeling on DRAGs [Relazione in Atti di Convegno]
Bolelli, Federico; Baraldi, Lorenzo; Cancilla, Michele; Grana, Costantino
abstract

In this paper we introduce a new Connected Components Labeling (CCL) algorithm which exploits a novel approach to model decision problems as Directed Acyclic Graphs with a root, which will be called Directed Rooted Acyclic Graphs (DRAGs). This structure supports the use of sets of equivalent actions, as required by CCL, and optimally leverages these equivalences to reduce the number of nodes (decision points). The advantage of this representation is that a DRAG, differently from decision trees usually exploited by the state-of-the-art algorithms, will contain only the minimum number of nodes required to reach the leaf corresponding to a set of condition values. This combines the benefits of using binary decision trees with a reduction of the machine code size. Experiments show a consistent improvement of the execution time when the model is applied to CCL.

2018 - Improving Skin Lesion Segmentation with Generative Adversarial Networks [Relazione in Atti di Convegno]
Pollastri, Federico; Bolelli, Federico; Paredes, Roberto; Grana, Costantino
abstract

This paper proposes a novel strategy that employs Generative Adversarial Networks (GANs) to augment data in the image segmentation field, and a Convolutional-Deconvolutional Neural Network (CDNN) to automatically generate lesion segmentation mask from dermoscopic images. Training the CDNN with our GAN generated data effectively improves the state-of-the-art.

2018 - Optimizing GPU-Based Connected Components Labeling Algorithms [Relazione in Atti di Convegno]
Allegretti, Stefano; Bolelli, Federico; Cancilla, Michele; Grana, Costantino
abstract

Connected Components Labeling (CCL) is a fundamental image processing technique, widely used in various application areas. Computational throughput of Graphical Processing Units (GPUs) makes them eligible for such a kind of algorithms. In the last decade, many approaches to compute CCL on GPUs have been proposed. Unfortunately, most of them have focused on 4-way connectivity neglecting the importance of 8-way connectivity. This paper aims to extend state-of-the-art GPU-based algorithms from 4 to 8-way connectivity and to improve them with additional optimizations. Experimental results revealed the effectiveness of the proposed strategies.

2018 - XDOCS: An Application to Index Historical Documents [Relazione in Atti di Convegno]
Bolelli, Federico; Borghi, Guido; Grana, Costantino
abstract

Dematerialization and digitalization of historical documents are key elements for their availability, preservation and diffusion. Unfortunately, the conversion from handwritten to digitalized documents presents several technical challenges. The XDOCS project is created with the main goal of making available and extending the usability of historical documents for a great variety of audience, like scholars, institutions and libraries. In this paper the core elements of XDOCS, i.e. page dewarping and word spotting technique, are described and two new applications, i.e. annotation/indexing and search tool, are presented.

2017 - Historical Handwritten Text Images Word Spotting through Sliding Window HOG Features [Relazione in Atti di Convegno]
Bolelli, Federico; Borghi, Guido; Grana, Costantino
abstract

In this paper we present an innovative technique to semi-automatically index handwritten word images. The proposed method is based on HOG descriptors and exploits Dynamic Time Warping technique to compare feature vectors elaborated from single handwritten words. Our strategy is applied to a new challenging dataset extracted from Italian civil registries of the XIX century. Experimental results, compared with some previously developed word spotting strategies, confirmed that our method outperforms competitors.

2017 - Indexing of Historical Document Images: Ad Hoc Dewarping Technique for Handwritten Text [Relazione in Atti di Convegno]
Bolelli, Federico
abstract

This work presents a research project, named XDOCS, aimed at extending to a much wider audience the possibility to access a variety of historical documents published on the web. The paper presents an overview of the indexing process that will be used to achieve the goal, focusing on the adopted dewarping technique. The proposed dewarping approach performs its task with the help of a transformation model which maps the projection of a curved surface to a 2D rectangular area. The novelty introduced with this work regards the possibility of applying dewarping to document images which contain both handwritten and typewritten text.

2017 - Two More Strategies to Speed Up Connected Components Labeling Algorithms [Relazione in Atti di Convegno]
Bolelli, Federico; Cancilla, Michele; Grana, Costantino
abstract

This paper presents two strategies that can be used to improve the speed of Connected Components Labeling algorithms. The first one operates on optimal decision trees considering image patterns occurrences, while the second one articulates how two scan algorithms can be parallelized using multi-threading. Experimental results demonstrate that the proposed methodologies reduce the total execution time of state-of-the-art two scan algorithms.

2016 - Optimized Connected Components Labeling with Pixel Prediction [Relazione in Atti di Convegno]
Grana, Costantino; Baraldi, Lorenzo; Bolelli, Federico
abstract

In this paper we propose a new paradigm for connected components labeling, which employs a general approach to minimize the number of memory accesses, by exploiting the information provided by already seen pixels, removing the need to check them again. The scan phase of our proposed algorithm is ruled by a forest of decision trees connected into a single graph. Every tree derives from a reduction of the complete optimal decision tree. Experimental results demonstrated that on low density images our method is slightly faster than the fastest conventional labeling algorithms.

2016 - YACCLAB - Yet Another Connected Components Labeling Benchmark [Relazione in Atti di Convegno]
Grana, Costantino; Bolelli, Federico; Baraldi, Lorenzo; Vezzani, Roberto
abstract

The problem of labeling the connected components (CCL) of a binary image is well-defined and several proposals have been presented in the past. Since an exact solution to the problem exists and should be mandatory provided as output, algorithms mainly differ on their execution speed. In this paper, we propose and describe YACCLAB, Yet Another Connected Components Labeling Benchmark. Together with a rich and varied dataset, YACCLAB contains an open source platform to test new proposals and to compare them with publicly available competitors. Textual and graphical outputs are automatically generated for three kinds of test, which analyze the methods from different perspectives. The fairness of the comparisons is guaranteed by running on the same system and over the same datasets. Examples of usage and the corresponding comparisons among state-of-the-art techniques are reported to confirm the potentiality of the benchmark.