Publications by Federico Bolelli

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.