Publications

QU-BraTS: MICCAI BraTS 2020 challenge on quantifying uncertainty in brain tumor segmentation — Analysis of ranking scores and benchmarking results

Abstract

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

Continue reading

Accurate and interpretable representations of environments with anticipatory learning classifier systems

Abstract

Anticipatory Learning Classifier Systems (ALCS) are rule- based machine learning algorithms that can simultaneously develop a complete representation of their environment and a decision policy based on this representation to solve their learning tasks. This paper intro- duces BEACS (Behavioral Enhanced Anticipatory Classifier System) in order to handle non-deterministic partially observable environments and to allow users to better understand the environmental representations issued by the system. BEACS is an ALCS that enhances and merges Probability-Enhanced Predictions and Behavioral Sequences approaches used in ALCS to handle such environments. The Probability-Enhanced Predictions consist in enabling the anticipation of several states, while the Behavioral Sequences permits the construction of sequences of ac- tions. The capabilities of BEACS have been studied on a thorough bench- mark of 23 mazes and the results show that BEACS can handle different kinds of non-determinism in partially observable environments, while describing completely and more accurately such environments. BEACS thus provides explanatory insights about created decision polices and environmental representations.

Continue reading

Current trends in blockchain implementations on the paradigm of public key infrastructure: A survey

Abstract

Since the emergence of the Bitcoin cryptocurrency, the blockchain technology has become the new Internet tool with which researchers claim to be able to solve any existing online problem. From immutable log ledger applications to authorisation systems applications, the current technological consensus implies that most of Internet problems could be effectively solved by deploying some form of blockchain environment. Regardless this ’consensus’, there are decentralised Internet-based applications on which blockchain technology can actually solve several problems and improve the functionality of these applications. The development of these new blockchain-based solutions is grouped into a new paradigm called Blockchain 3.0 and its concepts go far beyond the well-known cryptocurrencies. In this paper, we study the current trends in the application of blockchain on the paradigm of Public Key Infrastructures (PKI). In particular, we focus on how these current trends can guide the exploration of a fully Decentralised Identity System, with blockchain as be part of the core technology.

Continue reading

One-class ant-miner: Selection of majority class rules for binary rule-based classification

Abstract

In recent years, high-performance models have been introduced based on deep learning; however, these models do not have high interpretability to complement their high efficiency. Rule-based classifiers can be used to obtain explainable artificial intelligence. Rule-based classifiers use a labeled dataset to extract rules that express the relationships between inputs and expected outputs. Although many evolutionary and non-evolutionary algorithms have developed to solve this problem, we hypothesize that rule-based evolutionary algorithms such as the AntMiner family can provide good approximate solutions to problems that cannot be addressed efficiently using other techniques. This study proposes a novel supervised rule-based classifier for binary classification tasks and evaluates the extent to which algorithms in the AntMiner family can address this problem. First, we describe different versions of AntMiner. We then introduce the one-class AntMiner (OCAntMiner) algorithm, which can work with different imbalance ratios. Next, we evaluate these algorithms using specific synthetic datasets based on the AUPRC, AUROC, and MCC evaluation metrics and rank them based on these metrics. The results demonstrate that the OCAntMiner algorithm performs better than other versions of AntMiner in terms of the specified metrics.

Continue reading

Gradient vector fields of discrete morse functions and watershed-cuts

Abstract

Continue reading

Residual 3D U-net with localization for brain tumor segmentation

Abstract

Continue reading

AGAT: Building and evaluating binary partition trees for image segmentation

Abstract

AGAT is a Java library dedicated to the construction, handling and evaluation of binary partition trees, a hierarchical data structure providing multiscale partitioning of images and, more generally, of valued graphs. On the one hand, this library offers functionalities to build binary partition trees in the usual way, but also to define multifeature trees, a novel and richer paradigm of binary partition trees built from multiple images and/or several criteria. On the other hand, it also allows one to manipulate the binary partition trees, for instance by defining/computing tree cuts that can be interpreted in particular as segmentations when dealing with image modeling. In addition, some evaluation tools are also provided, which allow one to evaluate the quality of different binary partition trees for such segmentation tasks. AGAT can be easily handled by various kinds of users (students, researchers, practitioners). It can be used as is for experimental purposes, but can also form a basis for the development of new methods and paradigms for construction, use and intensive evaluation of binary partition trees. Beyond the usual imaging applications, its underlying structure also allows for more general developments in graph-based analysis, leading to a wide range of potential applications in computer vision, image/data analysis and machine learning.

Continue reading

Introducing the boundary-aware loss for deep image segmentation

Abstract

Most contemporary supervised image segmentation methods do not preserve the initial topology of the given input (like the closeness of the contours). One can generally remark that edge points have been inserted or removed when the binary prediction and the ground truth are compared. This can be critical when accurate localization of multiple interconnected objects is required. In this paper, we present a new loss function, called, Boundary-Aware loss (BALoss), based on the Minimum Barrier Distance (MBD) cut algorithm. It is able to locate what we call the leakage pixels and to encode the boundary information coming from the given ground truth. Thanks to this adapted loss, we are able to significantly refine the quality of the predicted boundaries during the learning procedure. Furthermore, our loss function is differentiable and can be applied to any kind of neural network used in image processing. We apply this loss function on the standard U-Net and DC U-Net on Electron Microscopy datasets. They are well-known to be challenging due to their high noise level and to the close or even connected objects covering the image space. Our segmentation performance, in terms of Variation of Information (VOI) and Adapted Rank Index (ARI), are very promising and lead to $\approx{}15%$ better scores of VOI and $\approx{}5%$ better scores of ARI than the state-of-the-art. The code of boundary-awareness loss is freely available at https://github.com/onvungocminh/MBD_BAL

Continue reading

Strong Euler wellcomposedness

Abstract

In this paper, we define a new flavour of well-composedness, called strong Euler well-composedness. In the general setting of regular cell complexes, a regular cell complex of dimension $n$ is strongly Euler well-composed if the Euler characteristic of the link of each boundary cell is $1$, which is the Euler characteristic of an $(n-1)$-dimensional ball. Working in the particular setting of cubical complexes canonically associated with $n$-D pictures, we formally prove in this paper that strong Euler well-composedness implies digital well-composedness in any dimension $n\geq 2$ and that the converse is not true when $n\geq 4$.

Continue reading

Continuous well-composedness implies digital well-composedness in $n$-D

Abstract

In this paper, we prove that when a $n$-D cubical set is continuously well-composed (CWC), that is, when the boundary of its continuous analog is a topological $(n-1)$-manifold, then it is digitally well-composed (DWC), which means that it does not contain any critical configuration. We prove this result thanks to local homology. This paper is the sequel of a previous paper where we proved that DWCness does not imply CWCness in 4D.

Continue reading