Oscar Camara

Bio: Oscar Camara is an academic researcher from Pompeu Fabra University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 31, co-authored 178 publications receiving 4386 citations. Previous affiliations of Oscar Camara include Centre national de la recherche scientifique & University College London.

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Abstract: Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the “Automatic Cardiac Diagnosis Challenge” dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

Generalized Overlap Measures for Evaluation and Validation in Medical Image Analysis

Abstract: Measures of overlap of labelled regions of images, such as the Dice and Tanimoto coefficients, have been extensively used to evaluate image registration and segmentation algorithms. Modern studies can include multiple labels defined on multiple images yet most evaluation schemes report one overlap per labelled region, simply averaged over multiple images. In this paper, common overlap measures are generalized to measure the total overlap of ensembles of labels defined on multiple test images and account for fractional labels using fuzzy set theory. This framework allows a single "figure-of-merit" to be reported which summarises the results of a complex experiment by image pair, by label or overall. A complementary measure of error, the overlap distance, is defined which captures the spatial extent of the nonoverlapping part and is related to the Hausdorff distance computed on grey level images. The generalized overlap measures are validated on synthetic images for which the overlap can be computed analytically and used as similarity measures in nonrigid registration of three-dimensional magnetic resonance imaging (MRI) brain images. Finally, a pragmatic segmentation ground truth is constructed by registering a magnetic resonance atlas brain to 20 individual scans, and used with the overlap measures to evaluate publicly available brain segmentation algorithms

Three-dimensional architecture of scar and conducting channels based on high resolution ce-CMR: insights for ventricular tachycardia ablation

Abstract: Background— Conducting channels are the target for ventricular tachycardia (VT) ablation. Conducting channels could be identified with contrast enhanced–cardiac magnetic resonance (ce-CMR) as border zone (BZ) corridors. A 3-dimensional (3D) reconstruction of the ce-CMR could allow visualization of the 3D structure of these BZ channels. Methods and Results— We included 21 patients with healed myocardial infarction and VT. A 3D high-resolution 3T ce-CMR was performed before CARTO-guided VT ablation. The left ventricular wall was segmented and characterized using a pixel signal intensity algorithm at 5 layers (endocardium, 25%, 50%, 75%, epicardium). A 3D color-coded shell map was obtained for each layer to depict the scar core and BZ distribution. The presence/characteristics of BZ channels were registered for each layer. Scar area decreased progressively from endocardium to epicardium (scar area/left ventricular area: 34.0±17.4% at endocardium, 24.1±14.7% at 25%, 16.3±12.1% at 50%, 13.1±10.4 at 75%, 12.1±9.3% at epicardium; P <0.01). Forty-five BZ channels (2.1±1.0 per patient, 23.7±12.0 mm length, mean minimum width 2.5±1.5 mm) were identified, 85% between the endocardium and 50% shell and 76% present in ≥1 layer. The ce-CMR–defined BZ channels identified 74% of the critical isthmus of clinical VTs and 50% of all the conducting channels identified in electroanatomic maps. Conclusions— Scar area in patients with healed myocardial infarction decreases from the endocardium to the epicardium. BZ channels, more commonly seen in the endocardium, display a 3D structure within the myocardial wall that can be depicted with ce-CMR. The use of ce-CMR–derived maps to guide VT ablation warrants further investigation.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Abstract: Convolutional Neural Networks (CNNs) have been recently employed to solve problems from both the computer vision and medical image analysis fields. Despite their popularity, most approaches are only able to process 2D images while most medical data used in clinical practice consists of 3D volumes. In this work we propose an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network. Our CNN is trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once. We introduce a novel objective function, that we optimise during training, based on Dice coefficient. In this way we can deal with situations where there is a strong imbalance between the number of foreground and background voxels. To cope with the limited number of annotated volumes available for training, we augment the data applying random non-linear transformations and histogram matching. We show in our experimental evaluation that our approach achieves good performances on challenging test data while requiring only a fraction of the processing time needed by other previous methods.

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Abstract: Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.

Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

Abstract: Medical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by existing metrics. First we present an overview of 20 evaluation metrics selected based on a comprehensive literature review. For fuzzy segmentation, which shows the level of membership of each voxel to multiple classes, fuzzy definitions of all metrics are provided. We present a discussion about metric properties to provide a guide for selecting evaluation metrics. Finally, we propose an efficient evaluation tool implementing the 20 selected metrics. The tool is optimized to perform efficiently in terms of speed and required memory, also if the image size is extremely large as in the case of whole body MRI or CT volume segmentation. An implementation of this tool is available as an open source project. We propose an efficient evaluation tool for 3D medical image segmentation using 20 evaluation metrics and provide guidelines for selecting a subset of these metrics that is suitable for the data and the segmentation task.