Class-Incremental Learning: Survey and Performance Evaluation on Image Classification.

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored - also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task-incremental learning, where a task-ID is provided at inference time. Recently, we have seen a shift towards class-incremental learning where the learner must discriminate at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing class-incremental learning methods for image classification, and in particular, we perform an extensive experimental evaluation on thirteen class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale image classification datasets, an investigation into small and large domain shifts, and a comparison of various network architectures.

Automated vortical blood flow-based estimation of mean pulmonary arterial pressure from 4D flow MRI.

PURPOSE: Elevated mean pulmonary arterial pressure (mPAP), or pulmonary hypertension (PH), is associated with vortical blood flow along the main pulmonary artery. We present and validate a method for automated detection and tracking of the PH-related vortex from magnetic resonance 4D flow data that allows estimation of mPAP. METHODS: The proposed method detects the presence of a PH-related vortex in the main pulmonary artery based on geometrical properties of swirling streamlines and estimates mPAP from the PH-related vortex duration (tvortex) using a previously established model. 4D flow data of 32 subjects (19/13 with/without PH) who underwent right heart catheterization (RHC) for mPAP measurement and diagnosis of PH (mPAP >20 mmHg) were used to compare visual and automated PH-related vortex detection and to validate estimated mPAP against RHC-derived results. RESULTS: Visually and automatically determined tvortex values correlated strongly (r = 0.98); they yielded no bias, and the standard deviation of differences between them was small (5.9% of the cardiac interval). mPAP estimates from visual and automated analyses both allowed diagnosis of PH with an area under the curve of 1.00 [0.89,1.00]. For subjects with PH, neither visually nor automatically estimated mPAP differed from mPAP measured by RHC, while the standard deviation between estimated and invasively measured mPAP was lower with visual estimation (3.1 mmHg vs. 5.3 mmHg). CONCLUSION: An automated method for PH-related vortex detection and tracking from magnetic resonance 4D flow data was introduced, which demonstrated very good agreement with visual analysis and accurate estimation of elevated mPAP.

A Continual Learning Survey: Defying Forgetting in Classification Tasks.

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern: (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods; and (4) baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.

Thoracic Aortic Mural Thrombus, Right Ventricular Clot and Pulmonary Embolism in a Patient With COVID-19 Pneumonia.

Since the outbreak of the COVID-19 pandemic, increasing evidence suggests that infected patients present a high incidence of thrombotic complications. We report a 67-year-old-woman admitted for severe acute respiratory syndrome coronavirus 2 infection. Chest CT images showed bilateral ground glass opacities, bilateral pulmonary embolism, right ventricular clot in transit and 2 thoracic aortic mural thrombus. Therapy was initiated with subcutaneous low-molecular-weight heparin, and the patient was discharged at 20 days asymptomatic. Complete resolution of the aortic thrombus was observed in a 1-month surveillance CT angiogram. Our case illustrates vascular complications in a COVID-19 patient and its effective treatment with anticoagulation.

Automated mitral valve vortex ring extraction from 4D-flow MRI.

PURPOSE: To present and validate a method for automated extraction and analysis of the temporal evolution of the mitral valve (MV) vortex ring from MR 4D-flow data. METHODS: The proposed algorithm uses the divergence-free part of the velocity vector field for Q criterion-based identification and tracking of MV vortex ring core and region within the left ventricle (LV). The 4D-flow data of 20 subjects (10 healthy controls, 10 patients with ischemic heart disease) were used to validate the algorithm against visual analysis as well as to assess the method's sensitivity to manual LV segmentation. Quantitative MV vortex ring parameters were analyzed with respect to both their differences between healthy subjects and patients and their correlation with transmitral peak velocities. RESULTS: The algorithm successfully extracted MV vortex rings throughout the entire cardiac cycle, which agreed substantially with visual analysis (Cohen's kappa = 0.77). Furthermore, vortex cores and regions were robustly detected even if a static end-diastolic LV segmentation mask was applied to all frames (Dice coefficients 0.82 ± 0.08 and 0.94 ± 0.02 for core and region, respectively). Early diastolic MV vortex ring vorticity, kinetic energy and circularity index differed significantly between healthy controls and patients. In contrast to vortex shape parameters, vorticity and kinetic energy correlated strongly with transmitral peak velocities. CONCLUSION: An automated method for temporal MV vortex ring extraction demonstrating robustness with respect to LV segmentation strategies is introduced. Quantitative vortex parameter analysis indicates importance of the MV vortex ring for LV diastolic (dys)function.

GTCreator: a flexible annotation tool for image-based datasets.

PURPOSE: Methodology evaluation for decision support systems for health is a time-consuming task. To assess performance of polyp detection methods in colonoscopy videos, clinicians have to deal with the annotation of thousands of images. Current existing tools could be improved in terms of flexibility and ease of use. METHODS: We introduce GTCreator, a flexible annotation tool for providing image and text annotations to image-based datasets. It keeps the main basic functionalities of other similar tools while extending other capabilities such as allowing multiple annotators to work simultaneously on the same task or enhanced dataset browsing and easy annotation transfer aiming to speed up annotation processes in large datasets. RESULTS: The comparison with other similar tools shows that GTCreator allows to obtain fast and precise annotation of image datasets, being the only one which offers full annotation editing and browsing capabilites. CONCLUSION: Our proposed annotation tool has been proven to be efficient for large image dataset annotation, as well as showing potential of use in other stages of method evaluation such as experimental setup or results analysis.