Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?

• URL: http://arxiv.org/abs/2210.15091v1
• Date: Thu, 27 Oct 2022 00:32:13 GMT
• Title: Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?
• Authors: Enamundram Naga Karthik, Anne Kerbrat, Pierre Labauge, Tobias Granberg, Jason Talbott, Daniel S. Reich, Massimo Filippi, Rohit Bakshi, Virginie Callot, Sarath Chandar, Julien Cohen-Adad
• Abstract summary: Experience replay is a well-known continual learning method. We show that replay is able to achieve positive backward transfer and reduce catastrophic forgetting. Our experiments show that replay is able to achieve positive backward transfer and reduce catastrophic forgetting.
• Score: 8.691839346510116
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Segmentation of Multiple Sclerosis (MS) lesions is a challenging problem. Several deep-learning-based methods have been proposed in recent years. However, most methods tend to be static, that is, a single model trained on a large, specialized dataset, which does not generalize well. Instead, the model should learn across datasets arriving sequentially from different hospitals by building upon the characteristics of lesions in a continual manner. In this regard, we explore experience replay, a well-known continual learning method, in the context of MS lesion segmentation across multi-contrast data from 8 different hospitals. Our experiments show that replay is able to achieve positive backward transfer and reduce catastrophic forgetting compared to sequential fine-tuning. Furthermore, replay outperforms the multi-domain training, thereby emerging as a promising solution for the segmentation of MS lesions. The code is available at this link: https://github.com/naga-karthik/continual-learning-ms

Related papers

• DCID: Deep Canonical Information Decomposition [84.59396326810085]
  We consider the problem of identifying the signal shared between two one-dimensional target variables. We propose ICM, an evaluation metric which can be used in the presence of ground-truth labels. We also propose Deep Canonical Information Decomposition (DCID) - a simple, yet effective approach for learning the shared variables.
  arXiv  Detail & Related papers  (2023-06-27T16:59:06Z)
• MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation [1.146419670457951]
  Current practices limit model training and supervised pre-training to one or a few similar datasets. We propose MultiTalent, a method that leverages multiple CT datasets with diverse and conflicting class definitions.
  arXiv  Detail & Related papers  (2023-03-25T11:37:16Z)
• LifeLonger: A Benchmark for Continual Disease Classification [59.13735398630546]
  We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection. Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch. Cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.
  arXiv  Detail & Related papers  (2022-04-12T12:25:05Z)
• Continual learning of longitudinal health records [0.0]
  We evaluate a variety of continual learning methods on longitudinal ICU data. We find that while several methods mitigate short-term forgetting, domain shift remains a challenging problem over large series of tasks.
  arXiv  Detail & Related papers  (2021-12-22T15:08:45Z)
• Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation [0.46023882211671957]
  Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability. We propose an architecture that leverages the simultaneous availability of two or more datasets to learn a disentanglement between the content and domain. We showcase that our method reduces catastrophic forgetting and outperforms state-of-the-art continual learning methods.
  arXiv  Detail & Related papers  (2021-07-19T10:55:21Z)
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations [78.12377360145078]
  Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. In this paper, we first study how biases in the dataset affect existing methods. We show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets.
  arXiv  Detail & Related papers  (2021-06-10T17:59:13Z)
• Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition [65.77962788209103]
  We propose class subset learning by dividing the long-tailed data into multiple class subsets according to prior knowledge. It enforces the model to focus on learning the subset-specific knowledge. The proposed framework proved to be effective for the long-tailed retinal diseases recognition task.
  arXiv  Detail & Related papers  (2021-04-22T13:39:33Z)
• A Study of Domain Generalization on Ultrasound-based Multi-Class Segmentation of Arteries, Veins, Ligaments, and Nerves Using Transfer Learning [12.869637050331306]
  We study the US-based segmentation of multiple classes through transfer learning by fine-tuning different contiguous blocks within the model. We propose a simple method for predicting generalization on unseen datasets and observe statistically significant differences between the fine-tuning methods.
  arXiv  Detail & Related papers  (2020-11-13T16:59:20Z)
• What is Wrong with Continual Learning in Medical Image Segmentation? [1.2020488155038649]
  Continual learning protocols are attracting increasing attention from the medical imaging community. In a continual setup, data from different sources arrives sequentially and each batch is only available for a limited period. We show that the benchmark outperforms two popular continual learning methods for the task of T2-weighted MR prostate segmentation.
  arXiv  Detail & Related papers  (2020-10-21T13:48:37Z)
• 4D Deep Learning for Multiple Sclerosis Lesion Activity Segmentation [49.32653090178743]
  We investigate whether extending this problem to full 4D deep learning using a history of MRI volumes can improve performance. We find that our proposed architecture outperforms previous approaches with a lesion-wise true positive rate of 0.84 at a lesion-wise false positive rate of 0.19.
  arXiv  Detail & Related papers  (2020-04-20T11:41:01Z)
• MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data [75.73881040581767]
  We propose a novel multi-site network (MS-Net) for improving prostate segmentation by learning robust representations. Our MS-Net improves the performance across all datasets consistently, and outperforms state-of-the-art methods for multi-site learning.
  arXiv  Detail & Related papers  (2020-02-09T14:11:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.