Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Close Broader context Not relevant

   Customized Segment Anything Model for Medical Image Segmentation

   Kaidong Zhang, Dong Liu · 2023 · Computer Vision and Pattern Recognition · AI summary available

   SAMed customizes a large-scale segmentation model for labeled medical datasets, whereas this paper improves segmentation through localized self-supervised pre-training.

   Abstract

   We propose SAMed, a general solution for medical image segmentation. Different from the previous methods, SAMed is built upon the large-scale image segmentation model, Segment Anything Model (SAM), to explore the new research paradigm of customizing large-scale models for medical image segmentation. SAMed applies the low-rank-based (LoRA) finetuning strategy to the SAM image encoder and finetunes it together with the prompt encoder and the mask decoder on labeled medical image segmentation datasets. We also observe the warmup finetuning strategy and the AdamW optimizer lead SAMed to successful convergence and lower loss. Different from SAM, SAMed could perform semantic segmentation on medica…

2. Close Same question Not relevant

   Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction

   Wenjia Bai, Chen Chen, Giacomo Tarroni et al. · 2019 · Computer Vision and Pattern Recognition · AI summary available

   Anatomical Position Prediction uses self-supervised learning to reduce annotation needs for medical image segmentation, as this paper does with localized contrast.

   Abstract

   In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks. However, successfully learning these features requires a large amount of manually annotated data, which is expensive to acquire and limited by the available resources of expert image analysts. Therefore, unsupervised, weakly-supervised and self-supervised feature learning techniques receive a lot of attention, which aim to utilise the vast amount of available data, while at the same time avoid or substantially reduce the effort of manual annotation. In this paper, we propose a…

3. Close Another approach to the problem Not relevant

   Dense Contrastive Learning for Self-Supervised Visual Pre-Training

   Xinlong Wang, Rufeng Zhang, Chunhua Shen et al. · 2020 · Computer Vision and Pattern Recognition · AI summary available

   Dense Contrastive Learning uses pixel-level contrastive pre-training for dense prediction, while this paper uses super-pixel regions to improve medical segmentation.

   Abstract

   To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline meth…

4. Close Broader context Not relevant

   Learning Directional Feature Maps for Cardiac MRI Segmentation

   Feng Cheng, Cheng Chen, Yukang Wang et al. · 2020 · Computer Vision and Pattern Recognition · AI summary available

   Learning Directional Feature Maps addresses cardiac MRI segmentation with boundary-directed features rather than self-supervised localized contrast.

   Abstract

   Cardiac MRI segmentation plays a crucial role in clinical diagnosis for evaluating personalized cardiac performance parameters. Due to the indistinct boundaries and heterogeneous intensity distributions in the cardiac MRI, most existing methods still suffer from two aspects of challenges: inter-class indistinction and intra-class inconsistency. To tackle these two problems, we propose a novel method to exploit the directional feature maps, which can simultaneously strengthen the differences between classes and the similarities within classes. Specifically, we perform cardiac segmentation and learn a direction field pointing away from the nearest cardiac tissue boundary to each pixel via a di…

5. Close Broader context Not relevant

   Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification

   Marawan Elbatel, Hualiang Wang, Robert Martí et al. · 2023 · Computer Vision and Pattern Recognition · AI summary available

   Federated Model Aggregation uses self-supervised priors for imbalanced medical image classification, rather than segmentation pre-training.

   Abstract

   In the medical field, federated learning commonly deals with highly imbalanced datasets, including skin lesions and gastrointestinal images. Existing federated methods under highly imbalanced datasets primarily focus on optimizing a global model without incorporating the intra-class variations that can arise in medical imaging due to different populations, findings, and scanners. In this paper, we study the inter-client intra-class variations with publicly available self-supervised auxiliary networks. Specifically, we find that employing a shared auxiliary pre-trained model, like MoCo-V2, locally on every client yields consistent divergence measurements. Based on these findings, we derive a …

6. Close Broader context Not relevant

   Robust Semi-Supervised Learning for Histopathology Images through Self-Supervision Guided Out-of-Distribution Scoring

   Nikhil Cherian Kurian, Varsha S, Abhijit Patil et al. · 2023 · Computer Vision and Pattern Recognition · AI summary available

   Robust Semi-Supervised Learning uses self-supervision to score out-of-distribution histopathology samples, not to learn localized segmentation representations.

   Abstract

   Semi-supervised learning (semi-SL) is a promising alternative to supervised learning for medical image analysis when obtaining good quality supervision for medical imaging is difficult. However, semi-SL assumes that the underlying distribution of unaudited data matches that of the few labeled samples, which is often violated in practical settings, particularly in medical images. The presence of out-of-distribution (OOD) samples in the unlabeled training pool of semi-SL is inevitable and can reduce the efficiency of the algorithm. Common preprocessing methods to filter out outlier samples may not be suitable for medical images that involve a wide range of anatomical structures and rare morpho…

7. Close Broader context Not relevant

   MeDSLIP: Medical Dual-Stream Language-Image Pre-training for Fine-grained Alignment

   Wenrui Fan, Mohammod Naimul Islam Suvon, Shuo Zhou et al. · 2024 · Computer Vision and Pattern Recognition · AI summary available

   MeDSLIP applies contrastive pre-training to fine-grained image-report alignment, whereas this paper targets localized representations for segmentation.

   Abstract

   Vision-language pre-training (VLP) models have shown significant advancements in the medical domain. Yet, most VLP models align raw reports to images at a very coarse level, without modeling fine-grained relationships between anatomical and pathological concepts outlined in reports and the corresponding semantic counterparts in images. To address this problem, we propose a Medical Dual-Stream Language-Image Pre-training (MeDSLIP) framework. Specifically, MeDSLIP establishes vision-language fine-grained alignments via disentangling visual and textual representations into anatomy-relevant and pathology-relevant streams. Moreover, a novel vision-language Prototypical Contr-astive Learning (Prot…

8. Close Review Not relevant

   Deep learning and its application to medical image segmentation

   Holger R. Roth, Chen Shen, Hirohisa Oda et al. · 2018 · Medical Imaging Technology, Volume 36 (2018), Issue 2, p. 63-71 · AI summary available

   Deep Learning and Its Application to Medical Image Segmentation surveys deep-learning approaches to medical segmentation, the task addressed by this paper.

   Abstract

   One of the most common tasks in medical imaging is semantic segmentation. Achieving this segmentation automatically has been an active area of research, but the task has been proven very challenging due to the large variation of anatomy across different patients. However, recent advances in deep learning have made it possible to significantly improve the performance of image recognition and semantic segmentation methods in the field of computer vision. Due to the data driven approaches of hierarchical feature learning in deep learning frameworks, these advances can be translated to medical images without much difficulty. Several variations of deep convolutional neural networks have been succ…