Adaptive Contrastive Learning with Dynamic Correlation for Multi-Phase Organ Segmentation

• URL: http://arxiv.org/abs/2210.08652v1
• Date: Sun, 16 Oct 2022 22:38:30 GMT
• Title: Adaptive Contrastive Learning with Dynamic Correlation for Multi-Phase Organ Segmentation
• Authors: Ho Hin Lee, Yucheng Tang, Han Liu, Yubo Fan, Leon Y. Cai, Qi Yang, Xin Yu, Shunxing Bao, Yuankai Huo, Bennett A. Landman
• Abstract summary: We propose a novel data-driven contrastive loss function that adapts the similar/dissimilar contrast relationship between samples in each minibatch at organ-level. We evaluate our proposed approach on multi-organ segmentation with both non-contrast CT datasets and the MICCAI 2015 BTCV Challenge contrast-enhance CT datasets.
• Score: 25.171694372205774
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent studies have demonstrated the superior performance of introducing ``scan-wise" contrast labels into contrastive learning for multi-organ segmentation on multi-phase computed tomography (CT). However, such scan-wise labels are limited: (1) a coarse classification, which could not capture the fine-grained ``organ-wise" contrast variations across all organs; (2) the label (i.e., contrast phase) is typically manually provided, which is error-prone and may introduce manual biases of defining phases. In this paper, we propose a novel data-driven contrastive loss function that adapts the similar/dissimilar contrast relationship between samples in each minibatch at organ-level. Specifically, as variable levels of contrast exist between organs, we hypothesis that the contrast differences in the organ-level can bring additional context for defining representations in the latent space. An organ-wise contrast correlation matrix is computed with mean organ intensities under one-hot attention maps. The goal of adapting the organ-driven correlation matrix is to model variable levels of feature separability at different phases. We evaluate our proposed approach on multi-organ segmentation with both non-contrast CT (NCCT) datasets and the MICCAI 2015 BTCV Challenge contrast-enhance CT (CECT) datasets. Compared to the state-of-the-art approaches, our proposed contrastive loss yields a substantial and significant improvement of 1.41% (from 0.923 to 0.936, p-value$<$0.01) and 2.02% (from 0.891 to 0.910, p-value$<$0.01) on mean Dice scores across all organs with respect to NCCT and CECT cohorts. We further assess the trained model performance with the MICCAI 2021 FLARE Challenge CECT datasets and achieve a substantial improvement of mean Dice score from 0.927 to 0.934 (p-value$<$0.01). The code is available at: https://github.com/MASILab/DCC_CL

Related papers

• Beyond Strong labels: Weakly-supervised Learning Based on Gaussian Pseudo Labels for The Segmentation of Ellipse-like Vascular Structures in Non-contrast CTs [4.765753560367118]
  This paper introduces a weakly-supervised framework for deep-learning based on vascular structures in CT scans. We assess the effectiveness of the proposed method on one local and two public datasets.
  arXiv  Detail & Related papers  (2024-02-05T20:08:53Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation [21.792652078631868]
  We propose an unsupervised approach to compute non-contrast segmentation without ground-truth label. Unlike generative adversarial approaches, we compute the pairwise morphological context with CECT to provide teacher guidance. We validate our approach on multi-organ segmentation with paired non-contrast & contrast-enhanced CT scans.
  arXiv  Detail & Related papers  (2022-05-12T06:36:33Z)
• The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation [8.035409264165937]
  Dice similarity coefficient (DSC) and Hausdorff distance (HD) are widely used for evaluating medical image segmentation. This work first proposes a new asymmetric detection metric, adapting those used in object detection, for planning prostate cancer procedures. We report pairwise agreement and correlation 1) between DSC and HD, and 2) between voxel-level DSC and recall-controlled precision at lesion-level.
  arXiv  Detail & Related papers  (2022-03-30T15:57:20Z)
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation [56.622832383316215]
  We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans. Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our empirical results show that CyTran outperforms all competing methods.
  arXiv  Detail & Related papers  (2021-10-12T23:25:03Z)
• Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation [64.59521853145368]
  Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features.
  arXiv  Detail & Related papers  (2021-09-08T07:56:51Z)
• Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images [49.1861463923357]
  We propose an uncertainty-guided dual-consistency learning network (UDC-Net) for semi-supervised COVID-19 lesion segmentation from CT images. Our proposed UDC-Net improves the fully supervised method by 6.3% in Dice and outperforms other competitive semi-supervised approaches by significant margins.
  arXiv  Detail & Related papers  (2021-04-07T16:23:35Z)
• Bone Segmentation in Contrast Enhanced Whole-Body Computed Tomography [2.752817022620644]
  This paper outlines a U-net architecture with novel preprocessing techniques to segment bone-bone marrow regions from low dose contrast enhanced whole-body CT scans. We have demonstrated that appropriate preprocessing is important for differentiating between bone and contrast dye, and that excellent results can be achieved with limited data.
  arXiv  Detail & Related papers  (2020-08-12T10:48:38Z)
• Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation [48.504790189796836]
  We present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe) We propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling. CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2% sim 9.4%$.
  arXiv  Detail & Related papers  (2020-05-27T06:58:39Z)
• A Deep learning Approach to Generate Contrast-Enhanced Computerised Tomography Angiography without the Use of Intravenous Contrast Agents [2.2840399926157806]
  We trained a 2-D Cycle Generative Adversarial Network for this non-contrast to contrast (NC2C) transformation task. This pipeline is able to differentiate between visually incoherent soft tissue regions in non-contrast CT images.
  arXiv  Detail & Related papers  (2020-03-02T22:20:08Z)

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.