Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gorade, Vandan, Mittal, Sparsh, Jha, Debesh, Singhal, Rekha, Bagci, Ulas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914904811765760
author Gorade, Vandan
Mittal, Sparsh
Jha, Debesh
Singhal, Rekha
Bagci, Ulas
author_facet Gorade, Vandan
Mittal, Sparsh
Jha, Debesh
Singhal, Rekha
Bagci, Ulas
contents Deep learning has demonstrated remarkable achievements in medical image segmentation. However, prevailing deep learning models struggle with poor generalization due to (i) intra-class variations, where the same class appears differently in different samples, and (ii) inter-class independence, resulting in difficulties capturing intricate relationships between distinct objects, leading to higher false negative cases. This paper presents a novel approach that synergies spatial and spectral representations to enhance domain-generalized medical image segmentation. We introduce the innovative Spectral Correlation Coefficient objective to improve the model's capacity to capture middle-order features and contextual long-range dependencies. This objective complements traditional spatial objectives by incorporating valuable spectral information. Extensive experiments reveal that optimizing this objective with existing architectures like UNet and TransUNet significantly enhances generalization, interpretability, and noise robustness, producing more confident predictions. For instance, in cardiac segmentation, we observe a 0.81 pp and 1.63 pp (pp = percentage point) improvement in DSC over UNet and TransUNet, respectively. Our interpretability study demonstrates that, in most tasks, objectives optimized with UNet outperform even TransUNet by introducing global contextual information alongside local details. These findings underscore the versatility and effectiveness of our proposed method across diverse imaging modalities and medical domains.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10373
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation
Gorade, Vandan
Mittal, Sparsh
Jha, Debesh
Singhal, Rekha
Bagci, Ulas
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Deep learning has demonstrated remarkable achievements in medical image segmentation. However, prevailing deep learning models struggle with poor generalization due to (i) intra-class variations, where the same class appears differently in different samples, and (ii) inter-class independence, resulting in difficulties capturing intricate relationships between distinct objects, leading to higher false negative cases. This paper presents a novel approach that synergies spatial and spectral representations to enhance domain-generalized medical image segmentation. We introduce the innovative Spectral Correlation Coefficient objective to improve the model's capacity to capture middle-order features and contextual long-range dependencies. This objective complements traditional spatial objectives by incorporating valuable spectral information. Extensive experiments reveal that optimizing this objective with existing architectures like UNet and TransUNet significantly enhances generalization, interpretability, and noise robustness, producing more confident predictions. For instance, in cardiac segmentation, we observe a 0.81 pp and 1.63 pp (pp = percentage point) improvement in DSC over UNet and TransUNet, respectively. Our interpretability study demonstrates that, in most tasks, objectives optimized with UNet outperform even TransUNet by introducing global contextual information alongside local details. These findings underscore the versatility and effectiveness of our proposed method across diverse imaging modalities and medical domains.
title Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.10373