Enhanced MRI Representation via Cross-series Masking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Churan, Gao, Fei, Yan, Lijun, Wang, Siwen, Yu, Yizhou, Wang, Yizhou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916516594712576
author Wang, Churan
Gao, Fei
Yan, Lijun
Wang, Siwen
Yu, Yizhou
Wang, Yizhou
author_facet Wang, Churan
Gao, Fei
Yan, Lijun
Wang, Siwen
Yu, Yizhou
Wang, Yizhou
contents Magnetic resonance imaging (MRI) is indispensable for diagnosing and planning treatment in various medical conditions due to its ability to produce multi-series images that reveal different tissue characteristics. However, integrating these diverse series to form a coherent analysis presents significant challenges, such as differing spatial resolutions and contrast patterns meanwhile requiring extensive annotated data, which is scarce in clinical practice. Due to these issues, we introduce a novel Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner. Specifically, CSM commences by randomly sampling a subset of regions and series, which are then strategically masked. In the training process, the cross-series representation is learned by utilizing the unmasked data to reconstruct the masked portions. This process not only integrates information across different series but also facilitates the ability to model both intra-series and inter-series correlations and complementarities. With the learned representation, the downstream tasks like segmentation and classification are also enhanced. Taking brain tissue segmentation, breast tumor benign/malignant classification, and prostate cancer diagnosis as examples, our method achieves state-of-the-art performance on both public and in-house datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhanced MRI Representation via Cross-series Masking
Wang, Churan
Gao, Fei
Yan, Lijun
Wang, Siwen
Yu, Yizhou
Wang, Yizhou
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Magnetic resonance imaging (MRI) is indispensable for diagnosing and planning treatment in various medical conditions due to its ability to produce multi-series images that reveal different tissue characteristics. However, integrating these diverse series to form a coherent analysis presents significant challenges, such as differing spatial resolutions and contrast patterns meanwhile requiring extensive annotated data, which is scarce in clinical practice. Due to these issues, we introduce a novel Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner. Specifically, CSM commences by randomly sampling a subset of regions and series, which are then strategically masked. In the training process, the cross-series representation is learned by utilizing the unmasked data to reconstruct the masked portions. This process not only integrates information across different series but also facilitates the ability to model both intra-series and inter-series correlations and complementarities. With the learned representation, the downstream tasks like segmentation and classification are also enhanced. Taking brain tissue segmentation, breast tumor benign/malignant classification, and prostate cancer diagnosis as examples, our method achieves state-of-the-art performance on both public and in-house datasets.
title Enhanced MRI Representation via Cross-series Masking
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.07387