Saved in:
Bibliographic Details
Main Authors: Jiang, Yankai, Lei, Wenhui, Zhang, Xiaofan, Zhang, Shaoting
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15744
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929737293627392
author Jiang, Yankai
Lei, Wenhui
Zhang, Xiaofan
Zhang, Shaoting
author_facet Jiang, Yankai
Lei, Wenhui
Zhang, Xiaofan
Zhang, Shaoting
contents Recent advancements in medical vision-language pre-training models have driven significant progress in zero-shot disease recognition. However, transferring image-level knowledge to pixel-level tasks, such as lesion segmentation in 3D CT scans, remains a critical challenge. Due to the complexity and variability of pathological visual characteristics, existing methods struggle to align fine-grained lesion features not encountered during training with disease-related textual representations. In this paper, we present Malenia, a novel multi-scale lesion-level mask-attribute alignment framework, specifically designed for 3D zero-shot lesion segmentation. Malenia improves the compatibility between mask representations and their associated elemental attributes, explicitly linking the visual features of unseen lesions with the extensible knowledge learned from previously seen ones. Furthermore, we design a Cross-Modal Knowledge Injection module to enhance both visual and textual features with mutually beneficial information, effectively guiding the generation of segmentation results. Comprehensive experiments across three datasets and 12 lesion categories validate the superior performance of Malenia.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15744
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
Jiang, Yankai
Lei, Wenhui
Zhang, Xiaofan
Zhang, Shaoting
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advancements in medical vision-language pre-training models have driven significant progress in zero-shot disease recognition. However, transferring image-level knowledge to pixel-level tasks, such as lesion segmentation in 3D CT scans, remains a critical challenge. Due to the complexity and variability of pathological visual characteristics, existing methods struggle to align fine-grained lesion features not encountered during training with disease-related textual representations. In this paper, we present Malenia, a novel multi-scale lesion-level mask-attribute alignment framework, specifically designed for 3D zero-shot lesion segmentation. Malenia improves the compatibility between mask representations and their associated elemental attributes, explicitly linking the visual features of unseen lesions with the extensible knowledge learned from previously seen ones. Furthermore, we design a Cross-Modal Knowledge Injection module to enhance both visual and textual features with mutually beneficial information, effectively guiding the generation of segmentation results. Comprehensive experiments across three datasets and 12 lesion categories validate the superior performance of Malenia.
title Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.15744