Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yue, Zhiling, Fang, Yingying, Yang, Liutao, Baid, Nikhil, Walsh, Simon, Yang, Guang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911012902404096
author Yue, Zhiling
Fang, Yingying
Yang, Liutao
Baid, Nikhil
Walsh, Simon
Yang, Guang
author_facet Yue, Zhiling
Fang, Yingying
Yang, Liutao
Baid, Nikhil
Walsh, Simon
Yang, Guang
contents Fibrotic Lung Disease (FLD) is a severe condition marked by lung stiffening and scarring, leading to respiratory decline. High-resolution computed tomography (HRCT) is critical for diagnosing and monitoring FLD; however, fibrosis appears as irregular, diffuse patterns with unclear boundaries, leading to high inter-observer variability and time-intensive manual annotation. To tackle this challenge, we propose DiffSeg, a novel weakly supervised semantic segmentation (WSSS) method that uses image-level annotations to generate pixel-level fibrosis segmentation, reducing the need for fine-grained manual labeling. Additionally, our DiffSeg incorporates a diffusion-based generative model to synthesize HRCT images with different levels of fibrosis from healthy slices, enabling the generation of the fibrosis-injected slices and their paired fibrosis location. Experiments indicate that our method significantly improves the accuracy of pseudo masks generated by existing WSSS methods, greatly reducing the complexity of manual labeling and enhancing the consistency of the generated masks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_03551
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation
Yue, Zhiling
Fang, Yingying
Yang, Liutao
Baid, Nikhil
Walsh, Simon
Yang, Guang
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Fibrotic Lung Disease (FLD) is a severe condition marked by lung stiffening and scarring, leading to respiratory decline. High-resolution computed tomography (HRCT) is critical for diagnosing and monitoring FLD; however, fibrosis appears as irregular, diffuse patterns with unclear boundaries, leading to high inter-observer variability and time-intensive manual annotation. To tackle this challenge, we propose DiffSeg, a novel weakly supervised semantic segmentation (WSSS) method that uses image-level annotations to generate pixel-level fibrosis segmentation, reducing the need for fine-grained manual labeling. Additionally, our DiffSeg incorporates a diffusion-based generative model to synthesize HRCT images with different levels of fibrosis from healthy slices, enabling the generation of the fibrosis-injected slices and their paired fibrosis location. Experiments indicate that our method significantly improves the accuracy of pseudo masks generated by existing WSSS methods, greatly reducing the complexity of manual labeling and enhancing the consistency of the generated masks.
title Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.03551