LungMend:用于重症肺结核CT肺掩码校正的仅健康潜伏扩散形状先验
LungMend: A Healthy-Only Latent Diffusion Shape Prior for Lung Mask Correction in Severe Tuberculosis CT
AI总结:
针对重症肺结核CT中肺分割模型遗漏空洞和实变的问题,提出仅用健康解剖结构训练的LungMend潜伏扩散后处理模型,可恢复遗漏区域并提升专家标注切片的准确性。
摘要:
R231等肺分割模型应用广泛,但在重症肺结核(TB)CT图像上表现不佳:空洞和实变区域类似非肺组织,会被排除在掩码之外。本文提出LungMend,一种仅利用健康解剖结构校正此类掩码的后处理模型。该潜伏扩散模型在健康肺组织上训练,结合合成损坏的掩码,无需任何病理数据或CT强度,即可从错误掩码和骨骼解剖结构中学习恢复完整肺组织。LungMend可恢复R231遗漏的空洞和实变区域,并提高专家标注切片的准确性。代码:this https URL
英文摘要:
Lung segmentation models such as R231 are widely used, but they fail on severe tuberculosis (TB) CT: cavities and consolidations look like non-lung tissue and are left out of the mask. We present LungMend, a post-processing model that corrects such masks using only healthy anatomy. A latent diffusion model, trained on healthy lungs with synthetically corrupted masks, learns to recover the complete lung from the faulty mask and the bone anatomy, without any pathological data or CT intensities. LungMend recovers cavities and consolidations that R231 misses and improves accuracy on expert-annotated slices. Code: https://github.com/noureddinekhiati/LungMend
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。