Deep Learning Models for <scp>CT</scp> Segmentation of Invasive Pulmonary Aspergillosis, Mucormycosis, Bacterial Pneumonia and Tuberculosis: A Multicentre Study
Disease-specific DL segmentation models exhibited high accuracy, particularly for PM and PTB. While IPA and BP models require refinement, all demonstrated cross-disease utility, suggesting immediate clinical value for preliminary lesion annotation. Future efforts should enhance datasets and optimise models for intricate cases.
Authors
- Chengbao Peng
- Lunfang Tan
- Zhengtu Li (ORCID: https://orcid.org/0000-0001-5584-7223)
- Jinping Zheng (ORCID: https://orcid.org/0000-0002-7511-661X)
- Junnan Pan (ORCID: https://orcid.org/0009-0003-2913-6577)
- Shuyi Liu
- Deyan Chen (ORCID: https://orcid.org/0000-0001-8141-662X)
- Feifei Huang
- Lina Liang (ORCID: https://orcid.org/0000-0002-1600-8993)
- Yun Li (ORCID: https://orcid.org/0000-0002-8101-0192)
- Feng Ye (ORCID: https://orcid.org/0000-0003-2005-9264)
- Junfeng Lin
- Xia Zhang (ORCID: https://orcid.org/0000-0002-1690-7577)
- Youwen Zhang (ORCID: https://orcid.org/0000-0002-0957-4276)
- Guodong Hu
- Huai Chen
Institutions
- Third Affiliated Hospital of Southern Medical University (CN)
- Second Affiliated Hospital of Guangzhou Medical University (CN)
- First Affiliated Hospital of Guangzhou Medical University (CN)
- Neusoft (China) (CN)
- State Key Laboratory of Respiratory Disease (CN)
- Gaozhou People's Hospital (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Mycoses
- Published
- 2025-06-28
- DOI
- https://doi.org/10.1111/myc.70084
- Citations
- 1
- Primary Topic
- Lung Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 1.52
Funders
- National Key Research and Development Program of China