Homology-feature-assisted quantification of fibrotic lesions in computed tomography images: a proof of concept for CT image feature-based prediction for gene-expression-distribution

• Published in: International journal for computer assisted radiology and surgery Vol. 20; no. 8; pp. 1703 - 1711
• Main Authors: Doi, Kentaro, Numasaki, Hodaka, Anetai, Yusuke, Natsume-Kitatani, Yayoi
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.08.2025; Springer Nature B.V
• Subjects: Classification; Computed tomography; Computer Imaging; Computer Science; Connectivity; COVID-19; Datasets; Feasibility studies; Fibrosis; Gene Expression; Health Informatics; Homology; Humans; Idiopathic Pulmonary Fibrosis - diagnostic imaging; Idiopathic Pulmonary Fibrosis - genetics; Image analysis; Imaging; Lesions; Lung cancer; Lung diseases; Medical imaging; Medicine; Medicine & Public Health; Original; Original Article; Patients; Pattern Recognition and Graphics; Pneumonia; Proof of Concept Study; Radiation therapy; Radiographic Image Interpretation, Computer-Assisted - methods; Radiology; Sensitivity and Specificity; Surgery; Tomography; Tomography, X-Ray Computed - methods; Tuning; Vision; Quantitative image analysis; Homology; CT image; Idiopathic interstitial pneumonias; Computer-aided diagnosis
• ISSN: 1861-6429; 1861-6410; 1861-6429
• DOI: 10.1007/s11548-025-03428-8

Purpose Computed tomography (CT) image is promising for diagnosing of interstitial idiopathic pneumonias (IIPs); however, quantification of IIPs lesions in CT images is required. This study aimed to quantitatively evaluate fibrotic lesions in CT images using homology-based image analysis. Methods We collected publicly available CT images comprising 47 fibrotic images and 36 non-fibrotic images. The homology-profile (HP) image analysis method provides b0 and b1 profiles, indicating the number of isolated components and holes in a binary image. We locally applied the HP method to the CT image and generated homology-based feature (HF) maps as resultant images. The collected images were randomly divided into the tuning dataset and the testing dataset. The cut-off value for classifying the HF map for fibrotic or non-fibrotic images was defined using receiver operating characteristic (ROC) analysis with the tuning dataset. This cut-off value was evaluated using the testing dataset with accuracy, sensitivity, specificity, and precision. Results We successfully visualized the quantification of fibrotic lesions in the HF map. The b0 HF map was more suitable for quantifying fibrotic lesions than b1. The mean cut-off value of the b0 HF map was 199, with all performances achieved at 1.0. Furthermore, the classification of the b0 HF map for fibrotic or lung cancer images achieved all maximum performances at 1.0. Conclusion This study demonstrated the feasibility of using the HF in quantitatively evaluating fibrotic lesions in CT images. Our proposed HP-based method can also be promising in quantifying the fibrotic lesions of patients with IIPs, which can be applicable to assist the diagnosis of IIPs.