Graph-based automatic detection and classification of lesion changes in pairs of CT studies for oncology follow-up

• Published in: International journal for computer assisted radiology and surgery Vol. 19; no. 2; pp. 241 - 251
• Main Authors: Rochman, Shalom, Szeskin, Adi, Lederman, Richard, Sosna, Jacob, Joskowicz, Leo
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.02.2024; Springer Nature B.V
• Subjects: Algorithms; Classification; Computed tomography; Computer aided decision processes; Computer Imaging; Computer Science; Datasets; Decision analysis; Evaluation; Follow-Up Studies; Graph matching; Graph theory; Health Informatics; Humans; Imaging; Lesions; Liver; Liver Neoplasms - diagnostic imaging; Liver Neoplasms - pathology; Lungs; Medical imaging; Medicine; Medicine & Public Health; Oncology; Original Article; Pattern Recognition and Graphics; Quantitative analysis; Radiology; Surgery; Tomography, X-Ray Computed - methods; Vision; Analysis of lesion changes; Lesion matching; Analysis of connected components; Longitudinal CT studies
• ISSN: 1861-6429; 1861-6410; 1861-6429
• DOI: 10.1007/s11548-023-03000-2

Purpose Radiological follow-up of oncology patients requires the quantitative analysis of lesion changes in longitudinal imaging studies, which is time-consuming, requires expertise, and is subject to variability. This paper presents a comprehensive graph-based method for the automatic detection and classification of lesion changes in current and prior CT scans. Methods The inputs are the current and prior CT scans and their organ and lesion segmentations. Classification of lesion changes is formalized as bipartite graph matching where lesion pairings are computed by adaptive overlap-based lesion matching. Six types of lesion changes are computed by connected components analysis. The method was evaluated on 208 pairs of lung and liver CT scans from 57 patients with 4600 lesions, 1713 lesion matchings and 2887 lesion changes. Ground-truth lesion segmentations, lesion matchings and lesion changes were created by an expert radiologist. Results Our method yields a lesion matching rate accuracy of 99.7% (394/395) and 95.0% (1252/1318) for the lung and liver datasets. Precision and recall are > 0.99 and 0.94 and 0.95 (respectively) for the detection of lesion changes. The analysis of lesion changes helped the radiologist detect 48 missed lesions and 8 spurious lesions in the input ground-truth lesion datasets. Conclusion The classification of lesion classification provides the clinician with a readily accessible and intuitive identification and classification of the lesion changes and their patterns in support of clinical decision making. Comprehensive automatic computer-aided lesion matching and analysis of lesion changes may improve quantitative follow-up and evaluation of disease status, assessment of treatment efficacy and response to therapy.