What question did this study set out to answer?

To develop and evaluate an automated CT liver lesion-tracking algorithm that monitors metastases over time and enhances response assessment.

July 16, 2026European Radiology Experimental0 citationsOpen Access

Automated model-based lesion tracking in CT: colorectal liver metastases as a use case for development and performance analysis

NKNalan KarunanayakeMemorial Sloan Kettering Cancer Center HYHao YangMemorial Sloan Kettering Cancer Center PGPengfei GengMemorial Sloan Kettering Cancer Center

Key Points

To develop and evaluate an automated CT liver lesion-tracking algorithm that monitors metastases over time and enhances response assessment.
87 adults with unresectable colorectal liver metastases received baseline and follow-up CT scans.
Developed machine learning-driven Auto-MBT for lesion tracking; compared performance with different registration methods.
Results stratified by lesion size and count, using a publicly available melanoma dataset for external testing.
Affine + Auto-MBT matched 458/464 lesions with precision/recall of 99%, detecting 28/30 new lesions (90%/93%).
Overall matching F1 for Auto-MBT was 0.989, outperforming deformable registration methods.
Confidence scores (0.72 for accepted vs 0.54 for rejected matches) supported decision-making in lesion tracking.

Abstract

OBJECTIVE: To develop and evaluate an automated CT liver lesion-tracking algorithm that matches lesions over time, detects new metastases, and reports per‑lesion confidence to support response assessment. MATERIALS AND METHODS: The study included 87 adults with unresectable colorectal liver metastases (CRLM) who had baseline and 8-week follow-up contrast-enhanced CT. Three radiologists generated a consensus reference. We developed a machine learning-driven, automated model-based lesion tracking (Auto-MBT) that provides per-lesion matching confidence. Performance was compared with: (1) deformable registration + overlap; (2) deformable registration + Auto-MBT; and (3) affine registration + Auto-MBT. Analyses were stratified by lesion size ( 10 per scan), and the triage utility of confidence scores was assessed by blinded adjudication. A publicly available melanoma dataset was used for external testing. RESULTS: On the CRLM test set (35 pairs), affine + Auto-MBT matched 458/464 lesions (precision/recall 99%), detected 28/30 new lesions (90%/93%), and identified 42/44 disappeared lesions (93%/96%). Overall matching F1 was 0.989; affine + Auto-MBT outperformed deformable + overlap (0.797) and deformable + Auto-MBT (0.959). Confidence scores were higher for radiologist-accepted matches than rejected matches (0.72 versus 0.54) supporting triage utility. On the external set (23 pairs), overall matching F1 was 0.994, affine + Auto-MBT outperformed deformable + overlap (0.768) and deformable + Auto-MBT (0.971). CONCLUSION: Auto-MBT accurately tracks CRLM and flags new lesions across sizes and counts, with per‑lesion confidence to triage, not replace, clinician review, enabling more comprehensive and accurate therapy response assessment. RELEVANCE STATEMENT: The automated tracking framework accurately matched liver lesions, including new and subcentimeter lesions, improving longitudinal assessment. KEY POINTS: Manual tracking of colorectal liver metastases (CRLM) on routine CT images is time-consuming and subject to inter-observer variability. The algorithm demonstrates robust lesion‑level tracking performance (F1 > 0.9) in high lesion‑count CRLM, including matched, new, and disappeared lesions. Automated total-tumor tracking complements Response Evaluation Criteria in Solid Tumors‒RECIST by quantifying all lesions, extending evaluation beyond limited target metastases.

问 AI

Bookmark

View Full Paper