Promptable Longitudinal Lesion Segmentation in Whole-Body CT
This work addresses the challenge of monitoring disease progression and treatment response in medical imaging, though it is incremental as it builds on an existing framework.
The authors tackled the problem of consistently tracking individual lesions across time in longitudinal whole-body CT scans by extending the LongiSeg framework with promptable capabilities and leveraging large-scale pretraining on synthetic data. Their approach improved segmentation performance by up to 6 Dice points compared to models trained from scratch.
Accurate segmentation of lesions in longitudinal whole-body CT is essential for monitoring disease progression and treatment response. While automated methods benefit from incorporating longitudinal information, they remain limited in their ability to consistently track individual lesions across time. Task 2 of the autoPET/CT IV Challenge addresses this by providing lesion localizations and baseline delineations, framing the problem as longitudinal promptable segmentation. In this work, we extend the recently proposed LongiSeg framework with promptable capabilities, enabling lesion-specific tracking through point and mask interactions. To address the limited size of the provided training set, we leverage large-scale pretraining on a synthetic longitudinal CT dataset. Our experiments show that pretraining substantially improves the ability to exploit longitudinal context, yielding an improvement of up to 6 Dice points compared to models trained from scratch. These findings demonstrate the effectiveness of combining longitudinal context with interactive prompting for robust lesion tracking. Code is publicly available at https://github.com/MIC-DKFZ/LongiSeg/tree/autoPET.