Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting
This work addresses a critical issue in medical imaging for clinical contexts like Multiple Sclerosis, where accurate detection of all lesion sizes is essential, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the problem of accurately detecting and segmenting both small and large lesions in medical images, where standard methods often miss small lesions or oversegment large ones. It proposes a novel reweighing strategy that increases small lesion detection performance while maintaining segmentation accuracy, showing vast outperformance over competing strategies on a large-scale, multi-scanner, multi-center dataset of Multiple Sclerosis patient images.
There are many clinical contexts which require accurate detection and segmentation of all focal pathologies (e.g. lesions, tumours) in patient images. In cases where there are a mix of small and large lesions, standard binary cross entropy loss will result in better segmentation of large lesions at the expense of missing small ones. Adjusting the operating point to accurately detect all lesions generally leads to oversegmentation of large lesions. In this work, we propose a novel reweighing strategy to eliminate this performance gap, increasing small pathology detection performance while maintaining segmentation accuracy. We show that our reweighing strategy vastly outperforms competing strategies based on experiments on a large scale, multi-scanner, multi-center dataset of Multiple Sclerosis patient images.