Segmentation-Consistent Probabilistic Lesion Counting
This work addresses lesion counting for medical diagnosis and treatment, providing a robust post hoc method that is incremental in enhancing segmentation models.
The authors tackled the problem of counting lesions in medical imaging by introducing a continuously differentiable function that maps segmentation predictions to lesion count probability distributions, resulting in accurate and well-calibrated count distributions that capture uncertainty.
Lesion counts are important indicators of disease severity, patient prognosis, and treatment efficacy, yet counting as a task in medical imaging is often overlooked in favor of segmentation. This work introduces a novel continuously differentiable function that maps lesion segmentation predictions to lesion count probability distributions in a consistent manner. The proposed end-to-end approach--which consists of voxel clustering, lesion-level voxel probability aggregation, and Poisson-binomial counting--is non-parametric and thus offers a robust and consistent way to augment lesion segmentation models with post hoc counting capabilities. Experiments on Gadolinium-enhancing lesion counting demonstrate that our method outputs accurate and well-calibrated count distributions that capture meaningful uncertainty information. They also reveal that our model is suitable for multi-task learning of lesion segmentation, is efficient in low data regimes, and is robust to adversarial attacks.