Segmentation-Consistent Probabilistic Lesion Counting

TL;DR

This paper presents a novel differentiable method to accurately count lesions in medical images by converting segmentation predictions into probability distributions, enhancing robustness and uncertainty estimation.

Contribution

The work introduces a non-parametric, end-to-end approach combining voxel clustering, probability aggregation, and Poisson-binomial counting for lesion counting.

Findings

Accurate and well-calibrated lesion count distributions.

Suitable for multi-task learning with segmentation.

Robust to adversarial attacks and effective in low data regimes.

Abstract

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.