Heatmap Regression for Lesion Detection using Pointwise Annotations
This addresses the problem of reducing annotation burden for medical professionals in lesion detection, though it is incremental as it builds on existing heatmap regression methods.
The paper tackles lesion detection in clinical images by using only pointwise annotations instead of time-consuming segmentation labels, achieving competitive detection performance and enabling effective segmentation pre-training with minimal labeled data.
In many clinical contexts, detecting all lesions is imperative for evaluating disease activity. Standard approaches pose lesion detection as a segmentation problem despite the time-consuming nature of acquiring segmentation labels. In this paper, we present a lesion detection method which relies only on point labels. Our model, which is trained via heatmap regression, can detect a variable number of lesions in a probabilistic manner. In fact, our proposed post-processing method offers a reliable way of directly estimating the lesion existence uncertainty. Experimental results on Gad lesion detection show our point-based method performs competitively compared to training on expensive segmentation labels. Finally, our detection model provides a suitable pre-training for segmentation. When fine-tuning on only 17 segmentation samples, we achieve comparable performance to training with the full dataset.