Bounding Maps for Universal Lesion Detection

TL;DR

This paper introduces a novel bounding map approach for universal lesion detection in CT scans, significantly reducing false positives and improving detection sensitivity without increasing inference time.

Contribution

It proposes a box-to-map method that replaces traditional anchor proposals with continuous bounding maps, enhancing two-stage detection frameworks.

Findings

Reduces false-positive rate in lesion detection.

Improves sensitivity by 1.68% to 3.85% at 4 FPs.

No extra inference time required.

Abstract

Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis systems. Many detection approaches achieve excellent results for ULD using possible bounding boxes (or anchors) as proposals. However, empirical evidence shows that using anchor-based proposals leads to a high false-positive (FP) rate. In this paper, we propose a box-to-map method to represent a bounding box with three soft continuous maps with bounds in x-, y- and xy- directions. The bounding maps (BMs) are used in two-stage anchor-based ULD frameworks to reduce the FP rate. In the 1 st stage of the region proposal network, we replace the sharp binary ground-truth label of anchors with the corresponding xy-direction BM hence the positive anchors are now graded. In the 2 nd stage, we add a branch that takes our continuous BMs in x- and y- directions for extra supervision of detailed locations. Our method, when embedded into three state-of-the-art two-stage anchor-based detection methods, brings a free detection accuracy improvement (e.g., a 1.68% to 3.85% boost of sensitivity at 4 FPs) without extra inference time.