# Bounding Maps for Universal Lesion Detection

arXiv: https://arxiv.org/abs/2007.09383 · HTML: https://mlsanity.com/paper/2007.09383/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [One-Shot Medical Landmark Detection](https://mlsanity.com/paper/2103.04527/) (2021)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [SATr: Slice Attention with Transformer for Universal Lesion Detection](https://mlsanity.com/paper/2203.07373/) (2022)
- [Asymmetric 3D Context Fusion for Universal Lesion Detection](https://mlsanity.com/paper/2109.08684/) (2021)
- [Conditional Training with Bounding Map for Universal Lesion Detection](https://mlsanity.com/paper/2103.12277/) (2021)

## Abstract (arXiv)

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.