# Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector

arXiv: https://arxiv.org/abs/1807.00436 · HTML: https://mlsanity.com/paper/1807.00436/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 4 of 4)

- [Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images](https://mlsanity.com/paper/2112.01535/) (2021)
- [DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection](https://mlsanity.com/paper/2203.06886/) (2022)
- [A CNN Segmentation-Based Approach to Object Detection and Tracking in Ultrasound Scans with Application to the Vagus Nerve Detection](https://mlsanity.com/paper/2106.13849/) (2021)
- [Dual-Attention Enhanced BDense-UNet for Liver Lesion Segmentation](https://mlsanity.com/paper/2107.11645/) (2021)

## Abstract (arXiv)

We present a focal liver lesion detection model leveraged by custom-designed multi-phase computed tomography (CT) volumes, which reflects real-world clinical lesion detection practice using a Single Shot MultiBox Detector (SSD). We show that grouped convolutions effectively harness richer information of the multi-phase data for the object detection model, while a naive application of SSD suffers from a generalization gap. We trained and evaluated the modified SSD model and recently proposed variants with our CT dataset of 64 subjects by five-fold cross validation. Our model achieved a 53.3% average precision score and ran in under three seconds per volume, outperforming the original model and state-of-the-art variants. Results show that the one-stage object detection model is a practical solution, which runs in near real-time and can learn an unbiased feature representation from a large-volume real-world detection dataset, which requires less tedious and time consuming construction of the weak phase-level bounding box labels.