# Universal Lesion Detection in CT Scans using Neural Network Ensembles

arXiv: https://arxiv.org/abs/2111.04886 · HTML: https://mlsanity.com/paper/2111.04886/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 9 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CT](https://mlsanity.com/paper/2009.02577/) (2020)
- [MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation](https://mlsanity.com/paper/1908.04373/) (2019)
- [FoveaBox: Beyond Anchor-based Object Detector](https://mlsanity.com/paper/1904.03797/) (2019)
- [Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels](https://mlsanity.com/paper/1906.02283/) (2019)
- [3D Context Enhanced Region-based Convolutional Neural Network for End-to-End Lesion Detection](https://mlsanity.com/paper/1806.09648/) (2018)
- [ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining](https://mlsanity.com/paper/1901.06359/) (2019)
- [Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale](https://mlsanity.com/paper/2001.07776/) (2020)
- [RECIST-Net: Lesion detection via grouping keypoints on RECIST-based annotation](https://mlsanity.com/paper/2107.08715/) (2021)

## Built on by (most cited first, 8 of 8)

- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography](https://mlsanity.com/paper/2405.18356/) (2024)
- [Weakly-Supervised Detection of Bone Lesions in CT](https://mlsanity.com/paper/2402.00175/) (2024)
- [Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methods](https://mlsanity.com/paper/2408.03393/) (2024)
- [Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT](https://mlsanity.com/paper/2504.05591/) (2025)
- [Text Embedded Swin-UMamba for DeepLesion Segmentation](https://mlsanity.com/paper/2508.06453/) (2025)
- [3D Universal Lesion Detection and Tagging in CT with Self-Training](https://mlsanity.com/paper/2504.05201/) (2025)
- [Correcting Class Imbalances with Self-Training for Improved Universal Lesion Detection and Tagging](https://mlsanity.com/paper/2504.05207/) (2025)

## Abstract (arXiv)

In clinical practice, radiologists are reliant on the lesion size when distinguishing metastatic from non-metastatic lesions. A prerequisite for lesion sizing is their detection, as it promotes the downstream assessment of tumor spread. However, lesions vary in their size and appearance in CT scans, and radiologists often miss small lesions during a busy clinical day. To overcome these challenges, we propose the use of state-of-the-art detection neural networks to flag suspicious lesions present in the NIH DeepLesion dataset for sizing. Additionally, we incorporate a bounding box fusion technique to minimize false positives (FP) and improve detection accuracy. Finally, to resemble clinical usage, we constructed an ensemble of the best detection models to localize lesions for sizing with a precision of 65.17% and sensitivity of 91.67% at 4 FP per image. Our results improve upon or maintain the performance of current state-of-the-art methods for lesion detection in challenging CT scans.