# ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining

arXiv: https://arxiv.org/abs/1901.06359 · HTML: https://mlsanity.com/paper/1901.06359/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2019.

## Built on by (most cited first, 21 of 21)

- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [SATr: Slice Attention with Transformer for Universal Lesion Detection](https://mlsanity.com/paper/2203.07373/) (2022)
- [Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss](https://mlsanity.com/paper/2105.01218/) (2021)
- [CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans](https://mlsanity.com/paper/2301.12291/) (2023)
- [Asymmetric 3D Context Fusion for Universal Lesion Detection](https://mlsanity.com/paper/2109.08684/) (2021)
- [Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective](https://mlsanity.com/paper/2401.04374/) (2024)
- [Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection](https://mlsanity.com/paper/2105.01828/) (2021)
- [Universal Lesion Detection in CT Scans using Neural Network Ensembles](https://mlsanity.com/paper/2111.04886/) (2021)
- [Conditional Training with Bounding Map for Universal Lesion Detection](https://mlsanity.com/paper/2103.12277/) (2021)
- [Universal Lymph Node Detection in T2 MRI using Neural Networks](https://mlsanity.com/paper/2204.00622/) (2022)
- [RECIST-Net: Lesion detection via grouping keypoints on RECIST-based annotation](https://mlsanity.com/paper/2107.08715/) (2021)
- [DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection](https://mlsanity.com/paper/2203.06886/) (2022)
- [Accurate Detection of Mediastinal Lesions with nnDetection](https://mlsanity.com/paper/2303.11214/) (2023)
- [An End-to-End Framework For Universal Lesion Detection With Missing Annotations](https://mlsanity.com/paper/2303.15024/) (2023)
- [Bag of Tricks for Long-Tailed Multi-Label Classification on Chest X-Rays](https://mlsanity.com/paper/2308.08853/) (2023)
- [Towards Robust Plant Disease Diagnosis with Hard-sample Re-mining Strategy](https://mlsanity.com/paper/2309.01903/) (2023)
- [Practical X-ray Gastric Cancer Diagnostic Support Using Refined Stochastic Data Augmentation and Hard Boundary Box Training](https://mlsanity.com/paper/2108.08158/) (2021)
- [Exploiting Liver CT scans in Colorectal Carcinoma genomics mutation classification](https://mlsanity.com/paper/2401.14206/) (2024)
- [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)
- [PDSE: A Multiple Lesion Detector for CT Images using PANet and Deformable Squeeze-and-Excitation Block](https://mlsanity.com/paper/2506.03608/) (2025)

## Abstract (arXiv)

Automatic lesion detection from computed tomography (CT) scans is an important task in medical imaging analysis. It is still very challenging due to similar appearances (e.g. intensity and texture) between lesions and other tissues, making it especially difficult to develop a universal lesion detector. Instead of developing a specific-type lesion detector, this work builds a Universal Lesion Detector (ULDor) based on Mask R-CNN, which is able to detect all different kinds of lesions from whole body parts. As a state-of-the-art object detector, Mask R-CNN adds a branch for predicting segmentation masks on each Region of Interest (RoI) to improve the detection performance. However, it is almost impossible to manually annotate a large-scale dataset with pixel-level lesion masks to train the Mask R-CNN for lesion detection. To address this problem, this work constructs a pseudo mask for each lesion region that can be considered as a surrogate of the real mask, based on which the Mask R-CNN is employed for lesion detection. On the other hand, this work proposes a hard negative example mining strategy to reduce the false positives for improving the detection performance. Experimental results on the NIH DeepLesion dataset demonstrate that the ULDor is enhanced using pseudo masks and the proposed hard negative example mining strategy and achieves a sensitivity of 86.21% with five false positives per image.