# Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT

arXiv: https://arxiv.org/abs/2504.05591 · HTML: https://mlsanity.com/paper/2504.05591/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 18 of 18)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge](https://mlsanity.com/paper/1612.08012/) (2016)
- [A New 2.5D Representation for Lymph Node Detection using Random Sets of Deep Convolutional Neural Network Observations](https://mlsanity.com/paper/1406.2639/) (2014)
- [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)
- [Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies](https://mlsanity.com/paper/2012.04872/) (2020)
- [Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology](https://mlsanity.com/paper/1904.04661/) (2019)
- [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)
- [AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes](https://mlsanity.com/paper/2005.01969/) (2020)
- [Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale](https://mlsanity.com/paper/2001.07776/) (2020)
- [Universal Lesion Detection in CT Scans using Neural Network Ensembles](https://mlsanity.com/paper/2111.04886/) (2021)
- [Transformer Lesion Tracker](https://mlsanity.com/paper/2206.06252/) (2022)

## Built on by (most cited first, 1 of 1)

- [LiMT: A Multi-task Liver Image Benchmark Dataset](https://mlsanity.com/paper/2511.19889/) (2025)

## Abstract (arXiv)

Radiologists routinely detect and size lesions in CT to stage cancer and assess tumor burden. To potentially aid their efforts, multiple lesion detection algorithms have been developed with a large public dataset called DeepLesion (32,735 lesions, 32,120 CT slices, 10,594 studies, 4,427 patients, 8 body part labels). However, this dataset contains missing measurements and lesion tags, and exhibits a severe imbalance in the number of lesions per label category. In this work, we utilize a limited subset of DeepLesion (6%, 1331 lesions, 1309 slices) containing lesion annotations and body part label tags to train a VFNet model to detect lesions and tag them. We address the class imbalance by conducting three experiments: 1) Balancing data by the body part labels, 2) Balancing data by the number of lesions per patient, and 3) Balancing data by the lesion size. In contrast to a randomly sampled (unbalanced) data subset, our results indicated that balancing the body part labels always increased sensitivity for lesions >= 1cm for classes with low data quantities (Bone: 80% vs. 46%, Kidney: 77% vs. 61%, Soft Tissue: 70% vs. 60%, Pelvis: 83% vs. 76%). Similar trends were seen for three other models tested (FasterRCNN, RetinaNet, FoveaBox). Balancing data by lesion size also helped the VFNet model improve recalls for all classes in contrast to an unbalanced dataset. We also provide a structured reporting guideline for a ``Lesions'' subsection to be entered into the ``Findings'' section of a radiology report. To our knowledge, we are the first to report the class imbalance in DeepLesion, and have taken data-driven steps to address it in the context of joint lesion detection and tagging.