# MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection

arXiv: https://arxiv.org/abs/1909.04247 · HTML: https://mlsanity.com/paper/1909.04247/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics](https://mlsanity.com/paper/2306.00864/) (2023)
- [SSMD: Semi-Supervised Medical Image Detection with Adaptive Consistency and Heterogeneous Perturbation](https://mlsanity.com/paper/2106.01544/) (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)
- [DualAttNet: Synergistic Fusion of Image-level and Fine-Grained Disease Attention for Multi-Label Lesion Detection in Chest X-rays](https://mlsanity.com/paper/2306.13813/) (2023)
- [RECIST-Net: Lesion detection via grouping keypoints on RECIST-based annotation](https://mlsanity.com/paper/2107.08715/) (2021)
- [Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training](https://mlsanity.com/paper/2201.01426/) (2022)
- [SSD-Faster Net: A Hybrid Network for Industrial Defect Inspection](https://mlsanity.com/paper/2207.00589/) (2022)
- [Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer](https://mlsanity.com/paper/2404.03819/) (2024)
- [Decodable and Sample Invariant Continuous Object Encoder](https://mlsanity.com/paper/2311.00187/) (2023)
- [Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data](https://mlsanity.com/paper/2103.12972/) (2021)
- [DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection](https://mlsanity.com/paper/2203.06886/) (2022)
- [An End-to-End Framework For Universal Lesion Detection With Missing Annotations](https://mlsanity.com/paper/2303.15024/) (2023)
- [3DLAND: 3D Lesion Abdominal Anomaly Localization Dataset](https://mlsanity.com/paper/2602.12820/) (2026)
- [An Efficient Anchor-free Universal Lesion Detection in CT-scans](https://mlsanity.com/paper/2203.16074/) (2022)
- [Integrating features from lymph node stations for metastatic lymph node detection](https://mlsanity.com/paper/2301.03202/) (2023)
- [Mixed-order self-paced curriculum learning for universal lesion detection](https://mlsanity.com/paper/2302.04677/) (2023)
- [MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images](https://mlsanity.com/paper/2505.18741/) (2025)

## Abstract (arXiv)

Universal lesion detection (ULD) on computed tomography (CT) images is an important but underdeveloped problem. Recently, deep learning-based approaches have been proposed for ULD, aiming to learn representative features from annotated CT data. However, the hunger for data of deep learning models and the scarcity of medical annotation hinders these approaches to advance further. In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors. Specifically, as radiologists tend to inspect multiple windows for an accurate diagnosis, we explicitly model this process and propose a multi-view feature pyramid network (FPN), where multi-view features are extracted from images rendered with varied window widths and window levels; to effectively combine this multi-view information, we further propose a position-aware attention module. With the proposed model design, the data-hunger problem is relieved as the learning task is made easier with the correctly induced clinical practice prior. We show promising results with the proposed model, achieving an absolute gain of 5.65% (in the sensitivity of FPs@4.0) over the previous state-of-the-art on the NIH DeepLesion dataset.