# GP-Unet: Lesion Detection from Weak Labels with a 3D Regression Network

arXiv: https://arxiv.org/abs/1705.07999 · HTML: https://mlsanity.com/paper/1705.07999/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2017.

## Built on by (most cited first, 7 of 7)

- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models](https://mlsanity.com/paper/2110.08429/) (2021)
- [From Classification to Segmentation with Explainable AI: A Study on Crack Detection and Growth Monitoring](https://mlsanity.com/paper/2309.11267/) (2023)
- [Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classification](https://mlsanity.com/paper/2206.05148/) (2022)
- [Computer-Aided Extraction of Select MRI Markers of Cerebral Small Vessel Disease: A Systematic Review](https://mlsanity.com/paper/2204.01411/) (2022)
- [Perivascular space Identification Nnunet for Generalised Usage (PINGU)](https://mlsanity.com/paper/2405.08337/) (2024)
- [KANDU-Net:A Dual-Channel U-Net with KAN for Medical Image Segmentation](https://mlsanity.com/paper/2409.20414/) (2024)

## Abstract (arXiv)

We propose a novel convolutional neural network for lesion detection from weak labels. Only a single, global label per image - the lesion count - is needed for training. We train a regression network with a fully convolutional architecture combined with a global pooling layer to aggregate the 3D output into a scalar indicating the lesion count. When testing on unseen images, we first run the network to estimate the number of lesions. Then we remove the global pooling layer to compute localization maps of the size of the input image. We evaluate the proposed network on the detection of enlarged perivascular spaces in the basal ganglia in MRI. Our method achieves a sensitivity of 62% with on average 1.5 false positives per image. Compared with four other approaches based on intensity thresholding, saliency and class maps, our method has a 20% higher sensitivity.