# Weakly Supervised Intracranial Hemorrhage Segmentation using Head-Wise Gradient-Infused Self-Attention Maps from a Swin Transformer in Categorical Learning

arXiv: https://arxiv.org/abs/2304.04902 · HTML: https://mlsanity.com/paper/2304.04902/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 56 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [DeepViT: Towards Deeper Vision Transformer](https://mlsanity.com/paper/2103.11886/) (2021)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Medical Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2009.13120/) (2020)
- [DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2106.06716/) (2021)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation](https://mlsanity.com/paper/2207.08518/) (2022)
- [TransMed: Transformers Advance Multi-modal Medical Image Classification](https://mlsanity.com/paper/2103.05940/) (2021)
- [DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks](https://mlsanity.com/paper/1605.07866/) (2016)
- [Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/1907.12303/) (2019)
- [Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps](https://mlsanity.com/paper/2204.11073/) (2022)
- [Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision](https://mlsanity.com/paper/2004.06816/) (2020)
- [Going to Extremes: Weakly Supervised Medical Image Segmentation](https://mlsanity.com/paper/2009.11988/) (2020)
- [Intracranial Hemorrhage Segmentation Using Deep Convolutional Model](https://mlsanity.com/paper/1910.08643/) (2019)
- [Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Images](https://mlsanity.com/paper/2007.00748/) (2020)
- [ScanNet: A Fast and Dense Scanning Framework for Metastatic Breast Cancer Detection from Whole-Slide Images](https://mlsanity.com/paper/1707.09597/) (2017)
- [GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation](https://mlsanity.com/paper/2112.02841/) (2021)
- [Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference](https://mlsanity.com/paper/2205.04227/) (2022)
- [A Real-World Demonstration of Machine Learning Generalizability: Intracranial Hemorrhage Detection on Head CT](https://mlsanity.com/paper/2102.04869/) (2021)
- [Weakly supervised deep learning-based intracranial hemorrhage localization](https://mlsanity.com/paper/2105.00781/) (2021)

## Built on by (most cited first, 6 of 6)

- [Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model](https://mlsanity.com/paper/2407.20461/) (2024)
- [Parkinson's Disease Detection from Resting State EEG using Multi-Head Graph Structure Learning with Gradient Weighted Graph Attention Explanations](https://mlsanity.com/paper/2408.00906/) (2024)
- [Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior](https://mlsanity.com/paper/2508.00235/) (2025)
- [Benchmarking Class Activation Map Methods for Explainable Brain Hemorrhage Classification on Hemorica Dataset](https://mlsanity.com/paper/2508.17699/) (2025)
- [Weakly supervised segmentation of intracranial aneurysms using a novel 3D focal modulation UNet](https://mlsanity.com/paper/2308.03001/) (2023)
- [Class Activation Map-based Weakly supervised Hemorrhage Segmentation using Resnet-LSTM in Non-Contrast Computed Tomography images](https://mlsanity.com/paper/2309.16627/) (2023)

## Abstract (arXiv)

Intracranial hemorrhage (ICH) is a life-threatening medical emergency that requires timely and accurate diagnosis for effective treatment and improved patient survival rates. While deep learning techniques have emerged as the leading approach for medical image analysis and processing, the most commonly employed supervised learning often requires large, high-quality annotated datasets that can be costly to obtain, particularly for pixel/voxel-wise image segmentation. To address this challenge and facilitate ICH treatment decisions, we introduce a novel weakly supervised method for ICH segmentation, utilizing a Swin transformer trained on an ICH classification task with categorical labels. Our approach leverages a hierarchical combination of head-wise gradient-infused self-attention maps to generate accurate image segmentation. Additionally, we conducted an exploratory study on different learning strategies and showed that binary ICH classification has a more positive impact on self-attention maps compared to full ICH subtyping. With a mean Dice score of 0.44, our technique achieved similar ICH segmentation performance as the popular U-Net and Swin-UNETR models with full supervision and outperformed a similar weakly supervised approach using GradCAM, demonstrating the excellent potential of the proposed framework in challenging medical image segmentation tasks. Our code is available at https://github.com/HealthX-Lab/HGI-SAM.