# ICHPro: Intracerebral Hemorrhage Prognosis Classification Via Joint-attention Fusion-based 3d Cross-modal Network

arXiv: https://arxiv.org/abs/2402.11307 · HTML: https://mlsanity.com/paper/2402.11307/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 17 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier](https://mlsanity.com/paper/2112.09356/) (2021)
- [AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification](https://mlsanity.com/paper/2101.08238/) (2021)
- [Refining activation downsampling with SoftPool](https://mlsanity.com/paper/2101.00440/) (2021)
- [GCS-ICHNet: Assessment of Intracerebral Hemorrhage Prognosis using Self-Attention with Domain Knowledge Integration](https://mlsanity.com/paper/2311.04772/) (2023)

## Built on by (most cited first, 10 of 10)

- [CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching](https://mlsanity.com/paper/2410.12261/) (2024)
- [Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts](https://mlsanity.com/paper/2504.12782/) (2025)
- [ICH-SCNet: Intracerebral Hemorrhage Segmentation and Prognosis Classification Network Using CLIP-guided SAM mechanism](https://mlsanity.com/paper/2411.04656/) (2024)
- [K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2505.23017/) (2025)
- [A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning](https://mlsanity.com/paper/2506.07236/) (2025)
- [TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2505.23312/) (2025)
- [Dual form Complementary Masking for Domain-Adaptive Image Segmentation](https://mlsanity.com/paper/2507.12008/) (2025)
- [TMI-CLNet: Triple-Modal Interaction Network for Chronic Liver Disease Prognosis From Imaging, Clinical, and Radiomic Data Fusion](https://mlsanity.com/paper/2502.00695/) (2025)
- [FADE: Adversarial Concept Erasure in Flow Models](https://mlsanity.com/paper/2507.12283/) (2025)
- [DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction](https://mlsanity.com/paper/2512.20898/) (2025)

## Abstract (arXiv)

Intracerebral Hemorrhage (ICH) is the deadliest subtype of stroke, necessitating timely and accurate prognostic evaluation to reduce mortality and disability. However, the multi-factorial nature and complexity of ICH make methods based solely on computed tomography (CT) image features inadequate. Despite the capacity of cross-modal networks to fuse additional information, the effective combination of different modal features remains a significant challenge. In this study, we propose a joint-attention fusion-based 3D cross-modal network termed ICHPro that simulates the ICH prognosis interpretation process utilized by neurosurgeons. ICHPro includes a joint-attention fusion module to fuse features from CT images with demographic and clinical textual data. To enhance the representation of cross-modal features, we introduce a joint loss function. ICHPro facilitates the extraction of richer cross-modal features, thereby improving classification performance. Upon testing our method using a five-fold cross-validation, we achieved an accuracy of 89.11%, an F1 score of 0.8767, and an AUC value of 0.9429. These results outperform those obtained from other advanced methods based on the test dataset, thereby demonstrating the superior efficacy of ICHPro. The code is available at our Github: https://github.com/YU-deep/ICH.