Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.15208 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912659216007168 |
|---|---|
| author | Vega, Daniela Ceballos, Hannah V. Vera, Javier S. Rodriguez, Santiago Perez, Alejandra Castillo, Angela Escobar, Maria Londoño, Dario Sarmiento, Luis A. Castro, Camila I. Rodriguez, Nadiezhda Briceño, Juan C. Arbeláez, Pablo |
| author_facet | Vega, Daniela Ceballos, Hannah V. Vera, Javier S. Rodriguez, Santiago Perez, Alejandra Castillo, Angela Escobar, Maria Londoño, Dario Sarmiento, Luis A. Castro, Camila I. Rodriguez, Nadiezhda Briceño, Juan C. Arbeláez, Pablo |
| contents | Prenatal diagnosis of Congenital Heart Diseases (CHDs) holds great potential for Artificial Intelligence (AI)-driven solutions. However, collecting high-quality diagnostic data remains difficult due to the rarity of these conditions, resulting in imbalanced and low-quality datasets that hinder model performance. Moreover, no public efforts have been made to integrate multiple sources of information, such as imaging and clinical data, further limiting the ability of AI models to support and enhance clinical decision-making. To overcome these challenges, we introduce the Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records (CARDIUM) dataset, the first publicly available multimodal dataset consolidating fetal ultrasound and echocardiographic images along with maternal clinical records for prenatal CHD detection. Furthermore, we propose a robust multimodal transformer architecture that incorporates a cross-attention mechanism to fuse feature representations from image and tabular data, improving CHD detection by 11% and 50% over image and tabular single-modality approaches, respectively, and achieving an F1 score of 79.8 $\pm$ 4.8% in the CARDIUM dataset. We will publicly release our dataset and code to encourage further research on this unexplored field. Our dataset and code are available at https://github.com/BCV-Uniandes/Cardium, and at the project website https://bcv-uniandes.github.io/CardiumPage/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15208 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CARDIUM: Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records Vega, Daniela Ceballos, Hannah V. Vera, Javier S. Rodriguez, Santiago Perez, Alejandra Castillo, Angela Escobar, Maria Londoño, Dario Sarmiento, Luis A. Castro, Camila I. Rodriguez, Nadiezhda Briceño, Juan C. Arbeláez, Pablo Computer Vision and Pattern Recognition Prenatal diagnosis of Congenital Heart Diseases (CHDs) holds great potential for Artificial Intelligence (AI)-driven solutions. However, collecting high-quality diagnostic data remains difficult due to the rarity of these conditions, resulting in imbalanced and low-quality datasets that hinder model performance. Moreover, no public efforts have been made to integrate multiple sources of information, such as imaging and clinical data, further limiting the ability of AI models to support and enhance clinical decision-making. To overcome these challenges, we introduce the Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records (CARDIUM) dataset, the first publicly available multimodal dataset consolidating fetal ultrasound and echocardiographic images along with maternal clinical records for prenatal CHD detection. Furthermore, we propose a robust multimodal transformer architecture that incorporates a cross-attention mechanism to fuse feature representations from image and tabular data, improving CHD detection by 11% and 50% over image and tabular single-modality approaches, respectively, and achieving an F1 score of 79.8 $\pm$ 4.8% in the CARDIUM dataset. We will publicly release our dataset and code to encourage further research on this unexplored field. Our dataset and code are available at https://github.com/BCV-Uniandes/Cardium, and at the project website https://bcv-uniandes.github.io/CardiumPage/ |
| title | CARDIUM: Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.15208 |