Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset
Accurate and interpretable segmentation of medical images is crucial for computer-aided diagnosis and image-guided interventions. This study explores the integration of semantic segmentation and explainable AI techniques on the MnMs-2 Cardiac MRI dataset. We propose a segmentation model that achieve...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2025-01-01
|
| Series: | Applied Computer Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/acss-2025-0002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823860532502855680 |
|---|---|
| author | Ayoob Mohamed Nettasinghe Oshan Sylvester Vithushan Bowala Helmini Mohideen Hamdaan |
| author_facet | Ayoob Mohamed Nettasinghe Oshan Sylvester Vithushan Bowala Helmini Mohideen Hamdaan |
| author_sort | Ayoob Mohamed |
| collection | DOAJ |
| description | Accurate and interpretable segmentation of medical images is crucial for computer-aided diagnosis and image-guided interventions. This study explores the integration of semantic segmentation and explainable AI techniques on the MnMs-2 Cardiac MRI dataset. We propose a segmentation model that achieves competitive dice scores (nearly 90 %) and Hausdorff distance (less than 70), demonstrating its effectiveness for cardiac MRI analysis. Furthermore, we leverage Grad-CAM, and Feature Ablation, explainable AI techniques, to visualise the regions of interest guiding the model predictions for a target class. This integration enhances interpretability, allowing us to gain insights into the model decision-making process and build trust in its predictions. |
| format | Article |
| id | doaj-art-d05820a6afb64f3190d1506e40788b9d |
| institution | Kabale University |
| issn | 2255-8691 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Computer Systems |
| spelling | doaj-art-d05820a6afb64f3190d1506e40788b9d2025-02-10T13:25:17ZengSciendoApplied Computer Systems2255-86912025-01-01301122010.2478/acss-2025-0002Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI DatasetAyoob Mohamed0Nettasinghe Oshan1Sylvester Vithushan2Bowala Helmini3Mohideen Hamdaan4Informatics Institute of Technology, Colombo, Sri LankaInformatics Institute of Technology, Colombo, Sri LankaInformatics Institute of Technology, Colombo, Sri LankaInformatics Institute of Technology, Colombo, Sri LankaInformatics Institute of Technology, Colombo, Sri LankaAccurate and interpretable segmentation of medical images is crucial for computer-aided diagnosis and image-guided interventions. This study explores the integration of semantic segmentation and explainable AI techniques on the MnMs-2 Cardiac MRI dataset. We propose a segmentation model that achieves competitive dice scores (nearly 90 %) and Hausdorff distance (less than 70), demonstrating its effectiveness for cardiac MRI analysis. Furthermore, we leverage Grad-CAM, and Feature Ablation, explainable AI techniques, to visualise the regions of interest guiding the model predictions for a target class. This integration enhances interpretability, allowing us to gain insights into the model decision-making process and build trust in its predictions.https://doi.org/10.2478/acss-2025-0002cardiac magnetic resonance imaging (cmri) semantic segmentationexplainable ai (xai)residual blocksvision transformer (vit) |
| spellingShingle | Ayoob Mohamed Nettasinghe Oshan Sylvester Vithushan Bowala Helmini Mohideen Hamdaan Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset Applied Computer Systems cardiac magnetic resonance imaging (cmri) semantic segmentation explainable ai (xai) residual blocks vision transformer (vit) |
| title | Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset |
| title_full | Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset |
| title_fullStr | Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset |
| title_full_unstemmed | Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset |
| title_short | Peering into the Heart: A Comprehensive Exploration of Semantic Segmentation and Explainable AI on the MnMs-2 Cardiac MRI Dataset |
| title_sort | peering into the heart a comprehensive exploration of semantic segmentation and explainable ai on the mnms 2 cardiac mri dataset |
| topic | cardiac magnetic resonance imaging (cmri) semantic segmentation explainable ai (xai) residual blocks vision transformer (vit) |
| url | https://doi.org/10.2478/acss-2025-0002 |
| work_keys_str_mv | AT ayoobmohamed peeringintotheheartacomprehensiveexplorationofsemanticsegmentationandexplainableaionthemnms2cardiacmridataset AT nettasingheoshan peeringintotheheartacomprehensiveexplorationofsemanticsegmentationandexplainableaionthemnms2cardiacmridataset AT sylvestervithushan peeringintotheheartacomprehensiveexplorationofsemanticsegmentationandexplainableaionthemnms2cardiacmridataset AT bowalahelmini peeringintotheheartacomprehensiveexplorationofsemanticsegmentationandexplainableaionthemnms2cardiacmridataset AT mohideenhamdaan peeringintotheheartacomprehensiveexplorationofsemanticsegmentationandexplainableaionthemnms2cardiacmridataset |