Multi-phase dual-encoder model for anomaly detection in medical imaging
An error in medical diagnosis is enough to change a life, and many are suffering from incorrect diagnoses. Deep learning models in healthcare face several challenges due to limited and imbalanced datasets, where anomaly samples often dominated in publicly available data and it is problematic to coll...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2025
|
| Online Access: | http://journalarticle.ukm.my/25782/ http://journalarticle.ukm.my/25782/1/267-285%20-.pdf |
| _version_ | 1848816448101679104 |
|---|---|
| author | Nur Rusyidah Azri, Saratha Sathasivam, Majid Khan Majahar Ali, |
| author_facet | Nur Rusyidah Azri, Saratha Sathasivam, Majid Khan Majahar Ali, |
| author_sort | Nur Rusyidah Azri, |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | An error in medical diagnosis is enough to change a life, and many are suffering from incorrect diagnoses. Deep learning models in healthcare face several challenges due to limited and imbalanced datasets, where anomaly samples often dominated in publicly available data and it is problematic to collect independent data due to strict privacy regulations. Furthermore, current models often perform poorly on small sample datasets and lack robustness across various types of medical imaging. To address these issues, we developed a novel model that capable of detecting anomalies in medical imaging across both small and large datasets. This model features a multiple phase of training and validation, with dual encoders and a shared decoder architecture. Our results demonstrate that this model outperforms established classification methods in medical imaging datasets, including BraTS2021, RESC, and BreastMNIST, by achieving superior accuracy in distinguishing normal and anomalous images based on reconstruction error metrics. Furthermore, the research explores the interpretability of latent space features using explanation methods along with visualization techniques. By automating the diagnostic process, our model aligns with Malaysia’s Healthcare Government Plan 2023 to reform the health system over the next 15 years and reduces workload for healthcare professionals. Our model can serve as a foundation for developing reliable diagnostic tools with interpretable latent space to understand the model’s decision. |
| first_indexed | 2025-11-15T01:06:02Z |
| format | Article |
| id | oai:generic.eprints.org:25782 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T01:06:02Z |
| publishDate | 2025 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:257822025-08-20T03:09:33Z http://journalarticle.ukm.my/25782/ Multi-phase dual-encoder model for anomaly detection in medical imaging Nur Rusyidah Azri, Saratha Sathasivam, Majid Khan Majahar Ali, An error in medical diagnosis is enough to change a life, and many are suffering from incorrect diagnoses. Deep learning models in healthcare face several challenges due to limited and imbalanced datasets, where anomaly samples often dominated in publicly available data and it is problematic to collect independent data due to strict privacy regulations. Furthermore, current models often perform poorly on small sample datasets and lack robustness across various types of medical imaging. To address these issues, we developed a novel model that capable of detecting anomalies in medical imaging across both small and large datasets. This model features a multiple phase of training and validation, with dual encoders and a shared decoder architecture. Our results demonstrate that this model outperforms established classification methods in medical imaging datasets, including BraTS2021, RESC, and BreastMNIST, by achieving superior accuracy in distinguishing normal and anomalous images based on reconstruction error metrics. Furthermore, the research explores the interpretability of latent space features using explanation methods along with visualization techniques. By automating the diagnostic process, our model aligns with Malaysia’s Healthcare Government Plan 2023 to reform the health system over the next 15 years and reduces workload for healthcare professionals. Our model can serve as a foundation for developing reliable diagnostic tools with interpretable latent space to understand the model’s decision. Penerbit Universiti Kebangsaan Malaysia 2025-03 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/25782/1/267-285%20-.pdf Nur Rusyidah Azri, and Saratha Sathasivam, and Majid Khan Majahar Ali, (2025) Multi-phase dual-encoder model for anomaly detection in medical imaging. Journal of Quality Measurement and Analysis, 21 (1). pp. 267-285. ISSN 2600-8602 https://www.ukm.my/jqma/ |
| spellingShingle | Nur Rusyidah Azri, Saratha Sathasivam, Majid Khan Majahar Ali, Multi-phase dual-encoder model for anomaly detection in medical imaging |
| title | Multi-phase dual-encoder model for anomaly detection in medical imaging |
| title_full | Multi-phase dual-encoder model for anomaly detection in medical imaging |
| title_fullStr | Multi-phase dual-encoder model for anomaly detection in medical imaging |
| title_full_unstemmed | Multi-phase dual-encoder model for anomaly detection in medical imaging |
| title_short | Multi-phase dual-encoder model for anomaly detection in medical imaging |
| title_sort | multi-phase dual-encoder model for anomaly detection in medical imaging |
| url | http://journalarticle.ukm.my/25782/ http://journalarticle.ukm.my/25782/ http://journalarticle.ukm.my/25782/1/267-285%20-.pdf |