Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.12268 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912876464177152 |
|---|---|
| author | Mukherjee, Rupam Daniel, Rajkumar Hazra, Soujanya Dasgupta, Shirin Mandal, Subhamoy |
| author_facet | Mukherjee, Rupam Daniel, Rajkumar Hazra, Soujanya Dasgupta, Shirin Mandal, Subhamoy |
| contents | Early detection of oral cancer and potentially malignant diseases is a major challenge in low-resource settings due to the scarcity of annotated data. We provide a unified approach for four-class oral lesion classification that incorporates deep learning, spectral analysis, and demographic data. A pathologist-verified subset of oral cavity images was curated from a publicly available dataset. Oral cavity pictures were processed using a fine-tuned ConvNeXt-v2 network for deep embeddings before being translated into the hyperspectral domain using a reconstruction algorithm. Haemoglobin-sensitive, textural, and spectral descriptors were obtained from the reconstructed hyperspectral cubes and combined with demographic data. Multiple machine-learning models were evaluated using patient-specific validation. Finally, an incremental heuristic meta-learner (IHML) was developed that merged calibrated base classifiers via probabilistic feature stacking and uncertainty-aware abstraction of multimodal representations with patient-level smoothing. By decoupling evidence extraction from decision fusion, IHML stabilizes predictions in heterogeneous, small-sample medical datasets. On an unseen test set, our proposed model achieved a macro F1 of 66.23% and an overall accuracy of 64.56%. The findings demonstrate that RGB-to-hyperspectral reconstruction and ensemble meta-learning improve diagnostic robustness in real-world oral lesion screening. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12268 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Patient-Aware Multimodal RGB-HSI Fusion via Incremental Heuristic Meta-Learning for Oral Lesion Classification Mukherjee, Rupam Daniel, Rajkumar Hazra, Soujanya Dasgupta, Shirin Mandal, Subhamoy Image and Video Processing Computer Vision and Pattern Recognition Early detection of oral cancer and potentially malignant diseases is a major challenge in low-resource settings due to the scarcity of annotated data. We provide a unified approach for four-class oral lesion classification that incorporates deep learning, spectral analysis, and demographic data. A pathologist-verified subset of oral cavity images was curated from a publicly available dataset. Oral cavity pictures were processed using a fine-tuned ConvNeXt-v2 network for deep embeddings before being translated into the hyperspectral domain using a reconstruction algorithm. Haemoglobin-sensitive, textural, and spectral descriptors were obtained from the reconstructed hyperspectral cubes and combined with demographic data. Multiple machine-learning models were evaluated using patient-specific validation. Finally, an incremental heuristic meta-learner (IHML) was developed that merged calibrated base classifiers via probabilistic feature stacking and uncertainty-aware abstraction of multimodal representations with patient-level smoothing. By decoupling evidence extraction from decision fusion, IHML stabilizes predictions in heterogeneous, small-sample medical datasets. On an unseen test set, our proposed model achieved a macro F1 of 66.23% and an overall accuracy of 64.56%. The findings demonstrate that RGB-to-hyperspectral reconstruction and ensemble meta-learning improve diagnostic robustness in real-world oral lesion screening. |
| title | Patient-Aware Multimodal RGB-HSI Fusion via Incremental Heuristic Meta-Learning for Oral Lesion Classification |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.12268 |