Multimodal RGB-HSI Feature Fusion with Patient-Aware Incremental Heuristic Meta-Learning for Oral Lesion Classification

• URL: http://arxiv.org/abs/2511.12268v1
• Date: Sat, 15 Nov 2025 15:48:28 GMT
• Title: Multimodal RGB-HSI Feature Fusion with Patient-Aware Incremental Heuristic Meta-Learning for Oral Lesion Classification
• Authors: Rupam Mukherjee, Rajkumar Daniel, Soujanya Hazra, Shirin Dasgupta, Subhamoy Mandal,
• Abstract summary: We present a unified four-class oral lesion classifier that integrates deep RGB embeddings, hyperspectral reconstruction, handcrafted spectral-textural descriptors, and demographic metadata.<n>Results demonstrate that hyperspectral reconstruction and uncertainty-aware meta-learning substantially improve robustness for real-world oral lesion screening.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Early detection of oral cancer and potentially malignant disorders is challenging in low-resource settings due to limited annotated data. We present a unified four-class oral lesion classifier that integrates deep RGB embeddings, hyperspectral reconstruction, handcrafted spectral-textural descriptors, and demographic metadata. A pathologist-verified subset of oral cavity images was curated and processed using a fine-tuned ConvNeXt-v2 encoder, followed by RGB-to-HSI reconstruction into 31-band hyperspectral cubes. Haemoglobin-sensitive indices, texture features, and spectral-shape measures were extracted and fused with deep and clinical features. Multiple machine-learning models were assessed with patient-wise validation. We further introduce an incremental heuristic meta-learner (IHML) that combines calibrated base classifiers through probabilistic stacking and patient-level posterior smoothing. On an unseen patient split, the proposed framework achieved a macro F1 of 66.23% and an accuracy of 64.56%. Results demonstrate that hyperspectral reconstruction and uncertainty-aware meta-learning substantially improve robustness for real-world oral lesion screening.

Related papers

• XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas [1.9322492427205764]
  XtraLight-MedMamba is an ultra-lightweight state-space-based deep learning framework for classifying tubular adenomas.<n>The model was evaluated on a curated dataset acquired from patients with low-grade tubular adenomas.<n>XtraLight-MedMamba achieved an accuracy of 97.18% and an F1-score of 0.9767 using approximately 32,000 parameters.
  arXiv  Detail & Related papers  (2026-02-04T18:07:51Z)
• One-shot synthesis of rare gastrointestinal lesions improves diagnostic accuracy and clinical training [45.49415063761575]
  EndoRare is a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image.<n>We validated the framework across four rare pathologies.<n>These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.
  arXiv  Detail & Related papers  (2025-12-30T15:07:09Z)
• Hemorica: A Comprehensive CT Scan Dataset for Automated Brain Hemorrhage Classification, Segmentation, and Detection [0.749500254646884]
  Hemorica is a publicly available collection of 372 head CT examinations acquired between 2012 and 2024.<n>Each scan has been exhaustively annotated for five ICH subtypes-epidural (EPH), subdural (SDH), subarachnoid (SAH), intraparenchymal (IPH)<n>Hemorica offers a unified, fine-grained benchmark that supports multi-task and curriculum learning.
  arXiv  Detail & Related papers  (2025-09-26T23:09:41Z)
• Exploring Strategies for Personalized Radiation Therapy Part I Unlocking Response-Related Tumor Subregions with Class Activation Mapping [17.401088816596054]
  This study compares three approaches for predicting treatment response: standard radiomics, gradient based features, and convolutional neural networks enhanced with Class Activation Mapping.<n>We analyzed 69 brain metastases from 39 patients treated with Gamma Knife radiosurgery.<n> Pixel wise CAM outperformed both radiomics and gradient based methods in classification accuracy.
  arXiv  Detail & Related papers  (2025-06-21T01:24:25Z)
• Hybrid Ensemble of Segmentation-Assisted Classification and GBDT for Skin Cancer Detection with Engineered Metadata and Synthetic Lesions from ISIC 2024 Non-Dermoscopic 3D-TBP Images [0.0]
  This work presents a hybrid machine and deep learning-based approach for classifying skin lesions.<n>It comprises 401,059 cropped lesion images extracted from 3D Total Body Photography (TBP), emulating non-dermoscopic, smartphone-like conditions.<n>Predictions are fused with a gradient-boosted decision tree (GBDT) ensemble enriched by engineered features and patient-specific relational metrics.
  arXiv  Detail & Related papers  (2025-06-03T22:00:03Z)
• GS-TransUNet: Integrated 2D Gaussian Splatting and Transformer UNet for Accurate Skin Lesion Analysis [44.99833362998488]
  We present a novel approach that combines 2D Gaussian splatting with the Transformer UNet architecture for automated skin cancer diagnosis.<n>Our findings illustrate significant advancements in the precision of segmentation and classification.<n>This integration sets new benchmarks in the field and highlights the potential for further research into multi-task medical image analysis methodologies.
  arXiv  Detail & Related papers  (2025-02-23T23:28:47Z)
• RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging [7.2993064695496255]
  This study investigates the reconstruction of hyperspectral signatures from RGB data to enhance surgical imaging. Various architectures based on convolutional neural networks (CNNs) and transformer models are evaluated. Transformer models exhibit superior performance in terms of RMSE, SAM, PSNR and SSIM.
  arXiv  Detail & Related papers  (2024-10-17T14:05:41Z)
• Orientation-Shared Convolution Representation for CT Metal Artifact Learning [63.67718355820655]
  During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts. Existing deep-learning-based methods have gained promising reconstruction performance. We propose an orientation-shared convolution representation strategy to adapt the physical prior structures of artifacts.
  arXiv  Detail & Related papers  (2022-12-26T13:56:12Z)
• Comparison of Machine Learning Classifiers to Predict Patient Survival and Genetics of GBM: Towards a Standardized Model for Clinical Implementation [44.02622933605018]
  Radiomic models have been shown to outperform clinical data for outcome prediction in glioblastoma (GBM) We aimed to compare nine machine learning classifiers to predict overall survival (OS), isocitrate dehydrogenase (IDH) mutation, O-6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation, epidermal growth factor receptor (EGFR) VII amplification and Ki-67 expression in GBM patients. xGB obtained maximum accuracy for OS (74.5%), AB for IDH mutation (88%), MGMT methylation (71,7%), Ki-67 expression (86,6%), and EGFR amplification (81,
  arXiv  Detail & Related papers  (2021-02-10T15:10:37Z)
• Spectral-Spatial Recurrent-Convolutional Networks for In-Vivo Hyperspectral Tumor Type Classification [49.32653090178743]
  We demonstrate the feasibility of in-vivo tumor type classification using hyperspectral imaging and deep learning. Our best model achieves an AUC of 76.3%, significantly outperforming previous conventional and deep learning methods.
  arXiv  Detail & Related papers  (2020-07-02T12:00:53Z)
• Spatio-spectral deep learning methods for in-vivo hyperspectral laryngeal cancer detection [49.32653090178743]
  Early detection of head and neck tumors is crucial for patient survival. Hyperspectral imaging (HSI) can be used for non-invasive detection of head and neck tumors. We present multiple deep learning techniques for in-vivo laryngeal cancer detection based on HSI.
  arXiv  Detail & Related papers  (2020-04-21T17:07:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.