Journal article 2 views
High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
,
Bilal Al-Sarireh,
Olivia Clare Irvine,
Brandon Mauri,
Victoria Higginbotham,
P.M. Anupama Bandaranayake,
S.H. Chandrashekhara,
Venkat Kanamarlapudi ,
Deb Roy
Journal of Pathology Informatics, Volume: 21, Start page: 100651
Swansea University Authors:
Tony Tang, Abhinav Mishra, Benjamin Mora , Olivia Clare Irvine, Victoria Higginbotham, Venkat Kanamarlapudi , Deb Roy
-
PDF | Version of Record
© 2026 The Authors. This is an open access article under the CC BY license.
Download (2.39MB)
DOI (Published version): 10.1016/j.jpi.2026.100651
Abstract
Pancreatic cancer remains one of the most lethal malignancies with less than 10% five-year survival rates, primarily due to late-stage diagnosis and limited early detection capabilities. Current diagnostic methods are expensive, time-intensive, and often inadequate for widespread screening applicati...
| Published in: | Journal of Pathology Informatics |
|---|---|
| ISSN: | 2153-3539 |
| Published: |
Elsevier BV
2026
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa71658 |
| Abstract: |
Pancreatic cancer remains one of the most lethal malignancies with less than 10% five-year survival rates, primarily due to late-stage diagnosis and limited early detection capabilities. Current diagnostic methods are expensive, time-intensive, and often inadequate for widespread screening applications. This study presents a novel, cost-effective approach using near-infrared (NIR) hyperspectral imaging combined with advanced machine learning for automated pancreatic tissue classification. We have developed a comprehensive pipeline incorporating autoencoder-based spatial feature extraction, multi-method consensus outlier detection, and systematically optimized neural network classifiers to distinguish between cancerous and non-cancerous pancreatic tissue samples. Our methodology was evaluated on 78 tissue microarray samples, with rigorous quality control yielding a final dataset of 69 high-quality specimens. The optimized classification model achieved 84% balanced accuracy using leave-one-out cross-validation, representing a 10% point improvement over conventional FICA+SVM approaches (74.0%) and approaching the performance of expensive conventional histopathological methods. Key technical innovations include consensus-based outlier detection, systematic hyperparameter optimization revealing optimal single-layer architectures with ELU activation, and interpretable attention mechanisms for diagnostic decision support. The demonstrated cost-effectiveness of NIR instrumentation combined with robust classification performance positions this approach as a promising pathway toward accessible, real-time pancreatic cancer screening tools that could significantly impact early detection rates and patient outcomes in diverse clinical settings. |
|---|---|
| Keywords: |
Machine learning; Near-infrared; Hyperspectral imaging; Pancreatic cancer; Automated tissue classification; Cancer diagnosis |
| College: |
Faculty of Science and Engineering |
| Funders: |
ZT acknowledges financial support from EPSRC and Swansea Bay Health Board. AM and DR acknowledge financial support from 23IND08 DI-VISION project and Hyper-Path project. The work has been carried out within the project 23IND08 DI-VISION which has received funding from the European Partnership on Metrology, cofinanced from the European Uninon's Horizon Europe Research and Innovation Programme and by the Participating States. Views and opinions expressed are however those of the author only and do not necessariliy reflect those of the European Union or EURAMET. Neither the European Union nor the granting authority can be held responsible for them. European Union's Horizon 2020 research and innovation program. The project Hyper-Path has received funding from Cancer Research Wales. |
| Start Page: |
100651 |