No Cover Image

Journal article 2 views

High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy

Tony Tang, Abhinav Mishra, Benjamin Mora Orcid Logo, Bilal Al-Sarireh, Olivia Clare Irvine, Brandon Mauri, Victoria Higginbotham, P.M. Anupama Bandaranayake, S.H. Chandrashekhara, Venkat Kanamarlapudi Orcid Logo, Deb Roy Orcid Logo

Journal of Pathology Informatics, Volume: 21, Start page: 100651

Swansea University Authors: Tony Tang, Abhinav Mishra, Benjamin Mora Orcid Logo, Olivia Clare Irvine, Victoria Higginbotham, Venkat Kanamarlapudi Orcid Logo, Deb Roy Orcid Logo

  • 71658.VoR.pdf

    PDF | Version of Record

    © 2026 The Authors. This is an open access article under the CC BY license.

    Download (2.39MB)

Check full text

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...

Full description

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
first_indexed 2026-03-23T16:01:40Z
last_indexed 2026-04-20T15:39:58Z
id cronfa71658
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>71658</id><entry>2026-03-23</entry><title>High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy</title><swanseaauthors><author><sid>d9d1694b107d75c34e1c4598871c8e74</sid><ORCID/><firstname>Tony</firstname><surname>Tang</surname><name>Tony Tang</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>184021f8cbe2e70e95028fdfb1284f24</sid><ORCID/><firstname>Abhinav</firstname><surname>Mishra</surname><name>Abhinav Mishra</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>557f93dfae240600e5bd4398bf203821</sid><ORCID>0000-0002-2945-3519</ORCID><firstname>Benjamin</firstname><surname>Mora</surname><name>Benjamin Mora</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a3854a376bba1300240d61b64775e91d</sid><ORCID/><firstname>Olivia Clare</firstname><surname>Irvine</surname><name>Olivia Clare Irvine</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>29dd07a8a73cf872888e406e01ee766f</sid><ORCID/><firstname>Victoria</firstname><surname>Higginbotham</surname><name>Victoria Higginbotham</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>63741801137148abfa4c00cd547dcdfa</sid><ORCID>0000-0002-8739-1483</ORCID><firstname>Venkat</firstname><surname>Kanamarlapudi</surname><name>Venkat Kanamarlapudi</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a18d76438369122184e83fb683d8d787</sid><ORCID>0000-0002-7528-8649</ORCID><firstname>Deb</firstname><surname>Roy</surname><name>Deb Roy</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-03-23</date><deptcode>EAAS</deptcode><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.</abstract><type>Journal Article</type><journal>Journal of Pathology Informatics</journal><volume>21</volume><journalNumber/><paginationStart>100651</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2153-3539</issnPrint><issnElectronic/><keywords>Machine learning; Near-infrared; Hyperspectral imaging; Pancreatic cancer; Automated tissue classification; Cancer diagnosis</keywords><publishedDay>1</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-04-01</publishedDate><doi>10.1016/j.jpi.2026.100651</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm>Other</apcterm><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.</funders><projectreference/><lastEdited>2026-04-20T16:51:08.5652572</lastEdited><Created>2026-03-23T10:24:37.3612614</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Chemistry</level></path><authors><author><firstname>Tony</firstname><surname>Tang</surname><orcid/><order>1</order></author><author><firstname>Abhinav</firstname><surname>Mishra</surname><orcid/><order>2</order></author><author><firstname>Benjamin</firstname><surname>Mora</surname><orcid>0000-0002-2945-3519</orcid><order>3</order></author><author><firstname>Bilal</firstname><surname>Al-Sarireh</surname><order>4</order></author><author><firstname>Olivia Clare</firstname><surname>Irvine</surname><orcid/><order>5</order></author><author><firstname>Brandon</firstname><surname>Mauri</surname><order>6</order></author><author><firstname>Victoria</firstname><surname>Higginbotham</surname><orcid/><order>7</order></author><author><firstname>P.M. Anupama</firstname><surname>Bandaranayake</surname><order>8</order></author><author><firstname>S.H.</firstname><surname>Chandrashekhara</surname><order>9</order></author><author><firstname>Venkat</firstname><surname>Kanamarlapudi</surname><orcid>0000-0002-8739-1483</orcid><order>10</order></author><author><firstname>Deb</firstname><surname>Roy</surname><orcid>0000-0002-7528-8649</orcid><order>11</order></author></authors><documents><document><filename>71658__36539__91d1e34ee49240309d2700f2241c313e.pdf</filename><originalFilename>71658.VoR.pdf</originalFilename><uploaded>2026-04-20T16:40:22.7071917</uploaded><type>Output</type><contentLength>2505803</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2026 The Authors. This is an open access article under the CC BY license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 71658 2026-03-23 High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy d9d1694b107d75c34e1c4598871c8e74 Tony Tang Tony Tang true false 184021f8cbe2e70e95028fdfb1284f24 Abhinav Mishra Abhinav Mishra true false 557f93dfae240600e5bd4398bf203821 0000-0002-2945-3519 Benjamin Mora Benjamin Mora true false a3854a376bba1300240d61b64775e91d Olivia Clare Irvine Olivia Clare Irvine true false 29dd07a8a73cf872888e406e01ee766f Victoria Higginbotham Victoria Higginbotham true false 63741801137148abfa4c00cd547dcdfa 0000-0002-8739-1483 Venkat Kanamarlapudi Venkat Kanamarlapudi true false a18d76438369122184e83fb683d8d787 0000-0002-7528-8649 Deb Roy Deb Roy true false 2026-03-23 EAAS 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. Journal Article Journal of Pathology Informatics 21 100651 Elsevier BV 2153-3539 Machine learning; Near-infrared; Hyperspectral imaging; Pancreatic cancer; Automated tissue classification; Cancer diagnosis 1 4 2026 2026-04-01 10.1016/j.jpi.2026.100651 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University Other 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. 2026-04-20T16:51:08.5652572 2026-03-23T10:24:37.3612614 Faculty of Science and Engineering School of Engineering and Applied Sciences - Chemistry Tony Tang 1 Abhinav Mishra 2 Benjamin Mora 0000-0002-2945-3519 3 Bilal Al-Sarireh 4 Olivia Clare Irvine 5 Brandon Mauri 6 Victoria Higginbotham 7 P.M. Anupama Bandaranayake 8 S.H. Chandrashekhara 9 Venkat Kanamarlapudi 0000-0002-8739-1483 10 Deb Roy 0000-0002-7528-8649 11 71658__36539__91d1e34ee49240309d2700f2241c313e.pdf 71658.VoR.pdf 2026-04-20T16:40:22.7071917 Output 2505803 application/pdf Version of Record true © 2026 The Authors. This is an open access article under the CC BY license. true eng http://creativecommons.org/licenses/by/4.0/
title High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
spellingShingle High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
Tony Tang
Abhinav Mishra
Benjamin Mora
Olivia Clare Irvine
Victoria Higginbotham
Venkat Kanamarlapudi
Deb Roy
title_short High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
title_full High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
title_fullStr High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
title_full_unstemmed High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
title_sort High-efficacy and affordable hyperspectral pancreatic tissue image analysis using near-infrared spectroscopy
author_id_str_mv d9d1694b107d75c34e1c4598871c8e74
184021f8cbe2e70e95028fdfb1284f24
557f93dfae240600e5bd4398bf203821
a3854a376bba1300240d61b64775e91d
29dd07a8a73cf872888e406e01ee766f
63741801137148abfa4c00cd547dcdfa
a18d76438369122184e83fb683d8d787
author_id_fullname_str_mv d9d1694b107d75c34e1c4598871c8e74_***_Tony Tang
184021f8cbe2e70e95028fdfb1284f24_***_Abhinav Mishra
557f93dfae240600e5bd4398bf203821_***_Benjamin Mora
a3854a376bba1300240d61b64775e91d_***_Olivia Clare Irvine
29dd07a8a73cf872888e406e01ee766f_***_Victoria Higginbotham
63741801137148abfa4c00cd547dcdfa_***_Venkat Kanamarlapudi
a18d76438369122184e83fb683d8d787_***_Deb Roy
author Tony Tang
Abhinav Mishra
Benjamin Mora
Olivia Clare Irvine
Victoria Higginbotham
Venkat Kanamarlapudi
Deb Roy
author2 Tony Tang
Abhinav Mishra
Benjamin Mora
Bilal Al-Sarireh
Olivia Clare Irvine
Brandon Mauri
Victoria Higginbotham
P.M. Anupama Bandaranayake
S.H. Chandrashekhara
Venkat Kanamarlapudi
Deb Roy
format Journal article
container_title Journal of Pathology Informatics
container_volume 21
container_start_page 100651
publishDate 2026
institution Swansea University
issn 2153-3539
doi_str_mv 10.1016/j.jpi.2026.100651
publisher Elsevier BV
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Chemistry{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Chemistry
document_store_str 1
active_str 0
description 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.
published_date 2026-04-01T16:51:10Z
_version_ 1863005262884896768
score 11.102646

Similar Items