| Title: |
Feature Fusion of Raman Chemical Imaging and Digital Histopathology using Machine Learning for Prostate Cancer Detection |
| Authors: |
Doherty, Trevor; McKeever, Susan; Al-Attar, Nebras; Murphy, Tiarnán; Aura, Claudia; Rahman, Arman; O'Neill,, Amanda; Finn, Stephen P.; Kay, Elaine; Gallagher, William M.; Watson, William G.; Gowen, Aoife; Jackman, Patrick |
| Contributors: |
Irish Health Research Board (Grant Number HRA-POR-2015-1078), with additional support from the Science Foundation Ireland Investigator Programme OPTi-PREDICT (grant code 15/IA/3104); and the Science Foundation Ireland Strategic Partnership Programme Precision Oncology Ireland POI (grant code 18/SPP/3522). Funding for the Irish Prostate Cancer Research Consortium tissue samples was from Science Foundation Ireland, Grant number: TRA/2010/18; Irish Cancer Society, Grant number: PCI11WAT; Welcome Trust-HRB Dublin Centre for Clinical Research. |
| Source: |
Articles |
| Publisher Information: |
Technological University Dublin |
| Publication Year: |
2021 |
| Collection: |
Dublin Institute of Technology: ARROW@DIT (Archiving Research Resources on he Web) |
| Subject Terms: |
Raman Chemical Imaging; Digital Histopathology; Machine Learning; Prostate Cancer Detection; Engineering |
| Description: |
The diagnosis of prostate cancer is challenging due to the heterogeneity of its presentations, leading to the over diagnosis and treatment of non-clinically important disease. Accurate diagnosis can directly benefit a patient’s quality of life and prognosis. Towards addressing this issue, we present a learning model for the automatic identification of prostate cancer. While many prostate cancer studies have adopted Raman spectroscopy approaches, none have utilised the combination of Raman Chemical Imaging (RCI) and other imaging modalities. This study uses multimodal images formed from stained Digital Histopathology (DP) and unstained RCI. The approach was developed and tested on a set of 178 clinical samples from 32 patients, containing a range of non-cancerous, Gleason grade 3 (G3) and grade 4 (G4) tissue microarray samples. For each histological sample, there is a pathologist labelled DP - RCI image pair. The hypothesis tested was whether multimodal image models can outperform single modality baseline models in terms of diagnostic accuracy. Binary non-cancer/cancer models and the more challenging G3/G4 differentiation were investigated. Regarding G3/G4 classification, the multimodal approach achieved a sensitivity of 73.8% and specificity of 88.1% while the baseline DP model showed a sensitivity and specificity of 54.1% and 84.7% respectively. The multimodal approach demonstrated a statistically significant 12.7% AUC advantage over the baseline with a value of 85.8% compared to 73.1%, also outperforming models based solely on RCI and median Raman spectra. Feature fusion of DP and RCI does not improve the more trivial task of tumour identification but does deliver an observed advantage in G3/G4 discrimination. Building on these promising findings, future work could include the acquisition of larger datasets for enhanced model generalization. |
| Document Type: |
article in journal/newspaper |
| File Description: |
application/pdf |
| Language: |
unknown |
| Relation: |
https://arrow.tudublin.ie/scschcomart/170; https://arrow.tudublin.ie/context/scschcomart/article/1183/viewcontent/Feature_Fusion_of_Raman_Chemical_Imaging_and_Digital.pdf |
| DOI: |
10.1039/D1AN00075F |
| Availability: |
https://arrow.tudublin.ie/scschcomart/170; https://doi.org/10.1039/D1AN00075F; https://arrow.tudublin.ie/context/scschcomart/article/1183/viewcontent/Feature_Fusion_of_Raman_Chemical_Imaging_and_Digital.pdf |
| Rights: |
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence ; http://creativecommons.org/licenses/by-nd/4.0/ |
| Accession Number: |
edsbas.8C2D15B |
| Database: |
BASE |