Explainable AI-Based Feature Selection Approaches for Raman Spectroscopy
Diagnostics · 18.08.2025 · 15 (16) · 2063
DOI: 10.3390/diagnostics15162063 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 18.08.2025. Verfasst von Nicola Rossberg und 4 weiteren Autor:innen. Beteiligte Einrichtung: Taighde Éireann-Research Ireland Center for Research Training in Artificial Intelligence, University College Cork, College Road, T12 K8AF Cork, Irela…. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Taighde Éireann - Research Ireland, the Taighde Éireann–Research Ireland, European Regional Development Fund.
Abstract (Originalsprache)
Background
Raman Spectroscopy is a non-invasive technique capable of characterising tissue constituents and detecting conditions such as cancer with high accuracy. Machine learning techniques can automate this task and discover relevant data patterns. However, the high-dimensional, multicollinear nature of Raman data makes their deployment and explainability challenging. A model’s transparency and ability to explain decision pathways have become crucial for medical integration. Consequently, an effective method of feature-reduction while minimising information loss is sought.
Methods
Two new feature selection methods for Raman spectroscopy are introduced. These methods are based on explainable deep learning approaches, considering Convolutional Neural Networks and Transformers. Their features are extracted using GradCam and attention scores, respectively. The performance of the extracted features is compared to established feature selection approaches across four classifiers and three datasets.
Results
We compared the proposed method against established feature selection approaches over three real-world datasets and different compression levels. Comparable accuracy levels were obtained using only 10% of features. Model-based approaches are the most accurate. Using Convolutional Neural Networks and Random Forest-assigned feature importance performs best when maintaining between 5–20% of features, while LinearSVC with L1 penalisation leads to higher accuracy when selecting only 1% of them. The proposed Convolutional Neural Networks-based GradCam approach has the highest average accuracy.
Conclusions
No approach is found to perform best in all scenarios, suggesting that multiple alternatives should be assessed in each application.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Taighde Éireann-Research Ireland Center for Research Training in Artificial Intelligence, University College Cork, College Road, T12 K8AF Cork, Ireland.
- School of Computer Science and Information Technology, University College Cork, College Road, T12 K8AF Cork, Ireland.
- Tyndall National Institute, Lee Maltings Complex Dyke Parade, T12 R5CP Cork, Ireland.
- Insight Center for Data Analytics, University College Cork, College Road, T12 K8AF Cork, Ireland.
ORCID-Profile: Nicola Rossberg, Rekha Gautam, Katarzyna Komolibus, Barry O'Sullivan, Andrea Visentin
Förderung
- Taighde Éireann - Research Ireland
- the Taighde Éireann–Research Ireland
- European Regional Development Fund
Zitieren
APA
Rossberg, N., Gautam, R., Komolibus, K., O'Sullivan, B., & Visentin, A. (2025). Explainable AI-Based Feature Selection Approaches for Raman Spectroscopy. Diagnostics, 15(16), 2063. https://doi.org/10.3390/diagnostics15162063
Vancouver
Rossberg N, Gautam R, Komolibus K, O'Sullivan B, Visentin A. Explainable AI-Based Feature Selection Approaches for Raman Spectroscopy. Diagnostics. 2025;15(16):2063. doi:10.3390/diagnostics15162063
BibTeX
@article{Rossberg2025,
author = {Rossberg, Nicola and Gautam, Rekha and Komolibus, Katarzyna and O'Sullivan, Barry and Visentin, Andrea},
title = {Explainable AI-Based Feature Selection Approaches for Raman Spectroscopy},
journal = {Diagnostics},
year = {2025},
volume = {15},
number = {16},
pages = {2063},
doi = {10.3390/diagnostics15162063}
}
EUVIMED