A framework for explainable deep learning for aiding clinical applications of quantitative phase imaging

Saransh Arora; Arushi Tandon; Srijan Ray; Narasimhan Rajaram; Ishan Barman

doi:10.1117/12.3002172

12 March 2024 A framework for explainable deep learning for aiding clinical applications of quantitative phase imaging

Saransh Arora, Arushi Tandon, Srijan Ray, Narasimhan Rajaram, Ishan Barman

Proceedings Volume 12852, Quantitative Phase Imaging X; 128520H (2024) https://doi.org/10.1117/12.3002172
Event: SPIE BiOS, 2024, San Francisco, California, United States

Conference Poster

Abstract

Quantitative Phase Imaging (QPI) holds immense promise as a powerful label-free and non-invasive clinical diagnostic tool, leveraging its exceptional sensitivity to phase shifts to capture high-quality and unique morphological data. However, as the adoption of deep learning algorithms becomes increasingly enticing for medical image analysis, clinicians’ apprehensions towards their black-box nature is a deterrent for the adoption of novel methods that rely on them. This study advocates for the integration of explainable AI techniques with QPI-based diagnostics to effectively interpret deep learning models' predictions, enabling them in aiding clinician decisions. Using radiation resistance in head and neck cancer as a model system, we investigate cells that have survived exposure to varying levels of radiation. We aim to identify subtle phenotypic differences induced by DNA damage, which might not be readily apparent without the application of sophisticated deep learning analysis. This investigation has the potential to provide valuable insights into the cellular responses to radiation and unravel intricate patterns that traditional analysis methods might overlook, possibly leading to actionable biomarkers. In addition, we compare the results of classical rule based interpretable methods with modern feature importance based explainability to answer - is the trade-off between interpretability and accuracy actually worth it? By providing transparent insights into the decision making process, explainable deep learning empowers clinicians to validate, interpret, and refine diagnostic outcomes, bridging the gap between cutting-edge technology and clinical practice.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Saransh Arora, Arushi Tandon, Srijan Ray, Narasimhan Rajaram, and Ishan Barman "A framework for explainable deep learning for aiding clinical applications of quantitative phase imaging", Proc. SPIE 12852, Quantitative Phase Imaging X, 128520H (12 March 2024); https://doi.org/10.1117/12.3002172

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available