Leveraging mid-infrared spectroscopic imaging and deep learning for tissue subtype classification in ovarian cancer

TL;DR

This study introduces a label-free, automated method using advanced mid-infrared spectroscopic imaging and deep learning to accurately classify ovarian tissue subtypes, potentially enhancing early cancer diagnosis and histopathology analysis.

Contribution

It presents the first use of optical photothermal infrared imaging combined with deep learning for quantitative, label-free ovarian tissue classification with high accuracy and validation on extensive patient data.

Findings

Achieved 98% classification accuracy for ovarian cell subtypes.

Demonstrated sub-cellular resolution surpassing diffraction-limited techniques.

Validated robustness with 74 patient samples and over 60 million data points.

Abstract

Mid-infrared spectroscopic imaging (MIRSI) is an emerging class of label-free techniques being leveraged for digital histopathology. Modern histopathologic identification of ovarian cancer involves tissue staining followed by morphological pattern recognition. This process is time-consuming, subjective, and requires extensive expertise. This paper presents the first label-free, quantitative, and automated histological recognition of ovarian tissue subtypes using a new MIRSI technique. This technique, called optical photothermal infrared (O-PTIR) imaging, provides a 10X enhancement in spatial resolution relative to prior instruments. It enables sub-cellular spectroscopic investigation of tissue at biochemically important fingerprint wavelengths. We demonstrate that enhanced resolution of sub-cellular features, combined with spectroscopic information, enables reliable classification of ovarian cell subtypes achieving a classification accuracy of 0.98. Moreover, we present statistically robust validation from 74 patient samples with over 60 million data points. We show that sub-cellular resolution from five wavenumbers is sufficient to outperform state-of-the-art diffraction-limited techniques from up to 235 wavenumbers. We also propose two quantitative biomarkers based on the relative quantities of epithelium and stroma that exhibits efficacy in early cancer diagnosis. This paper demonstrates that combining deep learning with intrinsic biochemical MIRSI measurements enables quantitative evaluation of cancerous tissue, improving the rigor and reproducibility of histopathology.