UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions

Dong, Y; Wan, J; Wang, X; Xue, JH; Zou, J; He, H; Li, P; ... Ma, H; + view all (2021) A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions. IEEE Transactions on Medical Imaging 10.1109/TMI.2021.3097200. (In press). Green open access

[thumbnail of Xue_A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions_AAM.pdf]
Preview
Text
Xue_A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions_AAM.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Polarization images encode high resolution microstructural information even at low resolution. We propose a framework combining polarization imaging and traditional microscopy imaging, constructing a dual-modality machine learning framework that is not only accurate but also generalizable and interpretable. We demonstrate the viability of our proposed framework using the cervical intraepithelial neoplasia grading task, providing a polarimetry feature parameter to quantitatively characterize microstructural variations with lesion progression in hematoxylin-eosin-stained pathological sections of cervical precancerous tissues. By taking advantages of polarization imaging techniques and machine learning methods, the model enables interpretable and quantitative diagnosis of cervical precancerous lesion cases with improved sensitivity and accuracy in a low-resolution and wide-field system. The proposed framework applies routine image-analysis technology to identify the macro-structure and segment the target region in H&E-stained pathological images, and then employs emerging polarization method to extract the micro-structure information of the target region, which intends to expand the boundary of the current image-heavy digital pathology, bringing new possibilities for quantitative medical diagnosis.

Type: Article
Title: A Polarization-Imaging-Based Machine Learning Framework for Quantitative Pathological Diagnosis of Cervical Precancerous Lesions
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/TMI.2021.3097200
Publisher version: https://doi.org/10.1109/TMI.2021.3097200
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery-pp.ucl.ac.uk/id/eprint/10132564
Downloads since deposit
16,200Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item