Opin vísindi

Automated Cancer Diagnostics via Analysis of Optical and Chemical Images by Deep and Shallow Learning

Automated Cancer Diagnostics via Analysis of Optical and Chemical Images by Deep and Shallow Learning


Title: Automated Cancer Diagnostics via Analysis of Optical and Chemical Images by Deep and Shallow Learning
Author: Isberg, Olof Gerdur
Giunchiglia, Valentina
McKenzie, James S.
Takats, Zoltan
Jonasson, Jon Gunnlaugur
Bodvarsdottir, Sigridur Klara   orcid.org/0000-0001-8799-8018
Thorsteinsdottir, Margret
Xiang, Yuchen
Date: 2022-05
Language: English
Scope:
University/Institute: Landspitali - The National University Hospital of Iceland
Department: Faculty of Medicine
Clinical Laboratory Services, Diagnostics and Blood Bank
Faculty of Pharmaceutical Sciences
Series: Metabolites; 12(5)
ISSN: 2218-1989
DOI: https://doi.org/10.3390/metabo12050455
Subject: Meinafræði; deep learning; DESI-MSI; diagnostics; FFPE; mass spectrometry imaging; shallow learning; Endocrinology, Diabetes and Metabolism; Biochemistry; Molecular Biology
URI: https://hdl.handle.net/20.500.11815/3435

Show full item record

Citation:

Isberg , O G , Giunchiglia , V , McKenzie , J S , Takats , Z , Jonasson , J G , Bodvarsdottir , S K , Thorsteinsdottir , M & Xiang , Y 2022 , ' Automated Cancer Diagnostics via Analysis of Optical and Chemical Images by Deep and Shallow Learning ' , Metabolites , vol. 12 , no. 5 , 455 . https://doi.org/10.3390/metabo12050455

Abstract:

Optical microscopy has long been the gold standard to analyse tissue samples for the diagnostics of various diseases, such as cancer. The current diagnostic workflow is time-consuming and labour-intensive, and manual annotation by a qualified pathologist is needed. With the ever-increasing number of tissue blocks and the complexity of molecular diagnostics, new approaches have been developed as complimentary or alternative solutions for the current workflow, such as digital pathology and mass spectrometry imaging (MSI). This study compares the performance of a digital pathology workflow using deep learning for tissue recognition and an MSI approach utilising shallow learning to annotate formalin-fixed and paraffin-embedded (FFPE) breast cancer tissue microarrays (TMAs). Results show that both deep learning algorithms based on conventional optical images and MSI-based shallow learning can provide automated diagnostics with F1-scores higher than 90%, with the latter intrinsically built on biochemical information that can be used for further analysis.

Description:

Funding Information: The Icelandic Centre for Research, grant no. 174566051 & 207301. The Icelandic Breast Cancer Research Fund, Göngum Saman. CRUK GC, NIHR/Imperial BRC. Dr Jean Alero Thomas Scholarship. Funding Information: Funding: The Icelandic Centre for Research, grant no. 174566051 & 207301. The Icelandic Breast Cancer Research Fund, Göngum Saman. CRUK GC, NIHR/Imperial BRC. Dr Jean Alero Thomas Scholarship. Publisher Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Files in this item

This item appears in the following Collection(s)