Development of a deep learning-based model to diagnose mixed-type gastric cancer accurately.

Ning, X; Liu, R; Wang, N; Xiao, X; Wu, S; Wang, Y; Yi, C; He, Y; Li, D; Chen, H

Development of a deep learning-based model to diagnose mixed-type gastric cancer accurately.

Ning, X Liu, R Wang, N Xiao, X Wu, S Wang, Y Yi, C He, Y Li, D Chen, H

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Int J Biochem Cell Biol, 2023, 162, pp. 106452
Issue Date:: 2023-09

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Sep 2024

Download Accepted versionAdobe PDF (2.34 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Ning, X
dc.contributor.author	Liu, R
dc.contributor.author	Wang, N
dc.contributor.author	Xiao, X
dc.contributor.author	Wu, S
dc.contributor.author	Wang, Y
dc.contributor.author	Yi, C
dc.contributor.author	He, Y
dc.contributor.author	Li, D
dc.contributor.author	Chen, H https://orcid.org/0000-0001-6883-3752
dc.date.accessioned	2024-04-22T04:53:06Z
dc.date.available	2023-07-19
dc.date.available	2024-04-22T04:53:06Z
dc.date.issued	2023-09
dc.identifier.citation	Int J Biochem Cell Biol, 2023, 162, pp. 106452
dc.identifier.issn	1357-2725
dc.identifier.issn	1878-5875
dc.identifier.uri	http://hdl.handle.net/10453/178192
dc.description.abstract	OBJECTIVE: The accurate diagnosis of mixed-type gastric cancer from pathology images presents a formidable challenge for pathologists, given its intricate features and resemblance to other subtypes of gastric cancer. Artificial Intelligence has the potential to overcome this hurdle. This study aimed to leverage deep machine learning techniques to establish a precise and efficient diagnostic approach for this cancer type which can also predict the metastatic risk using two software, U-Net and QuPath, which have not been trialled in gastric cancers. METHODS: A U-Net neural network was trained to recognise, and segment differentiated components from 186 pathology images of mixed-type gastric cancer. Undifferentiated components in the same images were annotated using the open-source pathology imaging software QuPath. The outcomes from U-Net and QuPath were used to calculate the ratios of differentiation/undifferentiated components which were correlated to lymph node metastasis. RESULTS: The models established by U-Net recognised ∼91% of the regions of interest, with precision, recall, and F1 values of 90.2%, 90.9% and 94.6%, respectively, indicating a high level of accuracy and reliability. Furthermore, the receiver operating characteristic curve analysis showed an area under the cure of 91%, indicating good performance. A bell-curve correlation between the differentiated/undifferentiated ratio and lymphatic metastasis was found (highest risk between 0.683 and 1.03), which is paradigm-shifting. CONCLUSION: U-Net and QuPath exhibit promising accuracy in the identification of differentiated and undifferentiated components in mixed-type gastric cancer, as well as paradigm-shifting prediction of metastasis. These findings bring us one step closer to their potential clinical application.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Elsevier
dc.relation.ispartof	Int J Biochem Cell Biol
dc.relation.isbasedon	10.1016/j.biocel.2023.106452
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	0601 Biochemistry and Cell Biology, 1101 Medical Biochemistry and Metabolomics, 1116 Medical Physiology
dc.subject.classification	Biochemistry & Molecular Biology
dc.subject.classification	3101 Biochemistry and cell biology
dc.subject.classification	3205 Medical biochemistry and metabolomics
dc.subject.mesh	Humans
dc.subject.mesh	Deep Learning
dc.subject.mesh	Stomach Neoplasms
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Reproducibility of Results
dc.subject.mesh	ROC Curve
dc.subject.mesh	Lymphatic Metastasis
dc.subject.mesh	Humans
dc.subject.mesh	Stomach Neoplasms
dc.subject.mesh	Lymphatic Metastasis
dc.subject.mesh	Reproducibility of Results
dc.subject.mesh	ROC Curve
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Deep Learning
dc.subject.mesh	Humans
dc.subject.mesh	Deep Learning
dc.subject.mesh	Stomach Neoplasms
dc.subject.mesh	Artificial Intelligence
dc.subject.mesh	Reproducibility of Results
dc.subject.mesh	ROC Curve
dc.subject.mesh	Lymphatic Metastasis
dc.title	Development of a deep learning-based model to diagnose mixed-type gastric cancer accurately.
dc.type	Journal Article
utslib.citation.volume	162
utslib.location.activity	Netherlands
utslib.for	0601 Biochemistry and Cell Biology
utslib.for	1101 Medical Biochemistry and Metabolomics
utslib.for	1116 Medical Physiology
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Science
pubs.organisational-group	University of Technology Sydney/Strength - CHT - Health Technologies
pubs.organisational-group	University of Technology Sydney/Faculty of Science/School of Life Sciences
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2024-09-01T00:00:00+1000Z
dc.date.updated	2024-04-22T04:53:02Z
pubs.publication-status	Published
pubs.volume	162

Abstract:

OBJECTIVE: The accurate diagnosis of mixed-type gastric cancer from pathology images presents a formidable challenge for pathologists, given its intricate features and resemblance to other subtypes of gastric cancer. Artificial Intelligence has the potential to overcome this hurdle. This study aimed to leverage deep machine learning techniques to establish a precise and efficient diagnostic approach for this cancer type which can also predict the metastatic risk using two software, U-Net and QuPath, which have not been trialled in gastric cancers. METHODS: A U-Net neural network was trained to recognise, and segment differentiated components from 186 pathology images of mixed-type gastric cancer. Undifferentiated components in the same images were annotated using the open-source pathology imaging software QuPath. The outcomes from U-Net and QuPath were used to calculate the ratios of differentiation/undifferentiated components which were correlated to lymph node metastasis. RESULTS: The models established by U-Net recognised ∼91% of the regions of interest, with precision, recall, and F1 values of 90.2%, 90.9% and 94.6%, respectively, indicating a high level of accuracy and reliability. Furthermore, the receiver operating characteristic curve analysis showed an area under the cure of 91%, indicating good performance. A bell-curve correlation between the differentiated/undifferentiated ratio and lymphatic metastasis was found (highest risk between 0.683 and 1.03), which is paradigm-shifting. CONCLUSION: U-Net and QuPath exhibit promising accuracy in the identification of differentiated and undifferentiated components in mixed-type gastric cancer, as well as paradigm-shifting prediction of metastasis. These findings bring us one step closer to their potential clinical application.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/178192