Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients
Abstract Background Cancer biomarkers play a pivotal role in the diagnosis, prognosis, and treatment response prediction of the disease. In this study, we analyzed the expression levels of RhoB and DNp73 proteins in rectal cancer, as captured in immunohistochemical images, to predict the 5‐year surv...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-12-01
|
Series: | Cancer Medicine |
Subjects: | |
Online Access: | https://doi.org/10.1002/cam4.6672 |
_version_ | 1797387136990707712 |
---|---|
author | Tuan D. Pham Xiao‐Feng Sun |
author_facet | Tuan D. Pham Xiao‐Feng Sun |
author_sort | Tuan D. Pham |
collection | DOAJ |
description | Abstract Background Cancer biomarkers play a pivotal role in the diagnosis, prognosis, and treatment response prediction of the disease. In this study, we analyzed the expression levels of RhoB and DNp73 proteins in rectal cancer, as captured in immunohistochemical images, to predict the 5‐year survival time of two patient groups: one with preoperative radiotherapy and one without. Methods The utilization of deep convolutional neural networks in medical research, particularly in clinical cancer studies, has been gaining substantial attention. This success primarily stems from their ability to extract intricate image features that prove invaluable in machine learning. Another innovative method for extracting features at multiple levels is the wavelet‐scattering network. Our study combines the strengths of these two convolution‐based approaches to robustly extract image features related to protein expression. Results The efficacy of our approach was evaluated across various tissue types, including tumor, biopsy, metastasis, and adjacent normal tissue. Statistical assessments demonstrated exceptional performance across a range of metrics, including prediction accuracy, classification accuracy, precision, and the area under the receiver operating characteristic curve. Conclusion These results underscore the potential of dual convolutional learning to assist clinical researchers in the timely validation and discovery of cancer biomarkers. |
first_indexed | 2024-03-08T22:19:33Z |
format | Article |
id | doaj.art-a95f763eda2f4893a3b14a4bc59300eb |
institution | Directory Open Access Journal |
issn | 2045-7634 |
language | English |
last_indexed | 2024-03-08T22:19:33Z |
publishDate | 2023-12-01 |
publisher | Wiley |
record_format | Article |
series | Cancer Medicine |
spelling | doaj.art-a95f763eda2f4893a3b14a4bc59300eb2023-12-18T14:43:08ZengWileyCancer Medicine2045-76342023-12-011223215022151810.1002/cam4.6672Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patientsTuan D. Pham0Xiao‐Feng Sun1Barts and The London School of Medicine and Dentistry Queen Mary University of London Turner Street London UKDivision of Oncology Department of Biomedical and Clinical Sciences Linkoping University Linkoping SwedenAbstract Background Cancer biomarkers play a pivotal role in the diagnosis, prognosis, and treatment response prediction of the disease. In this study, we analyzed the expression levels of RhoB and DNp73 proteins in rectal cancer, as captured in immunohistochemical images, to predict the 5‐year survival time of two patient groups: one with preoperative radiotherapy and one without. Methods The utilization of deep convolutional neural networks in medical research, particularly in clinical cancer studies, has been gaining substantial attention. This success primarily stems from their ability to extract intricate image features that prove invaluable in machine learning. Another innovative method for extracting features at multiple levels is the wavelet‐scattering network. Our study combines the strengths of these two convolution‐based approaches to robustly extract image features related to protein expression. Results The efficacy of our approach was evaluated across various tissue types, including tumor, biopsy, metastasis, and adjacent normal tissue. Statistical assessments demonstrated exceptional performance across a range of metrics, including prediction accuracy, classification accuracy, precision, and the area under the receiver operating characteristic curve. Conclusion These results underscore the potential of dual convolutional learning to assist clinical researchers in the timely validation and discovery of cancer biomarkers.https://doi.org/10.1002/cam4.6672artificial intelligencebiomarkersimmunohistochemistryrectal cancer |
spellingShingle | Tuan D. Pham Xiao‐Feng Sun Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients Cancer Medicine artificial intelligence biomarkers immunohistochemistry rectal cancer |
title | Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients |
title_full | Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients |
title_fullStr | Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients |
title_full_unstemmed | Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients |
title_short | Wavelet scattering networks in deep learning for discovering protein markers in a cohort of Swedish rectal cancer patients |
title_sort | wavelet scattering networks in deep learning for discovering protein markers in a cohort of swedish rectal cancer patients |
topic | artificial intelligence biomarkers immunohistochemistry rectal cancer |
url | https://doi.org/10.1002/cam4.6672 |
work_keys_str_mv | AT tuandpham waveletscatteringnetworksindeeplearningfordiscoveringproteinmarkersinacohortofswedishrectalcancerpatients AT xiaofengsun waveletscatteringnetworksindeeplearningfordiscoveringproteinmarkersinacohortofswedishrectalcancerpatients |