Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer
ObjectiveTo develop and validate a noninvasive radiomic-based machine learning (ML) model to identify P504s/P63 status and further achieve the diagnosis of prostate cancer (PCa).MethodsA retrospective dataset of patients with preoperative prostate MRI examination and P504s/P63 pathological immunohis...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-06-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.911426/full |
_version_ | 1811240615707410432 |
---|---|
author | Yun-Fan Liu Xin Shu Xiao-Feng Qiao Guang-Yong Ai Li Liu Jun Liao Shuang Qian Xiao-Jing He |
author_facet | Yun-Fan Liu Xin Shu Xiao-Feng Qiao Guang-Yong Ai Li Liu Jun Liao Shuang Qian Xiao-Jing He |
author_sort | Yun-Fan Liu |
collection | DOAJ |
description | ObjectiveTo develop and validate a noninvasive radiomic-based machine learning (ML) model to identify P504s/P63 status and further achieve the diagnosis of prostate cancer (PCa).MethodsA retrospective dataset of patients with preoperative prostate MRI examination and P504s/P63 pathological immunohistochemical results between June 2016 and February 2021 was conducted. As indicated by P504s/P63 expression, the patients were divided into label 0 (atypical prostatic hyperplasia), label 1 (benign prostatic hyperplasia, BPH) and label 2 (PCa) groups. This study employed T2WI, DWI and ADC sequences to assess prostate diseases and manually segmented regions of interest (ROIs) with Artificial Intelligence Kit software for radiomics feature acquisition. Feature dimensionality reduction and selection were performed by using a mutual information algorithm. Based on screened features, P504s/P63 prediction models were established by random forest (RF), gradient boosting decision tree (GBDT), logistic regression (LR), adaptive boosting (AdaBoost) and k-nearest neighbor (KNN) algorithms. The performance was evaluated by the area under the ROC curve (AUC) and accuracy.ResultsA total of 315 patients were enrolled. Among the 851 radiomic features, the 32 top features were derived from T2WI, in which the gray-level run length matrix (GLRLM) and gray-level cooccurrence matrix (GLCM) features accounted for the largest proportion. Among the five models, the RF algorithm performed best in general evaluations (microaverage AUC=0.920, macroaverage AUC=0.870) and provided the most accurate result in further sublabel prediction (the accuracies of label 0, 1, and 2 were 0.831, 0.831, and 0.932, respectively). In comparative sequence analyses, T2WI was the best single-sequence candidate (microaverage AUC=0.94 and macroaverage AUC=0.78). The merged datasets of T2WI, DWI, and ADC yielded optimal AUCs (microaverage AUC=0.930 and macroaverage AUC=0.900).ConclusionsThe radiomic-based RF classifier has the potential to be used to evaluate the presurgical P504s/P63 status and further diagnose PCa noninvasively and accurately. |
first_indexed | 2024-04-12T13:23:21Z |
format | Article |
id | doaj.art-d6c7c3681b6e42b58699a5e168ee2af3 |
institution | Directory Open Access Journal |
issn | 2234-943X |
language | English |
last_indexed | 2024-04-12T13:23:21Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Oncology |
spelling | doaj.art-d6c7c3681b6e42b58699a5e168ee2af32022-12-22T03:31:24ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-06-011210.3389/fonc.2022.911426911426Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate CancerYun-Fan Liu0Xin Shu1Xiao-Feng Qiao2Guang-Yong Ai3Li Liu4Jun Liao5Shuang Qian6Xiao-Jing He7Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaBig Data and Software Engineering College, Chongqing University, Chongqing, ChinaBig Data and Software Engineering College, Chongqing University, Chongqing, ChinaBig Data and Software Engineering College, Chongqing University, Chongqing, ChinaDepartment of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaObjectiveTo develop and validate a noninvasive radiomic-based machine learning (ML) model to identify P504s/P63 status and further achieve the diagnosis of prostate cancer (PCa).MethodsA retrospective dataset of patients with preoperative prostate MRI examination and P504s/P63 pathological immunohistochemical results between June 2016 and February 2021 was conducted. As indicated by P504s/P63 expression, the patients were divided into label 0 (atypical prostatic hyperplasia), label 1 (benign prostatic hyperplasia, BPH) and label 2 (PCa) groups. This study employed T2WI, DWI and ADC sequences to assess prostate diseases and manually segmented regions of interest (ROIs) with Artificial Intelligence Kit software for radiomics feature acquisition. Feature dimensionality reduction and selection were performed by using a mutual information algorithm. Based on screened features, P504s/P63 prediction models were established by random forest (RF), gradient boosting decision tree (GBDT), logistic regression (LR), adaptive boosting (AdaBoost) and k-nearest neighbor (KNN) algorithms. The performance was evaluated by the area under the ROC curve (AUC) and accuracy.ResultsA total of 315 patients were enrolled. Among the 851 radiomic features, the 32 top features were derived from T2WI, in which the gray-level run length matrix (GLRLM) and gray-level cooccurrence matrix (GLCM) features accounted for the largest proportion. Among the five models, the RF algorithm performed best in general evaluations (microaverage AUC=0.920, macroaverage AUC=0.870) and provided the most accurate result in further sublabel prediction (the accuracies of label 0, 1, and 2 were 0.831, 0.831, and 0.932, respectively). In comparative sequence analyses, T2WI was the best single-sequence candidate (microaverage AUC=0.94 and macroaverage AUC=0.78). The merged datasets of T2WI, DWI, and ADC yielded optimal AUCs (microaverage AUC=0.930 and macroaverage AUC=0.900).ConclusionsThe radiomic-based RF classifier has the potential to be used to evaluate the presurgical P504s/P63 status and further diagnose PCa noninvasively and accurately.https://www.frontiersin.org/articles/10.3389/fonc.2022.911426/fullP504s/P63machine learningMRIimmunohistochemistryprostate cancer |
spellingShingle | Yun-Fan Liu Xin Shu Xiao-Feng Qiao Guang-Yong Ai Li Liu Jun Liao Shuang Qian Xiao-Jing He Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer Frontiers in Oncology P504s/P63 machine learning MRI immunohistochemistry prostate cancer |
title | Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer |
title_full | Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer |
title_fullStr | Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer |
title_full_unstemmed | Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer |
title_short | Radiomics-Based Machine Learning Models for Predicting P504s/P63 Immunohistochemical Expression: A Noninvasive Diagnostic Tool for Prostate Cancer |
title_sort | radiomics based machine learning models for predicting p504s p63 immunohistochemical expression a noninvasive diagnostic tool for prostate cancer |
topic | P504s/P63 machine learning MRI immunohistochemistry prostate cancer |
url | https://www.frontiersin.org/articles/10.3389/fonc.2022.911426/full |
work_keys_str_mv | AT yunfanliu radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT xinshu radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT xiaofengqiao radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT guangyongai radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT liliu radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT junliao radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT shuangqian radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer AT xiaojinghe radiomicsbasedmachinelearningmodelsforpredictingp504sp63immunohistochemicalexpressionanoninvasivediagnostictoolforprostatecancer |