Cargando…

Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning

This study is aimed to explore the performance of texture-based machine learning and image-based deep-learning for enhancing detection of Transitional-zone prostate cancer (TZPCa) in the background of benign prostatic hyperplasia (BPH), using a one-to-one correlation between prostatectomy-based path...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Myoung Seok, Kim, Young Jae, Moon, Min Hoan, Kim, Kwang Gi, Park, Jeong Hwan, Sung, Chang Kyu, Jeong, Hyeon, Son, Hwancheol
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Lippincott Williams & Wilkins 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10545268/
https://www.ncbi.nlm.nih.gov/pubmed/37773806
http://dx.doi.org/10.1097/MD.0000000000035039
_version_ 1785114636556697600
author Lee, Myoung Seok
Kim, Young Jae
Moon, Min Hoan
Kim, Kwang Gi
Park, Jeong Hwan
Sung, Chang Kyu
Jeong, Hyeon
Son, Hwancheol
author_facet Lee, Myoung Seok
Kim, Young Jae
Moon, Min Hoan
Kim, Kwang Gi
Park, Jeong Hwan
Sung, Chang Kyu
Jeong, Hyeon
Son, Hwancheol
author_sort Lee, Myoung Seok
collection PubMed
description This study is aimed to explore the performance of texture-based machine learning and image-based deep-learning for enhancing detection of Transitional-zone prostate cancer (TZPCa) in the background of benign prostatic hyperplasia (BPH), using a one-to-one correlation between prostatectomy-based pathologically proven lesion and MRI. Seventy patients confirmed as TZPCa and twenty-nine patients confirmed as BPH without TZPCa by radical prostatectomy. For texture analysis, a radiologist drew the region of interest (ROI) for the pathologically correlated TZPCa and the surrounding BPH on T2WI. Significant features were selected using Least Absolute Shrinkage and Selection Operator (LASSO), trained by 3 types of machine learning algorithms (logistic regression [LR], support vector machine [SVM], and random forest [RF]) and validated by the leave-one-out method. For image-based machine learning, both TZPCa and BPH without TZPCa images were trained using convolutional neural network (CNN) and underwent 10-fold cross validation. Sensitivity, specificity, positive and negative predictive values were presented for each method. The diagnostic performances presented and compared using an ROC curve and AUC value. All the 3 Texture-based machine learning algorithms showed similar AUC (0.854–0.861)among them with generally high specificity (0.710–0.775). The Image-based deep learning showed high sensitivity (0.946) with good AUC (0.802) and moderate specificity (0.643). Texture -based machine learning can be expected to serve as a support tool for diagnosis of human-suspected TZ lesions with high AUC values. Image-based deep learning could serve as a screening tool for detecting suspicious TZ lesions in the context of clinically suspected TZPCa, on the basis of the high sensitivity.
format Online
Article
Text
id pubmed-10545268
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Lippincott Williams & Wilkins
record_format MEDLINE/PubMed
spelling pubmed-105452682023-10-03 Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning Lee, Myoung Seok Kim, Young Jae Moon, Min Hoan Kim, Kwang Gi Park, Jeong Hwan Sung, Chang Kyu Jeong, Hyeon Son, Hwancheol Medicine (Baltimore) 6800 This study is aimed to explore the performance of texture-based machine learning and image-based deep-learning for enhancing detection of Transitional-zone prostate cancer (TZPCa) in the background of benign prostatic hyperplasia (BPH), using a one-to-one correlation between prostatectomy-based pathologically proven lesion and MRI. Seventy patients confirmed as TZPCa and twenty-nine patients confirmed as BPH without TZPCa by radical prostatectomy. For texture analysis, a radiologist drew the region of interest (ROI) for the pathologically correlated TZPCa and the surrounding BPH on T2WI. Significant features were selected using Least Absolute Shrinkage and Selection Operator (LASSO), trained by 3 types of machine learning algorithms (logistic regression [LR], support vector machine [SVM], and random forest [RF]) and validated by the leave-one-out method. For image-based machine learning, both TZPCa and BPH without TZPCa images were trained using convolutional neural network (CNN) and underwent 10-fold cross validation. Sensitivity, specificity, positive and negative predictive values were presented for each method. The diagnostic performances presented and compared using an ROC curve and AUC value. All the 3 Texture-based machine learning algorithms showed similar AUC (0.854–0.861)among them with generally high specificity (0.710–0.775). The Image-based deep learning showed high sensitivity (0.946) with good AUC (0.802) and moderate specificity (0.643). Texture -based machine learning can be expected to serve as a support tool for diagnosis of human-suspected TZ lesions with high AUC values. Image-based deep learning could serve as a screening tool for detecting suspicious TZ lesions in the context of clinically suspected TZPCa, on the basis of the high sensitivity. Lippincott Williams & Wilkins 2023-09-29 /pmc/articles/PMC10545268/ /pubmed/37773806 http://dx.doi.org/10.1097/MD.0000000000035039 Text en Copyright © 2023 the Author(s). Published by Wolters Kluwer Health, Inc. https://creativecommons.org/licenses/by-nc/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution-Non Commercial License 4.0 (CCBY-NC) (https://creativecommons.org/licenses/by-nc/4.0/) , where it is permissible to download, share, remix, transform, and buildup the work provided it is properly cited. The work cannot be used commercially without permission from the journal.
spellingShingle 6800
Lee, Myoung Seok
Kim, Young Jae
Moon, Min Hoan
Kim, Kwang Gi
Park, Jeong Hwan
Sung, Chang Kyu
Jeong, Hyeon
Son, Hwancheol
Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning
title Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning
title_full Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning
title_fullStr Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning
title_full_unstemmed Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning
title_short Transitional zone prostate cancer: Performance of texture-based machine learning and image-based deep learning
title_sort transitional zone prostate cancer: performance of texture-based machine learning and image-based deep learning
topic 6800
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10545268/
https://www.ncbi.nlm.nih.gov/pubmed/37773806
http://dx.doi.org/10.1097/MD.0000000000035039
work_keys_str_mv AT leemyoungseok transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT kimyoungjae transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT moonminhoan transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT kimkwanggi transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT parkjeonghwan transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT sungchangkyu transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT jeonghyeon transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning
AT sonhwancheol transitionalzoneprostatecancerperformanceoftexturebasedmachinelearningandimagebaseddeeplearning