Cargando…

Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer

Background: We investigated the feasibility of a deep learning algorithm (DLA) based on apparent diffusion coefficient (ADC) maps for the segmentation and discrimination of clinically significant cancer (CSC, Gleason score ≥ 7) from non-CSC in patients with prostate cancer (PCa). Methods: Data from...

Descripción completa

Detalles Bibliográficos
Autores principales: Hong, Sujin, Kim, Seung Ho, Yoo, Byeongcheol, Kim, Joo Yeon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10453750/
https://www.ncbi.nlm.nih.gov/pubmed/37623009
http://dx.doi.org/10.3390/curroncol30080528
_version_ 1785096015577088000
author Hong, Sujin
Kim, Seung Ho
Yoo, Byeongcheol
Kim, Joo Yeon
author_facet Hong, Sujin
Kim, Seung Ho
Yoo, Byeongcheol
Kim, Joo Yeon
author_sort Hong, Sujin
collection PubMed
description Background: We investigated the feasibility of a deep learning algorithm (DLA) based on apparent diffusion coefficient (ADC) maps for the segmentation and discrimination of clinically significant cancer (CSC, Gleason score ≥ 7) from non-CSC in patients with prostate cancer (PCa). Methods: Data from a total of 149 consecutive patients who had undergone 3T-MRI and been pathologically diagnosed with PCa were initially collected. The labelled data (148 images for GS6, 580 images for GS7) were applied for tumor segmentation using a convolutional neural network (CNN). For classification, 93 images for GS6 and 372 images for GS7 were used. For external validation, 22 consecutive patients from five different institutions (25 images for GS6, 70 images for GS7) representing different MR machines were recruited. Results: Regarding segmentation and classification, U-Net and DenseNet were used, respectively. The tumor Dice scores for internal and external validation were 0.822 and 0.7776, respectively. As for classification, the accuracies of internal and external validation were 73 and 75%, respectively. For external validation, diagnostic predictive values for CSC (sensitivity, specificity, positive predictive value and negative predictive value) were 84, 48, 82 and 52%, respectively. Conclusions: Tumor segmentation and discrimination of CSC from non-CSC is feasible using a DLA developed based on ADC maps (b2000) alone.
format Online
Article
Text
id pubmed-10453750
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104537502023-08-26 Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer Hong, Sujin Kim, Seung Ho Yoo, Byeongcheol Kim, Joo Yeon Curr Oncol Article Background: We investigated the feasibility of a deep learning algorithm (DLA) based on apparent diffusion coefficient (ADC) maps for the segmentation and discrimination of clinically significant cancer (CSC, Gleason score ≥ 7) from non-CSC in patients with prostate cancer (PCa). Methods: Data from a total of 149 consecutive patients who had undergone 3T-MRI and been pathologically diagnosed with PCa were initially collected. The labelled data (148 images for GS6, 580 images for GS7) were applied for tumor segmentation using a convolutional neural network (CNN). For classification, 93 images for GS6 and 372 images for GS7 were used. For external validation, 22 consecutive patients from five different institutions (25 images for GS6, 70 images for GS7) representing different MR machines were recruited. Results: Regarding segmentation and classification, U-Net and DenseNet were used, respectively. The tumor Dice scores for internal and external validation were 0.822 and 0.7776, respectively. As for classification, the accuracies of internal and external validation were 73 and 75%, respectively. For external validation, diagnostic predictive values for CSC (sensitivity, specificity, positive predictive value and negative predictive value) were 84, 48, 82 and 52%, respectively. Conclusions: Tumor segmentation and discrimination of CSC from non-CSC is feasible using a DLA developed based on ADC maps (b2000) alone. MDPI 2023-08-01 /pmc/articles/PMC10453750/ /pubmed/37623009 http://dx.doi.org/10.3390/curroncol30080528 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hong, Sujin
Kim, Seung Ho
Yoo, Byeongcheol
Kim, Joo Yeon
Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer
title Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer
title_full Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer
title_fullStr Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer
title_full_unstemmed Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer
title_short Deep Learning Algorithm for Tumor Segmentation and Discrimination of Clinically Significant Cancer in Patients with Prostate Cancer
title_sort deep learning algorithm for tumor segmentation and discrimination of clinically significant cancer in patients with prostate cancer
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10453750/
https://www.ncbi.nlm.nih.gov/pubmed/37623009
http://dx.doi.org/10.3390/curroncol30080528
work_keys_str_mv AT hongsujin deeplearningalgorithmfortumorsegmentationanddiscriminationofclinicallysignificantcancerinpatientswithprostatecancer
AT kimseungho deeplearningalgorithmfortumorsegmentationanddiscriminationofclinicallysignificantcancerinpatientswithprostatecancer
AT yoobyeongcheol deeplearningalgorithmfortumorsegmentationanddiscriminationofclinicallysignificantcancerinpatientswithprostatecancer
AT kimjooyeon deeplearningalgorithmfortumorsegmentationanddiscriminationofclinicallysignificantcancerinpatientswithprostatecancer