Cargando…
A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens
Prostate cancer is a significant cause of morbidity and mortality in the USA. In this paper, we develop a computer-aided diagnostic (CAD) system for automated grade groups (GG) classification using digitized prostate biopsy specimens (PBSs). Our CAD system aims to firstly classify the Gleason patter...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8538079/ https://www.ncbi.nlm.nih.gov/pubmed/34695922 http://dx.doi.org/10.3390/s21206708 |
_version_ | 1784588421678759936 |
---|---|
author | Hammouda, Kamal Khalifa, Fahmi El-Melegy, Moumen Ghazal, Mohamed Darwish, Hanan E. Abou El-Ghar, Mohamed El-Baz, Ayman |
author_facet | Hammouda, Kamal Khalifa, Fahmi El-Melegy, Moumen Ghazal, Mohamed Darwish, Hanan E. Abou El-Ghar, Mohamed El-Baz, Ayman |
author_sort | Hammouda, Kamal |
collection | PubMed |
description | Prostate cancer is a significant cause of morbidity and mortality in the USA. In this paper, we develop a computer-aided diagnostic (CAD) system for automated grade groups (GG) classification using digitized prostate biopsy specimens (PBSs). Our CAD system aims to firstly classify the Gleason pattern (GP), and then identifies the Gleason score (GS) and GG. The GP classification pipeline is based on a pyramidal deep learning system that utilizes three convolution neural networks (CNN) to produce both patch- and pixel-wise classifications. The analysis starts with sequential preprocessing steps that include a histogram equalization step to adjust intensity values, followed by a PBSs’ edge enhancement. The digitized PBSs are then divided into overlapping patches with the three sizes: 100 × 100 ([Formula: see text]), 150 × 150 ([Formula: see text]), and 200 × 200 ([Formula: see text]), pixels, and 75% overlap. Those three sizes of patches represent the three pyramidal levels. This pyramidal technique allows us to extract rich information, such as that the larger patches give more global information, while the small patches provide local details. After that, the patch-wise technique assigns each overlapped patch a label as GP categories (1 to 5). Then, the majority voting is the core approach for getting the pixel-wise classification that is used to get a single label for each overlapped pixel. The results after applying those techniques are three images of the same size as the original, and each pixel has a single label. We utilized the majority voting technique again on those three images to obtain only one. The proposed framework is trained, validated, and tested on 608 whole slide images (WSIs) of the digitized PBSs. The overall diagnostic accuracy is evaluated using several metrics: precision, recall, F1-score, accuracy, macro-averaged, and weighted-averaged. The ([Formula: see text]) has the best accuracy results for patch classification among the three CNNs, and its classification accuracy is 0.76. The macro-averaged and weighted-average metrics are found to be around 0.70–0.77. For GG, our CAD results are about 80% for precision, and between 60% to 80% for recall and F1-score, respectively. Also, it is around 94% for accuracy and NPV. To highlight our CAD systems’ results, we used the standard ResNet50 and VGG-16 to compare our CNN’s patch-wise classification results. As well, we compared the GG’s results with that of the previous work. |
format | Online Article Text |
id | pubmed-8538079 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-85380792021-10-24 A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens Hammouda, Kamal Khalifa, Fahmi El-Melegy, Moumen Ghazal, Mohamed Darwish, Hanan E. Abou El-Ghar, Mohamed El-Baz, Ayman Sensors (Basel) Article Prostate cancer is a significant cause of morbidity and mortality in the USA. In this paper, we develop a computer-aided diagnostic (CAD) system for automated grade groups (GG) classification using digitized prostate biopsy specimens (PBSs). Our CAD system aims to firstly classify the Gleason pattern (GP), and then identifies the Gleason score (GS) and GG. The GP classification pipeline is based on a pyramidal deep learning system that utilizes three convolution neural networks (CNN) to produce both patch- and pixel-wise classifications. The analysis starts with sequential preprocessing steps that include a histogram equalization step to adjust intensity values, followed by a PBSs’ edge enhancement. The digitized PBSs are then divided into overlapping patches with the three sizes: 100 × 100 ([Formula: see text]), 150 × 150 ([Formula: see text]), and 200 × 200 ([Formula: see text]), pixels, and 75% overlap. Those three sizes of patches represent the three pyramidal levels. This pyramidal technique allows us to extract rich information, such as that the larger patches give more global information, while the small patches provide local details. After that, the patch-wise technique assigns each overlapped patch a label as GP categories (1 to 5). Then, the majority voting is the core approach for getting the pixel-wise classification that is used to get a single label for each overlapped pixel. The results after applying those techniques are three images of the same size as the original, and each pixel has a single label. We utilized the majority voting technique again on those three images to obtain only one. The proposed framework is trained, validated, and tested on 608 whole slide images (WSIs) of the digitized PBSs. The overall diagnostic accuracy is evaluated using several metrics: precision, recall, F1-score, accuracy, macro-averaged, and weighted-averaged. The ([Formula: see text]) has the best accuracy results for patch classification among the three CNNs, and its classification accuracy is 0.76. The macro-averaged and weighted-average metrics are found to be around 0.70–0.77. For GG, our CAD results are about 80% for precision, and between 60% to 80% for recall and F1-score, respectively. Also, it is around 94% for accuracy and NPV. To highlight our CAD systems’ results, we used the standard ResNet50 and VGG-16 to compare our CNN’s patch-wise classification results. As well, we compared the GG’s results with that of the previous work. MDPI 2021-10-09 /pmc/articles/PMC8538079/ /pubmed/34695922 http://dx.doi.org/10.3390/s21206708 Text en © 2021 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 Hammouda, Kamal Khalifa, Fahmi El-Melegy, Moumen Ghazal, Mohamed Darwish, Hanan E. Abou El-Ghar, Mohamed El-Baz, Ayman A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens |
title | A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens |
title_full | A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens |
title_fullStr | A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens |
title_full_unstemmed | A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens |
title_short | A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens |
title_sort | deep learning pipeline for grade groups classification using digitized prostate biopsy specimens |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8538079/ https://www.ncbi.nlm.nih.gov/pubmed/34695922 http://dx.doi.org/10.3390/s21206708 |
work_keys_str_mv | AT hammoudakamal adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT khalifafahmi adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT elmelegymoumen adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT ghazalmohamed adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT darwishhanane adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT abouelgharmohamed adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT elbazayman adeeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT hammoudakamal deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT khalifafahmi deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT elmelegymoumen deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT ghazalmohamed deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT darwishhanane deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT abouelgharmohamed deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens AT elbazayman deeplearningpipelineforgradegroupsclassificationusingdigitizedprostatebiopsyspecimens |