{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:34:01Z","timestamp":1775583241203,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2021,10,9]],"date-time":"2021-10-09T00:00:00Z","timestamp":1633737600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Program for Research &amp; Innovation in Health and Biomedical Sciences Academy of Scientific Research and Technology","award":["Academy of Scientific Research and Technology"],"award-info":[{"award-number":["Academy of Scientific Research and Technology"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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\u2019 edge enhancement. The digitized PBSs are then divided into overlapping patches with the three sizes: 100 \u00d7 100 (CNNS), 150 \u00d7 150 (CNNM), and 200 \u00d7 200 (CNNL), 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 (CNNL) 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\u20130.77. 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\u2019 results, we used the standard ResNet50 and VGG-16 to compare our CNN\u2019s patch-wise classification results. As well, we compared the GG\u2019s results with that of the previous work.<\/jats:p>","DOI":"10.3390\/s21206708","type":"journal-article","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T21:37:49Z","timestamp":1633901869000},"page":"6708","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["A Deep Learning Pipeline for Grade Groups Classification Using Digitized Prostate Biopsy Specimens"],"prefix":"10.3390","volume":"21","author":[{"given":"Kamal","family":"Hammouda","sequence":"first","affiliation":[{"name":"BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3318-2851","authenticated-orcid":false,"given":"Fahmi","family":"Khalifa","sequence":"additional","affiliation":[{"name":"BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moumen","family":"El-Melegy","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Assiut University, Assiut 71515, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9045-6698","authenticated-orcid":false,"given":"Mohamed","family":"Ghazal","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanan E.","family":"Darwish","sequence":"additional","affiliation":[{"name":"Mathematics Department, Faculty of Science, Mansoura University, Mansoura 35516, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Abou El-Ghar","sequence":"additional","affiliation":[{"name":"Radiology Department, Urology and Nephrology Center, Mansoura University, Mansoura 35516, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7264-1323","authenticated-orcid":false,"given":"Ayman","family":"El-Baz","sequence":"additional","affiliation":[{"name":"BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,9]]},"reference":[{"key":"ref_1","unstructured":"American Cancer Society (2021, October 03). Cancer Facts and Figures. Available online: https:\/\/www.cancer.org\/research\/cancer-facts-statistics\/all-cancer-facts-figures\/cancer-facts-figures-2021.html."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2532","DOI":"10.1001\/jama.2017.7248","article-title":"The diagnosis and treatment of prostate cancer: A review","volume":"317","author":"Litwin","year":"2017","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1590\/S1677-55382007000500005","article-title":"Interobserver agreement of Gleason score and modified Gleason score in needle biopsy and in surgical specimen of prostate cancer","volume":"33","author":"Veloso","year":"2007","journal-title":"Int. Braz. J. Urol."},{"key":"ref_4","first-page":"1","article-title":"Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer","volume":"2","author":"Nagpal","year":"2019","journal-title":"NPJ Digit. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1111\/his.13712","article-title":"Defining clinically significant prostate cancer on the basis of pathological findings","volume":"74","author":"Matoso","year":"2019","journal-title":"Histopathology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1097\/PAS.0000000000000530","article-title":"The 2014 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma","volume":"40","author":"Epstein","year":"2016","journal-title":"Am. J. Surg. Pathol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1111\/j.1365-2559.2006.02393.x","article-title":"A UK-based investigation of inter-and intra-observer reproducibility of Gleason grading of prostatic biopsies","volume":"48","author":"Melia","year":"2006","journal-title":"Histopathology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1111\/his.12008","article-title":"Standardization of Gleason grading among 337 European pathologists","volume":"62","author":"Egevad","year":"2013","journal-title":"Histopathology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1647","DOI":"10.1111\/j.1464-410X.2008.08255.x","article-title":"Concordance between Gleason scores of needle biopsies and radical prostatectomy specimens: A population-based study","volume":"103","author":"Wahlqvist","year":"2009","journal-title":"BJU Int."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.eururo.2013.03.029","article-title":"Phase 3 study of adjuvant radiotherapy versus wait and see in pT3 prostate cancer: Impact of pathology review on analysis","volume":"64","author":"Bottke","year":"2013","journal-title":"Eur. Urol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1056\/NEJMoa1801993","article-title":"MRI-targeted or standard biopsy for prostate-cancer diagnosis","volume":"378","author":"Kasivisvanathan","year":"2018","journal-title":"N. Engl. J. Med."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hammouda, K., Khalifa, F., Soliman, A., Abdeltawab, H., Ghazal, M., Abou El-Ghar, M., Haddad, A., Darwish, H.E., Keynton, R., and El-Baz, A. (2020, January 3\u20137). A 3D CNN with a Learnable Adaptive Shape Prior for Accurate Segmentation of Bladder Wall Using MR Images. Proceedings of the 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, IA, USA.","DOI":"10.1109\/ISBI45749.2020.9098733"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wildeboer, R.R., van Sloun, R.J., Wijkstra, H., and Mischi, M. (2020). Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods. Comput. Methods Programs Biomed., 189.","DOI":"10.1016\/j.cmpb.2020.105316"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hammouda, K., Khalifa, F., Soliman, A., Ghazal, M., Abou El-Ghar, M., Badawy, M., Darwish, H., Khelifi, A., and El-Baz, A. (2021). A multiparametric MRI-based CAD system for accurate diagnosis of bladder cancer staging. Comput. Med. Imaging Graph., 90.","DOI":"10.1016\/j.compmedimag.2021.101911"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Reda, I., Khalil, A., Elmogy, M., Abou El-Fetouh, A., Shalaby, A., Abou El-Ghar, M., Elmaghraby, A., Ghazal, M., and El-Baz, A. (2018). Deep learning role in early diagnosis of prostate cancer. Technol. Cancer Res. Treat., 17.","DOI":"10.1177\/1533034618775530"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1148\/radiol.2019190938","article-title":"Classification of cancer at prostate MRI: Deep learning versus clinical PI-RADS assessment","volume":"293","author":"Schelb","year":"2019","journal-title":"Radiology"},{"key":"ref_17","first-page":"101342A","article-title":"Classification of clinical significance of MRI prostate findings using 3D convolutional neural networks","volume":"Volume 10134","author":"Mehrtash","year":"2017","journal-title":"Proceedings of the Medical Imaging 2017: Computer-Aided Diagnosis"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-30535-1","article-title":"Automated Gleason grading of prostate cancer tissue microarrays via deep learning","volume":"8","author":"Arvaniti","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_19","unstructured":"Bulten, W., Pinckaers, H., van Boven, H., Vink, R., de Bel, T., van Ginneken, B., van der Laak, J., de Kaa, C.H.v., and Litjens, G. (2019). Automated gleason grading of prostate biopsies using deep learning. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-64206-x","article-title":"A new framework for performing cardiac Strain Analysis from cine MRi imaging in Mice","volume":"10","author":"Hammouda","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med Image Anal."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_23","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_24","first-page":"2011","article-title":"Survey of contrast enhancement techniques based on histogram equalization","volume":"2","author":"Kaur","year":"2011","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"023009","DOI":"10.1117\/1.JEI.26.2.023009","article-title":"Smoothing and enhancement algorithms for underwater images based on partial differential equations","volume":"26","author":"Nnolim","year":"2017","journal-title":"J. Electron. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_27","unstructured":"(2021, October 03). Website for the Dataset. Available online: https:\/\/www.kaggle.com\/c\/prostate-cancer-grade-assessment."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A review on evaluation metrics for data classification evaluations","volume":"5","author":"Hossin","year":"2015","journal-title":"Int. J. Data Min. Knowl. Manag. Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"McNee, S.M., Riedl, J., and Konstan, J.A. (2006, January 22\u201327). Being accurate is not enough: How accuracy metrics have hurt recommender systems. Proceedings of the CHI\u201906 Extended Abstracts on Human Factors in Computing Systems, New York, NY, USA.","DOI":"10.1145\/1125451.1125659"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1016\/S1470-2045(14)70361-4","article-title":"Active monitoring, radical prostatectomy, or radiotherapy for localised prostate cancer: Study design and diagnostic and baseline results of the ProtecT randomised phase 3 trial","volume":"15","author":"Lane","year":"2014","journal-title":"Lancet Oncol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.1200\/JCO.2015.65.7759","article-title":"Active surveillance for the management of localized prostate cancer (Cancer Care Ontario guideline): American Society of Clinical Oncology clinical practice guideline endorsement","volume":"34","author":"Chen","year":"2016","journal-title":"J. Clin. Oncol. Off. J. Am. Soc. Clin. Oncol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.juro.2010.03.021","article-title":"The value of mandatory second opinion pathology review of prostate needle biopsy interpretation before radical prostatectomy","volume":"184","author":"Brimo","year":"2010","journal-title":"J. Urol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1097\/PAS.0000000000001151","article-title":"Impact of deep learning assistance on the histopathologic review of lymph nodes for metastatic breast cancer","volume":"42","author":"Steiner","year":"2018","journal-title":"Am. J. Surg. Pathol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"859","DOI":"10.5858\/arpa.2018-0147-OA","article-title":"Artificial intelligence\u2013based breast cancer nodal metastasis detection: Insights into the black box for pathologists","volume":"143","author":"Liu","year":"2019","journal-title":"Arch. Pathol. Lab. Med."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1016\/S0960-9822(03)00290-2","article-title":"Superior underwater vision in a human population of sea gypsies","volume":"13","author":"Dacke","year":"2003","journal-title":"Curr. Biol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1053\/hupa.2001.21135","article-title":"Interobserver reproducibility of Gleason grading of prostatic carcinoma: General pathologist","volume":"32","author":"Allsbrook","year":"2001","journal-title":"Hum. Pathol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1038\/s41591-019-0583-3","article-title":"Deep learning-based classification of mesothelioma improves prediction of patient outcome","volume":"25","author":"Courtiol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wulczyn, E., Steiner, D.F., Xu, Z., Sadhwani, A., Wang, H., Flament-Auvigne, I., Mermel, C.H., Chen, P.H.C., Liu, Y., and Stumpe, M.C. (2020). Deep learning-based survival prediction for multiple cancer types using histopathology images. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0233678"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Marrone, M., Potosky, A.L., Penson, D., and Freedman, A.N. (2015). A 22 gene-expression assay, Decipher\u00ae(GenomeDx Biosciences) to predict five-year risk of metastatic prostate cancer in men treated with radical prostatectomy. PLoS Curr., 7.","DOI":"10.1371\/currents.eogt.761b81608129ed61b0b48d42c04f92a4"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1038\/modpathol.2016.49","article-title":"Disease-specific survival of patients with invasive cribriform and intraductal prostate cancer at diagnostic biopsy","volume":"29","author":"Kweldam","year":"2016","journal-title":"Mod. Pathol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/20\/6708\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:11:04Z","timestamp":1760166664000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/20\/6708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,9]]},"references-count":41,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["s21206708"],"URL":"https:\/\/doi.org\/10.3390\/s21206708","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,9]]}}}