The value of artificial intelligence for detection and grading of prostate cancer in human prostatectomy specimens: a validation study

• Published in: Patient safety in surgery Vol. 16; no. 1; p. 36
• Main Authors: Kudo, Maíra Suzuka, Gomes de Souza, Vinicius Meneguette, Estivallet, Carmen Liane Neubarth, de Amorim, Henrique Alves, Kim, Fernando J, Leite, Katia Ramos Moreira, Moraes, Matheus Cardoso
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 23.11.2022; BioMed Central; BMC
• Subjects: Accuracy; Analysis; Artificial intelligence; Artificial neural networks; Biopsy image; Cancer; Cancer surgery; Clinical aspects; Convolutional neural network; Datasets; Deep learning; Evaluation; Hypotheses; Image classification; Laboratories; Neural networks; Oncology, Experimental; Pathology; Prostate cancer; Prostatectomy; Quality; Sensitivity; Surgery; Urological surgery; Biopsy image; Pathology; Artificial intelligence; Prostate cancer; Convolutional neural network
• ISSN: 1754-9493; 1754-9493
• DOI: 10.1186/s13037-022-00345-6

The Gleason grading system is an important clinical practice for diagnosing prostate cancer in pathology images. However, this analysis results in significant variability among pathologists, hence creating possible negative clinical impacts. Artificial intelligence methods can be an important support for the pathologist, improving Gleason grade classifications. Consequently, our purpose is to construct and evaluate the potential of a Convolutional Neural Network (CNN) to classify Gleason patterns. The methodology included 6982 image patches with cancer, extracted from radical prostatectomy specimens previously analyzed by an expert uropathologist. A CNN was constructed to accurately classify the corresponding Gleason. The evaluation was carried out by computing the corresponding 3 classes confusion matrix; thus, calculating the percentage of precision, sensitivity, and specificity, as well as the overall accuracy. Additionally, k-fold three-way cross-validation was performed to enhance evaluation, allowing better interpretation and avoiding possible bias. The overall accuracy reached 98% for the training and validation stage, and 94% for the test phase. Considering the test samples, the true positive ratio between pathologist and computer method was 85%, 93%, and 96% for specific Gleason patterns. Finally, precision, sensitivity, and specificity reached values up to 97%. The CNN model presented and evaluated has shown high accuracy for specifically pattern neighbors and critical Gleason patterns. The outcomes are in line and complement others in the literature. The promising results surpassed current inter-pathologist congruence in classical reports, evidencing the potential of this novel technology in daily clinical aspects.