The potential of convolutional neural network diagnosing prostate cancer
- PDF / 1,384,893 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 14 Downloads / 174 Views
ORIGINAL ARTICLE
The potential of convolutional neural network diagnosing prostate cancer Maíra Suzuka Kudo 1 & Vinicius Meneguette Gomes de Souza 2 & Gabriel de Souza Amaral 1 & Petrônio Augusto de Souza Melo 2 & Carmen Liane Neubarth Estivallet 2 & Eric Rocha Santos 1 & Henrique Alves de Amorim 1 & Matheus Cardoso Moraes 1 & Katia Ramos Moreira Leite 2 Received: 10 February 2020 / Accepted: 22 September 2020 # Sociedade Brasileira de Engenharia Biomedica 2020
Abstract Introduction There were more than 1,276,106 new cases of prostate cancer (PC) in 2018 worldwide (GLOBOCAN). Early and precise diagnosis leads to cure chances up to 90%. Digital rectal examination and PSA serum levels are employed for prostate cancer screening. If both exams are suspicious for cancer, the patient will be submitted to a prostate biopsy. Histological diagnosis and grading are crucial to the proper manage of the patients and are not always easy to evaluate, demanding experience of pathologists. To test the possibility to adopt artificial intelligent to diagnose PC, we studied a set of prostate biopsy sample images that were input to a specifically constructed convolutional neural network. Purpose Evaluate the potential of the convolutional neural network for the classification of cancer and non-cancer patches extracted from prostate biopsy images. Methods Thirty-two prostate cancer biopsy images were obtained and reviewed by a single uropathologist and then transformed into 2594 fragments to feed the CNN. The methodology has been divided into clinical approaches—to extract patches—and computational approaches—the CNN implementation. Results The k-fold three-way cross-validation method was used, resulting in a 98.3% output accuracy in distinguishing cancer from non-cancer. Conclusion The presented method proved to be robust and trustworthy comparing with an expert pathologist report. Keywords Convolutional neural network . Artificial intelligence . Prostate cancer . Pathology . Biopsy image
Introduction According to the World Health Organization, about 1.1 million men are diagnosed with prostate cancer (PC) annually with more than 300,000 deaths, representing the fifth deadliest cancer in men (Ferlay et al. 2015). The Brazilian National * Maíra Suzuka Kudo [email protected] Vinicius Meneguette Gomes de Souza [email protected] 1
Laboratory of Image and Signal Processing of the Institute of Science and Technology, Federal University of São Paulo – UNIFESP, 330 Talim St. Room 108 - Jardim Aeroporto, Sao Jose dos Campos, SP 12231-280, Brazil
2
Laboratory of Medical Investigations Number 55, Sao Paulo University Medical School – FMUSP, Dr Arnaldo Avenue, 455, Room 2145 – Cerqueira Cesar,, Sao Paulo, SP 01246-903, Brazil
Cancer Institute (Câncer INd 2018) estimated 68,000 new PC cases in 2018, responsible for one-third of cancer affecting men in Brazil. Aging is considered the main risk factor related to PC development (Bell et al. 2015), together with familial history and the heritance of predisposition genes as BRCA2. Early di
Data Loading...
