PROMETEO: A CNN-Based Computer-Aided Diagnosis System for WSI Prostate Cancer Detection
| Autor: | Lourdes Duran-Lopez, Antonio Felix Conde-Martin, Juan Pedro Dominguez-Morales, Alejandro Linares-Barranco, Saturnino Vicente-Diaz |
|---|---|
| Přispěvatelé: | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores, Universidad de Sevilla. TEP-108: Robótica y Tecnología de Computadores Aplicada a la Rehabilitación, Ministerio de Economía y Competitividad (MINECO). España, Junta de Andalucía, [Duran-Lopez, Lourdes] Univ Seville, Robot & Technol Comp Lab, Seville 41012, Spain, [Dominguez-Morales, Juan P.] Univ Seville, Robot & Technol Comp Lab, Seville 41012, Spain, [Vicente-Diaz, Saturnino] Univ Seville, Robot & Technol Comp Lab, Seville 41012, Spain, [Linares-Barranco, Alejandro] Univ Seville, Robot & Technol Comp Lab, Seville 41012, Spain, [Felix Conde-Martin, Antonio] Virgen de Valme Hosp, Pathol Anat Unit, Seville 41014, Spain, Spanish Grant, European Regional Development Fund, Andalusian Regional Project PAIDI2020, FEDER |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Prostate biopsy General Computer Science Whole-slide images Computer science Convolutional neural network Causes of cancer 03 medical and health sciences Prostate cancer 0302 clinical medicine Prostate medicine General Materials Science Biopsies medicine.diagnostic_test business.industry Deep learning General Engineering whole-slide images Cancer deep learning Histology Pattern recognition Computer-aided diagnosis medicine.disease Classification prostate cancer Normalization 030104 developmental biology medicine.anatomical_structure Convolutional Neural Networks (CNN) 030220 oncology & carcinogenesis Medical Image Analysis Convolutional neural networks computer-aided diagnosis Artificial intelligence lcsh:Electrical engineering. Electronics. Nuclear engineering business medical image analysis lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 8, Pp 128613-128628 (2020) idUS: Depósito de Investigación de la Universidad de Sevilla Universidad de Sevilla (US) idUS. Depósito de Investigación de la Universidad de Sevilla instname |
| ISSN: | 2169-3536 |
| Popis: | Prostate cancer is currently one of the most commonly-diagnosed types of cancer among males. Although its death rate has dropped in the last decades, it is still a major concern and one of the leading causes of cancer death. Prostate biopsy is a test that confirms or excludes the presence of cancer in the tissue. Samples extracted from biopsies are processed and digitized, obtaining gigapixel-resolution images called wholeslide images, which are analyzed by pathologists. Automated intelligent systems could be useful for helping pathologists in this analysis, reducing fatigue and making the routine process faster. In this work, a novel Deep Learning based computer-aided diagnosis system is presented. This system is able to analyze wholeslide histology images that are first patch-sampled and preprocessed using different filters, including a novel patch-scoring algorithm that removes worthless areas from the tissue. Then, patches are used as input to a custom Convolutional Neural Network, which gives a report showing malignant regions on a heatmap. The impact of applying a stain-normalization process to the patches is also analyzed in order to reduce color variability between different scanners. After training the network with a 3-fold cross-validation method, 99.98% accuracy, 99.98% F1 score and 0.999 AUC are achieved on a separate test set. The computation time needed to obtain the heatmap of a whole-slide image is, on average, around 15 s. Our custom network outperforms other state-of-the-art works in terms of computational complexity for a binary classification task between normal and malignant prostate whole-slide images at patch level. Ministerio de Economía y Competitividad COFNET TEC2016-77785-P Junta de Andalucía AT17_5410_USE |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|