Prospects and Challenges of Artificial Intelligence and Computer Science for the Future of Urology
- PDF / 452,182 Bytes
- 3 Pages / 595.276 x 790.866 pts Page_size
- 45 Downloads / 169 Views
EDITORIAL
Prospects and Challenges of Artificial Intelligence and Computer Science for the Future of Urology Rodrigo Suarez‑Ibarrola1 · Arkadiusz Miernik1
© The Author(s) 2020
Artificial intelligence (AI) refers to the computational capability of machines to perform intellectual processes typical of human cognitive functions, such as learning, reasoning, and problem-solving. AI has permeated nearly all aspects of health care and it will increasingly continue to do so over the coming years. It initiated already a transformation on how medicine is practiced; revolutionizing traditional diagnostic, clinical decision-making and treatment-response assessment procedures. By providing more accurate and reliable clinical decisions, it will progressively play a central role in preventive medicine and will become an integral part of health care systems worldwide. Perhaps the most promising role for AI will be as an add-on to or augmentation of human providers resulting in improved efforts towards precision medicine [1]. The global revenue of the AI health care market is increasing at a rate of 40% and is expected to reach $6.6 billion by 2021 reducing treatment costs by 50% [2]. Undoubtedly, Urology is entering a new and exciting era with AI at its side; how we set about facing its new opportunities and challenges for a widespread implementation will likely have far-reaching consequences for the future of medical practice. In this World Journal of Urology special issue, we gathered a series of articles from leading experts in emerging topics on the field of computer-guided technologies and AI in Urology. The aim was to present engaging and debategenerating articles that represent the current standpoint of several technologies and also point to future perspectives. Specific subfields covered by this issue include machine learning, deep learning, convolutional neural networks (CNN), radiomics, language processing, big data analysis, human–computer interaction, AI decision-making, * Rodrigo Suarez‑Ibarrola rodrigo.suarez@uniklinik‑freiburg.de Arkadiusz Miernik arkadiusz.miernik@uniklinik‑freiburg.de 1
Department of Urology, Faculty of Medicine, University of Freiburg - Medical Center, Freiburg, Germany
intelligent robotics, image processing and segmentation, and smartphone-based applications. A comprehensive, though detailed, panorama of machine and deep learning applications in urolithiasis, renal cell carcinoma, bladder and prostate cancer (PCa), outlines how these algorithms may augment surgical outcome prediction accuracy and enhance individualized medicine [3]. For instance, image texture feature extraction or radiomics has shown to be beneficial to differentiate between benign and malignant small renal masses, predict Fuhrman nuclear grade, and determine gene expression-based molecular signatures [4]. Furthermore, the emergence of AI-assisted endoscopy has prompted researchers to train CNNs with large image and video datasets to improve cystoscopic lesion detection, diagnose carcinoma in situ more accurately, and
Data Loading...
