Home > Riviste > Minerva Urology and Nephrology > Fascicoli precedenti > Minerva Urology and Nephrology 2022 October;74(5) > Minerva Urology and Nephrology 2022 October;74(5):538-50

ULTIMO FASCICOLO
 

JOURNAL TOOLS

Opzioni di pubblicazione
eTOC
Per abbonarsi
Sottometti un articolo
Segnala alla tua biblioteca
 

ARTICLE TOOLS

Publication history
Estratti
Permessi
Per citare questo articolo
Share

 

REVIEW   

Minerva Urology and Nephrology 2022 October;74(5):538-50

DOI: 10.23736/S2724-6051.22.04758-9

Copyright © 2022 EDIZIONI MINERVA MEDICA

lingua: Inglese

Artificial intelligence to predict oncological outcome directly from hematoxylin and eosin-stained slides in urology

Frederik WESSELS 1, 2, Sara KUNTZ 1, Eva KRIEGHOFF-HENNING 1, Max SCHMITT 1, Volker BRAUN 3, Thomas S. WORST 2, Manuel NEUBERGER 2, Matthias STEEG 4, Timo GAISER 4, Stefan FRÖHLING 5, Maurice-Stephan MICHEL 2, Philipp NUHN 2, Titus J. BRINKER 1

1 Digital Biomarkers for Oncology Group, National Center for Tumor Diseases (NCT), German Cancer Research Center (DKFZ), Heidelberg, Germany; 2 Department of Urology and Urological Surgery, Medical Faculty Mannheim of Heidelberg University, University Medical Center Mannheim, Mannheim, Germany; 3 Library for the Medical Faculty Mannheim of Heidelberg University, Mannheim, Germany; 4 Institute of Pathology, Medical Faculty Mannheim of Heidelberg University, University Medical Center Mannheim, Mannheim, Germany; 5 National Center for Tumor Diseases, German Cancer Research Center, Heidelberg, Germany



INTRODUCTION: Artificial intelligence (AI) has been successfully applied for automatic tumor detection and grading in histopathological image analysis in urologic oncology. The aim of this review was to assess the applicability of these approaches in image-based oncological outcome prediction.
EVIDENCE ACQUISITION: A systematic literature search was conducted using the databases MEDLINE through PubMed and Web of Science up to April 20, 2021. Studies investigating AI approaches to determine the risk of recurrence, metastasis, or survival directly from H&E-stained tissue sections in prostate, renal cell or urothelial carcinoma were included. Characteristics of the AI approach and performance metrics were extracted and summarized. Risk of bias (RoB) was assessed using the PROBAST tool.
EVIDENCE SYNTHESIS: 16 studies yielding a total of 6658 patients and reporting on 17 outcome predictions were included. Six studies focused on renal cell, six on prostate and three on urothelial carcinoma while one study investigated renal cell and urothelial carcinoma. Handcrafted feature extraction was used in five, a convolutional neural network (CNN) in six and a deep feature extraction in four studies. One study compared a CNN with handcrafted feature extraction. In seven outcome predictions, a multivariable comparison with clinicopathological parameters was reported. Five of them showed statistically significant hazard ratios for the AI’s model’s-prediction. However, RoB was high in 15 outcome predictions and unclear in two.
CONCLUSIONS: The included studies are promising but predominantly early pilot studies, therefore primarily highlighting the potential of AI approaches. Additional well-designed studies are needed to assess the actual clinical applicability.


KEY WORDS: Deep learning; Urology; Prognosis; Pathology; Urogenital neoplasms

inizio pagina