A deep learning-based semiautomated workflow for triaging follow-up MR scans in treated nasopharyngeal carcinoma

A deep learning-based semiautomated workflow for triaging follow-up MR scans in treated nasopharyngeal carcinoma

It is imperative to optimally utilize virtues and obviate defects of fully automated analysis and expert knowledge in new paradigms of healthcare. We present a deep learning-based semiautomated workflow (RAINMAN) with 12,809 follow-up scans among 2,172 patients with treated nasopharyngeal carcinoma...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:iScience 2023-12, Vol.26 (12), p.108347-108347, Article 108347
Hauptverfasser: Huang, Ying-Ying, Deng, Yi-Shu, Liu, Yang, Qiang, Meng-Yun, Qiu, Wen-Ze, Xia, Wei-Xiong, Jing, Bing-Zhong, Feng, Chen-Yang, Chen, Hao-Hua, Cao, Xun, Zhou, Jia-Yu, Huang, Hao-Yang, Zhan, Ze-Jiang, Deng, Ying, Tang, Lin-Quan, Mai, Hai-Qiang, Sun, Ying, Xie, Chuan-Miao, Guo, Xiang, Ke, Liang-Ru, Lv, Xing, Li, Chao-Feng
Format: Artikel
Sprache:eng
Schlagworte:
Applied computing
Health technology
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:It is imperative to optimally utilize virtues and obviate defects of fully automated analysis and expert knowledge in new paradigms of healthcare. We present a deep learning-based semiautomated workflow (RAINMAN) with 12,809 follow-up scans among 2,172 patients with treated nasopharyngeal carcinoma from three centers (ChiCTR.org.cn, Chi-CTR2200056595). A boost of diagnostic performance and reduced workload was observed in RAINMAN compared with the original manual interpretations (internal vs. external: sensitivity, 2.5% [p = 0.500] vs. 3.2% [p = 0.031]; specificity, 2.9% [p 
ISSN:2589-0042
2589-0042
DOI:10.1016/j.isci.2023.108347