Scholarlink

Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation. We evaluated the joint impact of a multi-pathology DLA EfficientReadCT on the time and accuracy of radiologists’ reading. 40 radiologists were randomly split into three experimental arms: control (10 radiologists), informed group (10 radiologists), and the experimental group (20 radiologists). Every arm used the same 200 CT studies retrospectively collected from BIMCV-COVID19 dataset; each radiologist provided readings for 20 CT studies. We compared radiologists’ interpretation time, and accuracy of their diagnostic report in terms of sensitivity and specificity with respect to 12 pathological findings. Of 20 radiologists in the experimental arm, 16 have improved reading time and sensitivity, two improved their time with a marginal drop in sensitivity, and two radiologists improved sensitivity with increased time. Overall, DLA introduction decreased reading time by \(20.6\%\) .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Impact of Deep Learning Aid on the Workload and Interpretation Accuracy of Radiologists on Chest Computed Tomography

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Anvar Kurmukov,
  • Valeria Chernina,
  • Regina Gareeva,
  • Maria Dugova,
  • Ekaterina Petrash,
  • Olga Aleshina,
  • Maxim Pisov,
  • Boris Shirokikh,
  • Valentin Samokhin,
  • Vladislav Proskurov,
  • Stanislav Shimovolos,
  • Maria Basova,
  • Mikhail Goncharov,
  • Eugenia Soboleva,
  • Maria Donskova,
  • Farukh Yaushev,
  • Alexey Shevtsov,
  • Alexey Zakharov,
  • Talgat Saparov,
  • Victor Gombolevskiy,
  • Mikhail Belyaev

摘要

Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation. We evaluated the joint impact of a multi-pathology DLA EfficientReadCT on the time and accuracy of radiologists’ reading. 40 radiologists were randomly split into three experimental arms: control (10 radiologists), informed group (10 radiologists), and the experimental group (20 radiologists). Every arm used the same 200 CT studies retrospectively collected from BIMCV-COVID19 dataset; each radiologist provided readings for 20 CT studies. We compared radiologists’ interpretation time, and accuracy of their diagnostic report in terms of sensitivity and specificity with respect to 12 pathological findings. Of 20 radiologists in the experimental arm, 16 have improved reading time and sensitivity, two improved their time with a marginal drop in sensitivity, and two radiologists improved sensitivity with increased time. Overall, DLA introduction decreased reading time by \(20.6\%\) .