The aim of this study was to compare the performance of a deep learning (DL)-based method used for diagnosing pulmonary nodules compared with the diagnostic approach of the radiologist in computed tomography (CT) of the chest. The authors included a total of 150 pathologically confirmed pulmonary nodules that were assessed and reported by radiologists. The study found that the DL-based method was able to achieve an accuracy that was comparable with that of the radiologists’ diagnostic approach in clinical practice.
Key points
- Deep learning-based method for diagnosing the pulmonary nodules in computed tomography provides a higher diagnostic certainty.
Authors: Ya-Wen Wang, Jian-Wei Wang, Shou-Xin Yang, Lin-Lin Qi, Hao-Liang Lin, Zhen Zhou & Yi-Zhou Yu
