Deep learning computer-aided detection system for pneumonia in febrile neutropenia patients: a diagnostic cohort study

BMC Pulmonary Medicine

Eui Jin Hwang¹  Jong Hyuk Lee¹  Jin Mo Goo¹  Jae Hyun Kim¹  Chang Min Park²  Woo Hyeon Lim³ 

[1] Department of Radiology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, 03080, Seoul, Korea;Department of Radiology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, 03080, Seoul, Korea;Institute of Medical and Biological Engineering, Medical Research Center, Seoul National University, 103 Daehak-ro, Jongno-gu, 03080, Seoul, Korea;Department of Radiology, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, 03080, Seoul, Korea;Namwon Medical Center, 365 Chungjeong-ro, 55726, Namwon, Jeollabuk-do, Korea;

关键词: Radiography;    Thoracic;    Deep learning;    Artificial intelligence;    Pneumonia;    Febrile neutropenia;   

DOI  :  10.1186/s12890-021-01768-0

来源: Springer

【 摘 要 】

BackgroundDiagnosis of pneumonia is critical in managing patients with febrile neutropenia (FN), however, chest X-ray (CXR) has limited performance in the detection of pneumonia. We aimed to evaluate the performance of a deep learning-based computer-aided detection (CAD) system in pneumonia detection in the CXRs of consecutive FN patients and investigated whether CAD could improve radiologists’ diagnostic performance when used as a second reader.MethodsCXRs of patients with FN (a body temperature ≥ 38.3 °C, or a sustained body temperature ≥ 38.0 °C for an hour; absolute neutrophil count < 500/mm3) obtained between January and December 2017 were consecutively included, from a single tertiary referral hospital. Reference standards for the diagnosis of pneumonia were defined by consensus of two thoracic radiologists after reviewing medical records and CXRs. A commercialized, deep learning-based CAD system was retrospectively applied to detect pulmonary infiltrates on CXRs. For comparing performance, five radiologists independently interpreted CXRs initially without the CAD results (radiologist-alone interpretation), followed by the interpretation with CAD. The sensitivities and specificities for detection of pneumonia were compared between radiologist-alone interpretation and interpretation with CAD. The standalone performance of the CAD was also evaluated, using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Moreover, sensitivity and specificity of standalone CAD were compared with those of radiologist-alone interpretation.ResultsAmong 525 CXRs from 413 patients (52.3% men; median age 59 years), pneumonia was diagnosed in 128 (24.4%) CXRs. In the interpretation with CAD, average sensitivity of radiologists was significantly improved (75.4% to 79.4%, P = 0.003) while their specificity remained similar (75.4% to 76.8%, P = 0.101), compared to radiologist-alone interpretation. The CAD exhibited AUC, sensitivity, and specificity of 0.895, 88.3%, and 68.3%, respectively. The standalone CAD exhibited higher sensitivity (86.6% vs. 75.2%, P < 0.001) and lower specificity (64.8% vs. 75.4%, P < 0.001) compared to radiologist-alone interpretation.ConclusionsIn patients with FN, the deep learning-based CAD system exhibited radiologist-level performance in detecting pneumonia on CXRs and enhanced radiologists’ performance.

【 授权许可】

CC BY