Deep learning-based detection system for multiclass lesions on chest radiographs: comparison with observer readings.
Objective: To investigate the feasibility of a deep learning-based detection (DLD) system for multiclass lesions on chest radiograph, in comparison with observers.Methods: A total of 15,809 chest radiographs were collected from two tertiary hospitals (7204 normal and 8605 abnormal with nodule/mass,...
| Publicado en: | European Radiology Vol. 30; no. 3; pp. 1359 - 1369 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
2020
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=148390833&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 148390833 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09387994 NPH jtl: European Radiology issn: 09387994 maglogo: N pubinfo: dt: 2020 vid: 30 iid: 3 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 148390833 148390833 NLM31748854 10.1007/s00330-019-06532-x NLM31748854 148390833 ppf: 1359 ppct: 10 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Deep learning-based detection system for multiclass lesions on chest radiographs: comparison with observer readings. aug: au: Park, Sohee Lee, Sang Min Lee, Kyung Hee Jung, Kyu-Hwan Bae, Woong Choe, Jooae Seo, Joon Beom affil: Department of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43 Gil, Songpa-gu, 138-736, Seoul, South Korea sug: subj: Lung Diseases Pleural Diseases Radiography, Thoracic Methods Pneumothorax Pleural Effusion ROC Curve Radiography Aged Lung Neoplasms Lung Diseases, Interstitial Female Solitary Pulmonary Nodule Pharmacokinetics Adult Male Sensitivity and Specificity Middle Age Aged: 65+ years Adult: 19-44 years Middle Aged: 45-64 years Female Male ab: Objective: To investigate the feasibility of a deep learning-based detection (DLD) system for multiclass lesions on chest radiograph, in comparison with observers.Methods: A total of 15,809 chest radiographs were collected from two tertiary hospitals (7204 normal and 8605 abnormal with nodule/mass, interstitial opacity, pleural effusion, or pneumothorax). Except for the test set (100 normal and 100 abnormal (nodule/mass, 70; interstitial opacity, 10; pleural effusion, 10; pneumothorax, 10)), radiographs were used to develop a DLD system for detecting multiclass lesions. The diagnostic performance of the developed model and that of nine observers with varying experiences were evaluated and compared using area under the receiver operating characteristic curve (AUROC), on a per-image basis, and jackknife alternative free-response receiver operating characteristic figure of merit (FOM) on a per-lesion basis. The false-positive fraction was also calculated.Results: Compared with the group-averaged observations, the DLD system demonstrated significantly higher performances on image-wise normal/abnormal classification and lesion-wise detection with pattern classification (AUROC, 0.985 vs. 0.958; p = 0.001; FOM, 0.962 vs. 0.886; p < 0.001). In lesion-wise detection, the DLD system outperformed all nine observers. In the subgroup analysis, the DLD system exhibited consistently better performance for both nodule/mass (FOM, 0.913 vs. 0.847; p < 0.001) and the other three abnormal classes (FOM, 0.995 vs. 0.843; p < 0.001). The false-positive fraction of all abnormalities was 0.11 for the DLD system and 0.19 for the observers.Conclusions: The DLD system showed the potential for detection of lesions and pattern classification on chest radiographs, performing normal/abnormal classifications and achieving high diagnostic performance.Key Points: • The DLD system was feasible for detection with pattern classification of multiclass lesions on chest radiograph. • The DLD system had high performance of image-wise classification as normal or abnormal chest radiographs (AUROC, 0.985) and showed especially high specificity (99.0%). • In lesion-wise detection of multiclass lesions, the DLD system outperformed all 9 observers (FOM, 0.962 vs. 0.886; p < 0.001). pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|