Literature DB >> 32661584

Automated identification of chest radiographs with referable abnormality with deep learning: need for recalibration.

Eui Jin Hwang1, Hyungjin Kim1, Jong Hyuk Lee1,2, Jin Mo Goo1, Chang Min Park3.   

Abstract

OBJECTIVES: To evaluate the calibration of a deep learning (DL) model in a diagnostic cohort and to improve model's calibration through recalibration procedures.
METHODS: Chest radiographs (CRs) from 1135 consecutive patients (M:F = 582:553; mean age, 52.6 years) who visited our emergency department were included. A commercialized DL model was utilized to identify abnormal CRs, with a continuous probability score for each CR. After evaluation of the model calibration, eight different methods were used to recalibrate the original model based on the probability score. The original model outputs were recalibrated using 681 randomly sampled CRs and validated using the remaining 454 CRs. The Brier score for overall performance, average and maximum calibration error, absolute Spiegelhalter's Z for calibration, and area under the receiver operating characteristic curve (AUROC) for discrimination were evaluated in 1000-times repeated, randomly split datasets.
RESULTS: The original model tended to overestimate the likelihood for the presence of abnormalities, exhibiting average and maximum calibration error of 0.069 and 0.179, respectively; an absolute Spiegelhalter's Z value of 2.349; and an AUROC of 0.949. After recalibration, significant improvements in the average (range, 0.015-0.036) and maximum (range, 0.057-0.172) calibration errors were observed in eight and five methods, respectively. Significant improvement in absolute Spiegelhalter's Z (range, 0.809-4.439) was observed in only one method (the recalibration constant). Discriminations were preserved in six methods (AUROC, 0.909-0.949).
CONCLUSION: The calibration of DL algorithm can be augmented through simple recalibration procedures. Improved calibration may enhance the interpretability and credibility of the model for users. KEY POINTS: • A deep learning model tended to overestimate the likelihood of the presence of abnormalities in chest radiographs. • Simple recalibration of the deep learning model using output scores could improve the calibration of model while maintaining discrimination. • Improved calibration of a deep learning model may enhance the interpretability and the credibility of the model for users.

Entities:  

Keywords:  Artificial intelligence; Calibration; Deep learning; Thoracic radiography

Mesh:

Year:  2020        PMID: 32661584     DOI: 10.1007/s00330-020-07062-7

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  3 in total

Review 1.  Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology.

Authors:  Yisak Kim; Ji Yoon Park; Eui Jin Hwang; Sang Min Lee; Chang Min Park
Journal:  J Thorac Dis       Date:  2021-12       Impact factor: 2.895

2.  Localization-adjusted diagnostic performance and assistance effect of a computer-aided detection system for pneumothorax and consolidation.

Authors:  Sun Yeop Lee; Sangwoo Ha; Min Gyeong Jeon; Hao Li; Hyunju Choi; Hwa Pyung Kim; Ye Ra Choi; Hoseok I; Yeon Joo Jeong; Yoon Ha Park; Hyemin Ahn; Sang Hyup Hong; Hyun Jung Koo; Choong Wook Lee; Min Jae Kim; Yeon Joo Kim; Kyung Won Kim; Jong Mun Choi
Journal:  NPJ Digit Med       Date:  2022-07-30

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

Authors:  Eui Jin Hwang; Jong Hyuk Lee; Jae Hyun Kim; Woo Hyeon Lim; Jin Mo Goo; Chang Min Park
Journal:  BMC Pulm Med       Date:  2021-12-07       Impact factor: 3.317

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.