Literature DB >> 31748854

Deep learning-based detection system for multiclass lesions on chest radiographs: comparison with observer readings.

Sohee Park1, Sang Min Lee2, Kyung Hee Lee3, Kyu-Hwan Jung4, Woong Bae4, Jooae Choe1, Joon Beom Seo1.   

Abstract

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).

Entities:  

Keywords:  Automated pattern recognition; Classification; Deep learning; Thoracic radiography

Year:  2019        PMID: 31748854     DOI: 10.1007/s00330-019-06532-x

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


  22 in total

1.  Improved detection of subtle lung nodules by use of chest radiographs with bone suppression imaging: receiver operating characteristic analysis with and without localization.

Authors:  Feng Li; Takeshi Hara; Junji Shiraishi; Roger Engelmann; Heber MacMahon; Kunio Doi
Journal:  AJR Am J Roentgenol       Date:  2011-05       Impact factor: 3.959

2.  Automated Triaging of Adult Chest Radiographs with Deep Artificial Neural Networks.

Authors:  Mauro Annarumma; Samuel J Withey; Robert J Bakewell; Emanuele Pesce; Vicky Goh; Giovanni Montana
Journal:  Radiology       Date:  2019-01-22       Impact factor: 11.105

3.  Chest radiography: new technological developments and their applications.

Authors:  S Schalekamp; B van Ginneken; N Karssemeijer; C M Schaefer-Prokop
Journal:  Semin Respir Crit Care Med       Date:  2014-01-30       Impact factor: 3.119

4.  Computer-aided detection improves detection of pulmonary nodules in chest radiographs beyond the support by bone-suppressed images.

Authors:  Steven Schalekamp; Bram van Ginneken; Emmeline Koedam; Miranda M Snoeren; Audrey M Tiehuis; Rianne Wittenberg; Nico Karssemeijer; Cornelia M Schaefer-Prokop
Journal:  Radiology       Date:  2014-03-12       Impact factor: 11.105

5.  Application of deep learning-based computer-aided detection system: detecting pneumothorax on chest radiograph after biopsy.

Authors:  Sohee Park; Sang Min Lee; Namkug Kim; Jooae Choe; Yongwon Cho; Kyung-Hyun Do; Joon Beom Seo
Journal:  Eur Radiol       Date:  2019-03-26       Impact factor: 5.315

6.  Usefulness of computer-aided diagnosis schemes for vertebral fractures and lung nodules on chest radiographs.

Authors:  Satoshi Kasai; Feng Li; Junji Shiraishi; Kunio Doi
Journal:  AJR Am J Roentgenol       Date:  2008-07       Impact factor: 3.959

7.  Predictive value and threshold detectability of lung tumors.

Authors:  H L Kundel
Journal:  Radiology       Date:  1981-04       Impact factor: 11.105

8.  Computer-aided Detection Fidelity of Pulmonary Nodules in Chest Radiograph.

Authors:  Nikolaos Dellios; Ulf Teichgraeber; Robert Chelaru; Ansgar Malich; Ismini E Papageorgiou
Journal:  J Clin Imaging Sci       Date:  2017-02-20

9.  Development and Validation of a Deep Learning-Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs.

Authors:  Eui Jin Hwang; Sunggyun Park; Kwang-Nam Jin; Jung Im Kim; So Young Choi; Jong Hyuk Lee; Jin Mo Goo; Jaehong Aum; Jae-Joon Yim; Julien G Cohen; Gilbert R Ferretti; Chang Min Park
Journal:  JAMA Netw Open       Date:  2019-03-01

10.  Sensitivity and specificity of lung cancer screening using chest low-dose computed tomography.

Authors:  Y Toyoda; T Nakayama; Y Kusunoki; H Iso; T Suzuki
Journal:  Br J Cancer       Date:  2008-05-06       Impact factor: 7.640

View more
  11 in total

Review 1.  LI-RADS and transplantation: challenges and controversies.

Authors:  Guilherme M Cunha; Dorathy E Tamayo-Murillo; Kathryn J Fowler
Journal:  Abdom Radiol (NY)       Date:  2021-01

2.  LI-RADS treatment response algorithm after first-line DEB-TACE: reproducibility and prognostic value at initial post-treatment CT/MRI.

Authors:  Ali Pirasteh; E Aleks Sorra; Hector Marquez; Robert C Sibley; Julia R Fielding; Abhinav Vij; Nicole E Rich; Ana Arroyo; Adam C Yopp; Gaurav Khatri; Amit G Singal; Takeshi Yokoo
Journal:  Abdom Radiol (NY)       Date:  2021-03-23

Review 3.  Current and emerging artificial intelligence applications in chest imaging: a pediatric perspective.

Authors:  Steven Schalekamp; Willemijn M Klein; Kicky G van Leeuwen
Journal:  Pediatr Radiol       Date:  2021-09-01

4.  Performance of an AI based CAD system in solid lung nodule detection on chest phantom radiographs compared to radiology residents and fellow radiologists.

Authors:  Alan A Peters; Amanda Decasper; Jaro Munz; Jeremias Klaus; Laura I Loebelenz; Maximilian Korbinian Michael Hoffner; Cynthia Hourscht; Johannes T Heverhagen; Andreas Christe; Lukas Ebner
Journal:  J Thorac Dis       Date:  2021-05       Impact factor: 3.005

Review 5.  Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis.

Authors:  Ravi Aggarwal; Viknesh Sounderajah; Guy Martin; Daniel S W Ting; Alan Karthikesalingam; Dominic King; Hutan Ashrafian; Ara Darzi
Journal:  NPJ Digit Med       Date:  2021-04-07

Review 6.  Artificial intelligence-assisted decision making for prognosis and drug efficacy prediction in lung cancer patients: a narrative review.

Authors:  Jingwei Li; Jiayang Wu; Zhehao Zhao; Qiran Zhang; Jun Shao; Chengdi Wang; Zhixin Qiu; Weimin Li
Journal:  J Thorac Dis       Date:  2021-12       Impact factor: 2.895

7.  Deep learning-based algorithm for lung cancer detection on chest radiographs using the segmentation method.

Authors:  Akitoshi Shimazaki; Daiju Ueda; Antoine Choppin; Akira Yamamoto; Takashi Honjo; Yuki Shimahara; Yukio Miki
Journal:  Sci Rep       Date:  2022-01-14       Impact factor: 4.379

8.  Association of Artificial Intelligence-Aided Chest Radiograph Interpretation With Reader Performance and Efficiency.

Authors:  Jong Seok Ahn; Shadi Ebrahimian; Shaunagh McDermott; Sanghyup Lee; Laura Naccarato; John F Di Capua; Markus Y Wu; Eric W Zhang; Victorine Muse; Benjamin Miller; Farid Sabzalipour; Bernardo C Bizzo; Keith J Dreyer; Parisa Kaviani; Subba R Digumarthy; Mannudeep K Kalra
Journal:  JAMA Netw Open       Date:  2022-08-01

9.  CT Image Analysis and Clinical Diagnosis of New Coronary Pneumonia Based on Improved Convolutional Neural Network.

Authors:  Wu Deng; Bo Yang; Wei Liu; Weiwei Song; Yuan Gao; Jia Xu
Journal:  Comput Math Methods Med       Date:  2021-07-20       Impact factor: 2.238

10.  Automated Radiology Alert System for Pneumothorax Detection on Chest Radiographs Improves Efficiency and Diagnostic Performance.

Authors:  Cheng-Yi Kao; Chiao-Yun Lin; Cheng-Chen Chao; Han-Sheng Huang; Hsing-Yu Lee; Chia-Ming Chang; Kang Sung; Ting-Rong Chen; Po-Chang Chiang; Li-Ting Huang; Bow Wang; Yi-Sheng Liu; Jung-Hsien Chiang; Chien-Kuo Wang; Yi-Shan Tsai
Journal:  Diagnostics (Basel)       Date:  2021-06-29
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.