TY - JOUR
T1 - Machine learning for lung CT texture analysis
T2 - Improvement of inter-observer agreement for radiological finding classification in patients with pulmonary diseases
AU - Ohno, Yoshiharu
AU - Aoyagi, Kota
AU - Takenaka, Daisuke
AU - Yoshikawa, Takeshi
AU - Ikezaki, Aina
AU - Fujisawa, Yasuko
AU - Murayama, Kazuhiro
AU - Hattori, Hidekazu
AU - Toyama, Hiroshi
N1 - Funding Information:
This work is “Original Research”, and was financially or technically supported by Canon Medical Systems Corporation , the Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675 and No. 20K08037).
Funding Information:
This study was financially and technically supported by Canon Medical Systems Corporation, the Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675 and No. 20K08037). Three of the authors are employees of Canon Medical Systems Corporation (K.A., A.I. and Y.F.) but did not have control over any of the data used in this study.
Funding Information:
In this study, Drs. Ohno, Yoshikawa, Murayama and Toyama have a research grant from Canon Medical Systems Corporation, Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675 and/or No. 20K08037). In addition, Dr. Takenaka has a research grant from Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675). Moreover, Mr. Aoyagi, Ms. Ikezaki and Ms. Fujisawa are employees of Canon Medical Systems Corporation.
Funding Information:
1. Yoshiharu Ohno, MD, PhD: Research Grant from Canon Medical Systems Corporation, the Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675 and No. 20K08037).
Funding Information:
3. Daisuke Takenaka, MD.: Research grant: Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675)
Funding Information:
4. Takeshi Yoshikawa, MD, PhD: Research Grant from Canon Medical Systems Corporation, the Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 18K07675 and No. 20K08037).
Funding Information:
7. Kazuhiro Murayama, MD, PhD: Research Grant from Canon Medical Systems Corporation, the Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 20K08037).
Funding Information:
9. Hiroshi Toyama, MD, PhD: Research Grant from Canon Medical Systems Corporation, the Smoking Research Foundation and Grants-in-Aid for Scientific Research from the Japanese Ministry of Education, Culture, Sports, Science and Technology (JSTS.KAKEN; No. 20K08037).
PY - 2021/1
Y1 - 2021/1
N2 - Purpose: To evaluate the capability ML-based CT texture analysis for improving interobserver agreement and accuracy of radiological finding assessment in patients with COPD, interstitial lung diseases or infectious diseases. Materials and methods: Training cases (n = 28), validation cases (n = 17) and test cases (n = 89) who underwent thin-section CT at a 320-detector row CT with wide volume scan and two 64-detector row CTs with helical scan were enrolled in this study. From 89 CT data, a total of 350 computationally selected ROI including normal lung, emphysema, nodular lesion, ground-glass opacity, reticulation and honeycomb were evaluated by three radiologists as well as by the software. Inter-observer agreements between consensus reading with and without using the software or software alone and standard references determined by consensus of pulmonologists and chest radiologists were determined using κ statistics. Overall distinguishing accuracies were compared among all methods by McNemar's test. Results: Agreements for consensus readings obtained with and without the software or the software alone with standard references were determined as significant and substantial or excellent (with the software: κ = 0.91, p < 0.0001; without the software: κ = 0.81, p < 0.0001; the software alone: κ = 0.79, p < 0.0001). Overall differentiation accuracy of consensus reading using the software (94.9 [332/350] %) was significantly higher than that of consensus reading without using the software (84.3 [295/350] %, p < 0.0001) and the software alone (82.3 [288/350] %, p < 0.0001). Conclusion: ML-based CT texture analysis software has potential for improving interobserver agreement and accuracy for radiological finding assessments in patients with COPD, interstitial lung diseases or infectious diseases.
AB - Purpose: To evaluate the capability ML-based CT texture analysis for improving interobserver agreement and accuracy of radiological finding assessment in patients with COPD, interstitial lung diseases or infectious diseases. Materials and methods: Training cases (n = 28), validation cases (n = 17) and test cases (n = 89) who underwent thin-section CT at a 320-detector row CT with wide volume scan and two 64-detector row CTs with helical scan were enrolled in this study. From 89 CT data, a total of 350 computationally selected ROI including normal lung, emphysema, nodular lesion, ground-glass opacity, reticulation and honeycomb were evaluated by three radiologists as well as by the software. Inter-observer agreements between consensus reading with and without using the software or software alone and standard references determined by consensus of pulmonologists and chest radiologists were determined using κ statistics. Overall distinguishing accuracies were compared among all methods by McNemar's test. Results: Agreements for consensus readings obtained with and without the software or the software alone with standard references were determined as significant and substantial or excellent (with the software: κ = 0.91, p < 0.0001; without the software: κ = 0.81, p < 0.0001; the software alone: κ = 0.79, p < 0.0001). Overall differentiation accuracy of consensus reading using the software (94.9 [332/350] %) was significantly higher than that of consensus reading without using the software (84.3 [295/350] %, p < 0.0001) and the software alone (82.3 [288/350] %, p < 0.0001). Conclusion: ML-based CT texture analysis software has potential for improving interobserver agreement and accuracy for radiological finding assessments in patients with COPD, interstitial lung diseases or infectious diseases.
UR - http://www.scopus.com/inward/record.url?scp=85096707859&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096707859&partnerID=8YFLogxK
U2 - 10.1016/j.ejrad.2020.109410
DO - 10.1016/j.ejrad.2020.109410
M3 - Article
C2 - 33246272
AN - SCOPUS:85096707859
VL - 134
JO - European Journal of Radiology
JF - European Journal of Radiology
SN - 0720-048X
M1 - 109410
ER -