Yoshiharu Ohno1, Kota Aoyagi2, Daisuke Takenaka3, Takeshi Yoshikawa4, Aina Ikezaki2, Yasuko Fujisawa2, Kazuhiro Murayama5, Hidekazu Hattori6, Hiroshi Toyama6. 1. Department of Radiology, Fujita Health University School of Medicine, Toyoake, Aichi, Japan; Joint Research Laboratory of Advanced Medical Imaging, Fujita Health University School of Medicine, Toyoake, Aichi, Japan; Division of Functional and Diagnostic Imaging Research, Department of Radiology, Kobe University Graduate School of Medicine, Kobe, Hyogo, Japan. Electronic address: yohno@fujita-hu.ac.jp. 2. Canon Medical Systems Corporation, Otawara, Tochigi, Japan. 3. Department of Diagnostic Radiology, Hyogo Cancer Center, Akashi, Hyogo, Japan. 4. Division of Functional and Diagnostic Imaging Research, Department of Radiology, Kobe University Graduate School of Medicine, Kobe, Hyogo, Japan; Department of Diagnostic Radiology, Hyogo Cancer Center, Akashi, Hyogo, Japan. 5. Joint Research Laboratory of Advanced Medical Imaging, Fujita Health University School of Medicine, Toyoake, Aichi, Japan. 6. Department of Radiology, Fujita Health University School of Medicine, Toyoake, Aichi, Japan.
Abstract
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.
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.