Machine learning for lung CT texture analysis: Improvement of inter-observer agreement for radiological finding classification in patients with pulmonary diseases

Abstract

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.

Predefined and data driven CT densitometric features predict critical illness and hospital length of stay in COVID-19 patients

“…Finally, the methods discussed in this study are focused on a global lung CT histogram analysis. Multi-threshold lung density analysis methods such as those described in already mentioned studies 10 , 12 , 15 or more advanced CT density/texture methods based on local lung pattern classification 30 were not tested and should deserve future attention.…”

Predefined and data driven CT densitometric features predict critical illness and hospital length of stay in COVID-19 patients

“…Finally, the methods discussed in this study are focused on a global lung CT histogram analysis. Multithreshold lung density analysis methods such as those described in already mentioned studies 10,12,15 or more advanced CT density/texture methods based on local lung pattern classi cation 29 were not tested and should deserve future attention.…”

Newly developed artificial intelligence algorithm for COVID-19 pneumonia: utility of quantitative CT texture analysis for prediction of favipiravir treatment effect

“…4) and was provided by Canon Medical Systems and installed on the same workstation. Basics of the three-dimensional (3D) ML-based texture analysis software was described in the past literature [ 13 , 17 ], and this section is briefly mentioned the algorithm.…”

“…Radiological severity was not considered in that study. For the current study, we developed a new ML-based CT texture analysis software for COVID-19, which evaluates radiological findings in lieu of expert chest radiologists and also functions as a second reader of CT images for various pulmonary diseases [ 13 ]. However, it has not been evaluated in terms of predicting therapeutic outcomes for COVID-19 patients.…”