Texture Analysis of Thoracic CT to Predict Hyperpolarized Gas MRI Lung Function

摘要

Objective: Hyperpolarized noble gas magnetic resonance imaging (MRI) provides valuable insights on lung function, andyet is not widely available, whereas thoracic x-ray computed tomography (CT) protocols are nearly universally accessible.Our aim was to develop a texture analysis pipeline to train and test machine learning classifiers, predicting MRI-basedventilation metrics from single-volume thoracic CT in patients with chronic obstructive pulmonary disease (COPD).Methods: MR ventilation maps were generated and registered to thoracic CT datasets. Images were segmented intovolumes of interest (15x15x15mm), resulting in approximately 6,000 volumes-of-interest per subject participant. 85 firstorderand texture features were calculated to describe each volume, including a new texture feature based on the size andoccurrence of CT clusters (we called the cluster volume matrix), which is similar to run-length-matrix. A LogisticRegression, Linear Support Vector Machine and Quadratic Support Vector Machine were trained using 5-fold crossvalidationon a cohort of seven subjects. The highest performing classification model was then applied to a test cohort ofthree subjects.Results: There was qualitative spatial agreement for the experimental MRI ventilation maps and the CT-predictedfunctional maps. The training set was classified with 71% accuracy, while the test set was classified with 66% accuracyand area under the curve (AUC) = 0.72.Conclusions: This proof-of-concept study demonstrated feasibility in a small group of patients with moderateclassification accuracy. Novel insights will be used to optimize this approach with future application to a largerheterogeneous patient cohort.