Artificial intelligence for diagnosis in interstitial lung disease and digital ontology for unclassified interstitial lung disease.
Authors
Affiliations (6)
Affiliations (6)
- Department of Respiratory Medicine, Kanagawa Cardiovascular and Respiratory Center, Tomioka-Higashi 6-16-1, Kanazawa-ku, Yokohama, 236-0051, Japan. Electronic address: [email protected].
- Medical Systems Research & Development Center, Fujifilm Corporation, 6-6-15 Minami-Aoyama, Minato-ku, Tokyo, 107-0062, Japan.
- Department of Radiology, Kanagawa Cardiovascular and Respiratory Center, Tomioka-Higashi 6-16-1, Kanazawa-ku, Yokohama, 236-0051, Japan.
- Department of Pathology, Saitama Medical University, 38 Morohongo, Moroyama-cho, Iruma-gun, 350-0495, Japan.
- Department of Pathology, Kanagawa Cardiovascular and Respiratory Center, Tomioka-Higashi 6-16-1, Kanazawa-ku, Yokohama, 236-0051, Japan.
- Department of Respiratory Medicine, Kanagawa Cardiovascular and Respiratory Center, Tomioka-Higashi 6-16-1, Kanazawa-ku, Yokohama, 236-0051, Japan.
Abstract
Multidisciplinary discussion (MDD) is the gold standard for diagnosis in interstitial lung disease (ILD). However, its inter-rater agreement is not satisfactory, and access to the MDD is limited due to a shortage of ILD experts. Therefore, artificial intelligence would be helpful for diagnosing ILD. We retrospectively analyzed data from 630 patients with ILD, including clinical information, CT images, and pathological results. The ILD classification into four clinicopathologic entities (i.e., idiopathic pulmonary fibrosis, non-specific interstitial pneumonia, hypersensitivity pneumonitis, connective tissue disease) consists of two stages: first, pneumonia pattern classification of CT images using a convolutional neural network (CNN) model; second, multimodal (clinical, radiological, and pathological) classification using a support vector machine (SVM). The performance of the classification algorithm was evaluated using 5-fold cross-validation. The mean accuracies of the CNN model and SVM were 62.4 % and 85.4 %, respectively. For multimodal classification using SVM, the overall accuracy was very high, especially with sensitivities for idiopathic pulmonary fibrosis and hypersensitivity pneumonitis exceeding 90 %. When pneumonia patterns from CT images, pathological results, or clinical information were not used, the SVM accuracy was 84.3 %, 70.3 % and 79.8 %, respectively, suggesting that pathological results contributed most to MDD diagnosis. When an unclassifiable interstitial pneumonia was input, the SVM output tended to align with the most likely diagnosis by the expert MDD team. The algorithm based on multimodal information can assist in diagnosing interstitial lung disease and is suitable for ontology diagnosis. (242 words).