Investigation of thoracic four-dimensional CT-based dimension reduction technique for extracting the robust radiomic features. (February 2019)

• Record Type: Journal Article
• Authors: Tanaka, Shohei; Kadoya, Noriyuki; Kajikawa, Tomohiro; Matsuda, Shohei; Dobashi, Suguru; Takeda, Ken; Jingu, Keiichi
• Is Part Of: Physica medica. Volume 58(2019)
• Page Start: 141
• Page End: 148
• Publication Date: 2019-02
• Subjects: Radiotherapy -- Radiomics -- 4D-CT -- Lung cancer; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2019.02.009
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: A technique to select robust radiomic features is suggested. In 4D-CT, respiratory motion seems to significantly affect reproducibility of radiomic features. Excessive dimension reduction may be prevented by using 4D-CT datasets around the end-exhale phase. Abstract: Robust feature selection in radiomic analysis is often implemented using the RIDER test-retest datasets. However, the CT Protocol between the facility and test-retest datasets are different. Therefore, we investigated possibility to select robust features using thoracic four-dimensional CT (4D-CT) scans that are available from patients receiving radiation therapy. In 4D-CT datasets of 14 lung cancer patients who underwent stereotactic body radiotherapy (SBRT) and 14 test-retest datasets of non-small cell lung cancer (NSCLC), 1170 radiomic features (shape: n = 16, statistics: n = 32, texture: n = 1122) were extracted. A concordance correlation coefficient (CCC) > 0.85 was used to select robust features. We compared the robust features in various 4D-CT group with those in test-retest. The total number of robust features was a range between 846/1170 (72%) and 970/1170 (83%) in all 4D-CT groups with three breathing phases (40%–60%); however, that was a range between 44/1170 (4%) and 476/1170 (41%) in all 4D-CT groups with 10 breathing phases. In test-retest, the total number of robust features was 967/1170 (83%); thus, the number of robust features in 4D-CT was almost equal to that in test-retest by using 40–60% breathing phases. In 4D-CT, respiratory motion is a factor that greatly affects the robustness of features, thus by using only 40–60% breathing phases, excessive dimension reduction will be able to be prevented in any 4D-CT datasets, and select robust features suitable for CT protocol of your own facility.