Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy. (October 2017)

• Record Type: Journal Article
• Authors: Kawata, Yasuo; Arimura, Hidetaka; Ikushima, Koujirou; Jin, Ze; Morita, Kento; Tokunaga, Chiaki; Yabu-uchi, Hidetake; Shioyama, Yoshiyuki; Sasaki, Tomonari; Honda, Hiroshi; Sasaki, Masayuki
• Is Part Of: Physica medica. Volume 42(2017)
• Page Start: 141
• Page End: 149
• Publication Date: 2017-10
• Subjects: Gross tumor volume (GTV) -- Planning computed tomography -- 18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) -- Pixel-based machine learning -- Image segmentation; 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.2017.08.012
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: The fuzzy c-means clustering (FCM) can be useful to delineate tumor regions. The suitable pixel-based machine learning differed depending on the tumor type. The average computational time of the FCM-based framework was significantly reduced. The variability on the results of the FCM-based framework was significantly reduced. Abstract: The aim of this study was to investigate the impact of pixel-based machine learning (ML) techniques, i.e., fuzzy-c-means clustering method (FCM), and the artificial neural network (ANN) and support vector machine (SVM), on an automated framework for delineation of gross tumor volume (GTV) regions of lung cancer for stereotactic body radiation therapy. The morphological and metabolic features for GTV regions, which were determined based on the knowledge of radiation oncologists, were fed on a pixel-by-pixel basis into the respective FCM, ANN, and SVM ML techniques. Then, the ML techniques were incorporated into the automated delineation framework of GTVs followed by an optimum contour selection (OCS) method, which we proposed in a previous study. The three-ML-based frameworks were evaluated for 16 lung cancer cases (six solid, four ground glass opacity (GGO), six part-solid GGO) with the datasets of planning computed tomography (CT) and 18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT images using the three-dimensional Dice similarity coefficient (DSC). DSC denotes the degree of region similarity between the GTVs contoured by radiation oncologists and those estimated using the automated framework. The FCM-based framework achieved the highest DSCs of 0.79 ± 0.06, whereas DSCs of the ANN-based and SVM-based frameworks were 0.76 ± 0.14 and 0.73 ± 0.14, respectively. The FCM-based framework provided the highest segmentation accuracy and precision without a learning process (lowest calculation cost). Therefore, the FCM-based framework can be useful for delineation of tumor regions in practical treatment planning.