Open AccessGantry angle classification with a fluence map in intensity-modulated radiotherapy for prostate cases using machine learning
Author(s) -
Hideharu Miura,
Shogo Ozawa,
Tsubasa Enosaki,
Masahiro Hayata,
Kiyoshi Yamada,
Yasushi Nagata
Publication year - 2018
Publication title -
polish journal of medical physics and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 5
eISSN - 1898-0309
pISSN - 1425-4689
DOI - 10.2478/pjmpe-2018-0023
Subject(s) - artificial intelligence , support vector machine , computer science , precision and recall , observer (physics) , k nearest neighbors algorithm , classifier (uml) , algorithm , pattern recognition (psychology) , physics , quantum mechanics
We investigated the gantry-angle classifier performance with a fluence map using three machine-learning algorithms, and compared it with human performance. Eighty prostate cases were investigated using a seven-field-intensity modulated radiotherapy treatment (IMRT) plan with beam angles of 0°, 50°, 100°, 155°, 205°, 260°, and 310°. The k-nearest neighbor (k-NN), logistic regression (LR), and support vector machine (SVM) algorithms were used. In the observer test, three radiotherapists assessed the gantry angle classification in a blind manner. The precision and recall rates were calculated for the machine learning and observer test. The average precision rate of the k-NN and LR algorithms were 94.8% and 97.9%, respectively. The average recall rate of the k-NN and LR algorithms were 94.3% and 97.9%, respectively. The SVM had 100% precision and recall rates. The gantry angles of 0°, 155°, and 205° had an accuracy of 100% in all algorithms. In the observer test, average precision and recall rates were 82.6% and 82.6%, respectively. All observers could easily classify the gantry angles of 0°, 155°, and 205° with a high degree of accuracy. Misclassifications occurred in gantry angles of 50°, 100°, 260°, and 310°. Machine learning could better classify gantry angles for prostate IMRT than human beings. In particular, the SVM algorithm had a perfect classification of 100%.