Premium
Deep learning‐based digitization of prostate brachytherapy needles in ultrasound images
Author(s) -
Andersén Christoffer,
Rydén Tobias,
Thunberg Per,
Lagerlöf Jakob H.
Publication year - 2020
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1002/mp.14508
Subject(s) - brachytherapy , convolutional neural network , ultrasound , prostate brachytherapy , nuclear medicine , data set , medicine , artificial intelligence , voxel , ground truth , computer science , radiology , radiation therapy
Purpose To develop, and evaluate the performance of, a deep learning‐based three‐dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) algorithm aimed at finding needles in ultrasound images used in prostate brachytherapy. Methods Transrectal ultrasound (TRUS) image volumes from 1102 treatments were used to create a clinical ground truth (CGT) including 24422 individual needles that had been manually digitized by medical physicists during brachytherapy procedures. A 3D CNN U‐net with 128 × 128 × 128 TRUS image volumes as input was trained using 17215 needle examples. Predictions of voxels constituting a needle were combined to yield a 3D linear function describing the localization of each needle in a TRUS volume. Manual and AI digitizations were compared in terms of the root‐mean‐square distance (RMSD) along each needle, expressed as median and interquartile range (IQR). The method was evaluated on a data set including 7207 needle examples. A subgroup of the evaluation data set (n = 188) was created, where the needles were digitized once more by a medical physicist (G1) trained in brachytherapy. The digitization procedure was timed. Results The RMSD between the AI and CGT was 0.55 (IQR: 0.35–0.86) mm. In the smaller subset, the RMSD between AI and CGT was similar (0.52 [IQR: 0.33–0.79] mm) but significantly smaller ( P < 0.001) than the difference of 0.75 (IQR: 0.49–1.20) mm between AI and G1. The difference between CGT and G1 was 0.80 (IQR: 0.48–1.18) mm, implying that the AI performed as well as the CGT in relation to G1. The mean time needed for human digitization was 10 min 11 sec, while the time needed for the AI was negligible. Conclusions A 3D CNN can be trained to identify needles in TRUS images. The performance of the network was similar to that of a medical physicist trained in brachytherapy. Incorporating a CNN for needle identification can shorten brachytherapy treatment procedures substantially.