A method of rapid quantification of patient‐specific organ doses for CT using deep‐learning‐based multi‐organ segmentation and GPU‐accelerated Monte Carlo dose computing. Issue 6 (3rd April 2020)

• Record Type: Journal Article
• Authors: Peng, Zhao; Fang, Xi; Yan, Pingkun; Shan, Hongming; Liu, Tianyu; Pei, Xi; Wang, Ge; Liu, Bob; Kalra, Mannudeep K.; Xu, X. George
• Is Part Of: Medical physics. Volume 47:Issue 6(2020)
• Page Start: 2526
• Page End: 2536
• Publication Date: 2020-04-03
• Subjects: convolutional neural network -- CT organ dose -- Monte Carlo -- multi‐organ segmentation -- patient‐specific; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.14131
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: One technical barrier to patient‐specific computed tomography (CT) dosimetry has been the lack of computational tools for the automatic patient‐specific multi‐organ segmentation of CT images and rapid organ dose quantification. When previous CT images are available for the same body region of the patient, the ability to obtain patient‐specific organ doses for CT — in a similar manner as radiation therapy treatment planning — will open the door to personalized and prospective CT scan protocols. This study aims to demonstrate the feasibility of combining deep‐learning algorithms for automatic segmentation of multiple radiosensitive organs from CT images with the GPU‐based Monte Carlo rapid organ dose calculation. Methods: A deep convolutional neural network (CNN) based on the U‐Net for organ segmentation is developed and trained to automatically delineate multiple radiosensitive organs from CT images. Two databases are used: The lung CT segmentation challenge 2017 (LCTSC) dataset that contains 60 thoracic CT scan patients, each consisting of five segmented organs, and the Pancreas‐CT (PCT) dataset, which contains 43 abdominal CT scan patients each consisting of eight segmented organs. A fivefold cross‐validation method is performed on both sets of data. Dice similarity coefficients (DSCs) are used to evaluate the segmentation performance against the ground truth. A GPU‐based Monte Carlo dose code, ARCHER, is used to calculate patient‐specific CT organ doses. The proposed method is evaluated in terms of relative dose errors (RDEs). To demonstrate the potential improvement of the new method, organ dose results are compared against those obtained for population‐average patient phantoms used in an off‐line dose reporting software, VirtualDose, at Massachusetts General Hospital. Results: The median DSCs are found to be 0.97 (right lung), 0.96 (left lung), 0.92 (heart), 0.86 (spinal cord), 0.76 (esophagus) for the LCTSC dataset, along with 0.96 (spleen), 0.96 (liver), 0.95 (left kidney), 0.90 (stomach), 0.87 (gall bladder), 0.80 (pancreas), 0.75 (esophagus), and 0.61 (duodenum) for the PCT dataset. Comparing with organ dose results from population‐averaged phantoms, the new patient‐specific method achieved smaller absolute RDEs (mean ± standard deviation) for all organs: 1.8% ± 1.4% (vs 16.0% ± 11.8%) for the lung, 0.8% ± 0.7% (vs 34.0% ± 31.1%) for the heart, 1.6% ± 1.7% (vs 45.7% ± 29.3%) for the esophagus, 0.6% ± 1.2% (vs 15.8% ± 12.7%) for the spleen, 1.2% ± 1.0% (vs 18.1% ± 15.7%) for the pancreas, 0.9% ± 0.6% (vs 20.0% ± 15.2%) for the left kidney, 1.7% ± 3.1% (vs 19.1% ± 9.8%) for the gallbladder, 0.3% ± 0.3% (vs 24.2% ± 18.7%) for the liver, and 1.6% ± 1.7% (vs 19.3% ± 13.6%) for the stomach. The trained automatic segmentation tool takes <5 s per patient for all 103 patients in the dataset. The Monte Carlo radiation dose calculations performed in parallel to the segmentation process using the GPU‐accelerated ARCHER code take <4 s per patient to achieve <0.5% statistical uncertainty in all organ doses for all 103 patients in the database. Conclusion: This work shows the feasibility to perform combined automatic patient‐specific multi‐organ segmentation of CT images and rapid GPU‐based Monte Carlo dose quantification with clinically acceptable accuracy and efficiency.