Fluence Map Prediction Using Deep Learning Models - Direct Plan Generation for Pancreas Stereotactic Body Radiation Therapy.

Abstract

Purpose: Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a difficult and time-consuming task. In this study, we aim to develop a novel deep learning framework to generate clinical-quality plans by direct prediction of fluence maps from patient anatomy using convolutional neural networks (CNNs). Materials and Methods: Our proposed framework utilizes two CNNs to predict intensity-modulated radiation therapy fluence maps and generate deliverable plans: (1) Field-dose CNN predicts field-dose distributions in the region of interest using planning images and structure contours; (2) a fluence map CNN predicts the final fluence map per beam using the predicted field dose projected onto the beam's eye view. The predicted fluence maps were subsequently imported into the treatment planning system for leaf sequencing and final dose calculation (model-predicted plans). One hundred patients previously treated with pancreas SBRT were included in this retrospective study, and they were split into 85 training cases and 15 test cases. For each network, 10% of training data were randomly selected for model validation. Nine-beam benchmark plans with standardized target prescription and organ-at-risk constraints were planned by experienced clinical physicists and used as the gold standard to train the model. Model-predicted plans were compared with benchmark plans in terms of dosimetric endpoints, fluence map deliverability, and total monitor units. Results: The average time for fluence-map prediction per patient was 7.1 s. Comparing model-predicted plans with benchmark plans, target mean dose, maximum dose (0.1 cc), and D95% absolute differences in percentages of prescription were 0.1, 3.9, and 2.1%, respectively; organ-at-risk mean dose and maximum dose (0.1 cc) absolute differences were 0.2 and 4.4%, respectively. The predicted plans had fluence map gamma indices (97.69 ± 0.96% vs. 98.14 ± 0.74%) and total monitor units (2,122 ± 281 vs. 2,265 ± 373) that were comparable to the benchmark plans. Conclusions: We develop a novel deep learning framework for pancreas SBRT planning, which predicts a fluence map for each beam and can, therefore, bypass the lengthy inverse optimization process. The proposed framework could potentially change the paradigm of treatment planning by harnessing the power of deep learning to generate clinically deliverable plans in seconds.

Department

Description

Provenance

Citation

Published Version (Please cite this version)

10.3389/frai.2020.00068

Publication Info

Wang, Wentao, Yang Sheng, Chunhao Wang, Jiahan Zhang, Xinyi Li, Manisha Palta, Brian Czito, Christopher G Willett, et al. (2020). Fluence Map Prediction Using Deep Learning Models - Direct Plan Generation for Pancreas Stereotactic Body Radiation Therapy. Frontiers in artificial intelligence, 3. p. 68. 10.3389/frai.2020.00068 Retrieved from https://hdl.handle.net/10161/22470.

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.

Scholars@Duke

Sheng

Yang Sheng

Assistant Professor of Radiation Oncology

My research interest focuses on machine learning and AI application in radiation oncology treatment planning, including prostate cancer, head-and-neck cancer and pancreatic cancer etc.

Wang

Chunhao Wang

Assistant Professor of Radiation Oncology
  • Deep learning methods for image-based radiotherapy outcome prediction and assessment
  • Machine learning in outcome modelling
  • Automation in radiotherapy planning and delivery



Palta

Manisha Palta

Associate Professor of Radiation Oncology

Clinical research in gastrointestinal malignancies, lymphomas and breast malignancies.

Czito

Brian Gary Czito

Professor of Radiation Oncology

Listed in Best Doctors in America. Listed in Top Doctors in North Carolina. His research interests include gastrointestinal malignancies, including treatment and integration of novel systemic agents with radiation therapy in the treatment of esophageal, gastric, hepatobiliary, pancreatic, colorectal and anal malignancies; phase I/II clinical trials evaluating novel systemic/targeted agents in conjunction with radiation therapy; investigation and optimization of the treatment of gastrointestinal malignancies, with focus on the above tumor sites.

Willett

Christopher G. Willett

Chair, Department of Radiation Oncology
Wu

Qiuwen Wu

Professor of Radiation Oncology

My research interests include intensity-modulated radiation therapy (IMRT), volumetric-modulated arc therapy (VMAT), Dynamic Electron Arc Radiotherapy (DEAR), and image-guided radiation therapy (IGRT). For IMRT, my work includes the development of the research platform, fast and accurate dose calculations, optimization based on physical and biological objectives such as generalized equivalent uniform dose (gEUD), and delivery with a dynamic multi-leaf collimator (DMLC). For VMAT, I am interested in optimization, quality assurance, and novel applications. For DEAR, I'm interested in the treatment planning and delivery verifications. For IGRT, my work includes the development of the infrastructure of the online and offline image guidance, characterization of patient anatomic changes and treatment uncertainties, margin calculations, and adaptive treatment planning. My recent research interests also include the use of AI in treatment planning, Brachytherapy dose calculation and plan optimization.

My clinical interests include prostate cancer, head and neck cancer, total body irradiation (TBI), and total skin irradiation (TSI)

Yin

Fang-Fang Yin

Gustavo S. Montana Distinguished Professor of Radiation Oncology

Stereotactic radiosurgery, Stereotactic body radiation therapy, treatment planning optimization, knowledge guided radiation therapy, intensity-modulated radiation therapy, image-guided radiation therapy, oncological imaging and informatics

Wu

Qingrong Wu

Professor of Radiation Oncology

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.