Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application
PurposeTo develop a deep learning-based AI agent, DDD-PIOP (Dose-Distribution-Driven PET Image Outcome Prediction), for predicting 18FDG-PET image outcomes of oropharyngeal cancer (OPC) in response to intensity-modulated radiation therapy (IMRT).MethodsDDD-PIOP uses pre-radiotherapy 18FDG-PET/CT ima...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-08-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fonc.2020.01592/full |
| _version_ | 1818341151031164928 |
|---|---|
| author | Chunhao Wang Chenyang Liu Yushi Chang Kyle Lafata Yunfeng Cui Jiahan Zhang Yang Sheng Yvonne Mowery David Brizel Fang-Fang Yin Fang-Fang Yin |
| author_facet | Chunhao Wang Chenyang Liu Yushi Chang Kyle Lafata Yunfeng Cui Jiahan Zhang Yang Sheng Yvonne Mowery David Brizel Fang-Fang Yin Fang-Fang Yin |
| author_sort | Chunhao Wang |
| collection | DOAJ |
| description | PurposeTo develop a deep learning-based AI agent, DDD-PIOP (Dose-Distribution-Driven PET Image Outcome Prediction), for predicting 18FDG-PET image outcomes of oropharyngeal cancer (OPC) in response to intensity-modulated radiation therapy (IMRT).MethodsDDD-PIOP uses pre-radiotherapy 18FDG-PET/CT images and the planned spatial dose distribution as the inputs, and it predicts the 18FDG-PET image outcomes in response to the planned IMRT delivery. This AI agent centralizes a customized convolutional neural network (CNN) as a deep learning approach, and it incorporates a few designs to enhance prediction accuracy. 66 OPC patients who received IMRT treatment on a sequential boost regime (2 Gy/daily fraction) were studied for DDD-PIOP development. 61 patients were used for AI agent training/validation, and the remaining five were used as independent tests. To evaluate the developed AI agent’s performance, the predicted mean standardized uptake values (SUVs) of gross tumor volume (GTV) and clinical target volume (CTV) were compared with the ground truth values. Overall SUV distribution accuracy was evaluated by gamma test passing rates under different criteria.ResultsThe developed DDD-PIOP successfully generated 18FDG-PET image outcome predictions for five test patients. The predicted mean SUV values of GTV/CTV were 3.50/1.41, which were close to the ground-truth values of 3.57/1.51. In 2D-based gamma tests, the average passing rate was 92.1% using 5%/10 mm criteria, which was improved to 95.9%/93.2% when focusing on GTV/CTV regions. 3D gamma test passing rates were 98.7% using 5%/10 mm criteria, and the corresponding GTV/CTV results were 99.8%/99.4%.ConclusionThe reported results suggest that the developed AI agent DDD-PIOP successfully predicted 18FDG-PET image outcomes with high quantitative accuracy. The generated voxel-based image outcome predictions could be used for treatment planning optimization prior to radiation delivery for the best individual-based outcome. |
| first_indexed | 2024-12-13T15:54:14Z |
| format | Article |
| id | doaj.art-d5793d8d6d3c4e2c8172190fc0a10285 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-13T15:54:14Z |
| publishDate | 2020-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-d5793d8d6d3c4e2c8172190fc0a102852022-12-21T23:39:22ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2020-08-011010.3389/fonc.2020.01592530249Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT ApplicationChunhao Wang0Chenyang Liu1Yushi Chang2Kyle Lafata3Yunfeng Cui4Jiahan Zhang5Yang Sheng6Yvonne Mowery7David Brizel8Fang-Fang Yin9Fang-Fang Yin10Department of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesMedical Physics Graduate Program, Duke Kunshan University, Kunshan, ChinaDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, CA, United StatesMedical Physics Graduate Program, Duke Kunshan University, Kunshan, ChinaPurposeTo develop a deep learning-based AI agent, DDD-PIOP (Dose-Distribution-Driven PET Image Outcome Prediction), for predicting 18FDG-PET image outcomes of oropharyngeal cancer (OPC) in response to intensity-modulated radiation therapy (IMRT).MethodsDDD-PIOP uses pre-radiotherapy 18FDG-PET/CT images and the planned spatial dose distribution as the inputs, and it predicts the 18FDG-PET image outcomes in response to the planned IMRT delivery. This AI agent centralizes a customized convolutional neural network (CNN) as a deep learning approach, and it incorporates a few designs to enhance prediction accuracy. 66 OPC patients who received IMRT treatment on a sequential boost regime (2 Gy/daily fraction) were studied for DDD-PIOP development. 61 patients were used for AI agent training/validation, and the remaining five were used as independent tests. To evaluate the developed AI agent’s performance, the predicted mean standardized uptake values (SUVs) of gross tumor volume (GTV) and clinical target volume (CTV) were compared with the ground truth values. Overall SUV distribution accuracy was evaluated by gamma test passing rates under different criteria.ResultsThe developed DDD-PIOP successfully generated 18FDG-PET image outcome predictions for five test patients. The predicted mean SUV values of GTV/CTV were 3.50/1.41, which were close to the ground-truth values of 3.57/1.51. In 2D-based gamma tests, the average passing rate was 92.1% using 5%/10 mm criteria, which was improved to 95.9%/93.2% when focusing on GTV/CTV regions. 3D gamma test passing rates were 98.7% using 5%/10 mm criteria, and the corresponding GTV/CTV results were 99.8%/99.4%.ConclusionThe reported results suggest that the developed AI agent DDD-PIOP successfully predicted 18FDG-PET image outcomes with high quantitative accuracy. The generated voxel-based image outcome predictions could be used for treatment planning optimization prior to radiation delivery for the best individual-based outcome.https://www.frontiersin.org/article/10.3389/fonc.2020.01592/fullPositron Emission Tomographydeep learningoropharangeal cancerIMRT (intensity modulated radiation therapy)outcome prediction |
| spellingShingle | Chunhao Wang Chenyang Liu Yushi Chang Kyle Lafata Yunfeng Cui Jiahan Zhang Yang Sheng Yvonne Mowery David Brizel Fang-Fang Yin Fang-Fang Yin Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application Frontiers in Oncology Positron Emission Tomography deep learning oropharangeal cancer IMRT (intensity modulated radiation therapy) outcome prediction |
| title | Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application |
| title_full | Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application |
| title_fullStr | Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application |
| title_full_unstemmed | Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application |
| title_short | Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application |
| title_sort | dose distribution driven pet image based outcome prediction ddd piop a deep learning study for oropharyngeal cancer imrt application |
| topic | Positron Emission Tomography deep learning oropharangeal cancer IMRT (intensity modulated radiation therapy) outcome prediction |
| url | https://www.frontiersin.org/article/10.3389/fonc.2020.01592/full |
| work_keys_str_mv | AT chunhaowang dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT chenyangliu dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT yushichang dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT kylelafata dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT yunfengcui dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT jiahanzhang dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT yangsheng dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT yvonnemowery dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT davidbrizel dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT fangfangyin dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication AT fangfangyin dosedistributiondrivenpetimagebasedoutcomepredictiondddpiopadeeplearningstudyfororopharyngealcancerimrtapplication |