Development of a real-time markerless tracking system for pancreatic cancer in carbon ion radiation therapy using deep learning

2022 Fiscal Year Research-status Report

• Project/Area Number: 22K15818
• Research Institution: Gunma University
• Principal Investigator: Varnava Maria 群馬大学, 重粒子線医学推進機構, 助教 (40913108)
• Project Period (FY): 2022-04-01 – 2025-03-31
• Keywords: tumor tracking / pancreatic cancer / deep learning / surface image guided / carbon ion radiotherapy

Outline of Annual Research Achievements

Pancreatic cancer is one of the most lethal cancers. One in three deaths in pancreatic cancer patients is related to tumor progression. Therefore, treatment methods that improve local tumor control may lead to better overall survival. The purpose for this year was to focus on developing a prediction model for the location of the target based on the surface of the patient, which will be the basis for the research. The following steps were taken:
・ Acquisition of patient data, data preprocessing, and mining
・ Use of recurrent neural networks to create prediction models for the location of the tumor.

Current Status of Research Progress

3: Progress in research has been slightly delayed.

Reason

It took a lot of time to collect and prepare all the data. The model is still under development because of the long calculation times and difficulties in solving technical difficulties during implementation.
There were also some delays in completing the GPU workstation for creating the prediction model.

Strategy for Future Research Activity

Complete the prediction model and continue as initially planned.

Causes of Carryover

It was necessary to transfer funds to this fiscal year in order to be able to purchase and complete the workstation for the development of the model. After completing the workstation, funds remained, which will be used for the model.