Regression Analysis of Rectal Cancer and Possible Application of Artificial Intelligence (AI) Utilization in Radiotherapy

Artificial Intelligence (AI) has been widely employed in the medical field in recent years in such areas as image segmentation, medical image registration, and computer-aided detection. This study explores one application of using AI in adaptive radiation therapy treatment planning by predicting the tumor volume reduction rate (TVRR). Cone beam computed tomography (CBCT) scans of twenty rectal cancer patients were collected to observe the change in tumor volume over the course of a standard five-week radiotherapy treatment. In addition to treatment volume, patient data including patient age, gender, weight, number of treatment fractions, and dose per fraction were also collected. Application of a stepwise regression model showed that age, dose per fraction and weight were the best predictors for tumor volume reduction rate.

Introducing matrix sparsity with kernel truncation into dose calculations for fluence optimization.

Deep learning algorithms for radiation therapy treatment planning automation require large patient datasets and complex architectures that often take hundreds of hours to train. Some of these algorithms require constant dose updating (such as with reinforcement learning) and may take days. When these algorithms rely on commerical treatment planning systems to perform dose calculations, the data pipeline becomes the bottleneck of the entire algorithm’s efficiency. Further, uniformly accurate distributions are not always needed for the training and approximations can be introduced to speed up the process without affecting the outcome. These approximations not only speed up the calculation process, but allow for custom algorithms to be written specifically for the purposes of use in AI/ML applications where the dose and fluence must be calculated a multitude of times for a multitude of different situations. Here we present and investigate the effect of introducing matrix sparsity through kernel truncation on the dose calculation for the purposes of fluence optimzation within these AI/ML algorithms. The basis for this algorithm relies on voxel discrimination in which numerous voxels are pruned from the computationally expensive part of the calculation. This results in a significant reduction in computation time and storage. Comparing our dose calculation against calculations in both a water phantom and patient anatomy in Eclipse without heterogenity corrections produced gamma index passing rates around 99% for individual and composite beams with uniform fluence and around 98% for beams with a modulated fluence. The resulting sparsity introduces a reduction in computational time and space proportional to the square of the sparsity tolerance with a potential decrease in cost greater than 10 times that of a dense calculation allowing not only for faster caluclations but for calculations that a dense algorithm could not perform on the same system.

A Mathematic Method to Adjust MLC Leaf End Position for Accuracy Dose Calculation in Carbon Ion Beam Radiation Therapy Treatment Planning System

IntroductionWe present a mathematic method to adjust the leaf end position for dose calculation correction in carbon ion radiation therapy treatment planning system. Methods and MaterialsA struggling range algorism of 400 MeV/n carbon ion beam in nine different multi-leaf collimator (MLC) materials was conducted to calculate the dose 50% point in order to derive the offset corrections in carbon ion treatment planning system (ciPlan). The visualized light field edge position in treatment planning system is denoted as Xtang.p and MLC position (Xmlc.p) is defined as the source to leaf end mid-point projection on axis for monitor unit calculation. The virtual source position of an energy at 400 MeV/n and struggling range in MLC at different field sizes were used to calculate the dose 50% position on axis. On-axis MLC offset (correction) could then be obtained from the position corresponding to 50% of the central axis dose minus the Xmlc.p MLC position. ResultsThe precise MLC position in carbon ion treatment planning system can be used an offset to do the correction. The offset correction of pure tungsten is the smallest among the others due to its shortest struggling range of carbon ion beam in MLC. The positions of 50% dose of all MLC materials are always located in between Xtang.p and Xmlc.p under the largest field of 12 cm by 12 cm. ConclusionsMLC offset should be adjusted carefully at different field size in treatment planning system especially of its small penumbra characteristic in carbon ion beam. It is necessary to find out the dose 50% position for adjusting MLC leaf edge on-axis location in the treatment planning system to reduce dose calculation error.

Assessing The Clinical Application Of The Van Herk Margin Formula For Lung Radiotherapy

In radiation therapy treatment planning, margins are added to the tumour volume to ensure that the correct radiation dose is delivered to the tumour in the presence of geometrical uncertainties. The van Herk margin formula (VHMF) was developed to calculate the minimum margin on the target to provide full coverage by 95% of the prescribed dose to 90% of the population. However, this formula is based on an ideal dose profile model that is not realistic for lung radiotherapy. The purpose of this study was to investigate the validity of the VHMF for lung radiotherapy with accurate dose calculation algorithms and respiratory motion modeling. Ultimately, the VHMF ensured sufficient target coverage, with the exception of small lesions in soft tissue; however, the derived PTV margins were larger than necessary. A novel planning approach using the VHMF was tested indicating the need to account for tumour motion trajectory and plan conformity.

Assessing The Clinical Application Of The Van Herk Margin Formula For Lung Radiotherapy

In radiation therapy treatment planning, margins are added to the tumour volume to ensure that the correct radiation dose is delivered to the tumour in the presence of geometrical uncertainties. The van Herk margin formula (VHMF) was developed to calculate the minimum margin on the target to provide full coverage by 95% of the prescribed dose to 90% of the population. However, this formula is based on an ideal dose profile model that is not realistic for lung radiotherapy. The purpose of this study was to investigate the validity of the VHMF for lung radiotherapy with accurate dose calculation algorithms and respiratory motion modeling. Ultimately, the VHMF ensured sufficient target coverage, with the exception of small lesions in soft tissue; however, the derived PTV margins were larger than necessary. A novel planning approach using the VHMF was tested indicating the need to account for tumour motion trajectory and plan conformity.