The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences student Carlos Cardenas and his advisor Laurence Court, Ph.D., along with fellow scientists at MD Anderson Cancer Center, have developed a new method for automating the contouring of high-risk clinical target volumes (CTVs) using artificial intelligence and deep neural networks. Both Cardenas and Court are affiliated with the GSBS Program in Medical Physics.
In the study, which was published in the June 2018 issue of the International Journal of Radiation Oncology*Biology*Physics, Cardenas investigated automating and standardizing the contouring of CTVs to reduce interphysician variability. This is one of the largest sources of uncertainty in head and neck radiation therapy, as a patient may be over- or under-dosed based on their doctor’s contouring technique – a process that establishes how much radiation a patient will receive and how the radiation treatment will be delivered.
For their work, Cardenas and Court along with other MD Anderson researchers analyzed data from 52 oropharyngeal cancer patients who had been treated at the cancer center from January 2006 to August 2010 and had previously had their gross tumor volumes and clinical tumor volumes contoured for their radiation therapy treatment.
With that information, they developed a deep-learning algorithm using deep auto-encoders to identify physician contouring patterns. These models use distance map information from surrounding anatomic structures and the gross tumor volume as input parameters and conduct voxel-based classification to identify voxels that are part of the high-risk CTV.
The study found that these predicted high-risk CTVs provided close agreement to the ground-truth compared with current interobserver variability. The predicted contours could be implemented clinically, with only minor or no changes.
The complete study can be viewed here.
Cardenas is also a recipient of a 2017-2018 Andrew Sowell-Wade Huggins Scholarship in Cancer Research.