Patient Safety

PV QA 3 - Poster Viewing Q&A 3

TU_28_3090 - Data Integrity Systems for Organ Contours in Radiation Therapy Planning

Tuesday, October 23
1:00 PM - 2:30 PM
Location: Innovation Hub, Exhibit Hall 3

Data Integrity Systems for Organ Contours in Radiation Therapy Planning
V. Shah, P. Lakshminarayanan, J. Moore, P. T. Tran, H. Quon, C. Deville Jr, and T. R. McNutt; Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD

Purpose/Objective(s): As clinical databases and segmentation techniques have become an integral aspect of clinical radiotherapy, effective tools must be created to ensure the integrity of treated contours. New advances in segmentation methods have improved the ability of clinicians to contour boundaries of organs at risk. However, there is still the potential to treat abnormal contours, resulting in erroneous radiation dosing of non-cancerous anatomy. The purpose of this research is to develop effective data integrity models for contoured anatomy in a radiotherapy workflow for both real-time and retrospective analysis.

Materials/Methods: Within this study, two classes of contour integrity models were developed: data driven models and contiguousness models. The data driven models aim to highlight contours which have attributes that deviate significantly from a gross set of contoured anatomy stored in a database and encompass the following regions of interest (ROI): bladder, femoral heads, spinal cord, and rectum. The contiguousness models, which individually analyze the geometry of contours to detect possible errors, are applied across many different ROI’s and are divided into two metrics: Extent and Region Growing over volume. After developing the metrics, we applied them to patient lists across the aforementioned ROIs. We then conducted a blind review of all the contours tested to detect possible false negatives where we marked all suspicious contours and compared the results to the initial analysis.

Results: We found that 70% of detected bladder contours were verified as abnormal while the spinal cord model and rectum model verified that 73% and 80% of contours were abnormal, respectively. The contiguousness models were the most accurate, however to differing degrees with the Region Growing model being most accurate. 100% of the detected non-contiguous contours were verified as abnormal, but in the cases of spinal cord, femoral heads, bladder, and rectum, the Region Growing model detected additional two to five abnormal contours that the Extent model failed to detect. Additionally, we was found that all the data driven models failed to detect all abnormal contours. The Region Growing contiguousness model produced zero false negatives in all regions of interest other than prostate. With regards to runtime, the contiguousness via extent model was very fast, taking an average of 0.2 seconds per contour. Conversely, the region growing method had a longer runtime which was dependent on the number of voxels in the contour.

Conclusion: Both contiguousness models are suited for real time use in clinical radiotherapy while the data driven models are better suited for retrospective use. Due to the success of these models and their ability to be used in real time, contour integrity systems should become integrated into the clinical planning to process to ensure only verified contours are treated, minimizing the risk of erroneous dosing to critical anatomy and improving the safety of radiation therapy.

Author Disclosure: V. Shah: None. P. Lakshminarayanan: None. J. Moore: None. P.T. Tran: Research Grant; PCORI, Movember-PCF, American Lung Association, Astellas-Medivation, Kimmel Foundation, ACS, NIH-NCI. Honoraria; Dendreon. Consultant; RefleXion Medical. Advisory Board; Dendreon, Astellas-Medivation. Travel Expenses; Dendreon, RefleXion Medical. Patent/License Fees/Copyright; Natsar Pharmaceuticals, Compounds and Methods of Use in Ablative RT. Chair of Radiation Oncology Study Section; RSNA R&E Foundation. Senior Editor; Cancer Research. C. Deville: None. T.R. McNutt: Research Grant; Elekta Oncology Systems, Philips Radiation Oncology Systems, Toshiba. Patent/License Fees/Copyright; Accuray-Tomotherapy, Sun Nuclear. President Elect; AAPM-MAC.

Todd McNutt, PhD

Johns Hopkins University: Associate Professor: Employee

Elekta Oncology Systems: Research Grants; Philips Radiation Oncology Systems: Research Grants; Toshiba: Research Grants

Accuray-Tomotherapy: Patent/License Fees/Copyright; Sun Nuclear: Patent/License Fees/Copyright

AAPM-MAC: President Elect


Send Email for Todd McNutt


TU_28_3090 - Data Integrity Systems for Organ Contours in Radiation Therapy Planning

Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for Data Integrity Systems for Organ Contours in Radiation Therapy Planning