MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Automated Identification of DICOM-RT Structures Using Map Projections and Machine Learning

D Cutright1*, T Wu1, A Roy2, M Gopalakrishnan3, B Mittal3 (1) University of Chicago Medicine, Chicago, IL, (2) The University of Texas at San Antonio, San Antonio, TX, (3) Northwestern Memorial Hospital, Chicago, IL

Presentations

(Sunday, 7/12/2020)   [Eastern Time (GMT-4)]

Room: AAPM ePoster Library

Purpose:
One of the more difficult problems associated with building large DICOM-RT databases is properly identifying regions-of-interest (ROIs) that were not consistently named. Prospectively, this problem can be addressed with standardized nomenclature, however, large-scale retrospective studies could greatly benefit from a more automated and robust method.

Methods:
As a proof-of-concept, we demonstrate feasibility of transforming ROI surface coordinates into a tensor, suitable for machine learning, to identify anatomical structures based on DICOM-RT structure coordinates. These tensors are calculated using the ROI’s centroid (self-centroid), a second ROI’s centroid (paired-centroid), or paired surface points of a second ROI (paired-surface) as origins. An algorithm was developed taking advantage of both the self-centroid method and a paired method where several passes of self-centroid results inform the paired method. Using a random forest classifying algorithm, models were generated and tested using a Head & Neck data set from a single physician, including 70 laryngeal patients and 1,699 anatomical ROIs among 30 ROI categories.

Results:
Overall accuracies and confusion matrices were generated for each tensor method, using the larynx as the paired ROI for the paired methods. Overall accuracies of 88.5%, 95.3%, and 93.8% were reported for the self-centroid, paired-centroid, and paired-surface methods, respectively. However, an overall accuracy of 100% with a single rejected ROI was observed when combining the self-centroid and paired-centroid methods – without explicitly identifying the “paired” ROI.

Conclusion:
Feasibility of automated ROI identification was demonstrated without the need for complicated and computationally expensive neural networks. This was accomplished by transforming DICOM-RT Structure coordinates with a map projection for input into a random forest machine learning algorithm.

Keywords

DICOM-RT, Deformation, Structure Analysis

Taxonomy

IM/TH- Mathematical/Statistical Foundational Skills: Machine Learning

Contact Email