Abstract
Traditionally, radiologists have crudely quantified tumor extent by measuring the longest and shortest dimension by dragging a cursor between opposite boundary points across a single image rather than full segmentation of the volumetric extent. For algorithmic-based volumetric segmentation, the degree of radiologist experiential involvement varies from confirming a fully automated segmentation, to making a single drag on an image to initiate semi-automated segmentation, to making multiple drags and clicks on multiple images during interactive segmentation. An experiment was designed to test an algorithm that allows various levels of interaction. Given the ground-truth of the BraTS training data, which delimits the brain tumors of 285 patients on multi-spectral MR, a computer simulation mimicked the process that a radiologist would follow to perform segmentation with real-time interaction. Clicks and drags were placed only where needed in response to the deviation between real-time segmentation results and assumed radiologist's goal, as provided by the ground-truth. Results of accuracy for various levels of interaction are presented along with estimated elapsed time, in order to measure efficiency. Average total elapsed time, including loading the study through confirming 3D contours, was 46 s.
Highlights
Malignant brain tumors often have unfavorable prognoses such as time to progression and overall survival, and have direct impact on motor and/or cognitive function and poor quality of life (Omuro and DeAngelis, 2013)
All current imaging assessment criteria [such as Response Evaluation Criteria in Solid Tumors (RECIST), Response Assessment in Neuro-Oncology (RANO), immune related RECIST, and immune related response criteria] used to evaluate tumor response in the clinical setting or in clinical trials rely on these freehand measurements to evaluate tumor size (Sorensen et al, 2008; Eisenhauer et al, 2009; Wolchok et al, 2009; Wen et al, 2010)
In a recent publication we presented Semi-Automated MapBAsed Segmentation (SAMBAS), which allows for real-time feedback by an expert radiologist (Gering et al, 2018)
Summary
Malignant brain tumors often have unfavorable prognoses such as time to progression and overall survival, and have direct impact on motor and/or cognitive function and poor quality of life (Omuro and DeAngelis, 2013). Multimodal MRI protocols allow for non-invasive interrogation of tumor heterogeneity and identification of phenotypic sub-regions i.e., peritumoral edema/invasion, enhancing active tumor core and necrotic regions which reflect tumor biological properties including tumor cellularity, vascularity, and blood-brain barrier integrity. Despite the exponential enhancement in imaging sequences, hardware and software, we have barely begun to tap the potential of non-invasive imaging to characterize the phenotype of tumors. Radiologic assessments are qualitative including tumor detection and image-based tumor staging or semi-quantitative using freehand uni-dimensional and. Tumor Segmentation by Simulating User Interaction bi-dimensional measurements of the tumor. All current imaging assessment criteria [such as Response Evaluation Criteria in Solid Tumors (RECIST), Response Assessment in Neuro-Oncology (RANO), immune related RECIST (irRECIST), and immune related response criteria (irRC)] used to evaluate tumor response in the clinical setting or in clinical trials rely on these freehand measurements to evaluate tumor size (Sorensen et al, 2008; Eisenhauer et al, 2009; Wolchok et al, 2009; Wen et al, 2010)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
