Measuring Efficiency of Semi-automated Brain Tumor Segmentation by Simulating User Interaction

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.

Preliminary Report on Computed Tomography Radiomics Features as Biomarkers to Immunotherapy Selection in Lung Adenocarcinoma Patients

“…The user initialized the lesion segmentation by drawing a long axis on a plane of the multiplanar reconstruction (MPR) (Figure 1A). A 2D segmentation updated in real-time with interactive feedback of the lesion boundary [23,24] and 2D segmentations on the other MPR planes were immediately proposed. When the contour on a MPR plane was unsatisfactory, the user could update the segmentation by either drawing long axes on the other MPR views or using a 2D brush tool (Figure 1B).…”

“…As the 3D segmentation was confirmed by the user, the measure of the long and short lesion axes was automatically determined by leveraging the volume delineation (Figure 2). A total of 573 radiomic metrics were extracted from the delineated VOIs as previously reported in [24]: 14 features based on Hounsfield unit (HU) values specific for lung CT images; 66 first-order profile features based on intensity values (statistical distribution of image value); 43 second-order profile features based on lesion shape (geometric analysis of shape, volume, curvature and volumetric length); 393 third-order profile features, i.e., texture features, with IBSI-consistent implementation [25] of the grey-level co-occurrence matrix (GLCM), the grey-level distance zone matrix (GLDZM), the grey-level run length matrix (GLRLM), the grey-level size zone matrix (GLSZM), the neighboring grey-level dependence matrix (NGLDM), the neighboring grey-tone difference matrix (NGTDM) and the different features' aggregation methods, as well as 57 features with higher-order profiles (statistical metrics after transformations and wavelet analysis).…”

Quantitative imaging decision support (QIDSTM) tool consistency evaluation and radiomic analysis by means of 594 metrics in lung carcinoma on chest CT scan

“…Conventionally, radiologists have measured tumor extent by the longest dimension on a single image rather than performing a full segmentation of the tumor volume. 2 …”

“…Semi-automated techniques outperform automatic approaches obtaining accurate and robust results. 2 , 11 Additionally, image analysis techniques have been used to provide prognostic biomarkers and to assess the treatment response with ever greater accuracy in order to provide personalized therapy. In particular, radiomic analysis methods, 12 , 13 which describe a region of interest using multiple quantitative features derived by images, have shown great potential to predict the survival in lung cancer patients.…”

“…Conventionally, radiologists have measured tumor extent by the longest dimension on a single image rather than performing a full segmentation of the tumor volume. 2 Based on these insights, several authors have proposed alternative methods by combining morphological-dimensional criteria with physiological-metabolic characteristics in order to overcome the limitations of traditional criteria. These alternative criteria allow to highlight the response to treatment by evaluating "functional" rather than purely "morphological" parameters by providing information relating to perfusion, vascularization, diffusion and metabolic properties of the tissues, which are more appropriate especially in the case of monitoring of "Target therapies."…”