Combining natural and artificial intelligence for robust automatic anatomy segmentation: Application in neck and thorax auto-contouring.

BACKGROUND: Automatic segmentation of 3D objects in computed tomography (CT) is challenging. Current methods, based mainly on artificial intelligence (AI) and end-to-end deep learning (DL) networks, are weak in garnering high-level anatomic information, which leads to compromised efficiency and robustness. This can be overcome by incorporating natural intelligence (NI) into AI methods via computational models of human anatomic knowledge. PURPOSE: We formulate a hybrid intelligence (HI) approach that integrates the complementary strengths of NI and AI for organ segmentation in CT images and illustrate performance in the application of radiation therapy (RT) planning via multisite clinical evaluation. METHODS: The system employs five modules: (i) body region recognition, which automatically trims a given image to a precisely defined target body region; (ii) NI-based automatic anatomy recognition object recognition (AAR-R), which performs object recognition in the trimmed image without DL and outputs a localized fuzzy model for each object; (iii) DL-based recognition (DL-R), which refines the coarse recognition results of AAR-R and outputs a stack of 2D bounding boxes (BBs) for each object; (iv) model morphing (MM), which deforms the AAR-R fuzzy model of each object guided by the BBs output by DL-R; and (v) DL-based delineation (DL-D), which employs the object containment information provided by MM to delineate each object. NI from (ii), AI from (i), (iii), and (v), and their combination from (iv) facilitate the HI system. RESULTS: The HI system was tested on 26 organs in neck and thorax body regions on CT images obtained prospectively from 464 patients in a study involving four RT centers. Data sets from one separate independent institution involving 125 patients were employed in training/model building for each of the two body regions, whereas 104 and 110 data sets from the 4 RT centers were utilized for testing on neck and thorax, respectively. In the testing data sets, 83% of the images had limitations such as streak artifacts, poor contrast, shape distortion, pathology, or implants. The contours output by the HI system were compared to contours drawn in clinical practice at the four RT centers by utilizing an independently established ground-truth set of contours as reference. Three sets of measures were employed: accuracy via Dice coefficient (DC) and Hausdorff boundary distance (HD), subjective clinical acceptability via a blinded reader study, and efficiency by measuring human time saved in contouring by the HI system. Overall, the HI system achieved a mean DC of 0.78 and 0.87 and a mean HD of 2.22 and 4.53 mm for neck and thorax, respectively. It significantly outperformed clinical contouring in accuracy and saved overall 70% of human time over clinical contouring time, whereas acceptability scores varied significantly from site to site for both auto-contours and clinically drawn contours. CONCLUSIONS: The HI system is observed to behave like an expert human in robustness in the contouring task but vastly more efficiently. It seems to use NI help where image information alone will not suffice to decide, first for the correct localization of the object and then for the precise delineation of the boundary.

Racial/Ethnic Disparities in Screening for and Awareness of High Cholesterol Among Pregnant Women Receiving Prenatal Care.

Background Atherosclerotic cardiovascular disease remains a leading cause of morbidity and mortality among women, with younger women being disproportionately affected by traditional cardiovascular risk factors such as dyslipidemia. Despite recommendations for lipid screening in early adulthood and the risks associated with maternal dyslipidemia during pregnancy, many younger women lack access to and utilization of early screening. Accordingly, our objective was to assess the prevalence of and disparities in lipid screening and awareness of high cholesterol as an atherosclerotic cardiovascular disease risk factor among pregnant women receiving prenatal care. Methods and Results We invited 234 pregnant women receiving prenatal care at 1 of 3 clinics affiliated with the University of Pennsylvania Health System to complete our survey. A total of 200 pregnant women (86% response rate) completed the survey. Overall, 59% of pregnant women (mean age 32.2 [±5.7] years) self-reported a previous lipid screening and 79% of women were aware of high cholesterol as an atherosclerotic cardiovascular disease risk factor. Stratified by racial/ethnic subgroups, non-Hispanic Black women were less likely to report a prior screening (43% versus 67%, P=0.022) and had lower levels of awareness (66% versus 92%, P<0.001) compared with non-Hispanic White women. Non-Hispanic Black women were more likely to see an obstetrician/gynecologist for their usual source of non-pregnancy care compared with non-Hispanic White women (18% versus 5%, P=0.043). Those seeing an obstetrician/gynecologist for usual care were less likely to report a prior lipid screening compared with those seeing a primary care physician (29% versus 63%, P=0.007). Conclusions Significant racial/ethnic disparities persist in lipid screening and risk factor awareness among pregnant women. Prenatal care may represent an opportunity to enhance access to and uptake of screening among younger women and reduce variations in accessing preventive care services.