This paper explores a deep-learning approach to evaluate the position of circular delimiters in cartridge case images. These delimiters define two regions of interest (ROI), corresponding to the breech face and the firing pin impressions, and are placed manually or by an image-processing algorithm. This positioning bears a significant impact on the performance of the image-matching algorithms for firearm identification, and an automated evaluation method would be beneficial to any computerized system. Our contribution consists in optimizing and training U-Net segmentation models from digital images of cartridge cases, intending to locate ROIs automatically. For the experiments, we used high-resolution 2D images from 1195 samples of cartridge cases fired by different 9MM firearms. Our results show that the segmentation models, trained on augmented data sets, exhibit a performance of 95.6% IoU (Intersection over Union) and 99.3% DC (Dice Coefficient) with a loss of 0.014 for the breech face images; and a performance of 95.9% IoU and 99.5% DC with a loss of 0.011 for the firing pin images. We observed that the natural shapes of predicted circles reduce the performance of segmentation models compared with perfect circles on ground truth masks suggesting that our method provide a more accurate segmentation of the real ROI shape. In practice, we believe that these results could be useful for firearms identification. In future work, the predictions may be used to evaluate the quality of delimiters on specimens in a database, or they could determine the region of interest on a cartridge case image.

Big social data and user-generated content have emerged as important sources of timely and rich knowledge to detect customers\' behavioral patterns. Revealing customer satisfaction through the use of user-generated content has been a significant issue in business, especially in the tourism and hospitality context. There have been many studies on customer satisfaction that take quantitative survey approaches. However, revealing customer satisfaction using big social data in the form of eWOM (electronic word of mouth) can be an effective way to better understand customers\' demands. In this study, we aim to develop a hybrid methodology based on supervised learning, text mining, and segmentation machine learning approaches to analyze big social data on travelers\' decision-making regarding hotels in Mecca, Saudi Arabia. To do so, we use support vector regression with sequential minimal optimization (SMO), latent Dirichlet allocation (LDA), and k-means approaches to develop the hybrid method. We collect data from travelers\' online reviews of Mecca hotels on TripAdvisor. The data are segmented, and travelers\' satisfaction is revealed for each segment based on their online reviews of hotels. The results show that the method is effective for big social data analysis and traveler segmentation in Mecca hotels. The results are discussed, and several recommendations and strategies for hotel managers are provided to enhance their service quality and improve customer satisfaction.

Supplemental material is available for this article. Keywords: Conventional Radiography, Thorax, Trauma, Ribs, Catheters, Segmentation, Diagnosis, Classification, Supervised Learning, Machine Learning © RSNA, 2021.

Abnormal atrioventricular valve present great challenges to the surgeon in achieving a successful repair, and thus present a great opportunity for enhanced 3D imaging to guide pre- and intra-operative management. Spatial and temporal resolution of 3D echocardiography enables 3D printing of valve morphology. However, non-linearity, angle dependence, speckle, blur, and resampling complicate segmentation compared to computed tomography (CT) and magnetic resonance imaging (MRI). A case of complex mitral valve disease in a pediatric patient is therefore presented to illustrate the technical challenges of segmentation and 3D printing from echocardiographic data.

BACKGROUND: High-cost high-need patients are typically defined by risk or cost thresholds which aggregate clinically diverse subgroups into a single \'high-need high-cost\' designation. Programs have had limited success in reducing utilization or improving quality of care for high-cost high-need Medicaid patients, which may be due to the underlying clinical heterogeneity of patients meeting high-cost high-need designations.
METHODS: Our objective was to segment a population of high-cost high-need Medicaid patients (N = 676,161) eligible for a national complex case management program between January 2012 and May 2015 to disaggregate clinically diverse subgroups. Patients were eligible if they were in the top 5 % of annual spending among UnitedHealthcare Medicaid beneficiaries. We used k-means cluster analysis, identified clusters using an information-theoretic approach, and named clusters using the patients\' pattern of acute and chronic conditions. We assessed one-year overall and preventable hospitalizations, overall and preventable emergency department (ED) visits, and cluster stability.
RESULTS: Six clusters were identified which varied by utilization and stability. The characteristic condition patterns were: 1) pregnancy complications, 2) behavioral health, 3) relatively few conditions, 4) cardio-metabolic disease, and complex illness with relatively 5) low or 6) high resource use. The patients varied by cluster by average ED visits (2.3-11.3), hospitalizations (0.3-2.0), and cluster stability (32-91%).
CONCLUSIONS: We concluded that disaggregating subgroups of high-cost high-need patients in a large multi-state Medicaid sample identified clinically distinct clusters of patients who may have unique clinical needs. Segmenting previously identified high-cost high-need populations thus may be a necessary strategy to improve the effectiveness of complex case management programs in Medicaid.

OBJECTIVE: The purpose of this article is to present a novel method for the CBCT subtraction analysis of 3D changes following alveolar ridge preservation (ARP) with the application of a semi-automatic segmentation workflow and spatial registration. The study hypothesis was that by utilizing our novel approach, better 3D visualization and improved volumetric and linear evaluations of alveolar reconstructive procedures could be achieved following ARP compared with existing methodologies.
METHODS: Ten surgical sites of 10 partially edentulous patients were treated with a tunneled guided bone regeneration approach for ARP. Spatial registration and a semi-automatic segmentation method were utilized to create 3D digital models of pre- and postoperative CBCT datasets for subtraction analysis. The primary outcome variable of the study was the volumetric difference between pre- and postoperative CBCT scans. Secondary outcome variables were horizontal and vertical linear measurements at the mesial, distal, and middle aspects of the alveolus.
RESULTS: Change of hard tissue volume averaged at 0.34 ± 0.99 cm3. The mean change of vertical hard tissue dimension was 5.97 ± 3.18 mm at the mesial, 6.40 ± 3.03 mm at the distal, and 7.01 ± 3.02 mm at the middle aspect of the extraction sites. Horizontal linear changes averaged at 6.19 ± 0.68 mm at the mesial, 6.32 ± 1.52 mm at the distal, and 6.90 ± 1.48 mm at the middle aspects of the extraction sites.
CONCLUSIONS: The digital reconstruction of CBCT datasets with the presented approach may provide a better understanding of the healing mechanisms following ARP. Not only the direct effect on extraction socket healing, but also the indirect positive effect on adjacent teeth can be visualized.

In clinical and forensic toxicology, hair analysis offers a larger window for detecting drug exposure than blood or urine. Drug measurements are generally carried out using a segmented lock of hair, but few articles report the use of a single hair to document drug exposure. Nevertheless, single hair analysis can be very useful, particularly if only small amounts of biological matrices are available. More data on analyzing new synthetic opioids (NSOs) in hair are needed to help interpretation in future cases. In this study, segmental single hair analysis is compared with segmental hair lock analysis to document an ocfentanil-related death. The hair lock and single hair analyses were performed using the LC-MS/MS method after decontamination and incubation. Ocfentanil (OcF) concentrations ranged from 42 to 150 pg/mg in the segmented hair lock, depending on the segments. The hair lock and single hair analyses showed similar results: the highest concentrations were measured in the first two centimeters and decreased from root to tip. The similar profiles obtained from both the lock of hair and the single hair demonstrate the relevance of single hair analysis in cases where very few data are available. This article describes OcF concentrations in an authentic hair sample after a documented intake of this molecule in a fatality.

The first patient-specific biomechanical model for planning the surgical reduction of acetabular fractures was developed in our institution and validated retrospectively. There are no prior studies showing its effectiveness in terms of reduction quality, operative duration and intraoperative bleeding. Therefore, we performed a case control study aiming to: 1) evaluate the effect of preoperative simulation by patient-specific biomechanical simulator on the operating time and intraoperative bleeding; 2) evaluate the effect of preoperative simulation by patient-specific biomechanical simulator on the quality of reduction.
All patients operated on between January 2019 and June 2019 after planning by biomechanical simulation were included in this case-control study. Each patient included was matched to 2 controls from our database (2015-2018) according to age and fracture-type. DICOM data were extracted from the preoperative high-resolution scanners to build a three-dimensional model of the fracture by semi-automatic segmentation. A biomechanical model was built to virtually simulate the different stages of surgical reduction. Surgery was then performed according to simulation data. Surgical duration, blood loss, radiological findings and intraoperative complications were recorded, analysed and compared.
Thirty patients were included, 10 in the simulation group and 20 in the control group. The two groups were comparable in terms of age, time from accident to surgery, fracture-type and surgical approach. The mean operative time was significantly reduced in the simulation group: 113min±33 (60-180) versus 196min±32 (60-260) (p=0.01). Mean blood loss was significantly reduced in the simulation group: 505mL±189 (100-750) versus 745mL±130 (200-850) (p<0.01). However, no significant difference was found in the radiological results according to Matta\'s criteria, although an anatomical reduction was obtained for 9 patients in the simulation group (90%) versus 12 patients in the control group (60%) (p=0.26). A postoperative neurological complication was recorded in the control group (sensory deficit of the lateral cutaneous nerve of thigh).
This study confirms the promising results of preoperative planning in acetabular trauma surgery based on patient-specific biomechanical simulation as well as its feasibility in routine clinical practice. By providing a better understanding of the fracture and its behavior, a reduction in intraoperative bleeding and in operative duration is achieved.
III; case-control study.

During disease outbreaks or pandemics, policy makers must convey information to the public for informative purposes (eg, morbidity or mortality rates). They must also motivate members of the public to cooperate with the guidelines, specifically by changing their usual behavior. Policy makers have traditionally adopted a didactic and formalistic stance by conveying dry, statistics-based health information to the public. They have not yet considered the alternative of providing health information in the form of narrative evidence, using stories that address both cognitive and emotional aspects. The aim of this viewpoint paper is to introduce policy makers to the advantages of using narrative evidence to provide health information during a disease outbreak or pandemic such as COVID-19. Throughout human history, authorities have tended to employ apocalyptic narratives during disease outbreaks or pandemics. This viewpoint paper proposes an alternative coping narrative that includes the following components: segmentation; barrier reduction; role models; empathy and support; strengthening self-efficacy, community efficacy, and coping tools; preventing stigmatization of at-risk populations; and communicating uncertainty. It also discusses five conditions for using narrative evidence to produce an effective communication campaign on social media: (1) identifying narratives that reveal the needs, personal experiences, and questions of different subgroups to tailor messaging to produce targeted behavioral change; (2) providing separate and distinct treatment of each information unit or theory that arises on social networks; (3) identifying positive deviants who found creative solutions for stress during the COVID-19 crisis not found by other members of the community; (4) creating different stories of coping; and (5) maintaining a dialogue with population subgroups (eg, skeptical and hesitant groups). The paper concludes by proposing criteria for evaluating the effectiveness of a narrative.

Non-Hodgkin lymphoma (NHL) of the oral cavity can present with pain, swelling and radiolucent lesion mimicking endodontic diseases. This article reports on a case of diffuse large B-cell lymphoma initially diagnosed and treated as periodontal disease and then endodontic disease in the maxillary anterior and premolar area of a 40-year old female. A cone beam computed tomography (CBCT) image of the lesion was taken. The lesion was segmented using Mimics software (Materialise NV, Lueven, Belgium). Three-dimensional models of the tumor were printed. During the surgical phase teeth #4, 6, and 7 were extracted and biopsy samples were obtained. Histopathologic examination showed invasive sheets of large, atypical, basophilic cells strongly and diffusely positive for CD20. Three-dimensional analysis, segmentation, and printing of radiolucent lesions of the jaws assists with differential diagnosis and efficient treatment. Oral health professionals can play a crucial role in the early detection and diagnosis of oral NHL, thereby preventing extensive loss of function and esthetics, and even saving lives.