UNASSIGNED: To evaluate organ at risk (OAR) auto-segmentation in the head and neck region of computed tomography images using two different commercially available deep-learning-based auto-segmentation (DLAS) tools in a single institutional clinical applications.
UNASSIGNED: Twenty-two OARs were manually contoured by clinicians according to published guidelines on planning computed tomography (pCT) images for 40 clinical head and neck cancer (HNC) cases. Automatic contours were generated for each patient using two deep-learning-based auto-segmentation models-Manteia AccuContour and MIM ProtégéAI. The accuracy and integrity of autocontours (ACs) were then compared to expert contours (ECs) using the Sørensen-Dice similarity coefficient (DSC) and Mean Distance (MD) metrics.
UNASSIGNED: ACs were generated for 22 OARs using AccuContour and 17 OARs using ProtégéAI with average contour generation time of 1 min/patient and 5 min/patient respectively. EC and AC agreement was highest for the mandible (DSC 0.90 ± 0.16) and (DSC 0.91 ± 0.03), and lowest for the chiasm (DSC 0.28 ± 0.14) and (DSC 0.30 ± 0.14) for AccuContour and ProtégéAI respectively. Using AccuContour, the average MD was<1mm for 10 of the 22 OARs contoured, 1-2mm for 6 OARs, and 2-3mm for 6 OARs. For ProtégéAI, the average mean distance was<1mm for 8 out of 17 OARs, 1-2mm for 6 OARs, and 2-3mm for 3 OARs.
UNASSIGNED: Both DLAS programs were proven to be valuable tools to significantly reduce the time required to generate large amounts of OAR contours in the head and neck region, even though manual editing of ACs is likely needed prior to implementation into treatment planning. The DSCs and MDs achieved were similar to those reported in other studies that evaluated various other DLAS solutions. Still, small volume structures with nonideal contrast in CT images, such as nerves, are very challenging and will require additional solutions to achieve sufficient results.

BACKGROUND: Low muscle mass and skeletal muscle mass (SMM) loss are associated with adverse patient outcomes, but the time-consuming nature of manual SMM quantification prohibits implementation of this metric in clinical practice. Therefore, we assessed the feasibility of automated SMM quantification compared to manual quantification. We evaluated both diagnostic accuracy for low muscle mass and associations of SMM (change) with survival in colorectal cancer (CRC) patients.
METHODS: Computed tomography (CT) images from CRC patients enrolled in two clinical studies were analyzed. We compared i) manual vs. automated segmentation of preselected slices at the third lumbar [L3] vertebra (\"semi-automated\"), and ii) manual L3-slice-selection + manual segmentation vs. automated L3-slice-selection + automated segmentation (\"fully-automated\"). Automated L3-selection and automated segmentation was performed with Quantib Body Composition v0.2.1. Bland-Altman analyses, within-subject coefficients of variation (WSCVs) and Intraclass Correlation Coefficients (ICCs) were used to evaluate the agreement between manual and automatic segmentation. Diagnostic accuracy for low muscle mass (defined by an established sarcopenia cut-off) was calculated with manual assessment as the \"gold standard\". Using either manual or automated assessment, Cox proportional hazard ratios (HRs) were used to study the association between changes in SMM (>5% decrease yes/no) during first-line metastatic CRC treatment and mortality adjusted for prognostic factors. SMM change was also assessed separately in weight-stable (<5%, i.e. occult SMM loss) patients.
RESULTS: In total, 1580 CT scans were analyzed, while a subset of 307 scans were analyzed in the fully-automated comparison. Included patients (n = 553) had a mean age of 63 ± 9 years and 39% were female. The semi-automated comparison revealed a bias of -2.41 cm2, 95% limits of agreement [-9.02 to 4.20], a WSCV of 2.25%, and an ICC of 0.99 (95% confidence intervals (CI) 0.97 to 1.00). The fully-automated comparison method revealed a bias of -0.08 cm2 [-10.91 to 10.75], a WSCV of 2.85% and an ICC of 0.98 (95% CI 0.98 to 0.99). Sensitivity and specificity for low muscle mass were 0.99 and 0.89 for the semi-automated comparison and 0.96 and 0.90 for the fully-automated comparison. SMM decrease was associated with shorter survival in both manual and automated assessment (n = 78/280, HR 1.36 [95% CI 1.03 to 1.80] and n = 89/280, HR 1.38 [95% CI 1.05 to 1.81]). Occult SMM loss was associated with shorter survival in manual assessment, but not significantly in automated assessment (n = 44/263, HR 1.43 [95% CI 1.01 to 2.03] and n = 51/2639, HR 1.23 [95% CI 0.87 to 1.74]).
CONCLUSIONS: Deep-learning based assessment of SMM at L3 shows reliable performance, enabling the use of CT measures to guide clinical decision making. Implementation in clinical practice helps to identify patients with low muscle mass or (occult) SMM loss who may benefit from lifestyle interventions.

3D reconstruction of human brain volumes at high resolution is now possible thanks to advancements in tissue clearing methods and fluorescence microscopy techniques. Analyzing the massive data produced with these approaches requires automatic methods able to perform fast and accurate cell counting and localization. Recent advances in deep learning have enabled the development of various tools for cell segmentation. However, accurate quantification of neurons in the human brain presents specific challenges, such as high pixel intensity variability, autofluorescence, non-specific fluorescence and very large size of data. In this paper, we provide a thorough empirical evaluation of three techniques based on deep learning (StarDist, CellPose and BCFind-v2, an updated version of BCFind) using a recently introduced three-dimensional stereological design as a reference for large-scale insights. As a representative problem in human brain analysis, we focus on a 4 -cm 3 portion of the Broca\'s area. We aim at helping users in selecting appropriate techniques depending on their research objectives. To this end, we compare methods along various dimensions of analysis, including correctness of the predicted density and localization, computational efficiency, and human annotation effort. Our results suggest that deep learning approaches are very effective, have a high throughput providing each cell 3D location, and obtain results comparable to the estimates of the adopted stereological design.

Background/Aim: To evaluate the performance of Chat Generative Pre-trained Transformer (ChatGPT), a large language model trained by Open artificial intelligence. Materials and Methods: This study has three main steps to evaluate the effectiveness of ChatGPT in the urologic field. The first step involved 35 questions from our institution\'s experts, who have at least 10 years of experience in their fields. The responses of ChatGPT versions were qualitatively compared with the responses of urology residents to the same questions. The second step assesses the reliability of ChatGPT versions in answering current debate topics. The third step was to assess the reliability of ChatGPT versions in providing medical recommendations and directives to patients\' commonly asked questions during the outpatient and inpatient clinic. Results: In the first step, version 4 provided correct answers to 25 questions out of 35 while version 3.5 provided only 19 (71.4% vs 54%). It was observed that residents in their last year of education in our clinic also provided a mean of 25 correct answers, and 4th year residents provided a mean of 19.3 correct responses. The second step involved evaluating the response of both versions to debate situations in urology, and it was found that both versions provided variable and inappropriate results. In the last step, both versions had a similar success rate in providing recommendations and guidance to patients based on expert ratings. Conclusion: The difference between the two versions of the 35 questions in the first step of the study was thought to be due to the improvement of ChatGPT\'s literature and data synthesis abilities. It may be a logical approach to use ChatGPT versions to inform the nonhealth care providers\' questions with quick and safe answers but should not be used to as a diagnostic tool or make a choice among different treatment modalities.

Melanoma is the most aggressive and prevalent form of skin cancer globally, with a higher incidence in men and individuals with fair skin. Early detection of melanoma is essential for the successful treatment and prevention of metastasis. In this context, deep learning methods, distinguished by their ability to perform automated and detailed analysis, extracting melanoma-specific features, have emerged. These approaches excel in performing large-scale analysis, optimizing time, and providing accurate diagnoses, contributing to timely treatments compared to conventional diagnostic methods. The present study offers a methodology to assess the effectiveness of an AlexNet-based convolutional neural network (CNN) in identifying early-stage melanomas. The model is trained on a balanced dataset of 10,605 dermoscopic images, and on modified datasets where hair, a potential obstructive factor, was detected and removed allowing for an assessment of how hair removal affects the model\'s overall performance. To perform hair removal, we propose a morphological algorithm combined with different filtering techniques for comparison: Fourier, Wavelet, average blur, and low-pass filters. The model is evaluated through 10-fold cross-validation and the metrics of accuracy, recall, precision, and the F1 score. The results demonstrate that the proposed model performs the best for the dataset where we implemented both a Wavelet filter and hair removal algorithm. It has an accuracy of 91.30%, a recall of 87%, a precision of 95.19%, and an F1 score of 90.91%.

Recent advancements in deep learning and artificial intelligence (AI) have profoundly impacted various fields, including diagnostic imaging. Integrating AI technologies such as deep learning and convolutional neural networks has the potential to drastically improve diagnostic methods in the field of dentistry and maxillofacial radiography. A systematic study that adhered to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards was carried out to examine the efficacy and uses of AI in dentistry and maxillofacial radiography. Incorporating cohort studies, case-control studies, and randomized clinical trials, the study used an interdisciplinary methodology. A thorough search spanning peer-reviewed research papers from 2009 to 2023 was done in databases including MEDLINE/PubMed and EMBASE. The inclusion criteria were original clinical research in English that employed AI models to recognize anatomical components in oral and maxillofacial pictures, identify anomalies, and diagnose disorders. The study looked at numerous research that used cutting-edge technology to show how accurate and dependable dental imaging is. Among the tasks covered by these investigations were age estimation, periapical lesion detection, segmentation of maxillary structures, assessment of dentofacial abnormalities, and segmentation of the mandibular canal. The study revealed important developments in the precise definition of anatomical structures and the identification of diseases. The use of AI technology in dental imaging marks a revolutionary development that will usher in a time of unmatched accuracy and effectiveness. These technologies have not only improved diagnostic accuracy and enabled early disease detection but have also streamlined intricate procedures, significantly enhancing patient outcomes. The symbiotic collaboration between human expertise and machine intelligence promises a future of more sophisticated and empathetic oral healthcare.

BACKGROUND: Insufficient physical activity due to social distancing and suppressed outdoor activities increases vulnerability to diseases like cardiovascular diseases, sarcopenia, and severe COVID-19. While bodyweight exercises, such as squats, effectively boost physical activity, incorrect postures risk abnormal muscle activation joint strain, leading to ineffective sessions or even injuries. Avoiding incorrect postures is challenging for novices without expert guidance. Existing solutions for remote coaching and computer-assisted posture correction often prove costly or inefficient.
OBJECTIVE: This study aimed to use deep neural networks to develop a personal workout assistant that offers feedback on squat postures using only mobile devices-smartphones and tablets. Deep learning mimicked experts\' visual assessments of proper exercise postures. The effectiveness of the mobile app was evaluated by comparing it with exercise videos, a popular at-home workout choice.
METHODS: Twenty participants were recruited without squat exercise experience and divided into an experimental group (EXP) with 10 individuals aged 21.90 (SD 2.18) years and a mean BMI of 20.75 (SD 2.11) and a control group (CTL) with 10 individuals aged 22.60 (SD 1.95) years and a mean BMI of 18.72 (SD 1.23) using randomized controlled trials. A data set with over 20,000 squat videos annotated by experts was created and a deep learning model was trained using pose estimation and video classification to analyze the workout postures. Subsequently, a mobile workout assistant app, Home Alone Exercise, was developed, and a 2-week interventional study, in which the EXP used the app while the CTL only followed workout videos, showed how the app helps people improve squat exercise.
RESULTS: The EXP significantly improved their squat postures evaluated by the app after 2 weeks (Pre: 0.20 vs Mid: 4.20 vs Post: 8.00, P=.001), whereas the CTL (without the app) showed no significant change in squat posture (Pre: 0.70 vs Mid: 1.30 vs Post: 3.80, P=.13). Significant differences were observed in the left (Pre: 75.06 vs Mid: 76.24 vs Post: 63.13, P=.02) and right (Pre: 71.99 vs Mid: 76.68 vs Post: 62.82, P=.03) knee joint angles in the EXP before and after exercise, with no significant effect found for the CTL in the left (Pre: 73.27 vs Mid: 74.05 vs Post: 70.70, P=.68) and right (Pre: 70.82 vs Mid: 74.02 vs Post: 70.23, P=.61) knee joint angles.
CONCLUSIONS: EXP participants trained with the app experienced faster improvement and learned more nuanced details of the squat exercise. The proposed mobile app, offering cost-effective self-discovery feedback, effectively taught users about squat exercises without expensive in-person trainer sessions.
BACKGROUND: Clinical Research Information Service KCT0008178 (retrospectively registered); https://cris.nih.go.kr/cris/search/detailSearch.do/24006.

To develop a decision tree model based on clinical information, molecular genetics information and pre-operative magnetic resonance imaging (MRI) radiomics-score (Rad-score) to investigate its predictive value for the risk of recurrence of glioblastoma (GBM) within one year after total resection. Patients with pathologically confirmed GBM at Huashan Hospital, Fudan University between November 2017 and June 2020 were retrospectively analyzed, and the enrolled patients were randomly divided into training and test sets according to the ratio of 3:1. The relevant clinical and MRI data of patients before, after surgery and follow-up were collected, and after feature extraction on preoperative MRI, the LASSO filter was used to filter the features and establish the Rad-score. Using the training set, a decision tree model for predicting recurrence of GBM within one year after total resection was established by the C5.0 algorithm, and scatter plots were generated to evaluate the prediction accuracy of the decision tree during model testing. The prediction performance of the model was also evaluated by calculating area under the receiver operating characteristic (ROC) curve (AUC), ACC, Sensitivity (SEN), Specificity (SPE) and other indicators. Besides, two external validation datasets from Wuhan union hospital and the second affiliated hospital of Xuzhou Medical University were used to verify the reliability and accuracy of the prediction model. According to the inclusion and exclusion criteria, 134 patients with GBM were finally identified for inclusion in the study, and 53 patients recurred within one year after total resection, with a mean recurrence time of 5.6 months. According to the importance of the predictor variables, a decision tree model for predicting recurrence based on five important factors, including patient age, Rad-score, O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation, pre-operative Karnofsky Performance Status (KPS) and Telomerase reverse transcriptase (TERT) promoter mutation, was developed. The AUCs of the model in the training and test sets were 0.850 and 0.719, respectively, and the scatter plot showed excellent consistency. In addition, the prediction model achieved AUCs of 0.810 and 0.702 in two external validation datasets from Wuhan union hospital and the second affiliated hospital of Xuzhou Medical University, respectively. The decision tree model based on clinicopathological risk factors and preoperative MRI Rad-score can accurately predict the risk of recurrence of GBM within one year after total resection, which can further guide the clinical optimization of patient treatment decisions, as well as refine the clinical management of patients and improve their prognoses to a certain extent.

Computational hemodynamics is increasingly being used to quantify hemodynamic characteristics in and around abdominal aortic aneurysms (AAA) in a patient-specific fashion. However, the time-consuming manual annotation hinders the clinical translation of computational hemodynamic analysis. Thus, we investigate the feasibility of using deep-learning-based image segmentation methods to reduce the time required for manual segmentation. Two of the latest deep-learning-based image segmentation methods, ARU-Net and CACU-Net, were used to test the feasibility of automated computer model creation for computational hemodynamic analysis. Morphological features and hemodynamic metrics of 30 computed tomography angiography (CTA) scans were compared between pre-dictions and manual models. The DICE score for both networks was 0.916, and the correlation value was above 0.95, indicating their ability to generate models comparable to human segmentation. The Bland-Altman analysis shows a good agreement between deep learning and manual segmentation results. Compared with manual (computational hemodynamics) model recreation, the time for automated computer model generation was significantly reduced (from ∼2 h to ∼10 min). Automated image segmentation can significantly reduce time expenses on the recreation of patient-specific AAA models. Moreover, our study showed that both CACU-Net and ARU-Net could accomplish AAA segmentation, and CACU-Net outperformed ARU-Net in terms of accuracy and time-saving.

BACKGROUND: The purpose of this study was to assess the volume of the pulmonary nodules and masses on serial chest X-rays (CXRs) from deep-learning-based automatic detection algorithm (DLAD)-based parameters.
METHODS: In a retrospective single-institutional study, 72 patients, who obtained serial CXRs (n = 147) for pulmonary nodules or masses with corresponding chest CT images as the reference standards, were included. A pre-trained DLAD based on a convolutional neural network was developed to detect and localize nodules using 13,710 radiographs and to calculate a localization map and the derived parameters (e.g., the area and mean probability value of pulmonary nodules) for each CXR, including serial follow-ups. For validation, reference 3D CT volumes were measured semi-automatically. Volume prediction models for pulmonary nodules were established through univariable or multivariable, and linear or non-linear regression analyses with the parameters. A polynomial regression analysis was performed as a method of a non-linear regression model.
RESULTS: Of the 147 CXRs and 208 nodules of 72 patients, the mean volume of nodules or masses was measured as 9.37 ± 11.69 cm3 (mean ± standard deviation). The area and CT volume demonstrated a linear correlation of moderate strength (i.e., R = 0.58, RMSE: 9449.9 mm3 m3 in a linear regression analysis). The area and mean probability values exhibited a strong linear correlation (R = 0.73). The volume prediction performance based on a multivariable regression model was best with a mean probability and unit-adjusted area (i.e.
UNASSIGNED: 7975.6 mm3, the smallest among the other variable parameters).
CONCLUSIONS: The prediction model with the area and the mean probability based on the DLAD showed a rather accurate quantitative estimation of pulmonary nodule or mass volume and the change in serial CXRs.