Dynamic Eyelid Evaluation Using a Deep Neural Network in Upper Blepharoplasty: A Prospective Multicenter Pilot Study.

Interobserver agreement of semi-automated and manual measurements of functional MRI metrics of treatment response in hepatocellular carcinoma

Purpose To compare the performance of a convolutional neural network (U-Net) with human-in-the-loop (HITL) validation against manual clinical measurements of thoracic aortic diameter at CT angiography. Materials and Methods This retrospective analysis included patients with thoracic aortic dilatation and at least two CT angiographic examinations between January 2006 and April 2023. Manual diameters were measured by technicians trained in the three-dimensional method. A multitask U-Net performed aortic segmentation, landmark localization, and automated aortic diameter measurements, followed by HITL validation. Discrepancies in diameter greater than 5 mm underwent expert remeasurement. Mid ascending aortic growth from U-Net and manual measurements were compared against a diameter-independent three-dimensional method (vascular deformation mapping). Agreement was assessed using Bland-Altman analysis and intraclass correlation coefficients. Results This study included 177 patients (101 [57%] male patients; median age, 64 years [IQR, 57-71]). Among 2028 paired measurements, 1955 (96%) passed the HITL validation. Validation reduced the 95% limits of agreement from -4.2 to 4.3 mm to -2.9 to 3.4 mm and reduced large discrepancies by 61% (from 61 to 23 measurements; P < .01). Expert remeasurements of discrepancies showed lower mean difference ± SD compared with U-Net measurements (2.2 mm ± 1.7 vs 7.0 mm ± 2.9; P < .01). U-Net measurements were more likely to yield negative growth values than manual measurements (odds ratio, 0.56; 95% CI: 0.44, 0.70; P < .01). Compared with vascular deformation mapping-derived growth, U-Net measurement showed stronger agreement than manual measurement (intraclass correlation coefficient, 0.74 [95% CI: 0.62, 0.80] vs 0.40 [95% CI: 0.18, 0.56]; P < .01). Conclusion Automated U-Net measurements of thoracic aorta diameters, when validated with an HITL approach, demonstrated stronger agreement with reference standard assessment than manual clinical measurements. Keywords: Aorta, Neural Networks, Vascular, CT Angiography, Segmentation, Thoracic Aortic Diameter Supplemental material is available for this article. © RSNA, 2025.

Validation of CalECG software for primary prevention heart failure patients: Reducing inter-observer measurement variability

Background and aim Eyelid position and contour abnormality could lead to various diseases, such as blepharoptosis, which is a common eyelid disease. Accurate assessment of eyelid morphology is important in the management of blepharoptosis. We aimed to proposed a novel deep learning-based image analysis to automatically measure eyelid morphological properties before and after blepharoptosis surgery. Methods This study included 135 ptotic eyes of 103 patients who underwent blepharoptosis surgery. Facial photographs were taken preoperatively and postoperatively. Margin reflex distance (MRD) 1 and 2 of the operated eyes were manually measured by a senior surgeon. Multiple eyelid morphological parameters, such as MRD1, MRD2, upper eyelid length and corneal area, were automatically measured by our deep learning-based image analysis. Agreement between manual and automated measurements, as well as two repeated automated measurements of MRDs were analysed. Preoperative and postoperative eyelid morphological parameters were compared. Postoperative eyelid contour symmetry was evaluated using multiple mid-pupil lid distances (MPLDs). Results The intraclass correlation coefficients (ICCs) between manual and automated measurements of MRDs ranged from 0.934 to 0.971 (p < .001), and the bias ranged from 0.09 mm to 0.15 mm. The ICCs between two repeated automated measurements were up to 0.999 (p < .001), and the bias was no more than 0.002 mm. After surgery, MRD1 increased significantly from 0.31 ± 1.17 mm to 2.89 ± 1.06 mm, upper eyelid length from 19.94 ± 3.61 mm to 21.40 ± 2.40 mm, and corneal area from 52.72 ± 15.97 mm2 to 76.31 ± 11.31mm2 (all p < .001). Postoperative binocular MPLDs at different angles (from 0° to 180°) showed no significant differences in the patients. Conclusion This technique had high accuracy and repeatability for automatically measuring eyelid morphology, which allows objective assessment of blepharoptosis surgical outcomes. Using only patients’ photographs, this technique has great potential in diagnosis and management of other eyelid-related diseases.

Purpose:This study compared three methods of acoustic algorithm-supported extraction and analysis of vocal tremor properties (i.e., rate, extent, and regularity of intensity level and fundamental frequency modulation): (a) visual perception and manual data extraction, (b) semi-automated data extraction, and (c) fully automated data extraction.Method:Forty-five midvowel sustained [a:] and [i:] audio recordings were collected as part of a scientific project to learn about the physiologic substrates of vocal tremor. This convenience data set contained vowels with a representative variety in vocal tremor severity. First, the vocal tremor properties in intensity level and fundamental frequency tracks were visually inspected and manually measured using Praat software. Second, the vocal tremor properties were determined using two Praat scripts: automated with the script of Maryn et al. (2019) and semi-automated with an adjusted version of this script to enable the user to intervene with the signal processing. The reliability of manual vocal tremor property measurement was assessed using the intraclass correlation coefficient. The properties as measured with the two scripts (automated vs. semi-automated) were compared with the manually determined properties using correlation and diagnostic accuracy statistical methods.Results:With intraclass correlation coefficients between .770 and .914, the reliability of the manual method was acceptable. The semi-automated method correlated with manual property measures better and was more accurate in diagnosing vocal tremor than the automated method.Discussion:Manual acoustic measurement of vocal tremor properties can be laborious and time-consuming. Automated or semi-automated acoustic methods may improve efficiency in vocal tremor property measurement in clinical as well as research settings. Although both Praat script-supported methods in this study yielded acceptable validity with the manual data measurements as a referent, the semi-automated method showed the best outcomes.Supplemental Material:https://doi.org/10.23641/asha.28873088

Malalignment in the lower limb structure occurs due to various causes. Accurately evaluating limb alignment in situations where malalignment needs correction is necessary. To create an automated support system to evaluate lower limb alignment by quantifying mechanical tibiofemoral angle (mTFA), mechanical lateral distal femoral angle (mLDFA), medial proximal tibial angle (MPTA), and joint line convergence angle (JLCA) on full-length weight-bearing radiographs of both lower extremities. In this retrospective study, we analysed 404 radiographs from one hospital for algorithm development and testing and 30 radiographs from another hospital for external validation. The performance of segmentation algorithm was compared to that of manual segmentation using the dice similarity coefficient (DSC). The agreement of alignment parameters was assessed using the intraclass correlation coefficient (ICC) for internal and external validation. The time taken to load the data and measure the four alignment parameters was recorded. The segmentation algorithm demonstrated excellent agreement with human-annotated segmentation for all anatomical regions (average similarity: 89–97%). Internal validation yielded good to very good agreement for all the alignment parameters (ICC ranges: 0.7213–0.9865). Interobserver correlations between manual and automatic measurements in external validation were good to very good (ICC scores: 0.7126–0.9695). The computer-aided measurement was 3.44 times faster than was the manual measurement. Our deep learning-based automated measurement algorithm accurately quantified lower limb alignment from radiographs and was faster than manual measurement.

ABSTRACTPurpose: To propose a novel approach for automated measurements of margin reflex distance (MRD) using digital image analysis and to evaluate the agreement between automated and manual measurements of MRD.Materials and Methods: This observational study included 132 eyes of 66 volunteers referred to an oculoplastic clinic for blepharoptosis. Preoperative facial photographs of participants were taken. MRD1 and MRD2 were measured manually by a senior surgeon and automatically by our image-based algorithm. Correlation analyses and Bland–Altman analyses were performed to evaluate the agreement between the two measurements.Results: A strong positive correlation was observed between automated and manual MRD1 measurements, with Spearman’s r = 0.968 (95% confidence interval [CI] = 0.949–0.976; P < .001) and intraclass correlation coefficient (ICC) = 0.966 (95% CI = 0.953–0.976; P < .001). The bias between automated and manual MRD1 measurements was 0.02 mm (95% CI = −0.06–0.10 mm), with 95% limits of agreement (LoA) = −0.88 to 0.92 mm. Agreement also existed in MRD2 measurements, with Spearman’s r = 0.803 (95% CI = 0.716–0.865; P < .001), ICC = 0.833 (95% CI = 0.772–0.879; P < .001), and bias = 0.34 mm (95% CI = 0.26–0.42 mm), 95% LoA = −0.54 to 1.22 mm.Conclusions: Automated eyelid measurements in blepharoptosis using the image-based approach compare favorably with clinical manual measurements. This novel approach allows an objective assessment of ptosis with high accuracy.

Objective: To assess the agreement between semiautomatic 3D measurements and manual measurements derived from WBCT images in patients with end-stage ankle osteoarthritis (AO) who underwent total ankle replacement (TAR). Methods: In this retrospective, IRB-approved study (ID #201904825), we evaluated patients who underwent TAR via the lateral trans-fibular approach for end-stage ankle OA. The study included 14 ankles from 14 patients. Raw multiplanar data were analyzed using CubeVue® software. Lateral talar station (LTS) was obtained in the sagittal plane, while hindfoot moment arm (HMA) and talar tilt angle (TTA) were calculated in the coronal view. Semiautomatic 3D measurements were performed using Disior® software. Intra-rater reliabilities were analyzed using the intraclass correlation coefficient (ICC). Agreement between methods was tested with Bland-Altman plots. Each measurement was assessed using the Wilcoxon signed-rank test. Alpha risk was set to 5% (α=0.05). P-values of ≤0.05 were considered significant. Results: ICC-measured reliabilities ranged from moderate to almost perfect for manual and semiautomatic WBCT measurements in the preoperative and postoperative groups for HMA and LTS. There was high correlation between parameters calculated from manual and semiautomatic measurements, and strong agreement between the readers and software in both groups. Conclusions: Manual (M) and semiautomatic (SA) 3D measurements expressed excellent agreement for pre- and postoperative groups, indicating a high correlation between the parameters calculated and strong agreement between the readers and the software in both groups. Level of Evidence III; Therapeutic Studies; Comparative Retrospective Study.

Objectives The aim of this study is to evaluate the surgical and functional outcomes of peno-scrotal vaginoplasty in a cohort of patients undergoing genital gender-affirming surgery. Methods A consecutive series of transgender women (assigned male at birth) who underwent peno-scrotal vaginoplasty at a single center were included in this study. Data were collected from a prospective database comprising 41 patients who underwent surgery between April 2018 and April 2024. Functional outcomes were assessed using a validated questionnaire specifically for transgender women (Operated Male to Female sexual function index), as well as two additional validated questionnaires commonly used for cisgender women (Female Sexual Function Index and Female Genital Self Image Scale). Results The median age of the cohort was 30 years (26-35), with a median BMI of 22 kg/m2 (20-25). Fourteen patients (35.9%) were smokers. The median follow-up duration was 18 months (10-26 months). In terms of surgical outcomes, median operative time was 305 minutes (280-340), and median neovaginal depth achieved was 14 cm (12-14). Median hospital stay was 8 days (7-9). There was one intraoperative complication (2.4%), a urethral injury, which was successfully repaired and required prolonged catheterization for 2 weeks. Postoperative complications included anemia, with 12 patients (29%) requiring blood transfusions. One patient (2.4%) developed rectovaginal fistula, which necessitated temporary colostomy to allow for proper healing. Late complications included five cases (12.2%) of partial neovaginal stenosis, possibly related to improper neovaginal dilation. Functional outcomes indicated high levels of satisfaction, with progressive improvement over time. Normal oMtFSFI scores were observed in 31.3% of patients at 3 months, 50% at 6 months, 54.4% at 12 months, and 66.7% at more than 12 months post-surgery. Multivariate analysis identified BMI as the only significant predictor of lower satisfaction (defined as achieving a normal oMtFSFI score at 12 months). Conclusions Peno-scrotal flap vaginoplasty is a viable and effective technique for genital gender-affirming surgery in transgender women (AMAB). The procedure is associated with a low incidence of major complications and results in high levels of patient satisfaction, with favorable aesthetic and functional outcomes. Conflicts of Interest No conflict of interest.

With the emergence of COVID-19, telemedicine use has increased dramatically as clinicians and patients have looked for alternatives to face-to-face care. Prior research has shown high levels of patient satisfaction and comparable quality of care. Video visits have been hypothesized to be one way to reduce burnout among clinicians, but there has been minimal research on physician views of virtual care. We sought to measure family physician experience with video visits at the start of the COVID-19 pandemic. We identified all faculty and resident physicians at a large academic department of family medicine who had conducted a video visit in the prior month and conducted an anonymous online 12-question survey about their experiences, satisfaction, and barriers with care. Most eligible physicians responded (102/109, 94%), of whom half (52%) reported this was their first month trying a video visit. There was very high satisfaction (91% very or somewhat satisfied). The majority of respondents felt that video visits were shorter (54%) or took the same amount of time (38%) as in-person visits. There was concern that many physicians had experienced a visit in which they felt video was not the appropriate platform given patient concerns. This study is among the first to assess physician experience with video visits. As the visits are perceived as shorter, they may offer a unique opportunity to address clinician burnout. There was a high level of satisfaction at our institution despite multiple technical challenges.

We define the long-term outcomes and rates of further operative intervention following displaced Bennett's fractures treated with Kirschner (K-) wire fixation between 1996 and 2009. We retrospectively identified 143 patients (127 men and 16 women) with a mean age at the time of injury of 33.2 years (18 to 75). Electronic records were examined and patients were invited to complete the Disabilities of the Arm, Shoulder and Hand (DASH) questionnaire in addition to a satisfaction questionnaire. The time since injury was a mean of 11.5 years (3.4 to 18.5). In total 11 patients had died, one had developed dementia and 12 patients were lost to follow-up. This left 119 patients available for recruitment. Of these, 57 did not respond, leaving a study group of 62 patients. Patients reported excellent functional outcomes and high levels of satisfaction at follow-up. Median satisfaction was 94% (interquartile range 91.5 to 97.5) and the mean DASH score was 3.0 (0 to 38). None of the patients had undergone salvage procedures and none of the responders had changed occupation or sporting activities. Long-term patient reported outcomes following displaced Bennett's fractures treated by closed reduction and K-wire fixation show excellent functional results and a high level of patient satisfaction. The rate of infection is low and similar to other surgical procedures with percutaneous K-wires.

AIM: To assess the level of patient satisfaction with behavioural counselling therapy among tobacco users attending counselling sessions in private dental colleges and dental outreach programs in Chennai, and to identify areas of strength and improvement within the counselling process. MATERIALS AND METHODS: A cross-sectional questionnaire-based study was conducted among 384 tobacco users, equally divided between participants from private dental colleges (n=192) and dental outreach programs (n=192). A structured 16-item questionnaire was used to evaluate satisfaction across key counselling parameters such as clarity of information, counsellor empathy, visual aids, reading materials, and perceived impact. Responses were recorded on a 4-point Likert scale (Strongly Agree to Strongly Disagree). Data were analyzed using descriptive statistics, and associations were evaluated using the Chi-square test, with p &lt; 0.05 considered statistically significant. RESULTS: High levels of satisfaction were reported for most aspects of the counselling, especially the counsellor’s professionalism (Q11), clarity in addressing doubts (Q12), and overall satisfaction with the session (Q14). Visual materials (Q6) also received near-universal approval. Question 3 (satisfaction with reading material) showed a statistically significant variation across duration of tobacco use (p = 0.031), with long-term users in outreach settings expressing comparatively lower satisfaction. Mild disagreement was also observed regarding cost-related discussions (Q9) and the impact of tobacco on family (Q10) among outreach participants. CONCLUSION: The study reveals a generally high level of patient satisfaction with behavioural counselling, affirming the effectiveness of current strategies, particularly in private dental settings. However, specific improvements are needed in the content delivery for long-term users, especially in outreach contexts. Tailoring educational materials and sensitively addressing cost and family-related issues can help enhance the counselling experience and strengthen tobacco cessation efforts

The purpose of this study was to assess the measurement accuracy and reproducibility of semiautomated metric and volumetric lymph node analysis in MDCT. Whole-body CT with IV contrast administration was performed on 112 patients. Peripheral (cervical, axillary, and inguinal), abdominal, and thoracic lymph nodes were evaluated independently by two radiologists both manually and with semiautomated segmentation software. Long-axis diameter, short-axis diameter, and volume were measured. Agreement between the semiautomated and manual measurements (measurement error), need for manual correction, and relative interobserver differences were determined. Statistical analysis encompassed the variance inhomogeneity test, intraclass correlation coefficients, and Bland-Altman plots. In total, 742 peripheral (cervical, axillary, and inguinal), abdominal, and thoracic lymph nodes (mean diameter, 13.2 ± 4.3 mm; range, 4-37 mm) were evaluated. Semiautomatic segmentation without need for further correction was possible for 480 of 742 lymph nodes (64.7%). Calculation of intraclass correlation coefficients revealed high correlation between manual and semiautomatic measurements (r = 0.70-0.81) with a slight trend toward size overestimation for semiautomatic short-axis diameter (14.3%; limits of agreement, -34.3%, 62.9%) and long-axis diameter (11.7%; limits of agreement, -25.2%, 48.5%). Bland-Altman plots showed significantly (p < 0.0001) lower interobserver differences for semiautomated short-axis diameter (1.2%; 95% CI, -39.9% to 42.3%) compared with the manual measurement (7.6%; 95% CI, -38.7% to 53.9%). Among all locations, the relative interobserver difference for semiautomatic volume (2.9%; 95% CI, -31.4% to 37.3%) was significantly lower than that for manual short-axis diameter (p < 0.0001), manual long-axis diameter (0.0178), and semiautomatic short-axis diameter (p < 0.0001). Semiautomatic short-axis diameter, particularly volume measurements, of lymph nodes are, irrespective of location, precise in terms of reproducibility and appear to be considerably more reliable than manual lymph node assessment.

It is currently unknown whether functional restrictions following total hip arthroplasty can reduce the prevalence of early postoperative dislocation. Our hypothesis was that dislocation was more likely to occur in patients who were not placed on these restrictions. We performed a prospective, randomized study to evaluate the role of postoperative functional restrictions on the prevalence of dislocation following uncemented total hip arthroplasty through an anterolateral approach. Of the 630 eligible consecutive patients, 265 patients (303 hips) consented to be randomized into one of two groups (the "restricted" group or the "unrestricted" group). The patients in both groups were asked to limit the range of motion of the hip to <90 degrees of flexion and 45 degrees of external and internal rotation and to avoid adduction for the first six weeks after the procedure. The patients in the restricted group were instructed to comply with additional hip precautions during the first six weeks postoperatively. Specifically, these patients were managed with the placement of an abduction pillow in the operating room before bed transfer and used pillows to maintain abduction while in bed; used elevated toilet seats and elevated chairs in the hospital, in the rehabilitation facility, and at home; and were prevented from sleeping on the side, from driving, and from being a passenger in an automobile. All patients were followed for a minimum of six months postoperatively. There was one dislocation in the entire cohort (prevalence, 0.33%). This dislocation occurred in a patient in the restricted group during transfer from the operating table to a bed with an abduction pillow in place. Patients in the unrestricted group were found to return to side-sleeping sooner (p < 0.001), to ride in automobiles more often (p < 0.026), to drive automobiles more often (p < 0.001), to return to work sooner (p < 0.001), and to have a higher level of satisfaction with the pace of their recovery (p < 0.001) than those in the restricted group. There was an additional expenditure of approximately $655 per patient in the restricted group. Total hip arthroplasty through an anterolateral approach is likely to be associated with a low dislocation rate. Removal of several restrictions did not increase the prevalence of dislocation following primary hip arthroplasty at our institution. However, it did promote substantially lower costs and was associated with a higher level of patient satisfaction as patients achieved a faster return to daily functions in the early postoperative period.

Background: To ensure the reliability of manual blood pressure (BP) readings in a clinical trial, sources of error due to measurement must be reduced as much as possible. Apart from following standard procedure for BP measurement and ensuring good equipments, the measurement errors that come from the assessors themselves should be assessed. Objective: To demonstrate the use of two-way random effects, interactions absent, absolute agreement (Type A), single measures (Type 1) intraclass correlation coefficient (ICC) in the assessment of reliability of manual BP readings among assessors involved in a clinical trial using manual BP measurement, by using an interrater reliability study conducted by the authors as an example study. Methods: The steps involved in obtaining ICC in the study were discussed. Sample size given the number of assessors in the study was calculated. BP was measured using regularly maintained mercury sphygnomanometers, following recommendations by Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure (JNC 7) for BP measurement in office setting. The outcomes were systolic and diastolic BP readings. A type of ICC, two-way random effects, interactions absent, absolute agreement (Type A), single measures (Type 1) ICC was chosen for the analysis and specifically discussed. Pre-requisite assumptions for ICC were meticulously checked and described. The interrater reliability for systolic and diastolic BP readings as expressed by ICC (single measure) were presented with confidence interval (CI). The ICCs obtained in the example study were discussed and concluded. The flaws of the study were also criticised. Results: The interrater reliability for systolic and diastolic BP measurements as expressed by ICC (single measure) were 0.87 (95% confidence interval [CI] 0.722, 0.956) and 0.77 (95% CI 0.560, 0.918) respectively. Conclusion: We demonstrated the steps required to obtain ICC. Since the use of manual BP measurement using mercury sphygmomanometer is still considered as gold standard of BP measurement, it is important that studies in which the BP outcome is measured using such method conduct interrater reliability studies properly.