"Diagnostic ability in oral pathology among different population clusters".

OBJECTIVES: To assess the diagnostic ability in detecting oral lesions among dentists, dental hygienists, dentistry students, oral hygiene students, and non-healthcare subjects. MATERIALS AND METHODS: Participants were invited to classify 30 images of oral lesions in "benign" or "suspected malignant" only based on the visual appearance of the lesion. Diagnostic accuracy was assessed by calculating sensitivity and specificity with 95% confidence intervals and stratified by population group and image features (color, shape, and size of the lesions). RESULTS: A total of 16,590 examinations by 553 subjects were analyzed. Overall sensitivity and specificity were 57% (95% confidence interval 56%-58%) and 64% (95% confidence interval 63%-65%). Diagnostic accuracy varied among population groups, with experienced dentists showing the lowest sensitivity (52%) and the highest specificity (71%). Red lesions, flat lesions, and large lesions had the lowest sensitivity (42%, 36%, 57%) but the highest specificity (70%, 75%, 76%). CONCLUSIONS: We found worrying low ability to detect suspected malignant oral lesions by both healthcare workers and non-healthcare subjects. Lesion-specific characteristics may lead to differences in recognition. Specific courses and more adequate teaching methods should be proposed to increase identification of oral lesions.

The impact of patient skin colour on diagnostic ability and confidence of medical students.

Previous literature has explored unconscious racial biases in clinical education and medicine, finding that people with darker skin tones can be underrepresented in learning resources and managed differently in a clinical setting. This study aimed to examine whether patient skin colour can affect the diagnostic ability and confidence of medical students, and their cognitive reasoning processes. We presented students with 12 different clinical presentations on both white skin (WS) and non-white skin (NWS). A think aloud (TA) study was conducted to explore students' cognitive reasoning processes (n = 8). An online quiz was also conducted where students submitted a diagnosis and confidence level for each clinical presentation (n = 185). In the TA interviews, students used similar levels of information gathering and analytical reasoning for each skin type but appeared to display increased uncertainty and reduced non-analytical reasoning methods for the NWS images compared to the WS images. In the online quiz, students were significantly more likely to accurately diagnose five of the 12 clinical presentations (shingles, cellulitis, Lyme disease, eczema and meningococcal disease) on WS compared to NWS (p < 0.01). With regards to students' confidence, they were significantly more confident diagnosing eight of the 12 clinical presentations (shingles, cellulitis, Lyme disease, eczema, meningococcal disease, urticaria, chickenpox and Kawasaki disease) on WS when compared to NWS (p < 0.01). These findings highlight the need to improve teaching resources to include a greater diversity of skin colours exhibiting clinical signs, to improve students' knowledge and confidence, and ultimately, to avoid patients being misdiagnosed due to the colour of their skin.

Microperimetry, Humphrey field analyzer, and optical coherence tomography in detecting glaucoma: a comparative performance study.

PURPOSE: To evaluate and compare the diagnostic performance of microperimetry (MP), visual field (VF) 10-2 and 24-2 tests, and spectral-domain optical coherence tomography (SD-OCT) in primary open-angle glaucoma (POAG). METHODS: The study consisted of 35 POAG and 42 control eyes were enrolled in this prospective study. Eligible participants were ≥ 50 years old. VF assessments were carried out using the Humphrey field analyzer (HFA) and Macular Integrity Assessment. Optic nerve head (ONH), retinal nerve fiber layer thickness (RNFLT), and ganglion cell inner-plexiform-layer thickness (GCIPLT) were measured by SD-OCT. Areas under the receiver operating characteristic curves (AUC) and sensitivities at 95% specificity were calculated for each parameter. RESULTS: HFA 24-2 had the largest AUC value among the functional parameters to differentiate POAG from control eyes [AUC: 0.950 (0.906-0.994), sensitivity at 95%:60]. HFA 24-2 showed a significantly better performance than the 10-2 test (p = 0.036). Among the SD-OCT structural parameters, minimum GCIPLT had the largest AUC value to differentiate POAG from control eyes [AUC: 0.952 (0.905-0.999), sensitivity at 95%:80]. In comparison of the functional and structural parameters, HFA 24-2 showed a significantly better performance than the 10-2 test (p = 0.036). In macular parameters, minimum GCPLT performed significantly better than HFA 10-2 (p = 0.015) in detecting POAG. There was no statistically significant difference between the comparative diagnostic performance of the RNFL, ONH, HFA, and MP (p > 0.05 for all comparisons). CONCLUSION: The structural and functional test results revealed that GCIPLT measurements had the highest diagnostic performance in detecting POAG. HFA 24-2 test performed better than 10-2 test in distinguishing glaucoma from healthy eyes. MP showed a similar performance with HFA 10-2 and may be considered a complementary diagnostic tool.

Comparison of obesity-related indices for identifying nonalcoholic fatty liver disease: a population-based cross-sectional study in China.

BACKGROUND: The relationship between nonalcoholic fatty liver disease (NAFLD) and obesity-related indices has been analyzed separately thus far, and evidence comparing these indices together is still lacking, especially in China. This study aimed to comprehensively evaluate the predictive performance of anthropometric and metabolic indices to identify NAFLD in Chinese adults. METHODS: This study recruited a total of 1748 participants who were 18 years or older in southeastern China. The systolic blood pressure (SBP), diastolic blood pressure (DBP), fasting blood glucose (FBG), total cholesterol (TC), triglycerides (TGs), low-density lipoprotein (LDL), waist circumference (WC), a body shape index (ABSI), atherogenic index of plasma (AIP), abdominal volume index (AVI), body adiposity index (BAI), body mass index (BMI), body roundness index (BRI), conicity index (CI), triglyceride glucose (TyG), waist hip ratio (WHR), and waist height ratio (WHtR) were measured. The association between these indices and NAFLD was analyzed via logistic analyses with odds ratios (ORs). Receiver operating characteristic (ROC) curves and areas under the curve (AUCs) were used to compare the predictive performance of these indices to identify NAFLD. RESULTS: BMI had the greatest total AUC (AUC = 0.841) in the ROC curve analysis. However, BRI and BMI both had the best diagnostic ability in males (AUC = 0.812), and BRI had the best diagnostic ability in females (AUC = 0.849). Furthermore, AVI had the greatest AUC for patients who were ~ 20 (AUC = 0.892) and ~ 40 years old (AUC = 0.831), while TyG showed a higher predictive ability than AVI in those who were ~ 60 years old (AUC = 0.766). CONCLUSION: This study identified sex- and age-specific indices for predicting NAFLD in Chinese subjects. Compared with indices for all age groups, sex- and age-specific indices can provide more accurate assistance for clinical diagnosis and treatment.

Measurement Conditions of End-Diastolic Ratio of Common Carotid Arteries Alter Diagnostic Ability for Large Artery Intracranial Occlusive Disease.

BACKGROUND: End-diastolic ratio, calculated by the side-to-side ratio of end-diastolic flow velocities of the common carotid arteries, is an indicator for large artery intracranial occlusive disease. However, the diagnostic ability of end-diastolic ratios derived from different measurement conditions is unclear. METHODS: End-diastolic ratios were measured twice by single carotid duplex ultrasonography. End-diastolic ratio1st was calculated from separate end-diastolic flow velocities measured during routine assessment. End-diastolic ratio2nd was calculated almost simultaneously without head rotation. For each end-diastolic ratio, the measurement conditions and prediction ability for occlusions of the internal carotid artery or proximal portion of the middle cerebral artery using an established cutoff of 1.4 or greater were compared. RESULTS: Two hundred thirty-three patients (147 men, median 67 years) were registered, with available intracranial artery information in 158 patients (67.8%) and occlusions detected in 7 patients (4.4%). End-diastolic ratio1st was significantly higher than end-diastolic ratio2nd (median 1.21 versus 1.08, P < .001). Compared with end-diastolic ratio1st, end-diastolic ratio2nd had a significantly shorter time interval (median 709 versus 28 seconds, P < .001) and smaller pulse rate difference (1.54 ± 5.10 versus .25 ± 4.63 beats per minute, P = .004). To predict occlusions, the sensitivity, specificity, and overall accuracy for end-diastolic ratio1st of 1.4 or greater were 85.7%, 70.9%, and 71.5%, respectively, and for end-diastolic ratio2nd of 1.4 or greater were 85.7%, 98.0%, and 97.5%, respectively. End-diastolic ratio2nd had better specificity and overall accuracy than end-diastolic ratio1st (P < .001). CONCLUSIONS: End-diastolic ratio varies with measurement conditions. Combined end-diastolic flow velocities measurement may improve diagnostic ability for large artery intracranial occlusive disease.

Factors Influencing Early Detection of Oral Cancer by Primary Health-Care Professionals.

The purposes of this study are to determine early detection practices performed by primary healthcare professionals, to compare medical and dental sub-groups, and to identify factors that influence the ability of medical and dental practitioners to recognize precancerous changes and clinical signs of oral cancer. A 28-item survey instrument was used to interview a total of 330 Jordanian primary health-care professionals (165 dental and 165 medical). An oral cancer knowledge scale (0 to 31) was generated from correct responses on oral cancer general knowledge. An early detection practice scale (0 to 24) was generated from the reported usage and frequency of procedures in oral cancer examination. Also, a diagnostic ability scale (0 to 100) was generated from correct selections of suspicious oral lesions. Only 17.8 % of the participants reported that they routinely performed oral cancer screening in practices. Their oral cancer knowledge scores ranged from 3 to 31 with a mean of 15.6. The early detection practice scores ranged from 2 to 21 with a mean of 11.6. A significant positive correlation was found between knowledge scores and early detection practice scores (r = 0.22; p < 0.001). The diagnostic ability scores ranged from 11.5 to 96 with a mean of 43.6. The diagnostic ability score was significantly correlated with knowledge scores (r = 0.39; p < 0.001), but not with early detection practice scores (r = 0.01; p = 0.92). Few significant differences were found between medical and dental primary care professionals. Continuous education courses on early diagnosis of oral cancer and oral mucosal lesions are needed for primary health-care professionals.

Symmetry-Based Biomedical Image Compression.

Image compression techniques aim at reducing the amount of data needed to accurately represent an image, such that the image can be economically transmitted or archived. This paper deals with employing symmetry as a parameter for compression of biomedical images. The approach presented in this paper offers great potential in complete lossless compression of the biomedical image under consideration, with the reconstructed image being mathematically identical to the original image. The method comprises getting rid of the redundant data and encoding the non-redundant data for the purpose of regenerating the image at the receiver section without any observable change in the image data.

Diagnostic performance of advanced tomosynthesis in patients with metal devices in the affected knee: a case report.

Simple radiography is the most frequently and widely available technology to examine bone pathologies. Computed tomography (CT) can evaluate pathologies more accurately in multiple planes and three dimensions; however, radiation exposure is much higher than with simple radiography. In addition, diagnostic ability is decreased for both technologies when metal devices are present. Tomosynthesis is a radiographic technology used to evaluate tissues quasi-three-dimensionally with less radiation exposure. Tomosynthesis technology was recently upgraded to reduce the effects of metal artifacts. This case report compares examination time, medical expense, image resolution, and radiation exposure for upgraded tomosynthesis, simple radiography, CT, and standard tomosynthesis in three patients with metal devices in the affected knees. Examination times were similar for the imaging technologies. Diagnostic performance was better for upgraded tomosynthesis than for simple radiography and standard tomosynthesis, and similar to that for CT. Moreover, radiation exposure and expense were higher for tomosynthesis than for simple radiography but lower than for CT. These findings suggest that upgraded tomosynthesis is the best method for evaluating bone pathology when metal devices are present and radiation exposure must be limited.

Diagnosis of Glaucoma Based on Few-Shot Learning with Wide-Field Optical Coherence Tomography Angiography.

This study evaluated the utility of incorporating deep learning into the relatively novel imaging technique of wide-field optical coherence tomography angiography (WF-OCTA) for glaucoma diagnosis. To overcome the challenge of limited data associated with this emerging imaging, the application of few-shot learning (FSL) was explored, and the advantages observed during its implementation were examined. A total of 195 eyes, comprising 82 normal controls and 113 patients with glaucoma, were examined in this study. The system was trained using FSL instead of traditional supervised learning. Model training can be presented in two distinct ways. Glaucoma feature detection was performed using ResNet18 as a feature extractor. To implement FSL, the ProtoNet algorithm was utilized to perform task-independent classification. Using this trained model, the performance of WF-OCTA through the FSL technique was evaluated. We trained the WF-OCTA validation method with 10 normal and 10 glaucoma images and subsequently examined the glaucoma detection effectiveness. FSL using the WF-OCTA image achieved an area under the receiver operating characteristic curve (AUC) of 0.93 (95% confidence interval (CI): 0.912-0.954) and an accuracy of 81%. In contrast, supervised learning using WF-OCTA images produced worse results than FSL, with an AUC of 0.80 (95% CI: 0.778-0.823) and an accuracy of 50% (p-values < 0.05). Furthermore, the FSL method using WF-OCTA images demonstrated improvement over the conventional OCT parameter-based results (all p-values < 0.05). This study demonstrated the effectiveness of applying deep learning to WF-OCTA for glaucoma diagnosis, highlighting the potential of WF-OCTA images in glaucoma diagnostics. Additionally, it showed that FSL could overcome the limitations associated with a small dataset and is expected to be applicable in various clinical settings.

Knowledge and Visual Differentiation Ability of the Pressure Injury Classification System and Incontinence-Associated Dermatitis among Hospital Nurses: A Descriptive Study.

This study investigated clinical nurses' knowledge and visual differentiation ability of the pressure injury classification system (PICS) and incontinence-associated dermatitis (IAD), additionally analyzing possible influencing factors. A convenience sample of 248 nurses took the PICS and IAD knowledge test (KT) and completed the visual differentiation ability test (VDAT), consisting of 21 photographs with clinical information. The overall mean score for correct answers was 12.65 ± 2.90 points in PICS and IAD KT and 11.43 ± 4.57 points in VDAT. Incorrect responses were most common for statements related to stage II, III, IAD for PICS and IAD KT, and deep tissue pressure injury (DTPI), unstageable, and stage III for VDAT. Significant correlations were found between PICS and IAD KT and VDAT (r = 0.252, p < 0.001). Factors affecting scores for VDAT were the scores of PICS and IAD KT, debridement experience in nursing patients with PI, and the management frequency of PI and IAD. Results indicate that nurses have an overall understanding of PICS and IAD, but low visual differentiation ability regarding stage III, DTPI, and unstageable PI. Continuing education is needed to further improve knowledge and visual differentiation ability for PICS and IAD.

The Presence of Pigmentation on Central Anterior Lens Capsule in the Human Leukocyte Antigen B27-Associated Anterior Uveitis and Its Value in Clinical Diagnosis.

PURPOSE: To report on the value of presence of pigmentation on central anterior lens capsule (PioLe) in HLA B27- associated anterior uveitis (HLA B27-AU). METHODS: 268 patients (320 eyes) with AU were reviewed. Two diagnostic models to predict probability of HLA-B27-AU were developed. The first model included 6 variables (age, gender, unilaterality, presence of non-granulomatous keratic precipitates, hypopyon, and intraocular pressure (IOP). The second model was developed to investigate the added value of PioLe into the first model. RESULTS:      Unilaterality, presence of hypopyon, IOP <21 mmHg and PioLe were characteristic for HLA-B27 positive patients (P≤0.003 for all). All of 6 variables had area under receiver operating characteristic curves (AuROC) ≤ 60, but PioLe reached even higher value (65.5). Diagnostic model I and II had AuROC 76.3% (95%CI, 68.4%-84.2%) and 80.0% (95%CI, 72.6%-87.5%), respectively. CONCLUSIONS: Unilaterality, hypopyon, IOP <21 mmHg and presence of PioLe are clinical signs suggesting HLA B27- AU.

Evaluation of glenoid morphology and bony Bankart lesion in shoulders with traumatic anterior instability using zero echo time magnetic resonance imaging.

Background: Preoperative computed tomography (CT) evaluation of bone morphometry aids in determining treatment strategies for shoulder instability. The use of zero echo time (ZTE) sequence in magnetic resonance imaging (MRI), a new bone cortex imaging technique, may help reduce radiation exposure and medical costs. Therefore, this study aimed to evaluate the glenoid morphology and detect the presence of bony Bankart lesion using ZTE MRI in shoulders with anterior instability and compare its diagnostic accuracy with that of CT. Methods: Thirty-six patients (36 shoulders) with anterior instability who underwent preoperative CT and MRI examinations between April 2019 and October 2021 were retrospectively analyzed. The percentages of glenoid bone defects on 3-dimensional (3D) CT and ZTE images were determined, and the correlation between these percentages was evaluated. The number of cases with bony Bankart lesion on CT and 2 types of ZTE (3D and CT-like) images was determined, and the diagnostic accuracy of ZTE for detecting bony Bankart lesion was assessed, with CT as the gold standard. Patients with bony Bankart lesion on CT images were divided into 2 groups based on whether the lesion was detectable on 3D ZTE or CT-like images. The longer diameters of bony Bankart lesion were compared between the groups. Results: The median percentage of glenoid bone loss was 12.1% (range, 1.3%-45.9%) and 12.3% (range, 0%-46.6%) on 3D CT and 3D ZTE images, respectively. The Spearman's rank correlation coefficient was 0.89. Bony Bankart lesion was detected in 18, 13, and 8 shoulders of the 36 patients on CT, 3D ZTE, and CT-like images, respectively. The overall diagnostic accuracy of the CT-like and 3D ZTE images for detecting bony Bankart lesion was 86.1% and 72.2%, respectively. A significant difference was observed between the groups with and without bony Bankart lesion on CT-like images in terms of the long diameter of the bone fragments on CT (P < .01). Conclusion: ZTE MRI demonstrated high reproducibility for the evaluation of glenoid bone defect in shoulders with anterior instability. Although no significant difference in the measurement was observed compared with that on CT, the ability of ZTE MRI to delineate bone Bankart lesion remains limited.

The ability of critical care nurses to identify pressure injury and incontinence-associated dermatitis: A multicentre cross-sectional survey.

AIM: To investigate the ability of critical care nurses to identify pressure injury and incontinence-associated dermatitis and analyse the possible influencing factors. DESIGN: Cross-sectional survey. METHODS: This study was conducted at 24 hospitals across 12 provinces in China. A self-made electronic questionnaire was used. Nurses identified and judged injuries according to the information provided. RESULTS: The average identification score for pressure injury and incontinence-associated dermatitis was 9.00 ± 3.51 points, and only 2.16% of nurses scored ≥16 points. The average correct identification rate for pressure injury and incontinence-associated dermatitis was 45%. The correct identification rate for stage 1 pressure injury was the highest, while those for stage 3, stage 4, deep tissue pressure injury and unstageable pressure injury were all lower than 50%; incontinence-associated dermatitis was also easily misjudged. Nurses' educational backgrounds, professional titles, job positions, hospital levels and learning frequency were the factors that affected their ability to identify pressure injury and incontinence-associated dermatitis.

Flexible Versus Rigid Laryngoscopy: A Prospective, Blinded Comparison of Image Quality.

OBJECTIVE: To compare flexible distal-chip laryngoscopy (FDL) and rigid telescopic laryngoscopy (RTL) in image quality and diagnostic ability. STUDY DESIGN: Prospective cohort study; blinded comparison. METHODS: Eighteen normal adult subjects were recruited to undergo both FDL and RTL and normalized videos were recorded. Three blinded laryngologists compared the videos for color fidelity, illumination, resolution, and vascularity, and indicated superiority with FDL, RTL, or no difference. Raters also reported if an abnormality was seen and in which video it was better visualized. Videos for two subjects were repeated to assess intra-rater reliability, making 20 video comparisons across 3 raters for a total of 60 ratings. Differences in responses were analyzed via Mann-Whitney U and Pearson Χ2. Inter-rater reliability was assessed via Fleiss' kappa, and intra-rater reliability was assessed via percent agreement. RESULTS: RTL was rated superior in all categories of image quality (47 vs 5 vs 8, P < 0.01; 47 vs 7 vs 6, P < 0.01; 51 vs 5 vs 4, P<0.01; 44 vs 9 vs 7, P < 0.01, respectively). An abnormality was seen 33 times with both modalities and 6 times with RTL only. When seen with both modalities, visualization was superior in RTL compared with FDL (29 vs 4, P <0.01). CONCLUSIONS: There was significant superiority of RTL in all categories of image quality, with slight inter-rater agreement for color fidelity, resolution, and vascularity. RTL was also significantly better for visualization of abnormalities. These findings suggest superior image quality in RTL compared with FDL, but further research is required to determine if this difference is clinically significant.

Objective evaluation of tongue diagnosis ability using a tongue diagnosis e-learning/e-assessment system based on a standardized tongue image database.

Background: In Kampo medicine, tongue examination is used to diagnose the pathological condition "Sho," but an objective evaluation method for its diagnostic ability has not been established. We constructed a tongue diagnosis electronic learning and evaluation system based on a standardized tongue image database. Purpose: This study aims to verify the practicality of this assessment system by evaluating the tongue diagnosis ability of Kampo specialists (KSs), medical professionals, and students. Methods: In the first study, we analyzed the answer data of 15 KSs in an 80-question tongue diagnosis test that assesses eight aspects of tongue findings and evaluated the (i) test score, (ii) test difficulty and discrimination index, (iii) diagnostic consistency, and (iv) diagnostic match rate between KSs. In the second study, we administered a 20-question common Kampo test and analyzed the answer data of 107 medical professionals and 56 students that assessed the tongue color discrimination ability and evaluated the (v) correct answer rate, (vi) test difficulty, and (vii) factors related to the correct answer rate. Result: In the first study, the average test score was 62.2 ± 10.7 points. Twenty-eight questions were difficult (correct answer rate, <50%), 34 were moderate (50%-85%), and 18 were easy (≥85%). Regarding intrarater reliability, the average diagnostic match rate of five KSs involved in database construction was 0.66 ± 0.08, and as for interrater reliability, the diagnostic match rate between the 15 KSs was 0.52 (95% confidence interval, 0.38-0.65) for Gwet's agreement coefficient 1, and the degree of the match rate was moderate. In the second study, the difficulty level of questions was moderate, with a correct rate of 81.3% for medical professionals and 82.1% for students. The discrimination index was good for medical professionals (0.35) and poor for students (0.06). Among medical professionals, the correct answer group of this question had a significantly higher total score on the Kampo common test than the incorrect answer group (85.3 ± 8.4 points vs. 75.8 ± 11.8 points, p < 0.01). Conclusion: This system can objectively evaluate tongue diagnosis ability and has high practicality. Utilizing this system can be expected to contribute to improving learners' tongue diagnosis ability and standardization of tongue diagnosis.

Diagnostic ability of vessel density of the optic nerve head and macula versus structural parameters with optical coherence tomography in pseudoexfoliative glaucoma.

PURPOSE: To evaluate the diagnostic ability of the vessel density (VD) of the optic nerve head (ONH) and the macula on optical coherence tomography (OCT) angiography and the retinal nerve layer thickness (RNFL) thickness and the macular ganglion cell complex (GCC) thickness on OCT in patients with pseudoexfoliative glaucoma (PXG). METHODS: Cross-sectional study including PXG patients and healthy controls. Demographic and clinical data were noted for all participants. Optical coherence tomography (OCT) and OCT angiography (OCTA) images of the ONH and macular area were obtained with the RS-3000 Advance OCT (Nidek Co., Gamagori, Japan). The RNFL and GCC thickness of different sectors was provided by the software. Macular VD of the superficial capillary plexus (SCP) and ONH VD of the radial peripapillary capillary plexus (RPCP) were registered. Groups were compared and area under the receiver operating characteristic (AUROC) curves were used to determine the power of discrimination of each parameter. RESULTS: RNFL and GCC thickness and ONH and macular VD were significantly lower in PXG patients compared with healthy controls (all, p<0.05). The best discrimination parameter was the average RNFL thickness (AUROC: 0.928). ONH VD AUROC was better than that of macular VD (AUROC: 0.897 and 0.780, respectively). ONH VD AUROC was comparable to RNFL thickness (p<0.001). CONCLUSIONS: The diagnostic ability of ONH vessel density in PXG appears comparable to that of the structural parameters, RNFL and GCC thickness, obtained with OCT, and may be a valuable tool in clinical practice.

Diagnostic Ability of Endoscopic Ultrasound-Guided Tissue Acquisition Using 19-Gauge Fine-Needle Biopsy Needle for Abdominal Lesions.

Attempts at performing endoscopic ultrasound-guided tissue acquisition (EUS-TA) with a 19G needle are increasing because histological diagnosis and comprehensive genomic profiling are a necessity. However, the diagnostic ability of the 19G fine-needle biopsy (FNB) needle, especially the third-generation FNB needle, is unclear and has been retrospectively reviewed. The 19G TopGain needle was used in 147 patients and 160 lesions between September 2020 and December 2021. The technical success rate of the biopsies was 99.4% (159/160). The early adverse event rate was 4.1% (6/147), and moderate or severe adverse event rate occurrence was 2.0% (3/147). The sensitivity, specificity, and accuracy of the 19G TopGain needle for 157 lesions with a confirmed diagnosis were 96.7%, 100%, and 96.8%, respectively. Rescue EUS-TA using the 19G TopGain needle was performed for nine lesions, and a successful diagnosis was made in six of these lesions (66.7%). The diagnostic ability of EUS-TA using the third-generation 19G TopGain needle was favorable. However, the use of 19G FNB needles may increase adverse events. Therefore, EUS-TA with a 19G FNB needle is mainly indicated in lesions where comprehensive genomic profiling may be necessary or the diagnosis could not be determined via EUS-TA using the 22G needle.

Ensemble learning of myocardial displacements for myocardial infarction detection in echocardiography.

Background: Early detection and localization of myocardial infarction (MI) can reduce the severity of cardiac damage through timely treatment interventions. In recent years, deep learning techniques have shown promise for detecting MI in echocardiographic images. Existing attempts typically formulate this task as classification and rely on a single segmentation model to estimate myocardial segment displacements. However, there has been no examination of how segmentation accuracy affects MI classification performance or the potential benefits of using ensemble learning approaches. Our study investigates this relationship and introduces a robust method that combines features from multiple segmentation models to improve MI classification performance by leveraging ensemble learning. Materials and Methods: Our method combines myocardial segment displacement features from multiple segmentation models, which are then input into a typical classifier to estimate the risk of MI. We validated the proposed approach on two datasets: the public HMC-QU dataset (109 echocardiograms) for training and validation, and an E-Hospital dataset (60 echocardiograms) from a local clinical site in Vietnam for independent testing. Model performance was evaluated based on accuracy, sensitivity, and specificity. Results: The proposed approach demonstrated excellent performance in detecting MI. It achieved an F1 score of 0.942, corresponding to an accuracy of 91.4%, a sensitivity of 94.1%, and a specificity of 88.3%. The results showed that the proposed approach outperformed the state-of-the-art feature-based method, which had a precision of 85.2%, a specificity of 70.1%, a sensitivity of 85.9%, an accuracy of 85.5%, and an accuracy of 80.2% on the HMC-QU dataset. On the external validation set, the proposed model still performed well, with an F1 score of 0.8, an accuracy of 76.7%, a sensitivity of 77.8%, and a specificity of 75.0%. Conclusions: Our study demonstrated the ability to accurately predict MI in echocardiograms by combining information from several segmentation models. Further research is necessary to determine its potential use in clinical settings as a tool to assist cardiologists and technicians with objective assessments and reduce dependence on operator subjectivity. Our research codes are available on GitHub at https://github.com/vinuni-vishc/mi-detection-echo.

Comparison between Deep-Learning-Based Ultra-Wide-Field Fundus Imaging and True-Colour Confocal Scanning for Diagnosing Glaucoma.

In this retrospective, comparative study, we evaluated and compared the performance of two confocal imaging modalities in detecting glaucoma based on a deep learning (DL) classifier: ultra-wide-field (UWF) fundus imaging and true-colour confocal scanning. A total of 777 eyes, including 273 normal control eyes and 504 glaucomatous eyes, were tested. A convolutional neural network was used for each true-colour confocal scan (Eidon AF™, CenterVue, Padova, Italy) and UWF fundus image (Optomap™, Optos PLC, Dunfermline, UK) to detect glaucoma. The diagnostic model was trained using 545 training and 232 test images. The presence of glaucoma was determined, and the accuracy and area under the receiver operating characteristic curve (AUC) metrics were assessed for diagnostic power comparison. DL-based UWF fundus imaging achieved an AUC of 0.904 (95% confidence interval (CI): 0.861−0.937) and accuracy of 83.62%. In contrast, DL-based true-colour confocal scanning achieved an AUC of 0.868 (95% CI: 0.824−0.912) and accuracy of 81.46%. Both DL-based confocal imaging modalities showed no significant differences in their ability to diagnose glaucoma (p = 0.135) and were comparable to the traditional optical coherence tomography parameter-based methods (all p > 0.005). Therefore, using a DL-based algorithm on true-colour confocal scanning and UWF fundus imaging, we confirmed that both confocal fundus imaging techniques had high value in diagnosing glaucoma.