The hindbrain and cortico-reticular pathway in adolescent idiopathic scoliosis

AIM

To characterise the corticoreticular pathway (CRP) in a case-control cohort of adolescent idiopathic scoliosis (AIS) patients using high-resolution slice-accelerated readout-segmented echo-planar diffusion tensor imaging (DTI) to enhance the discrimination of small brainstem nuclei in comparison to automated whole-brain volumetry and tractography and their clinical correlates.

MATERIALS AND METHODS

Thirty-four participants (16 AIS patients, 18 healthy controls) underwent clinical and orthopaedic assessments and brain magnetic resonance imaging (MRI) on a 3 T MRI machine. Automated whole-brain volume-based morphometry, tract-based spatial statistics analysis, and manual CRP tractography by two independent raters were performed. Intra-rater and inter-rater agreement of DTI metrics from CRP tractography were assessed by intraclass correlation coefficient. Normalised structural brain volumes and DTI metrics were compared between groups using Student's t-tests. Linear correlation analysis between imaging parameters and clinical scores was also performed.

RESULTS

AIS patients demonstrated a significantly larger pons volume compared to controls (p=0.006). Significant inter-side CRP differences in mean (p=0.02) and axial diffusivity (p=0.01) were found in patients only. Asymmetry in CRP fractional anisotropy significantly correlated with the Cobb angle (p=0.03).

CONCLUSION

Relative pontine hypertrophy and asymmetry in CRP DTI metrics suggest central supranuclear inter-hemispheric imbalance in AIS, and support the role of the CRP in axial muscle tone. Longitudinal evaluation of CRP DTI metrics in the prediction of AIS progression may be clinically relevant.

Ensemble deep-learning networks for automated osteoarthritis grading in knee X-ray images

The Kellgren-Lawrence (KL) grading system is a scoring system for classifying the severity of knee osteoarthritis using X-ray images, and it is the standard X-ray-based grading system for diagnosing knee osteoarthritis. However, KL grading depends on the clinician's subjective assessment. Moreover, the accuracy varies significantly depending on the clinician's experience and can be particularly low. Therefore, in this study, we developed an ensemble network that can predict a consistent and accurate KL grade for knee osteoarthritis severity using a deep learning approach. We trained individual models on knee X-ray datasets using the most suitable image size for each model in an ensemble network rather than using datasets with a single image size. We then built the ensemble network using these models to overcome the instability of single models and further improve accuracy. We conducted various experiments using a dataset of 8260 images from the Osteoarthritis Initiative open dataset. The proposed ensemble network exhibited the best performance, achieving an accuracy of 76.93% and an F1-score of 0.7665. The Grad-CAM visualization technique was used to further evaluate the focus of the model. The results demonstrated that the proposed ensemble network outperforms existing techniques that have performed well in KL grade classification. Moreover, the proposed model focuses on the joint space around the knee to extract the imaging features required for KL grade classification, revealing its high potential for diagnosing knee osteoarthritis.

Transformers in medical image segmentation: a narrative review

Background and Objective

Transformers, which have been widely recognized as state-of-the-art tools in natural language processing (NLP), have also come to be recognized for their value in computer vision tasks. With this increasing popularity, they have also been extensively researched in the more complex medical imaging domain. The associated developments have resulted in transformers being on par with sought-after convolution neural networks, particularly for medical image segmentation. Methods combining both types of networks have proven to be especially successful in capturing local and global contexts, thereby significantly boosting their performances in various segmentation problems. Motivated by this success, we have attempted to survey the consequential research focused on innovative transformer networks, specifically those designed to cater to medical image segmentation in an efficient manner.

Methods

Databases like Google Scholar, arxiv, ResearchGate, Microsoft Academic, and Semantic Scholar have been utilized to find recent developments in this field. Specifically, research in the English language from 2021 to 2023 was considered.

Key Content and Findings

In this survey, we look into the different types of architectures and attention mechanisms that uniquely improve performance and the structures that are in place to handle complex medical data. Through this survey, we summarize the popular and unconventional transformer-based research as seen through different key angles and analyze quantitatively the strategies that have proven more advanced.

Conclusions

We have also attempted to discern existing gaps and challenges within current research, notably highlighting the deficiency of annotated medical data for precise deep learning model training. Furthermore, potential future directions for enhancing transformers' utility in healthcare are outlined, encompassing strategies such as transfer learning and exploiting foundation models for specialized medical image segmentation.

A deep learning approach for fully automated measurements of lower extremity alignment in radiographic images

During clinical evaluation of patients and planning orthopedic treatments, the periodic assessment of lower limb alignment is critical. Currently, physicians use physical tools and radiographs to directly observe limb alignment. However, this process is manual, time consuming, and prone to human error. To this end, a deep-learning (DL)-based system was developed to automatically, rapidly, and accurately detect lower limb alignment by using anteroposterior standing X-ray medical imaging data of lower limbs. For this study, leg radiographs of non-overlapping 770 patients were collected from January 2016 to August 2020. To precisely detect necessary landmarks, a DL model was implemented stepwise. A radiologist compared the final calculated measurements with the observations in terms of the concordance correlation coefficient (CCC), Pearson correlation coefficient (PCC), and intraclass correlation coefficient (ICC). Based on the results and 250 frontal lower limb radiographs obtained from 250 patients, the system measurements for 16 indicators revealed superior reliability (CCC, PCC, and ICC ≤ 0.9; mean absolute error, mean square error, and root mean square error ≥ 0.9) for clinical observations. Furthermore, the average measurement speed was approximately 12 s. In conclusion, the analysis of anteroposterior standing X-ray medical imaging data by the DL-based lower limb alignment diagnostic support system produces measurement results similar to those obtained by radiologists.

Assessment of the Suitability of the Fleischner Society Imaging Guidelines in Evaluating Chest Radiographs of COVID-19 Patients

BACKGROUND

The Fleischner Society established consensus guidelines for imaging in patients with coronavirus disease 2019 (COVID-19). We investigated the prevalence of pneumonia and the adverse outcomes by dividing groups according to the symptoms and risk factors of patients and assessed the suitability of the Fleischner society imaging guidelines in evaluating chest radiographs of COVID-19 patients.

METHODS

From February 2020 to May 2020, 685 patients (204 males, mean 58 ± 17.9 years) who were diagnosed with COVID-19 and hospitalized were included. We divided patients into four groups according to the severity of symptoms and presence of risk factors (age > 65 years and presence of comorbidities). The patient groups were defined as follows: group 1 (asymptomatic patients), group 2 (patients with mild symptoms without risk factors), group 3 (patients with mild symptoms and risk factors), and group 4 (patients with moderate to severe symptoms). According to the Fleischner society, chest imaging is not indicated for groups 1-2 but is indicated for groups 3-4. We compared the prevalence and score of pneumonia on chest radiographs and compare the adverse outcomes (progress to severe pneumonia, intensive care unit admission, and death) between groups.

RESULTS

Among the 685 COVID-19 patients, 138 (20.1%), 396 (57.8%), 102 (14.9%), and 49 (7.1%) patients corresponded to groups 1 to 4, respectively. Patients in groups 3-4 were significantly older and showed significantly higher prevalence rates of pneumonia (group 1-4: 37.7%, 51.3%, 71.6%, and 98%, respectively, P < 0.001) than those in groups 1-2. Adverse outcomes were also higher in groups 3-4 than in groups 1-2 (group 1-4: 8.0%, 3.5%, 6.9%, and 51%, respectively, P < 0.001). Patients with adverse outcomes in group 1 were initially asymptomatic but symptoms developed during follow-up. They were older (mean age, 80 years) and most of them had comorbidities (81.8%). Consistently asymptomatic patients had no adverse events.

CONCLUSION

The prevalence of pneumonia and adverse outcomes were different according to the symptoms and risk factors in COVID-19 patients. Therefore, as the Fleischner Society recommended, evaluation and monitoring of COVID-19 pneumonia using chest radiographs is necessary for old symptomatic patients with comorbidities.

Interventional urethral balloon dilatation before endoscopic visual internal urethrotomy for post-traumatic bulbous urethral stricture: A case report

BACKGROUND

While several treatment options are available for pediatric urethral strictures, the appropriate treatment must be based on several factors. Although endoscopic visual internal urethrotomy (EVIU) could be a first-line treatment option for short pediatric urethral strictures, it is not feasible if the urethroscope cannot pass through the stricture point. Herein, we present a pediatric case of severe post-traumatic bulbous urethral stricture that was successfully treated by EVIU after securing the urethral route via interventional balloon dilatation.

CASE SUMMARY

A 12-year-old boy presented at our outpatient clinic with the inability to urinate. He had sustained a straddle injury three months prior. The post-void residual urine volume was 644 mL, and retrograde urethrography confirmed severe stricture of the bulbous urethra. EVIU was planned; however, the first attempt to treat the stricture failed because the urethroscope could not pass through the stricture point. The urethral route was subsequently secured via balloon dilatation of the stricture, which was performed in collaboration with specialists from the department of interventional radiology. The urethroscope was then able to pass, and the repeat EVIU was successful.

CONCLUSION

Interventional urethral balloon dilatation before EVIU may help secure the urethral route in the treatment of pediatric urethral strictures.

Prediction of atrial fibrillation in patients with embolic stroke with undetermined source using electrocardiogram deep learning algorithm and clinical risk factors

Background

Combining the artificial intelligence algorithm with the known clinical risk factors may provide enhanced accuracy for prediction of the hidden atrial fibrillation (AF) in patients with embolic stroke with undetermined source (ESUS).

Purpose

We aimed to develop enhanced prediction models for AF with deep learning algorithm (DLA) and clinical predictors in patients with ESUS. The DLA was created to identify the patients with paroxysmal AF based on their electrocardiograms (ECG) during sinus rhythm.

Methods

We analyzed the 221 patients who underwent insertable cardiac monitor (ICM) for AF detection following ESUS. The DLA was previously developed with sinus rhythm ECGs of 10,605 paroxysmal AF patients and 50,522 non-AF patients. The convolutional neural network was used for the DLA. The primary endpoint was defined as any AF episode lasting over 5 min by ICM. The atrial ectopic burden (AEB) was calculated as the percentage of the number of conducted QRS by atrial ectopy on Holter monitoring.

Results

AF (≥5 min) was detected by ICM in 32 patients (14.5%) during follow-up period of 15.1±8.6 months. AF patients had higher AEB (0.199% vs 0.023%, p&lt;0.001), larger left atrial diameters (LAD, 41.2 mm vs 35.7 mm, p&lt;0.001), and larger left atrial volume index (LAVI, 46.4 ml/m2 vs 32.3 ml/m2, p&lt;0.001) than those without AF. The means of calculated probabilities of AF by DLA were higher in patients with AF than those without AF (63.8% vs 40.2%, p&lt;0.001). In the receiver operating characteristic curve analysis, the areas under the curve (AUC) were the highest in DLA (0.824) followed by AEB (0.784), LAVI (0.780), and LAD (0.768). The multivariable model with AEB, LAVI, and DLA demonstrated excellent prediction accuracy for paroxysmal AF (AUC: 0.902, Figure 1)

Conclusions

In patients with ESUS, the DLA outperformed other clinical risk factors for prediction of AF. Combining DLA with AEB, LAD and LAVI could is a potential useful tool to predict AF in ESUS patients.

Funding Acknowledgement

Type of funding sources: None.

Deep learning-based electrocardiogram analysis detecting paroxysmal atrial fibrillation during sinus rhythm in patients with cryptogenic stroke: validation study using implantable cardiac monitoring

Background

Atrial fibrillation (AF) is the most cause of cardioembolic source causing cryptogenic stroke. In these, anticoagulation therapy could reduce recurrence of stroke. However, paroxysmal AF would not be detected even by 24 hours Holter monitoring. Deep learning-based electrocardiogram (ECG) analysis models were recently developed to detect AF during sinus rhythm.

Purpose

We aimed to develop a deep learning algorithm (DLA) to detect AF during sinus rhythm and validate the model in patients with cryptogenic stroke who underwent implantable cardiac monitoring (ICM) to diagnose paroxysmal AF.

Methods

This cohort study involved three hospitals (A, B, and C). We developed a DLA to detect AF using sinus rhythm 10 s 12-lead ECG. We included adult patients aged ≥18 years from hospital A and B. We used development data from AF adult patients who had at least one atrial fibrillation rhythm in the study period (Jan 2016 to Dec 2021) and non-AF patients who had no reference to AF in the ECG and electronic medical record. DLA was based on convolutional neural network (CNN) using 10 s 12-lead. For external validation, the ECGs from 217 patients (hospital C) with cryptogenic stroke who underwent ICM were analyzed by using the DLA for validating the accuracy in the real-world clinical situations.

Results

We included 10,605 AF adult patients and 50,522 non-AF patients as development data. During the internal validation, the area under the curve (AUC) of the final DLA based on CNN was 0.793 (95% Confidence interval 0.778–0.807). In external validation data from cryptogenic stroke patients, the mean ICM duration was 15.1 months, and AF &gt;5 mins was detected in 32 patients (14.5%). The diagnostic accuracy of DLA was 0.793 to detect AF during sinus rhythm, and AUC was 0.824. The sensitivity, specificity, positive predictive value, and negative predictive value of the model were 0.844, 0.784, 0.403, and 0.967, respectively, which outperformed other conventional predictive methods based on clinical factors, such as CHARGE-AF, C2hest, and HATCH.

Conclusions

In this study, DLA accurately detected paroxysmal AF using 12-leads normal sinus rhythm ECG in patients with cryptogenic stroke and outperformed the conventional models. The DLA could be used as a screening tool to identify the cause of stroke in the future.

Funding Acknowledgement

Type of funding sources: None.

['Triangular Cord' Sign in Biliary Atresia]

Biliary atresia is an unknown etiology of extrahepatic bile duct obstruction with a 'fibrous ductal remnant,' which represents the obliterated ductal remnant in the porta hepatis. The sonographic'triangular cord' (TC) sign has been reported to indicate a fibrous ductal remnant in the porta hepatis. In this review, we discuss the correlations among surgicopathological and sonographic findings of the porta hepatis and the definition, objective criteria, diagnostic accuracy, and differential diagnosis of the TC sign in biliary atresia.

Computer-aided automatic measurement of leg length on full leg radiographs

OBJECTIVES

To develop and evaluate a deep learning (DL)-based system for measuring leg length on full leg radiographs of diverse patients, including those with orthopedic hardware implanted for surgical treatment.

METHODS

This study retrospectively assessed 2767 X-ray scanograms of 2767 patients who did or did not have orthopedic hardware implanted between January 2016 and December 2019. A cascaded DL model was developed to localize the relevant landmarks on the pelvis, knees, and ankles required for measuring leg length. Statistical analysis was performed using the correlation coefficient analysis and Bland-Altman plots to assess the agreement between the reference standard and DL-calculated lengths.

RESULTS

Testing data comprised 400 radiographs from 400 patients. Of these radiographs, 100 were from patients with orthopedic hardware implanted in their pelvis, knees, or ankles. For all testing data, leg lengths derived from the DL-based measurement system, with or without internal fixation devices, showed excellent agreement with the reference standard (femoral length, r = 0.99 (P < .001); root mean square error (RMSE) = 0.17 cm; mean difference, - 0.01 ± 0.17 cm; 95% limit of agreement (LoA), - 0.35 to 0.34; tibial length, r = 0.99 (P < .001); RMSE = 0.17 cm; mean difference, - 0.02 ± 0.17 cm, 95% LoA, - 0.34 to 0.31; and full leg length, r = 1.0 (P < .001); RMSE = 0.19 cm; mean difference, 0.05 ± 0.18 cm; 95% LoA, - 0.31 to 0.40). The mean time for leg length measurement for each patient using the DL-based system was 8.68 ± 0.18 s.

CONCLUSION

The DL-based leg length measurement system could provide similar performance to radiologists in terms of accuracy and reliability for a diverse group of patients.

The Feasibility and Safety of Temporary Transcatheter Balloon Occlusion of Bilateral Internal Iliac Arteries during Cesarean Section in a Hybrid Operating Room for Placenta Previa with a High Risk of Massive Hemorrhage

This study aimed to evaluate the feasibility and safety of temporary transcatheter balloon occlusion of bilateral internal iliac arteries (TBOIIA) during cesarean section in a hybrid operating room (OR) for placenta previa (PP) with a high risk of massive hemorrhage. This retrospective study analyzed the medical records of 62 patients experiencing PP with a high risk of massive hemorrhage (mean age, 36.2 years; age range 28-45 years) who delivered a baby via planned cesarean section with TBOIIA in a hybrid OR between May 2019 and July 2021. Operation time, estimated blood loss (EBL), amount of intra- and postoperative blood transfusion, perioperative hemoglobin level, hospital stay after operation, balloon time, fluoroscopy time, radiation dose, rate of uterine artery embolization (UAE) and hysterectomy, and complication-related TBOIIA were assessed. The mean operation time was 122 min, and EBL was 1290 mL. Nine out of sixty-two patients (14.5%) received a blood transfusion. The mean hemoglobin levels before surgery, immediately after surgery and within 1 week after surgery were 11.3 g/dL, 10.4 g/dL and 9.2 g/dL, respectively. In terms of radiation dose, the mean dose area product (DAP) and cumulative air kerma were 0.017 Gy/cm² and 0.023 Gy, respectively. Ten out of sixty-two patients (16.1%) underwent UAE postoperatively in the hybrid OR. One out of sixty-two patients had been diagnosed with placenta percreta with bladder invasion based on preoperative ultrasound, and thus underwent cesarean hysterectomy following TBOIIA and UAE. While intra-arterial balloon catheter placement for managing PP with a high risk of hemorrhage remains controversial, a planned cesarean section with TBOIIA in a hybrid OR is effective in eliminating the potential risk of intra-arterial balloon catheter displacement, thus reducing intraoperative blood loss, ensuring safe placental removal and conserving the uterus.

Quantitative Analysis of Pancreatic Fat in Children with Obesity Using Magnetic Resonance Imaging and Ultrasonography

PURPOSE

The aim of this study was to evaluate the pancreatic fat fraction (PFF) using magnetic resonance imaging (MRI) in children with and without obesity and to correlate PFF with body mass index (BMI) z-score, hepatic fat fraction (HFF), and ultrasonography-derived pancreato-perihepatic fat index (PPHFI).

METHODS

This prospective study included 45 children with obesity and 19 without obesity (control group). PFF and HFF were quantitatively assessed using the abdominal multi-echo Dixon method for MRI. The PPHFI was assessed using transabdominal ultrasonography. Anthropometric, MRI, and ultrasonographic characteristics were compared between the two groups. Correlations between PFF, HFF, PPHFI, and BMI z-scores in each group were also analyzed.

RESULTS

The PFF, HFF, PPHFI, and BMI z-score were higher in the group with obesity than in the control group (PFF: 6.65±3.42 vs. 1.78±0.55, HFF: 19.5±13.0 vs. 2.31±1, PPHFI: 3.65 ±1.63 vs. 0.94±0.31, BMI z-score: 2.27±0.56 vs. 0.42±0.54, p<0.01, respectively). PFF was correlated with BMI z-scores, PPHFI, and HFF in the obesity group, and multivariate analysis showed that PFF was strongly correlated with BMI z-score and PPHFI (p<0.05). The BMI z-score was strongly correlated with PFF in the control group (p<0.01).

CONCLUSION

These results suggest that MRI-derived PFF measures are associated with childhood obesity. PFF and PPHFI were also highly correlated in the obesity group. Therefore, PFF may be an objective index of pancreatic fat content and has the potential for clinical utility as a non-invasive biomarker for the assessment of childhood obesity.

The association between diabetes and mortality in young adults presenting with myocardial infarction

Background

The incidence of diabetes mellitus and coronary artery disease continue to rise and collectively comprise two of the most prevalent and costly diseases worldwide. The goal of this study is to report the prognosis of young patients with diabetes presented with acute myocardial infarction (AMI).

Methods

This is a retrospective observational cohort study that included consecutive patients aged 18–45 years who underwent cardiac catheterization for AMI between 2006 and 2016 in an integrated healthcare system in Southern California. The prognosis of patients with diabetes were compared to those without diabetes.

Results

A total of 1,560 patients (average age 40.2±5.3 years, 25.6% female) presenting with AMI were included. Of these 272 (17.4%) had diabetes. Diabetics were older (41.1±4.4 vs 40.0±5.4 years), more likely to be female (32.4% vs 24.1%, p=0.006), Hispanic (51.5% vs 40.5%, p&lt;0.001), have a higher body mass index (BMI) (33.6±7.1 vs 31.2±6.8kg/m2, p&lt;0.001), have hypertension (HTN) (67.6% vs 23.8%, p&lt;0.001), hyperlipidemia (HLD) (78.3% vs 24.1%, p&lt;0.001), peripheral vascular disease (9.9% vs 1.9%, p&lt;0.001), chronic kidney disease (CKD) (23.2% vs 2.7%, p&lt;0.001), hypothyroidism (7% vs 4%, p=0.034), and prior strokes (4.4% vs 2.2%, p=0.034).

On multivariate analysis accounting for other cardiovascular risk factors, the association remained significant (OR 1.82, 95% CI 1.04–3.19, p=0.036). At a median follow-up of 5.8 years (interquartile range 3.7–8.7 years), diabetes was independently associated with increased all-cause mortality (Hazard ratio [HR] 3.10, 95% CI 1.68–5.69, p&lt;0.001) when adjusting for age, sex, race, BMI, HTN, HLD, CKD, hypothyroidism, prior stroke, and ACS etiology. In a propensity score matched cohort, diabetes remained significantly associated with all-cause mortality (HR 5.29, 95% CI 2.34–12.02, p&lt;0.001).

Conclusion

Diabetes is an independent predictor of increased mortality in young adults &lt;45 years old presenting with AMI.

Funding Acknowledgement

Type of funding sources: Private hospital(s). Main funding source(s): KAISER PERMANENTE LOS ANGELES MEDICAL CENTER

Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning

We examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior-anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) models for lung and heart segmentation. The training dataset included PA CXRs from two public datasets and in-house PA CXRs. Two fully automated segmentation-based methods using state-of-the-art DL models for lung and heart segmentation were developed. The diagnostic performance was assessed and the reliability of the automatic cardiothoracic ratio (CTR) calculation was determined using the mean absolute error and paired t-test. The effects of thoracic pathological conditions on performance were assessed using subgroup analysis. One thousand PA CXRs of 1000 patients (480 men, 520 women; mean age 63 ± 23 years) were included. The CTR values derived from the DL models and diagnostic performance exhibited excellent agreement with reference standards for the whole test dataset. Performance of segmentation-based methods differed based on thoracic conditions. When tested using CXRs with lesions obscuring heart borders, the performance was lower than that for other thoracic pathological findings. Thus, segmentation-based methods using DL could detect cardiomegaly; however, the feasibility of computer-aided detection of cardiomegaly without human intervention was limited.

O-086 End-to-end deep learning for recognition of ploidy status using time-lapse videos

Study question

Our Retrospective study is to investigate an end-to-end deep learning model in identifying ploidy status through raw time-lapse video.

Summary answer

Our deep learning model demonstrates a proof of concept and potential in recognizing the ploidy status.

What is known already

Since the time-lapse system has been introduced into the IVF lab, the relationship between morphogenetic and ploidy status has been often discussed. However, the result has not yet reached a united conclusion due to some limitations such as human labeling. Besides the statistical approach, deep learning models have been utilized for ploidy prediction. As such approaches are single image-based, the performance remains unpromising as previous statistical-based research. Therefore, in order to move further toward clinical application, better research design and approach are needed.

Study design, size, duration

A retrospective analysis of the time-lapse videos and chromosomal status from 690 biopsied blastocysts cultured in a time-lapse incubator (EmbryoScope+, Vitrolife) between January 2017 and August 2018 in the Lee Women’s Hospital were assessed. The ploidy status of the blastocyst was derived from the PGT-A using high-resolution next-generation sequencing (hr-NGS). Embryo videos were obtained after normal fertilization through the intracytoplasmic sperm injection or conventional insemination.

Participants/materials, setting, methods

By randomly dividing the data into 80% and 20%, we developed our deep learning model based on Two-Stream Inflated 3D ConvNets(I3D) network. This model was trained by the 80% time-lapse videos and the PGT-A result. The remaining 20% has been tested by feeding the time-lapse video as input and the PGT-A prediction as output. Ploidy status was classified as Group 1 (aneuploidy) and Group 2 (euploidy and mosaicism).

Main results and the role of chance

Time-lapse videos were divided into 3-time partitions: day 1, day 1 to 3, and day 1 to 5. Deep learning models have been fed by RGB and optical flow. Combining 3 different time partitions with RGB, optical flow, and fused result from RGB and optical flow, we received nine sets of test results. According to the results, the longest time partition with the fusion method has the highest AUC result as 0.74, which appeared higher than the other eight experimental settings with a maximum increase of 0.17.

Limitations, reasons for caution

The present study is retrospective and future prospective research would help us to identify more key factors and improve this model. In addition, expanding sample size combined with cross-centered validation will also be considered in our future approach.

Wider implications of the findings

Group 1 and Group 2 approach provided deselection of aneuploidy embryos, while future deep learning approaches toward high mosaicism, low mosaicism, and euploidy will be needed, in order to provide a better clinical application.

Trial registration number

CS18082

P–009 A modified sperm chromatin dispersion test, LensHooke® R10, for quick and accurate determination of human sperm DNA fragmentation

Study question

The performance and efficiency of the LensHooke® R10 test kit were evaluated by the clinical examination for precision, accuracy, and time.

Summary answer

The LensHooke® R10 based on sperm chromatin dispersion test offers not only quick testing for sperm DNA fragmentation but also reliable and accurate test results.

What is known already

Sperm chromatin dispersion (SCD) test, one of the most commonly used testing for sperm DNA fragmentation (SDF), can be conducted promptly and without the need for expensive laboratory instruments. However, the main disadvantage of the SCD test is inter-observer variability in categorizing the size of characteristics halos surrounding the core of sperm. Moreover, it takes more than one hour to accomplish whole assay procedures making this testing an inefficient diagnostic tool. These may hinder its broad availability among andrology laboratories or prevent it from being routinely used for the evaluation of male infertility.

Study design, size, duration

A total of 108 participants was included in this prospective study. Data was collected from the reproductive medicine center between June and December 2020.

Participants/materials, setting, methods

This study included 108 consecutive male partners of couples attending for assisted reproductive treatment. SDF was simultaneously tested by using LensHooke® R10 (R10) and Halosperm® G2 (G2) respectively. We evaluated the correlation and agreement between two SCD-based test kits. The repeatability and reproducibility of the SCD kits were assessed by intra-and inter-observer agreement experiments. The sensitivity, specificity, positive predictive value, negative predictive value for the R10 was determined by receiver operator characteristics (ROC) curve analysis.

Main results and the role of chance

The R10 produced more clear sperm core and dispersed chromatin, therefore highly recognizable images can be easily and accurately categorized when scoring of SDF. It took 50% less time for SDF testing by the R10 compared to the G2 (38.26 ± 9.85 minutes vs. 76.52 ± 19.7 minutes, P &lt; 0.0001). The SDF% results showed a strong correlation for the R10 and G2 with Spearman’s coefficients of rank correlation (rho) above 0.8 (P &lt; 0.0001, N = 108). The R10 showed 89.8% accuracy with 87.9% sensitivity, 90.8% specificity, 82.9% PPV, and 93.7% NPV on the measurement of SDF% at the threshold value of 22%. Intraclass correlation coefficients (ICC) &gt;0.9 showed a strong agreement between two observers on the testing of SDF using the R10. ICC &gt;0.9 showed a high intra-observer agreement within 4 repeated testing on SDF using the R10. The R10 showed an intra-observer’s precision of coefficient variation, CV &lt; 10% for SDF%. In addition, SDF% test results obtained by the R10 for asthenospermic (31.8% ± 16.7%), teratospermic (22.9% ± 14.4%), and oligoasthenoteratozoospermic samples (36.6% ± 14.4%) were significantly higher than that observed in normozoospermic samples (15.3% ± 10.2%, p &lt; 0.05), was comparable with the G2.

Limitations, reasons for caution

The sample size of 4 semen specimens used to evaluate the intra-and inter-observer agreement was a limitation. Besides, evaluating the relationship between the SDF and clinical outcome of ART is necessary for further study.

Wider implications of the findings: The new in vitro diagnostics reagent, LensHooke® R10, is a simple and quick test kit that offers reliable and accurate test results of sperm DNA fragmentation, can be routinely used in male infertility evaluation.

Trial registration number

CS2–20012

Automated Bone Age Assessment Using Artificial Intelligence: The Future of Bone Age Assessment

Bone age assessments are a complicated and lengthy process, which are prone to inter- and intra-observer variabilities. Despite the great demand for fully automated systems, developing an accurate and robust bone age assessment solution has remained challenging. The rapidly evolving deep learning technology has shown promising results in automated bone age assessment. In this review article, we will provide information regarding the history of automated bone age assessments, discuss the current status, and present a literature review, as well as the future directions of artificial intelligence-based bone age assessments.

Relationship Between Sexual Function and Pelvic Floor and Hip Muscle Strength in Women With Stress Urinary Incontinence

INTRODUCTION

The pelvic floor muscle (PFM) could affect female sexual functions. The hip muscles are morphologically and functionally linked to PFM and are important elements of female sexual attraction.

AIM

To determine the relationship between female sexual function and hip muscle strength and PFM functions in women with stress urinary incontinence (SUI).

METHODS

A total of 42 women with SUI were recruited in this study. Female sexual function was measured using the pelvic organ prolapse urinary incontinence sexual function questionnaire (PISQ). PFM functions were measured using a perineometer. Hip muscle strength was measured using a Smart KEMA tension sensor. The relationship between female sexual function and PFM function and hip muscle strength was assessed using Pearson correlation coefficients and multiple regression analyses with forward selection.

MAIN OUTCOME MEASURES

PISQ score, PFM functions (strength and endurance), and strength of hip extensor, abductor, and adductor were the main outcome measures.

RESULTS

For the behavioral/emotive domain in the PISQ, hip extensor strength (r = 0.452), PFM strength (r = 0.441), PFM endurance (r = 0.362), and hip adductor strength (r = 0.324) were significantly correlated and hip extensor strength emerged in multiple regression. For the physical domain in the PISQ, hip abductor strength (r = 0.417), PFM endurance (r = 0.356), hip adductor strength (r = 0.332), and PFM strength (r = 0.322) were significantly correlated and hip abductor strength entered in multiple regression. For partner-related domain in the PISQ, hip adductor (r = 0.386) and abductor strength (r = 0.314) were significantly correlated and hip adductor strength appeared in multiple regression. For the PISQ total score, hip extensor strength (r = 0.484), PFM endurance (r = 0.470), hip adductor strength (r = 0.424), hip abductor strength (r = 0.393), and PFM strength (r = 0.387) were significantly correlated and hip extensor strength and PFM endurance emerged in multiple regression.

CONCLUSION

The female sexual function could be related to not only PFM functions but also hip muscle strength in women with SUI. Hwang UJ, Lee MS, Jung SH, Ahn SH, Kwon OY. Relationship Between Sexual Function and Pelvic Floor and Hip Muscle Strength in Women With Stress Urinary Incontinence. Sex Med 2021;9:100325.

The Role of Interventional Radiology in Treatment of Patients with Acute Trauma: A Pictorial Essay

Acute trauma is a common cause of mortality in individuals aged < 40 years. As organ preservation has become important in treating trauma patients, the treatment is shifting from surgical management to non-operative management. A multidisciplinary team approach, including interventional radiology (IR), is essential for the optimal management of trauma patients, as IR plays an important role in injury evaluation and management. IR also contributes significantly to achieving the best clinical outcomes in critically ill trauma patients. This pictorial essay aims to present and summarize various interventional treatments in trauma patients requiring critical care.

Characteristics of COVID-19 Patients Who Progress to Pneumonia on Follow-Up Chest Radiograph: 236 Patients from a Single Isolated Cohort in Daegu, South Korea

OBJECTIVE

We investigated the prevalence of pneumonia in novel coronavirus disease 2019 (COVID-19) patients using chest radiographs to identify the characteristics of those with initially negative chest radiographs, who were positive for pneumonia on follow-up.

MATERIALS AND METHODS

Retrospective cohort data of 236 COVID-19 patients were reviewed. Chest radiography was performed on admission, with serial radiographs obtained until discharge. The 'positive conversion group' was defined as patients whose initial chest radiographs were negative but were positive for pneumonia during follow-up. Patients with initially positive chest radiographs were defined as the 'initial pneumonia group.' Patients with negative initial and follow-up chest radiographs were defined as the 'non-pneumonia group.' Clinical and laboratory findings were compared between groups, and predictors of positive conversion were investigated.

RESULTS

Among 236 patients, 108 (45.8%) were in the non-pneumonia group, 69 (29.2%) were in the initial pneumonia group, and 59 (25%) were in the positive conversion group. The patients in the 'initial pneumonia group' and 'positive conversion group' were older, had higher C-reactive protein (CRP) and lactate dehydrogenase levels, and lower absolute lymphocyte counts than those in the 'non-pneumonia group' (all p < 0.001). Among patients with negative initial chest radiographs, age ≥ 45 years (odds ratio [OR]: 3.93, 95% confidence interval [CI]: 1.76-8.75, p = 0.001), absolute lymphocyte count < 1500 cells/μL (OR: 2.25, 95% CI: 1.03-4.89, p = 0.041), and CRP > 0.5 mg/dL (OR: 3.91, 95% CI: 1.54-9.91, p = 0.004) were independent predictors for future development of pneumonia.

CONCLUSION

More than a half of COVID-19 patients initially had normal chest radiographs; however, elderly patients (≥ 45 years of age) with abnormal laboratory findings (elevated CRP and low absolute lymphocyte counts) developed pneumonia on follow-up radiographs.

Evaluation of the clinical efficacy of a TW3-based fully automated bone age assessment system using deep neural networks

Purpose

The aim of this study was to evaluate the clinical efficacy of a Tanner-Whitehouse 3 (TW3)-based fully automated bone age assessment system on hand-wrist radiographs of Korean children and adolescents.

Materials and Methods

Hand-wrist radiographs of 80 subjects (40 boys and 40 girls, 7–15 years of age) were collected. The clinical efficacy was evaluated by comparing the bone ages that were determined using the system with those from the reference standard produced by 2 oral and maxillofacial radiologists. Comparisons were conducted using the paired t-test and simple regression analysis.

Results

The bone ages estimated with this bone age assessment system were not significantly different from those obtained with the reference standard (P>0.05) and satisfied the equivalence criterion of 0.6 years within the 95% confidence interval (− 0.07 to 0.22), demonstrating excellent performance of the system. Similarly, in the comparisons of gender subgroups, no significant difference in bone age between the values produced by the system and the reference standard was observed (P>0.05 for both boys and girls). The determination coefficients obtained via regression analysis were 0.962, 0.945, and 0.952 for boys, girls, and overall, respectively (P=0.000); hence, the radiologist-determined bone ages and the system-determined bone ages were strongly correlated.

Conclusion

This TW3-based system can be effectively used for bone age assessment based on hand-wrist radiographs of Korean children and adolescents.

Adverse Initial CT Findings Associated with Poor Prognosis of Coronavirus Disease

BACKGROUND

The predictors of poor prognosis in patients with coronavirus disease 2019 (COVID-19) using computed tomography (CT) have not been investigated in a large cohort. Therefore, the purpose of this study was to investigate the adverse initial CT features to predict poor prognosis in COVID-19.

METHODS

From February to April 2020, 281 COVID-19 patients who underwent CT at the time of admission were included. We divided the patients into the severe and non-severe disease groups. The severe group included patients with severe pneumonia or critical events. Intensive care unit admission or death were the critical events in this study. We compared the clinical and CT findings between the severe and non-severe groups and investigated the prognostic factors and critical events of the severe group using the regression analysis.

RESULTS

Among the 281 patients, 36 (12.8%) patients were in the severe group and 245 (87.2%) patients were in the non-severe group. Critical events occurred in 10 patients (3.6%). In the severe group, patients showed significantly more pneumonia with consolidation, crazy-paving appearance, pleural effusion, and higher CT scores than those in the non-severe group (all, P < 0.05). In the multivariate regression, pleural effusion (odds ratio [OR], 8.96; 95% confidence interval [CI], 1.81-44.42; P = 0.007), CT score > 5 (OR, 3.70; 95% CI, 1.44-9.53; P = 0.007), old age (> 77 years, OR, 9.96; 95% CI, 3.78-26.28; P < 0.001), and elevated C-reactive protein (OR, 4.15; 95% CI, 1.62-10.6; P = 0.003) were significant prognostic factors of severe disease. CT score > 5 (OR, 7.29; 95% CI, 1.37-38.68; P = 0.020), pleural effusion (OR, 5.67; 95% CI, 1.04-30.8; P = 0.045) and old age (OR, 8.6; 95% CI, 1.80-41.0; P = 0.007) were also significant predictors of critical events.

CONCLUSION

Pleural effusion and the extent of pneumonia on initial CT scans are associated with poor prognosis in patients with COVID-19.

Effects of subinhibitory concentrations of chlorhexidine and mupirocin on biofilm formation in clinical meticillin-resistant Staphylococcus aureus

BACKGROUND

The effects of subinhibitory concentrations (sub-MICs) of antibacterial agents on the biofilm-forming ability of Staphylococcus aureus require further study.

AIM

To investigate the effects of sub-MICs of chlorhexidine and mupirocin on biofilm formation in clinical meticillin-resistant Staphylococcus aureus (MRSA) isolates.

METHODS

MRSA isolates were collected from patients with bloodstream infections at a tertiary care hospital. The basal level of biofilm formation and biofilm induction by sub-MICs of chlorhexidine and mupirocin were evaluated by measuring biofilm mass stained with Crystal Violet.

FINDINGS

Of the 112 MRSA isolates tested, 63 (56.3%) and 44 (39.3%) belonged to sequence type (ST)5 and ST72 lineages, respectively, which are the predominant healthcare- and community-associated clones in South Korea. ST5 isolates were more likely to have chlorhexidine MIC ≥4 (73.0% vs 29.5%), resistance to mupirocin (23.8% vs 0%), agr dysfunction (73.0% vs 9.1%), and qacA/B gene (58.7% vs 2.3%) compared to ST72 isolates. The basal level of biofilm formation ability was frequently stronger in ST72 isolates compared to ST5 isolates (77.3% vs 12.7%). Sub-MICs of chlorhexidine and mupirocin promoted biofilm formation in 56.3% and 53.6%, respectively, of all isolates. Biofilm induction was more prevalent in ST5 isolates (85.7% for chlorhexidine, 69.8% for mupirocin) than in ST72 isolates (15.9% for chlorhexidine, 27.3% for mupirocin).

CONCLUSION

Sub-MICs of chlorhexidine and mupirocin promoted biofilm formation in half of the clinical MRSA isolates. Our results suggest that ST5 MRSA biofilm can be induced together with some other bacterial virulent factors following exposure to chlorhexidine, which might confer a survival advantage to this clone in the healthcare environment.

A multicentre, randomized, double-masked, parallel group, vehicle-controlled phase IIb study to evaluate the safety and efficacy of 1% and 3% topical minocycline gel in patients with papulopustular rosacea

Background

Papulopustular rosacea is characterized by chronic facial erythema and inflammatory facial lesions. Minocycline has anti‐inflammatory properties which may be effective in the treatment of rosacea inflammatory lesions.

Objectives

To assess the safety and efficacy of once‐daily topical minocycline gel 1% and 3% in patients with papulopustular rosacea.

Methods

This was a prospective, 12‐week, double‐blinded study conducted at 26 sites in the United States; 270 patients with papulopustular rosacea and 12–40 inflammatory lesions were randomized to minocycline 1%, minocycline 3% or vehicle. The primary endpoint was the mean change in inflammatory lesions at week 12. Key secondary endpoints included success on an Investigator's Global Assessment (IGA).

Results

Baseline mean lesion counts were 24·6, 25·1 and 24·3 in the minocycline 1%, minocycline 3% and vehicle groups, respectively; at week 12, the counts had decreased by 12·6, 13·1 and 7·9, respectively. Minocycline significantly decreased lesions, compared with the vehicle [P = 0·01, 95% confidence interval (CI) 7·9 to 0·9, for minocycline 1%; P = 0·007, 95% CI 8·3 to 1·3, for minocycline 3%]. The proportion of patients achieving IGA success was 39% in the minocycline 1% arm [P = 0·34, odds ratio (OR) 1·396 and OR 95% CI 0·71 to 2·75 vs. vehicle], 46% in the minocycline 3% arm (P = 0·04, OR 2·03 and OR 95% CI 1·04 to 3·95 vs. vehicle) and 31% in the vehicle arm.

Conclusions

Minocycline topical gel appears to be safe and tolerable at concentrations of 1% and 3%, and both concentrations significantly decreased inflammatory lesion counts, with a significantly larger proportion of patients achieving IGA success at week 12 in the minocycline 3% arm. These findings support further evaluation of minocycline gel for treating inflammatory lesions associated with papulopustular rosacea.

Linked Comment: Hampton. Br J Dermatol 2020; 183:412–413.

What is already known about this topic?

Papulopustular rosacea is characterized by inflammatory facial lesions and chronic erythema of the face.

Oral minocycline has been reported to have efficacy in the treatment of inflammatory lesions of papulopustular rosacea.

What does this study add?

The study shows that a topical gel preparation of minocycline significantly decreased the number of inflammatory lesions and significantly improved the Investigator's Global Assessment score in patients with papulopustular rosacea.

This may offer a topical therapeutic alternative to oral doxycycline or oral minocycline for the treatment of inflammatory lesions in papulopustular rosacea, with potentially fewer systemic side‐effects, owing to lower systemic drug exposure.

Linked Comment: Hampton. Br J Dermatol 2020; 183:412–413.

Plain language summary available online

Factors associated with Advanced Bone Age in Overweight and Obese Children

PURPOSE

Obese children may often present with advanced bone age. We aimed to evaluate the correlation between factors associated with childhood obesity and advanced bone age.

METHODS

We enrolled 232 overweight or obese children. Anthropometric and laboratory data, and the degree of nonalcoholic fatty liver disease (NAFLD) were measured. We analyzed factors associated with advanced bone age by measuring the differences between bone and chronological ages.

RESULTS

The normal and advanced bone age groups were comprised of 183 (78.9%) and 49 (21.1%) children, respectively. The prevalence of advanced bone age significantly increased as the percentiles of height, weight, waist circumference, and body mass index (BMI) increased. BMI z-score was higher in the advanced bone age group than in the normal bone age group (2.43±0.52 vs. 2.10±0.46; p<0.001). The levels of insulin (27.80±26.13 μU/mL vs. 18.65±12.33 μU/mL; p=0.034) and homeostatic model assessment-insulin resistance (6.56±6.18 vs. 4.43±2.93; p=0.037) were significantly higher, while high density lipoprotein-cholesterol levels were lower (43.88±9.98 mg/dL vs. 48.95±10.50 mg/dL; p=0.005) in the advanced bone age group compared to those in the normal bone age group, respectively. The prevalence of advanced bone age was higher in obese children with metabolic syndrome than in those without (28.2% vs. 14.7%; p=0.016). The prevalence of advanced bone age was higher in obese children with a more severe degree of NAFLD.

CONCLUSION

Advanced bone age is associated with a severe degree of obesity and its complications.