Search

Abstract High-energy impacts, like vehicle crashes or falls, can lead to pelvic ring injuries. Rapid diagnosis and treatment are crucial due to the risks of severe bleeding and organ damage. Pelvic radiography promptly assesses fracture extent and location, but struggles to diagnose bleeding. The AO/OTA classification system grades pelvic instability, but its complexity limits its use in emergency settings. This study develops and evaluates a deep learning algorithm to classify pelvic fractures on radiographs per the AO/OTA system. Pelvic radiographs of 773 patients with pelvic fractures and 167 patients without pelvic fractures were retrospectively analyzed at a single center. Pelvic fractures were classified into types A, B, and C using medical records categorized by an orthopedic surgeon according to the AO/OTA classification system. Accuracy, Dice Similarity Coefficient (DSC), and F1 score were measured to evaluate the diagnostic performance of the deep learning algorithms. The segmentation model showed high performance with 0.98 accuracy and 0.96–0.97 DSC. The AO/OTA classification model demonstrated effective performance with a 0.47–0.80 F1 score and 0.69–0.88 accuracy. Additionally, the classification model had a macro average of 0.77–0.94. Performance evaluation of the models showed relatively favorable results, which can aid in early classification of pelvic fractures.

Abstract Background We aimed to determine the feasibility of utilizing deep learning-based predictions of the indications for cracked tooth extraction using panoramic radiography. Methods Panoramic radiographs of 418 teeth (group 1: 209 normal teeth; group 2: 209 cracked teeth) were evaluated for the training and testing of a deep learning model. We evaluated the performance of the cracked diagnosis model for individual teeth using InceptionV3, ResNet50, and EfficientNetB0. The cracked tooth diagnosis model underwent fivefold cross-validation with 418 data instances divided into training, validation, and test sets at a ratio of 3:1:1. Results To evaluate the feasibility, the sensitivity, specificity, accuracy, and F1 score of the deep learning models were calculated, with values of 90.43–94.26%, 52.63–60.77%, 72.01–75.84%, and 76.36–79.00%, respectively. Conclusion We found that the indications for cracked tooth extraction can be predicted to a certain extent through a deep learning model using panoramic radiography.

Purpose The aim of this study was to demonstrate the effectiveness of a machine learning-based radiomics model for distinguishing tumor response and overall survival in patients with unresectable colorectal liver metastases (CRLM) treated with targeted biological therapy. Methods We prospectively recruited 17 patients with unresectable liver metastases of colorectal cancer, who had been given targeted biological therapy as the first line of treatment. All patients underwent liver magnetic resonance imaging (MRI) three times up until 8 weeks after chemotherapy. We evaluated the diagnostic performance of machine learning-based radiomics model in tumor response of liver MRI compared with the guidelines for the Response Evaluation Criteria in Solid Tumors. Overall survival was evaluated using the Kaplan-Meier analysis and compared to the Cox proportional hazard ratios following univariate and multivariate analyses. Results Performance measurement of the trained model through metrics showed the accuracy of the machine learning model to be 76.5%, and the area under the receiver operating characteristic curve was 0.857 (95% confidence interval [CI], 0.605–0.976; P

Abstract With the recent increase in traffic accidents, pelvic fractures are increasing, second only to skull fractures, in terms of mortality and risk of complications. Research is actively being conducted on the treatment of intra-abdominal bleeding, the primary cause of death related to pelvic fractures. Considerable preliminary research has also been performed on segmenting tumors and organs. However, studies on clinically useful algorithms for bone and pelvic segmentation, based on developed models, are limited. In this study, we explored the potential of deep-learning models presented in previous studies to accurately segment pelvic regions in X-ray images. Data were collected from X-ray images of 940 patients aged 18 or older at Gachon University Gil Hospital from January 2015 to December 2022. To segment the pelvis, Attention U-Net, Swin U-Net, and U-Net were trained, thereby comparing and analyzing the results using five-fold cross-validation. The Swin U-Net model displayed relatively high performance compared to Attention U-Net and U-Net models, achieving an average sensitivity, specificity, accuracy, and dice similarity coefficient of 96.77%, of 98.50%, 98.03%, and 96.32%, respectively.

Objective Urinary tract infection is one of the most prevalent bacterial infectious diseases in outpatient treatment, and 50–80% of women experience it more than once, with a recurrence rate of 40–50% within a year; consequently, preventing re-hospitalization of patients is critical. However, in the field of urology, no research on the analysis of the re-hospitalization status for urinary tract infections using machine learning algorithms has been reported to date. Therefore, this study uses various machine learning algorithms to analyze the clinical and nonclinical factors related to patients who were re-hospitalized within 30 days of urinary tract infection. Methods Data were collected from 497 patients re-hospitalized for urinary tract infections within 30 days and 496 patients who did not require re-hospitalization. The re-hospitalization factors were analyzed using four machine learning algorithms: gradient boosting classifier, random forest, naive Bayes, and logistic regression. Results The best-performing gradient boosting classifier identified respiratory rate, days of hospitalization, albumin, diastolic blood pressure, blood urea nitrogen, body mass index, systolic blood pressure, body temperature, total bilirubin, and pulse as the top-10 factors that affect re-hospitalization because of urinary tract infections. The 993 patients whose data were collected were divided into risk groups based on these factors, and the re-hospitalization rate, days of hospitalization, and medical expenses were observed to decrease from the high- to low-risk group. Conclusions This study showed new possibilities in analyzing the status of urinary tract infection-related re-hospitalization using machine learning. Identifying factors affecting re-hospitalization and incorporating preventable and reinforcement-based treatment programs can aid in reducing the re-hospitalization rate and average number of days of hospitalization, thereby reducing medical expenses.

Background/Objectives: During gastroscopy, accurately identifying the anatomical locations of the gastrointestinal tract is crucial for developing diagnostic aids, such as lesion localization and blind spot alerts. Methods: This study utilized a dataset of 31,403 still images from 1000 patients with normal findings to annotate the anatomical locations within the images and develop a classification model. The model was then applied to videos of 20 esophagogastroduodenoscopy procedures, where it was validated for real-time location prediction. To address instability of predictions caused by independent frame-by-frame assessment, we implemented a hard-voting-based post-processing algorithm that aggregates results from seven consecutive frames, improving the overall accuracy. Results: Among the tested models, InceptionV3 demonstrated superior performance for still images, achieving an F1 score of 79.79%, precision of 80.57%, and recall of 80.08%. For video data, the InceptionResNetV2 model performed best, achieving an F1 score of 61.37%, precision of 73.08%, and recall of 57.21%. These results indicate that the deep learning models not only achieved high accuracy in position recognition for still images but also performed well on video data. Additionally, the post-processing algorithm effectively stabilized the predictions, highlighting its potential for real-time endoscopic applications. Conclusions: This study demonstrates the feasibility of predicting the gastrointestinal tract locations during gastroscopy and suggests a promising path for the development of advanced diagnostic aids to assist clinicians. Furthermore, the location information generated by this model can be leveraged in future technologies, such as automated report generation and supporting follow-up examinations for patients.

Depending on the degree of fracture, pelvic fracture can be accompanied by vascular damage, and in severe cases, it may progress to hemorrhagic shock. Pelvic radiography can quickly diagnose pelvic fractures, and the Association for Osteosynthesis Foundation and Orthopedic Trauma Association (AO/OTA) classification system is useful for evaluating pelvic fracture instability. This study aimed to develop a radiomics-based machine-learning algorithm to quickly diagnose fractures on pelvic X-ray and classify their instability. data used were pelvic anteroposterior radiographs of 990 adults over 18 years of age diagnosed with pelvic fractures, and 200 normal subjects. A total of 93 features were extracted based on radiomics:18 first-order, 24 GLCM, 16 GLRLM, 16 GLSZM, 5 NGTDM, and 14 GLDM features. To improve the performance of machine learning, the feature selection methods RFE, SFS, LASSO, and Ridge were used, and the machine learning models used LR, SVM, RF, XGB, MLP, KNN, and LGBM. Performance measurement was evaluated by area under the curve (AUC) by analyzing the receiver operating characteristic curve. The machine learning model was trained based on the selected features using four feature-selection methods. When the RFE feature selection method was used, the average AUC was higher than that of the other methods. Among them, the combination with the machine learning model SVM showed the best performance, with an average AUC of 0.75±0.06. By obtaining a feature-importance graph for the combination of RFE and SVM, it is possible to identify features with high importance. The AO/OTA classification of normal pelvic rings and pelvic fractures on pelvic AP radiographs using a radiomics-based machine learning model showed the highest AUC when using the SVM classification combination. Further research on the radiomic features of each part of the pelvic bone constituting the pelvic ring is needed.

Abstract An in situ measurement of a CO2 reduction reaction (CO2RR) in Cu‐phthalocyanine (CuPC) molecules adsorbed on an Au(111) surface is performed using electrochemical scanning tunneling microscopy. One intriguing phenomenon monitored in situ during CO2RR is that a well‐ordered CuPC adlayer is formed into an unsuspected nanocluster via molecular restructuring. At an electrode potential of −0.7 V versus Ag/AgCl, the Au surface is covered mainly with the clusters, showing restructuring‐induced CO2RR catalytic activity. Using a measurement of X‐ray photoelectron spectroscopy, it is revealed that the nanocluster represents a Cu complex with its formation mechanism. This work provides an in situ observation of the restructuring of the electrocatalyst to understand the surface‐reactive correlations and suggests the CO2RR catalyst works at a relatively low potential using the CuPC‐derived Cu nanoclusters as active species.

Abstract Slippery surfaces (i.e., surfaces that display high liquid droplet mobility) are receiving significant attention due to their biofluidic applications. Non‐textured, all‐solid, slippery hydrophilic (SLIC) surfaces are an emerging class of rare and counter‐intuitive surfaces. In this work, the interactions of blood and bacteria with SLIC surfaces are investigated. The SLIC surfaces demonstrate significantly lower platelet and leukocyte adhesion (≈97.2% decrease in surface coverage), and correspondingly low platelet activation, as well as significantly lower bacterial adhesion (≈99.7% decrease in surface coverage of live Escherichia Coli and ≈99.6% decrease in surface coverage of live Staphylococcus Aureus) and proliferation compared to untreated silicon substrates, indicating their potential for practical biomedical applications. The study envisions that the SLIC surfaces will pave the path to improved biomedical devices with favorable blood and bacteria interactions.

Abstract Background In this study, we investigated whether deep learning-based prediction of osseointegration of dental implants using plain radiography is possible. Methods Panoramic and periapical radiographs of 580 patients (1,206 dental implants) were used to train and test a deep learning model. Group 1 (338 patients, 591 dental implants) included implants that were radiographed immediately after implant placement, that is, when osseointegration had not yet occurred. Group 2 (242 patients, 615 dental implants) included implants radiographed after confirming successful osseointegration. A dataset was extracted using random sampling and was composed of training, validation, and test sets. For osseointegration prediction, we employed seven different deep learning models. Each deep-learning model was built by performing the experiment 10 times. For each experiment, the dataset was randomly separated in a 60:20:20 ratio. For model evaluation, the specificity, sensitivity, accuracy, and AUROC (Area under the receiver operating characteristic curve) of the models was calculated. Results The mean specificity, sensitivity, and accuracy of the deep learning models were 0.780–0.857, 0.811–0.833, and 0.799–0.836, respectively. Furthermore, the mean AUROC values ranged from to 0.890–0.922. The best model yields an accuracy of 0.896, and the worst model yields an accuracy of 0.702. Conclusion This study found that osseointegration of dental implants can be predicted to some extent through deep learning using plain radiography. This is expected to complement the evaluation methods of dental implant osseointegration that are currently widely used.

Factors influencing the sour taste of coffee and the properties of chlorogenic acid are not yet fully understood. This study aimed to evaluate the impact of roasting degree on pH-associated changes in coffee bean extract and the thermal stability of chlorogenic acid. Coffee bean extract pH decreased up to a chromaticity value of 75 but increased with higher chromaticity values. Ultraviolet–visible spectrophotometry and structural analysis attributed this effect to chlorogenic and caffeic acids. Moreover, liquid chromatography-mass spectrometry analysis identified four chlorogenic acid types in green coffee bean extract. Chlorogenic acid isomers were eluted broadly on HPLC, and a chlorogenic acid fraction graph with two peaks, fractions 5 and 9, was obtained. Among the various fractions, the isomer in fraction 5 had significantly lower thermal stability, indicating that thermal stability differs between chlorogenic acid isomers.

In this study, we propose a deep learning-based nystagmus detection algorithm using video oculography (VOG) data to diagnose benign paroxysmal positional vertigo (BPPV). Various deep learning architectures were utilized to develop and evaluate nystagmus detection models. Among the four deep learning architectures used in this study, the CNN1D model proposed as a nystagmus detection model demonstrated the best performance, exhibiting a sensitivity of 94.06 ± 0.78%, specificity of 86.39 ± 1.31%, precision of 91.34 ± 0.84%, accuracy of 91.02 ± 0.66%, and an F1-score of 92.68 ± 0.55%. These results indicate the high accuracy and generalizability of the proposed nystagmus diagnosis algorithm. In conclusion, this study validates the practicality of deep learning in diagnosing BPPV and offers avenues for numerous potential applications of deep learning in the medical diagnostic sector. The findings of this research underscore its importance in enhancing diagnostic accuracy and efficiency in healthcare.

Gamma-aminobutyric acid type A receptor (GABAAR), the ionotropic receptor of GABA, is expressed in macrophages and in the nervous system; however, its role in innate immunity is unknown. Herein, we identified myeloid GABAAR subunit α4 (Gabra4) as a critical regulator of autophagy and a promoter of host innate defense during infection and inflammation. Myeloid Gabra4 deficiency led to defective mycobacterial clearance during infection and increased susceptibility to septic shock. Gabra4 deletion exaggerated inflammatory responses and suppressed the activation of autophagy in macrophages upon infectious and inflammatory stimuli. Mechanistically, Gabra4-mediated signaling led to upregulation of autophagy in macrophages via intracellular calcium release and AMP-activated protein kinase (AMPK) signaling activation, which was required for linking autophagy and antimicrobial responses. Additionally, Gabra4 was required to generate mitochondrial reactive oxygen species, thereby triggering autophagy and antimicrobial responses to mycobacteria. Metabolomics analysis showed that Gabra4 was critical for glucose metabolism and aerobic glycolysis in macrophages. Our findings demonstrate that myeloid Gabra4 coordinates autophagy, inflammation, and immunometabolism to promote innate host defense against pathogenic and dangerous stimuli. Abbreviation AM: Alveolar macrophage; AMPK: AMP-activated protein kinase; ASC: Apoptosis-associated speck-like protein containing a CARD; ATP: Adenosine 5’-triphosphate; BAL: Bronchoalveolar lavage; BCG: Mycobacterium bovis Bacillus Calmette–Guérin; BMDM: Bone marrow-derived macrophage; CCL: CC motif chemokine ligand; CFU: Colony forming unit; CKO: Conditional knock out; CXCL: C-X-C motif ligand; Dpi: Days post-infection; ECAR: Extracellular acidification rate; EGFP: Enhanced green fluorescent protein; FOXO3: Forkhead box O3; GABA: Gamma-aminobutyric acid; GABAAR: GABA type A receptor; Gabarap: GABA type A receptor-associated protein; Gabarapl1: GABA type A receptor-associated protein like 1; GABRA4: Gamma-aminobutyric acid type A receptor subunit alpha4; HIF-1α: Hypoxia-inducible factor-1 alpha; IL: Interleukin; i.n.: Intranasal; i.p.: Intraperitoneal; LDHA: Lactate dehydrogenase A; LPS: Lipopolysaccharide; Mabc: Mycobacteroides abscessus subsp. abscessus; MOI: Multiplicities of infection; Mtb: Mycobacterium tuberculosis; mtROS: Mitochondrial reactive oxygen species; OCR: Oxygen consumption rate; OXPHOS: Oxidative phosphorylation; PM: Peritoneal macrophage; TNF: Tumor necrosis factor; WT: Wild type

Abstract Background Itaconate, a crucial immunometabolite, plays a critical role in linking immune and metabolic functions to influence host defense and inflammation. Due to its polar structure, the esterified cell-permeable derivatives of itaconate are being developed to provide therapeutic opportunities in infectious and inflammatory diseases. Yet, it remains largely uncharacterized whether itaconate derivatives have potentials in promoting host-directed therapeutics (HDT) against mycobacterial infections. Here, we report dimethyl itaconate (DMI) as the promising candidate for HDT against both Mycobacterium tuberculosis (Mtb) and nontuberculous mycobacteria by orchestrating multiple innate immune programs. Results DMI per se has low bactericidal activity against Mtb, M. bovis Bacillus Calmette–Guérin (BCG), and M. avium (Mav). However, DMI robustly activated intracellular elimination of multiple mycobacterial strains (Mtb, BCG, Mav, and even to multidrug-resistant Mtb) in macrophages and in vivo. DMI significantly suppressed the production of interleukin-6 and -10, whereas it enhanced autophagy and phagosomal maturation, during Mtb infection. DMI-mediated autophagy partly contributed to antimicrobial host defenses in macrophages. Moreover, DMI significantly downregulated the activation of signal transducer and activator of transcription 3 signaling during infection with Mtb, BCG, and Mav. Conclusion Together, DMI has potent anti-mycobacterial activities in macrophages and in vivo through promoting multifaceted ways for innate host defenses. DMI may bring light to new candidate for HDT against Mtb and nontuberculous mycobacteria, both of which infections are often intractable with antibiotic resistance.

Sepsis: chemical modulation of selective autophagy alleviates systemic inflammation Sepsis is a life-threatening condition that occurs when the body’s response to infection damages its own organs. Autophagy protects the body by degrading harmful materials in the cell using the lysosome. It has been an outstanding question whether autophagy can fight systemic inflammation in sepsis. Researchers in South Korea led by Eun-Kyeong Jo at Chungnam National University and Yong Tae Kwon at Seoul National University developed small molecule chemicals that target the autophagic receptor p62/SQSTSM-1/Sequestosome-1 to induce therapeutic efficacy during septic responses. In a mouse model of septic shock, these orally administrative compounds halted the production of proinflammatory molecules and reduced oxidative stress in mitochondria by facilitating the autophagic turnover of damaged mitochondria. Chemical modulation of p62 is now emerging as a therapeutic strategy to treat sepsis responsible for 11 million deaths a year.

Abstract Early diagnosis of deep venous thrombosis is essential for reducing complications, such as recurrent pulmonary embolism and venous thromboembolism. There are numerous studies on enhancing efficiency of computer-aided diagnosis, but clinical diagnostic approaches have never been considered. In this study, we evaluated the performance of an artificial intelligence (AI) algorithm in the detection of iliofemoral deep venous thrombosis on computed tomography angiography of the lower extremities to investigate the effectiveness of using the clinical approach during the feature extraction process of the AI algorithm. To investigate the effectiveness of the proposed method, we created synthesized images to consider practical diagnostic procedures and applied them to the convolutional neural network-based RetinaNet model. We compared and analyzed the performances based on the model’s backbone and data. The performance of the model was as follows: ResNet50: sensitivity = 0.843 (± 0.037), false positives per image = 0.608 (± 0.139); ResNet152 backbone: sensitivity = 0.839 (± 0.031), false positives per image = 0.503 (± 0.079). The results demonstrated the effectiveness of the suggested method in using computed tomography angiography of the lower extremities, and improving the reporting efficiency of the critical iliofemoral deep venous thrombosis cases.

Abstract Segmentation of the cervical spine in tandem with three cranial bones, hard palate, basion, and opisthion using X-ray images is crucial for measuring metrics used to diagnose traumatic atlanto-occipital dislocation (TAOD). Previous studies utilizing automated segmentation methods have been limited to segmenting parts of the cervical spine (C3 ~ C7), due to difficulties in defining the boundaries of C1 and C2 bones. Additionally, there has yet to be a study that includes cranial bone segmentations necessary for determining TAOD diagnosing metrics, which are usually defined by measuring the distance between certain cervical (C1 ~ C7) and cranial (hard palate, basion, opisthion) bones. For this study, we trained a U-Net model on 513 sagittal X-ray images with segmentations of both cervical and cranial bones for an automated solution to segmenting important features for diagnosing TAOD. Additionally, we tested U-Net derivatives, recurrent residual U-Net, attention U-Net, and attention recurrent residual U-Net to observe any notable differences in segmentation behavior. The accuracy of U-Net models ranged from 99.07 to 99.12%, and dice coefficient values ranged from 88.55 to 89.41%. Results showed that all 4 tested U-Net models were capable of segmenting bones used in measuring TAOD metrics with high accuracy.

Ohmyungsamycin A (OMS) is a newly identified cyclic peptide that exerts antimicrobial effects against Mycobacterium tuberculosis. However, its role in nontuberculous mycobacteria (NTMs) infections has not been clarified. Mycobacteroides abscessus (Mabc) is a rapidly growing NTM that has emerged as a human pathogen in both immunocompetent and immunosuppressed individuals. In this study, we demonstrated that OMS had significant antimicrobial effects against Mabc infection in both immunocompetent and immunodeficient mice, and in macrophages. OMS treatment amplified Mabc-induced expression of M1-related proinflammatory cytokines and inducible nitric oxide synthase, and significantly downregulated arginase-1 expression in murine macrophages. In addition, OMS augmented Mabc-mediated production of mitochondrial reactive oxygen species (mtROS), which promoted M1-like proinflammatory responses in Mabc-infected macrophages. OMS-induced production of mtROS and nitric oxide was critical for OMS-mediated antimicrobial responses during Mabc infections. Notably, the combination of OMS and rifabutin had a synergistic effect on the antimicrobial responses against Mabc infections in vitro, in murine macrophages, and in zebrafish models in vivo. Collectively, these data strongly suggest that OMS may be an effective M1-like adjunctive therapeutic against Mabc infections, either alone or in combination with antibiotics.

In the medical field, artificial intelligence has been used in various ways with many developments. However, most artificial intelligence technologies are developed so that one model can perform only one task, which is a limitation in designing the complex reading process of doctors with artificial intelligence. Multi-task learning is an optimal way to overcome the limitations of single-task learning methods. Multi-task learning can create a model that is efficient and advantageous for generalization by simultaneously integrating various tasks into one model. This study investigated the concepts, types, and similar concepts as multi-task learning, and examined the status and future possibilities of multi-task learning in the medical research.

Objectives The objective of this study was to investigate the factors associated with website operation among medical facilities. Methods A cross-sectional study design was employed to investigate 1,519 hospitals, 33,043 medical clinics (MCs), and 18,240 dental clinics (DCs) as of 2020. The main outcome variable was analyzed according to technological, organizational, and environmental factors. Results The percentages of small hospitals, MCs, and DCs with websites were 26.4%, 9.0%, and 6.6%, respectively. For small hospitals, the nearby presence of a subway station (odds ratio [OR] = 2.772; 95% confidence interval [CI], 1.973–3.892; p < 0.0001) was the only factor significantly associated with website operation status. Among medical and dental clinics, the percentage of specialists—MCs (OR = 1.002; 95% CI, 1.000–1.004; p = 0.0175) and DCs (OR = 1.002; 95% CI, 1.001–1.004; p = 0.0061), the nearby presence of a subway station—MCs (OR = 2.954; 95% CI, 2.613–3.339; p < 0.0001) and DCs (OR = 3.444; 95% CI, 2.945–4.028; p < 0.0001), and the number of clinics in the local area—MCs (OR = 1.029; 95% CI, 1.026–1.031; p < 0.0001) and DCs (OR = 1.080; 95% CI, 1.066–1.093; p < 0.0001)—were significantly associated with website operation. Conclusions Clinics are critically affected by internal and external factors regarding website operation relative to small hospitals. Healthcare policymakers involved with information technologies may need to pay attention to those factors associated with website dispersion among small clinics.

Accurate paranasal sinus segmentation is essential for reducing surgical complications through surgical guidance systems. This study introduces a multiclass Convolutional Neural Network (CNN) segmentation model by comparing four 3D U-Net variations—normal, residual, dense, and residual-dense. Data normalization and training were conducted on a 40-patient test set (20 normal, 20 abnormal) using 5-fold cross-validation. The normal 3D U-Net demonstrated superior performance with an F1 score of 84.29% on the normal test set and 79.32% on the abnormal set, exhibiting higher true positive rates for the sphenoid and maxillary sinus in both sets. Despite effective segmentation in clear sinuses, limitations were observed in mucosal inflammation. Nevertheless, the algorithm’s enhanced segmentation of abnormal sinuses suggests potential clinical applications, with ongoing refinements expected for broader utility.

Abstract In living-donor liver transplantation, the safety of the donor is critical. In addition, accurately measuring the liver volume is significant as the amount that can be resected from living donors is limited. In this paper, we propose an automated segmentation and volume estimation method for the liver in computed tomography imaging based on a deep learning-based segmentation network. Our framework was trained using the data of 191 donors, achieved a dice similarity coefficient of 0.789, 0.869, 0.955, and 0.899, respectively, in the segmentation task for the left lobe, right lobe, caudate lobe, and whole liver. Moreover, the R^2 score reached 0.980, 0.996, 0.953, and 0.996 in the volume estimation task. We demonstrate that our approach provides accurate and quantitative liver segmentation results, reducing the error in liver volume estimation. Therefore, we expected to be used as an aid in estimating liver volume from CT volume data for living-donor liver transplantation.

Abstract Background Distinguishing benign lesion from early malignancy in melanocytic lesions of the nail unit still remains a diagnostic challenge, both clinically and histopathologically. While several immunohistochemistry (IHC) stainings have been suggested to help discriminate benign subungual melanocytic proliferation (SMP) and subungual melanoma in situ (MIS), the diagnostic utility of IHC staining for cyclin D1 and PRAME has not been thoroughly investigated in melanocytic lesions of nail unit. Methods This retrospective study included cases of benign SMP and subungual MIS confirmed by biopsy at Asan Medical Center from January 2016 to December 2020. Cases of melanocytic activation without proliferation and melanoma where dermal invasion was identified were excluded. Cyclin D1 and PRAME expression was assessed by counting proportion of melanocytes with nuclear positivity under 200x magnification. Results A total of 14 patients with benign SMP and 13 patients with subungual MIS were included in this study. 11 patients with benign SMP (71.4%) and 5 patients with subungual MIS (38.5%) showed > 60% nuclear immunostaining for cyclin D1, respectively. While 13 patients with benign SMP (92.9%) showed totally negative staining for PRAME, 10 patients with subungual MIS (76.9%) exhibited > 50% nuclear immunostaining for PRAME. Using the cutoff of 10%, PRAME exhibited good overall discrimination between benign SMP and subungual MIS (AUC = 0.849, 95% CI = 0.659–0.957). Conclusions This study suggests that PRAME IHC staining as a reliable discriminator in distinguishing subungual MIS from benign SMP.

Most of the development of gastric disease prediction models has utilized pre-trained models from natural data, such as ImageNet, which lack knowledge of medical domains. This study proposes Gastro-BaseNet, a classification model trained using gastroscopic image data for abnormal gastric lesions. To prove performance, we compared transfer-learning based on two pre-trained models (Gastro-BaseNet and ImageNet) and two training methods (freeze and fine-tune modes). The effectiveness was verified in terms of classification at the image-level and patient-level, as well as the localization performance of lesions. The development of Gastro-BaseNet had demonstrated superior transfer learning performance compared to random weight settings in ImageNet. When developing a model for predicting the diagnosis of gastric cancer and gastric ulcers, the transfer-learned model based on Gastro-BaseNet outperformed that based on ImageNet. Furthermore, the model’s performance was highest when fine-tuning the entire layer in the fine-tune mode. Additionally, the trained model was based on Gastro-BaseNet, which showed higher localization performance, which confirmed its accurate detection and classification of lesions in specific locations. This study represents a notable advancement in the development of image analysis models within the medical field, resulting in improved diagnostic predictive accuracy and aiding in making more informed clinical decisions in gastrointestinal endoscopy.

Otitis media with effusion (OME), primarily seen in children aged 2 years and younger, is characterized by the presence of fluid in the middle ear, often resulting in hearing loss and aural fullness. While deep learning networks have been explored to aid OME diagnosis, prior work did not often specify if pediatric images were used for training, causing uncertainties about their clinical relevance, especially due to important distinctions between the tympanic membranes of small children and adults. We trained cross-validated ResNet50, DenseNet201, InceptionV3, and InceptionResNetV2 models on 1150 pediatric tympanic membrane images from otoendoscopes to classify OME. When assessed using a separate dataset of 100 pediatric tympanic membrane images, the models achieved mean accuracies of 92.9% (ResNet50), 97.2% (DenseNet201), 96.0% (InceptionV3), and 94.8% (InceptionResNetV2), compared to the seven otolaryngologists that achieved accuracies between 84.0% and 69.0%. The results showed that even the worst-performing model trained on fold 3 of InceptionResNetV2 with an accuracy of 88.0% exceeded the accuracy of the highest-performing otolaryngologist at 84.0%. Our findings suggest that these specifically trained deep learning models can potentially enhance the clinical diagnosis of OME using pediatric otoendoscopic tympanic membrane images.

Abstract Pancreas segmentation is necessary for observing lesions, analyzing anatomical structures, and predicting patient prognosis. Therefore, various studies have designed segmentation models based on convolutional neural networks for pancreas segmentation. However, the deep learning approach is limited by a lack of data, and studies conducted on a large computed tomography dataset are scarce. Therefore, this study aims to perform deep-learning-based semantic segmentation on 1006 participants and evaluate the automatic segmentation performance of the pancreas via four individual three-dimensional segmentation networks. In this study, we performed internal validation with 1,006 patients and external validation using the cancer imaging archive pancreas dataset. We obtained mean precision, recall, and dice similarity coefficients of 0.869, 0.842, and 0.842, respectively, for internal validation via a relevant approach among the four deep learning networks. Using the external dataset, the deep learning network achieved mean precision, recall, and dice similarity coefficients of 0.779, 0.749, and 0.735, respectively. We expect that generalized deep-learning-based systems can assist clinical decisions by providing accurate pancreatic segmentation and quantitative information of the pancreas for abdominal computed tomography.

This study aimed to develop a convolutional neural network (CNN) using the EfficientNet algorithm for the automated classification of acute appendicitis, acute diverticulitis, and normal appendix and to evaluate its diagnostic performance. We retrospectively enrolled 715 patients who underwent contrast-enhanced abdominopelvic computed tomography (CT). Of these, 246 patients had acute appendicitis, 254 had acute diverticulitis, and 215 had normal appendix. Training, validation, and test data were obtained from 4,078 CT images (1,959 acute appendicitis, 823 acute diverticulitis, and 1,296 normal appendix cases) using both single and serial (RGB [red, green, blue]) image methods. We augmented the training dataset to avoid training disturbances caused by unbalanced CT datasets. For classification of the normal appendix, the RGB serial image method showed a slightly higher sensitivity (89.66 vs. 87.89%; p = 0.244), accuracy (93.62% vs. 92.35%), and specificity (95.47% vs. 94.43%) than did the single image method. For the classification of acute diverticulitis, the RGB serial image method also yielded a slightly higher sensitivity (83.35 vs. 80.44%; p = 0.019), accuracy (93.48% vs. 92.15%), and specificity (96.04% vs. 95.12%) than the single image method. Moreover, the mean areas under the receiver operating characteristic curve (AUCs) were significantly higher for acute appendicitis (0.951 vs. 0.937; p < 0.0001), acute diverticulitis (0.972 vs. 0.963; p = 0.0025), and normal appendix (0.979 vs. 0.972; p = 0.0101) with the RGB serial image method than those obtained by the single method for each condition. Thus, acute appendicitis, acute diverticulitis, and normal appendix could be accurately distinguished on CT images by our model, particularly when using the RGB serial image method.

Nontuberculous mycobacterial pulmonary diseases (NTM-PDs) are emerging as global health threats with issues of antibiotic resistance. Accumulating evidence suggests that the gut–lung axis may provide novel candidates for host-directed therapeutics against various infectious diseases. However, little is known about the gut–lung axis in the context of host protective immunity to identify new therapeutics for NTM-PDs. This study was performed to identify gut microbes and metabolites capable of conferring pulmonary immunity to NTM-PDs. Using metabolomics analysis of sera from NTM-PD patients and mouse models, we showed that the levels of l-arginine were decreased in sera from NTM-PD patients and NTM-infected mice. Oral administration of l-arginine significantly enhanced pulmonary antimicrobial activities with the expansion of IFN-γ-producing effector T cells and a shift to microbicidal (M1) macrophages in the lungs of NTM-PD model mice. Mice that received fecal microbiota transplants from l-arginine-treated mice showed increased protective host defense in the lungs against NTM-PD, whereas l-arginine-induced pulmonary host defense was attenuated in mice treated with antibiotics. Using 16S rRNA sequencing, we further showed that l-arginine administration resulted in enrichment of the gut microbiota composition with Bifidobacterium species. Notably, oral treatment with either Bifidobacterium pseudolongum or inosine enhanced antimicrobial pulmonary immune defense against NTM infection, even with multidrug-resistant clinical NTM strains. Our findings indicate that l-arginine-induced gut microbiota remodeling with enrichment of B. pseudolongum boosts pulmonary immune defense against NTM infection by driving the protective gut–lung axis in vivo.

Abstract Cervical cancer is the second most common cancer in women worldwide with a mortality rate of 60%. Cervical cancer begins with no overt signs and has a long latent period, making early detection through regular checkups vitally immportant. In this study, we compare the performance of two different models, machine learning and deep learning, for the purpose of identifying signs of cervical cancer using cervicography images. Using the deep learning model ResNet-50 and the machine learning models XGB, SVM, and RF, we classified 4119 Cervicography images as positive or negative for cervical cancer using square images in which the vaginal wall regions were removed. The machine learning models extracted 10 major features from a total of 300 features. All tests were validated by fivefold cross-validation and receiver operating characteristics (ROC) analysis yielded the following AUCs: ResNet-50 0.97(CI 95% 0.949–0.976), XGB 0.82(CI 95% 0.797–0.851), SVM 0.84(CI 95% 0.801–0.854), RF 0.79(CI 95% 0.804–0.856). The ResNet-50 model showed a 0.15 point improvement (p

Abstract Cold atmospheric plasma generates free radicals through the ionization of air at room temperature. Its effect and safety profile as a treatment modality for atopic dermatitis lesions have not been evaluated prospectively enough. We aimed to investigate the effect and safety of cold atmospheric plasma in patients with atopic dermatitis with a prospective pilot study. Cold atmospheric plasma treatment or sham control treatment were applied respectively in randomly assigned and symmetric skin lesions. Three treatment sessions were performed at weeks 0, 1, and 2. Clinical severity indices were assessed at weeks 0, 1, 2, and 4 after treatment. Additionally, the microbial characteristics of the lesions before and after treatments were analyzed. We included 22 patients with mild to moderate atopic dermatitis presented with symmetric lesions. We found that cold atmospheric plasma can alleviate the clinical severity of atopic dermatitis. Modified atopic dermatitis antecubital severity and eczema area and severity index score were significantly decreased in the treated group. Furthermore, scoring of atopic dermatitis score and pruritic visual analog scales significantly improved. Microbiome analysis revealed significantly reduced proportion of Staphylococcus aureus in the treated group. Cold atmospheric plasma can significantly improve mild and moderate atopic dermatitis without safety issues.

Abstract The vertebral compression is a significant factor for determining the prognosis of osteoporotic vertebral compression fractures and is generally measured manually by specialists. The consequent misdiagnosis or delayed diagnosis can be fatal for patients. In this study, we trained and evaluated the performance of a vertebral body segmentation model and a vertebral compression measurement model based on convolutional neural networks. For vertebral body segmentation, we used a recurrent residual U-Net model, with an average sensitivity of 0.934 (± 0.086), an average specificity of 0.997 (± 0.002), an average accuracy of 0.987 (± 0.005), and an average dice similarity coefficient of 0.923 (± 0.073). We then generated 1134 data points on the images of three vertebral bodies by labeling each segment of the segmented vertebral body. These were used in the vertebral compression measurement model based on linear regression and multi-scale residual dilated blocks. The model yielded an average mean absolute error of 2.637 (± 1.872) (%), an average mean square error of 13.985 (± 24.107) (%), and an average root mean square error of 3.739 (± 2.187) (%) in fractured vertebral body data. The proposed algorithm has significant potential for aiding the diagnosis of vertebral compression fractures.

Mycobacterial acyl carrier protein (AcpM; Rv2244), a key protein involved in Mycobacterium tuberculosis (Mtb) mycolic acid production, has been shown to suppress host cell death during mycobacterial infection. This study reports that mycobacterial AcpM works as an effector to subvert host defense and promote bacterial growth by increasing microRNA (miRNA)-155-5p expression. In murine bone marrow-derived macrophages (BMDMs), AcpM protein prevented transcription factor EB (TFEB) from translocating to the nucleus in BMDMs, which likely inhibited transcriptional activation of several autophagy and lysosomal genes. Although AcpM did not suppress autophagic flux in BMDMs, AcpM reduced Mtb and LAMP1 co-localization indicating that AcpM inhibits phagolysosomal fusion during Mtb infection. Mechanistically, AcpM boosted the Akt-mTOR pathway in BMDMs by upregulating miRNA-155-5p, a SHIP1-targeting miRNA. When miRNA-155-5p expression was inhibited in BMDMs, AcpM-induced increased intracellular survival of Mtb was suppressed. In addition, AcpM overexpression significantly reduced mycobacterial clearance in C3HeB/FeJ mice infected with recombinant M. smegmatis strains. Collectively, our findings point to AcpM as a novel mycobacterial effector to regulate antimicrobial host defense and a potential new therapeutic target for Mtb infection.

Abstract Background Skeletal muscle depletion (sarcopenia) is associated with poor prognosis in patients with lung cancer. We analyzed changes in skeletal muscle area using serial computed tomography (CT) until the death of patients with advanced squamous cell lung cancer (SQCLC). Methods This retrospective study comprised 70 consecutive patients who underwent palliative chemotherapy for SQCLC. The cross‐sectional area of the skeletal muscle at the level of the first lumbar vertebra (L1) was measured using chest CT. An artificial intelligence algorithm was developed and used for the serial assessment of the muscle area. Sarcopenia was defined as an L1 skeletal muscle index 3.24 cm2/month) had shorter overall survival than patients losing skeletal muscle slowly (median, 5.7 vs. 12.0 months, p

Abstract The habenula is one of the most important brain regions for investigating the etiology of psychiatric diseases such as major depressive disorder (MDD). However, the habenula is challenging to delineate with the naked human eye in brain imaging due to its low contrast and tiny size, and the manual segmentation results vary greatly depending on the observer. Therefore, there is a great need for automatic quantitative analytic methods of the habenula for psychiatric research purposes. Here we propose an automated segmentation and volume estimation method for the habenula in 7 Tesla magnetic resonance imaging based on a deep learning-based semantic segmentation network. The proposed method, using the data of 69 participants (33 patients with MDD and 36 normal controls), achieved an average precision, recall, and dice similarity coefficient of 0.869, 0.865, and 0.852, respectively, in the automated segmentation task. Moreover, the intra-class correlation coefficient reached 0.870 in the volume estimation task. This study demonstrates that this deep learning-based method can provide accurate and quantitative analytic results of the habenula. By providing rapid and quantitative information on the habenula, we expect our proposed method will aid future psychiatric disease studies.

Silwal, Kim et al. show that mitofusin-2 (MFN2), a mitochondrial fusion protein, promotes innate host defense through coordinated orchestration of immunometabolism and xenophagy via HIF-1α in macrophages during bacterial infection. This study provides insights into how mitochondria-shaping protein is involved in host defense against intracellular bacterial infection.

Abstract Background Annual influenza vaccination is an important public health measure to prevent influenza infections and is strongly recommended for cardiovascular disease (CVD) patients, especially in the current coronavirus disease 2019 (COVID-19) pandemic. The aim of this study is to develop a machine learning model to identify Korean adult CVD patients with low adherence to influenza vaccination Methods Adults with CVD (n = 815) from a nationally representative dataset of the Fifth Korea National Health and Nutrition Examination Survey (KNHANES V) were analyzed. Among these adults, 500 (61.4%) had answered "yes" to whether they had received seasonal influenza vaccinations in the past 12 months. The classification process was performed using the logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB) machine learning techniques. Because the Ministry of Health and Welfare in Korea offers free influenza immunization for the elderly, separate models were developed for the

Abstract While colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.

Purpose: To compare image resolution and depth between the microscope versus intracameral illumination images during 3D heads-up cataract surgery. Methods: We collected 25 consecutive patients who had cataract surgery using the 3D viewing system. Based on bright, contrast, visibility, and color balance, the digital images (RGB color and three monochromes) extracted at the same point of the procedures were compared between the two illuminations. Results: Contrast values of green and blue channels except for red channel and visibility values of all three channels were higher in the intracameral illumination images than in the microscope images (P < 0.001, t-test). Color balance values of both green/red and blue/red were higher in the intracameral illumination images than in the microscope images (P < 0.001, t-test). Conclusion: The digital images in the digitally assisted cataract surgery were enhanced by using the intracameral illumination. Considering the contrast and color balance in the 3D cataract surgery, the intracameral illumination may be better than the microscope illumination.

The global incidence of Mycobacterium abscessus (Mabc), a rapidly growing nontuberculous mycobacterial strain that causes treatment-refractory pulmonary diseases, is increasing. Despite this, the host factors that allow for protection against infection are largely unknown. In this study, we found that sirtuin 3 (SIRT3), a mitochondrial protein deacetylase, plays a critical role in host defense against Mabc infection. Mabc decreased SIRT3 and upregulated mitochondrial oxidative stress in macrophages. SIRT3 deficiency led to increased bacterial loads, histopathological, and mitochondrial damage, and pathological inflammation during Mabc infection. Administration of scavengers of mitochondrial reactive oxygen species significantly decreased the in vivo Mabc burden and excessive inflammation, and induced SIRT3 expression in infected lungs. Notably, SIRT3 agonist (resveratrol) significantly decreased Mabc growth and attenuated inflammation in mice and zebrafishes, indicating the key role for SIRT3 in metazoan host defense. Collectively, these data strongly suggest that SIRT3 is a host-directed therapeutic target against Mabc infection by controlling mitochondrial homeostasis.

Deep learning has recently become one of the most actively researched technologies in the field of medical imaging. The availability of sufficient data and the latest advances in algorithms are important factors that influence the development of deep learning models. However, several other factors should be considered in developing an optimal generalized deep learning model. All the steps, including data collection, labeling, and pre-processing and model training, validation, and complexity can affect the performance of deep learning models. Therefore, appropriate optimization methods should be considered for each step during the development of a deep learning model. In this review, we discuss the important factors to be considered for the optimal development of deep learning models.

Objectives Changes in the pancreatic volume (PV) are useful as potential clinical markers for some pancreatic-related diseases. The objective of this study was to measure the volume of the pancreas using computed tomography (CT) volumetry and to evaluate the relationships between sex, age, body mass index (BMI), and sarcopenia. Methods We retrospectively analyzed the abdominal CT scans of 1,003 subjects whose ages ranged between 10 and 90 years. The pancreas was segmented manually to define the region of interest (ROI) based on CT images, and then the PVs were measured by counting the voxels in all ROIs within the pancreas boundary. Sarcopenia was identified by examination of CT images that determined the cross-sectional area of the skeletal muscle around the third lumbar vertebra. Results The mean volume of the pancreas was 62.648 ± 19.094 cm3. The results indicated a negative correlation between the PV and age. There was a positive correlation between the PV and BMI for both sexes, females, and males (r = 0.343, p < 0.001; r = 0.461, p < 0.001; and r = 0.244, p < 0.001, respectively). Additionally, there was a positive correlation between the PV and sarcopenia for females (r = 0.253, p < 0.001) and males (r = 0.200, p < 0.001). Conclusions CT pancreas volumetry results may help physicians follow up or predict conditions of the pancreas after interventions for pancreatic-related disease in the future.

Purpose To evaluate a deep learning model to predict recurrence of thyroid tumor using preoperative ultrasonography (US). Materials and Methods We included representative images from 229 US-based patients (male:female = 42:187; mean age, 49.6 years) who had been diagnosed with thyroid cancer on preoperative US and subsequently underwent thyroid surgery. After selecting each representative transverse or longitudinal US image, we created a data set from the resulting database of 898 images after augmentation. The Python 2.7.6 and Keras 2.1.5 framework for neural networks were used for deep learning with a convolutional neural network. We compared the clinical and histological features between patients with and without recurrence. The predictive performance of the deep learning model between groups was evaluated using receiver operating characteristic (ROC) analysis, and the area under the ROC curve served as a summary of the prognostic performance of the deep learning model to predict recurrent thyroid cancer. Results Tumor recurrence was noted in 49 (21.4%) among the 229 patients. Tumor size and multifocality varied significantly between the groups with and without recurrence (p < 0.05). The overall mean area under the curve (AUC) value of the deep learning model for prediction of recurrent thyroid cancer was 0.9 ± 0.06. The mean AUC value was 0.87 ± 0.03 in macrocarcinoma and 0.79 ± 0.16 in microcarcinoma. Conclusion A deep learning model for analysis of US images of thyroid cancer showed the possibility of predicting recurrence of thyroid cancer.

Objectives Demand for hand sanitizers has surged since the coronavirus broke out and spread around the world. Hand sanitizers are usually applied by squirting the sanitizer liquid when one presses a pump with one’s hand. This causes many people to come into contact with the pump handle, which increases the risk of viral transmission. Some hand sanitizers on the market are automatically pumped. However, because sanitizer containers and pump devices are designed to be compatible only between products produced by the same manufacturer, consumers must also repurchase the container for the liquid if they replace the hand sanitizer. Therefore, this paper suggests the design of an automatic hand sanitizer system compatible with various sanitizer containers. Methods An automatic hand sanitizer system was designed, which will be presented in two stages describing the instrument structure and control parts. This work focused on using the elasticity of pumps and improving people’s access to devices. Results We have designed an automatic hand sanitizer system that is compatible with various containers. When one moves one’s hand close to the device sensor, the hand sanitizer container is pumped once. Conclusions The automatic hand sanitizer device proposed in this paper is ultimately expected to contribute to contactless hand disinfection in public places and virus infection prevention. Additionally, it is economical and eco-friendly by decreasing waste emissions.

Purpose This study was conducted to evaluate the diagnostic performance of machine learning in differentiating follicular adenoma from carcinoma using preoperative ultrasonography (US). Methods In this retrospective study, preoperative US images of 348 nodules from 340 patients were collected from two tertiary referral hospitals. Two experienced radiologists independently reviewed each image and categorized the nodules according to the 2015 American Thyroid Association guideline. Categorization of a nodule as highly suspicious was considered a positive diagnosis for malignancy. The nodules were manually segmented, and 96 radiomic features were extracted from each region of interest. Ten significant features were selected and used as final input variables in our in-house developed classifier models based on an artificial neural network (ANN) and support vector machine (SVM). The diagnostic performance of radiologists and both classifier models was calculated and compared. Results In total, 252 nodules from 245 patients were confirmed as follicular adenoma and 96 nodules from 95 patients were diagnosed as follicular carcinoma. As measures of diagnostic performance, the average sensitivity, specificity, and accuracy of the two experienced radiologists in discriminating follicular adenoma from carcinoma on preoperative US images were 24.0%, 84.0%, and 64.8%, respectively. The sensitivity, specificity, and accuracy of the ANN and SVM-based models were 32.3%, 90.1%, and 74.1% and 41.7%, 79.4%, and 69.0%, respectively. The kappa value of the two radiologists was 0.076, corresponding to slight agreement. Conclusion Machine learning-based classifier models may aid in discriminating follicular adenoma from carcinoma using preoperative US.

ObjectivesBack pain, especially lower back pain, is experienced in 60% to 80% of adults at some points during their lives. Various studies have found that lower back pain is a very common problem among adolescents, and the highest incidence rates are for adults in their 30s. There has been a remarkable increase in using computer-aided diagnosis to assist doctors in the interpretation of medical images. Spine segmentation in computed tomography (CT) scans using algorithmic methods allows improved diagnosis of back pain.MethodsIn this study, we developed a web-based automatic spine segmentation method using deep learning and obtained the dice coefficient by comparison with the predicted image. Our method is based on convolutional neural networks for segmentation. More specifically, we train a hierarchical data format file using U-Net architecture and then insert the test data label to perform segmentation. Thus, we obtained more specific and detailed results. A total of 344 CT images were used in the experiment. Of these, 330 were used for learning, and the remaining 14 for testing.ResultsOur method achieved an average dice coefficient of 90.4%, a precision of 96.81%, and an F1-score of 91.64%.ConclusionsThe proposed web-based deep learning approach can be very practical and accurate for spine segmentation as a diagnostic method.

The ability of Mycobacterium tuberculosis (Mtb) to persist in its host may enable an evolutionary advantage for drug resistant variants to emerge. A potential strategy to prevent persistence and gain drug efficacy is to directly target the activity of enzymes that are crucial for persistence. We present a method for expedited discovery and structure-based design of lead compounds by targeting the hypoxia-associated enzyme L-alanine dehydrogenase (AlaDH). Biochemical and structural analyses of AlaDH confirmed binding of nucleoside derivatives and showed a site adjacent to the nucleoside binding pocket that can confer specificity to putative inhibitors. Using a combination of dye-ligand affinity chromatography, enzyme kinetics and protein crystallographic studies, we show the development and validation of drug prototypes. Crystal structures of AlaDH-inhibitor complexes with variations at the N6 position of the adenyl-moiety of the inhibitor provide insight into the molecular basis for the specificity of these compounds. We describe a drug-designing pipeline that aims to block Mtb to proliferate upon re-oxygenation by specifically blocking NAD accessibility to AlaDH. The collective approach to drug discovery was further evaluated through in silico analyses providing additional insight into an efficient drug development strategy that can be further assessed with the incorporation of in vivo studies.

Background Although deep neural networks have shown promising results in the diagnosis of skin cancer, a prospective evaluation in a real-world setting could confirm these results. This study aimed to evaluate whether an algorithm (http://b2019.modelderm.com) improves the accuracy of nondermatologists in diagnosing skin neoplasms. Methods A total of 285 cases (random series) with skin neoplasms suspected of malignancy by either physicians or patients were recruited in two tertiary care centers located in South Korea. An artificial intelligence (AI) group (144 cases, mean [SD] age, 57.0 [17.7] years; 62 [43.1%] men) was diagnosed via routine examination with photographic review and assistance by the algorithm, whereas the control group (141 cases, mean [SD] age, 61.0 [15.3] years; 52 [36.9%] men) was diagnosed only via routine examination with a photographic review. The accuracy of the nondermatologists before and after the interventions was compared. Results Among the AI group, the accuracy of the first impression (Top-1 accuracy; 58.3%) after the assistance of AI was higher than that before the assistance (46.5%, P = .008). The number of differential diagnoses of the participants increased from 1.9 ± 0.5 to 2.2 ± 0.6 after the assistance (P < .001). In the control group, the difference in the Top-1 accuracy between before and after reviewing photographs was not significant (before, 46.1%; after, 51.8%; P = .19), and the number of differential diagnoses did not significantly increase (before, 2.0 ± 0.4; after, 2.1 ± 0.5; P = .57). Conclusions In real-world settings, AI augmented the diagnostic accuracy of trainee doctors. The limitation of this study is that the algorithm was tested only for Asians recruited from a single region. Additional international randomized controlled trials involving various ethnicities are required.

Purpose Lunit INSIGHT CXR (Lunit) is a commercially available deep-learning algorithm-based decision support system for chest radiography (CXR). This retrospective study aimed to evaluate the concordance rate of radiologists and Lunit for thoracic abnormalities in a multicenter health screening cohort. Methods and materials We retrospectively evaluated the radiology reports and Lunit results for CXR at several health screening centers in August 2020. Lunit was adopted as a clinical decision support system (CDSS) in routine clinical practice. Subsequently, radiologists completed their reports after reviewing the Lunit results. The DLA result was provided as a color map with an abnormality score (%) for thoracic lesions when the score was greater than the predefined cutoff value of 15%. Concordance was achieved when (a) the radiology reports were consistent with the DLA results (“accept”), (b) the radiology reports were partially consistent with the DLA results (“edit”) or had additional lesions compared with the DLA results (“add”). There was discordance when the DLA results were rejected in the radiology report. In addition, we compared the reading times before and after Lunit was introduced. Finally, we evaluated systemic usability scale questionnaire for radiologists and physicians who had experienced Lunit. Results Among 3,113 participants (1,157 men; mean age, 49 years), thoracic abnormalities were found in 343 (11.0%) based on the CXR radiology reports and 621 (20.1%) based on the Lunit results. The concordance rate was 86.8% (accept: 85.3%, edit: 0.9%, and add: 0.6%), and the discordance rate was 13.2%. Except for 479 cases (7.5%) for whom reading time data were unavailable (n = 5) or unreliable (n = 474), the median reading time increased after the clinical integration of Lunit (median, 19s vs. 14s, P < 0.001). Conclusion The real-world multicenter health screening cohort showed a high concordance of the chest X-ray report and the Lunit result under the clinical integration of the deep-learning solution. The reading time slight increased with the Lunit assistance.

BackgroundAlthough accurate treatment response assessment for brain metastases (BMs) is crucial, it is highly labor intensive. This retrospective study aimed to develop a computer-aided detection (CAD) system for automated BM detection and treatment response evaluation using deep learning.MethodsWe included 214 consecutive MRI examinations of 147 patients with BM obtained between January 2015 and August 2016. These were divided into the training (174 MR images from 127 patients) and test datasets according to temporal separation (temporal test set #1; 40 MR images from 20 patients). For external validation, 24 patients with BM and 11 patients without BM from other institutions were included (geographic test set). In addition, we included 12 MRIs from BM patients obtained between August 2017 and March 2020 (temporal test set #2). Detection sensitivity, dice similarity coefficient (DSC) for segmentation, and agreements in one-dimensional and volumetric Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria between CAD and radiologists were assessed.ResultsIn the temporal test set #1, the sensitivity was 75.1% (95% confidence interval [CI]: 69.6%, 79.9%), mean DSC was 0.69 ± 0.22, and false-positive (FP) rate per scan was 0.8 for BM ≥ 5 mm. Agreements in the RANO-BM criteria were moderate (κ, 0.52) and substantial (κ, 0.68) for one-dimensional and volumetric, respectively. In the geographic test set, sensitivity was 87.7% (95% CI: 77.2%, 94.5%), mean DSC was 0.68 ± 0.20, and FP rate per scan was 1.9 for BM ≥ 5 mm. In the temporal test set #2, sensitivity was 94.7% (95% CI: 74.0%, 99.9%), mean DSC was 0.82 ± 0.20, and FP per scan was 0.5 (6/12) for BM ≥ 5 mm.ConclusionsOur CAD showed potential for automated treatment response assessment of BM ≥ 5 mm.