Search

To evaluate the effect of the deep learning model reconstruction (DLM) method in terms of image quality and diagnostic agreement in low-dose computed tomography (LDCT) for interstitial lung disease (ILD), 193 patients who underwent LDCT for suspected ILD were retrospectively reviewed. Datasets were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction Veo (ASiR-V), and DLM. For image quality analysis, the signal, noise, signal-to-noise ratio (SNR), blind/referenceless image spatial quality evaluator (BRISQUE), and visual scoring were evaluated. Also, CT patterns of usual interstitial pneumonia (UIP) were classified according to the 2022 idiopathic pulmonary fibrosis (IPF) diagnostic criteria. The differences between CT images subjected to FBP, ASiR-V 30%, and DLM were evaluated. The image noise and BRISQUE scores of DLM images was lower and SNR was higher than that of the ASiR-V and FBP images (ASiR-V vs. DLM, p < 0.001 and FBP vs. DLR-M, p < 0.001, respectively). The agreement of the diagnostic categorization of IPF between the three reconstruction methods was almost perfect (κ  =  0.992, CI 0.990-0.994). Image quality was improved with DLM compared to ASiR-V and FBP., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Kim et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Dysarthria may present during the natural course of many degenerative neurological conditions. Hypokinetic and ataxic dysarthria are common in movement disorders and represent the underlying neuropathology. We developed an artificial intelligence (AI) model to distinguish ataxic dysarthria and hypokinetic dysarthria from normal speech and differentiate ataxic and hypokinetic speech in parkinsonian diseases and cerebellar ataxia. We screened 804 perceptual speech analyses performed in the Samsung Medical Center Neurology Department between January 2017 and December 2020. The data of patients diagnosed with parkinsonian disorders or cerebellar ataxia were included. Two speech tasks (numbering from 1 to 50 and reading nine sentences) were analyzed. We adopted convolutional neural networks and developed a patch-wise wave splitting and integrating AI system for audio classification (PWSI-AI-AC) to differentiate between ataxic and hypokinetic speech. Of the 395 speech recordings for the reading task, 76, 112, and 207 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. Of the 409 recordings of the numbering task, 82, 111, and 216 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. The reading and numbering task recordings were classified with 5-fold cross-validation using PWSI-AI-AC as follows: hypokinetic dysarthria vs. others (area under the curve: 0.92 ± 0.01 and 0.92 ± 0.02), ataxia vs. others (0.93 ± 0.04 and 0.89 ± 0.02), hypokinetic dysarthria vs. ataxia (0.96 ± 0.02 and 0.95 ± 0.01), hypokinetic dysarthria vs. none (0.86 ± 0.03 and 0.87 ± 0.05), and ataxia vs. none (0.87 ± 0.07 and 0.87 ± 0.09), respectively. PWSI-AI-AC showed reliable performance in differentiating ataxic and hypokinetic dysarthria and effectively augmented data to classify the types even with limited training samples. The proposed fully automatic AI system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases., Competing Interests: The authors have declared that no competing interests exist.

Background: This study aims to develop artificial intelligence (AI) system to automatically classify patients with maxillary sinus fungal ball (MFB), chronic rhinosinusitis (CRS), and healthy controls (HCs)., Methods: We collected 512 coronal image sets from ostiomeatal unit computed tomography (OMU CT) performed on subjects who visited a single tertiary hospital. These data included 254 MFB, 128 CRS, and 130 HC subjects and were used for training the proposed AI system. The AI system takes these 1024 sets of half CT images as input and classifies these as MFB, CRS, or HC. To optimize the classification performance, we adopted a 3-D convolutional neural network of ResNet 18. We also collected 64 coronal OMU CT image sets for external validation, including 26 MFB, 18 CRS, and 20 HCs from subjects from another referral hospital. Finally, the performance of the developed AI system was compared with that of the otolaryngology resident physicians., Results: Classification performance was evaluated using internal 5-fold cross-validation (818 training and 206 internal validation data) and external validation (128 data). The area under the receiver operating characteristic over the internal 5-fold cross-validation and the external validation was 0.96 ±0.006 and 0.97 ±0.006, respectively. The accuracy of the internal 5-fold cross-validation and the external validation was 87.5 ±2.3% and 88.4 ±3.1%, respectively. As a result of performing a classification test on external validation data from six otolaryngology resident physicians, the accuracy was obtained as 84.6 ±11.3%., Conclusions: This AI system is the first study to classify MFB, CRS, and HC using deep neural networks to the best of our knowledge. The proposed system is fully automatic but performs similarly to or better than otolaryngology resident physicians. Therefore, we believe that in regions where otolaryngology specialists are scarce, the proposed AI will perform sufficiently effective diagnosis on behalf of doctors., Competing Interests: The authors have declared that no competing interests exist.

Purpose: Early detection and classification of bone tumors in the proximal femur is crucial for their successful treatment. This study aimed to develop an artificial intelligence (AI) model to classify bone tumors in the proximal femur on plain radiographs., Methods: Standard anteroposterior hip radiographs were obtained from a single tertiary referral center. A total of 538 femoral images were set for the AI model training, including 94 with malignant, 120 with benign, and 324 without tumors. The image data were pre-processed to be optimized for training of the deep learning model. The state-of-the-art convolutional neural network (CNN) algorithms were applied to pre-processed images to perform three-label classification (benign, malignant, or no tumor) on each femur. The performance of the CNN model was verified using fivefold cross-validation and was compared against that of four human doctors., Results: The area under the receiver operating characteristic (AUROC) of the best performing CNN model for the three-label classification was 0.953 (95% confidence interval, 0.926-0.980). The diagnostic accuracy of the model (0.853) was significantly higher than that of the four doctors (0.794) (P = 0.001) and also that of each doctor individually (0.811, 0.796, 0.757, and 0.814, respectively) (P<0.05). The mean sensitivity, specificity, precision, and F1 score of the CNN models were 0.822, 0.912, 0.829, and 0.822, respectively, whereas the mean values of four doctors were 0.751, 0.889, 0.762, and 0.797, respectively., Conclusions: The AI-based model demonstrated high performance in classifying the presence of bone tumors in the proximal femur on plain radiographs. Our findings suggest that AI-based technology can potentially reduce the misdiagnosis of doctors who are not specialists in musculoskeletal oncology., Competing Interests: The authors have declared that no competing interests exist.

Constipation is a common condition that affects individuals of all ages, and prolonged constipation needs to be prevented to avoid potential complications and reduce the additional stress on individuals with pre-medical conditions. This study aimed to evaluate the effects of heat-inactivated Lactobacillus plantarum (HLp-nF1) on loperamide-induced constipation in rats. Constipation-induced male rats were treated orally with low to high doses of HLp-nF1 and an anti-constipation medication Dulcolax for five weeks. Study has 8 groups, control group; loperamide-treated group; Dulcolax-treated group; treatment with 3.2 × 1010, 8 × 1010 and 1.6 × 1011, cells/mL HLp-nF1; Loperamide + Dulcolax treated group. HLp-nF1 treated rats showed improvements in fecal pellet number, weight, water content, intestinal transit length, and contractility compared to the constipation-induced rats. Also, an increase in the intestine mucosal layer thickness and the number of mucin-producing crypt epithelial cells were observed in HLp-nF1-treated groups. Further, the levels of inflammatory cytokines levels were significantly downregulated by treatment with HLp-nF1 and Dulcolax. Notably, the metagenomics sequencing analysis demonstrated a similar genus pattern to the pre-preparation group and control with HLp-nF1 treatment. In conclusion, the administration of >3.2 × 1010 cells/mL HLp-nF1 has a positive impact on the constipated rats overall health., Competing Interests: The authors have read the journal’s policy and the authors of this manuscript have the following competing interests: IYK is a paid employee of Biogenics Korea. There are no patents, products in development or marketing products to declare. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

Background: Pancreatic pseudocysts (PC) and walled-off necrosis (WON) are common complications of severe pancreatitis. Endoscopic ultrasound (EUS)-guided drainage has replaced surgery as the standard treatment for PC/WON. We developed a novel lumen-apposing metal stent (LAMS) with an anti-reflux valve to prevent infectious complications caused by food reflux into the cyst cavity. This retrospective study investigated the efficacy and safety of EUS-guided drainage using this LAMS., Methods: We investigated and compared the treatment outcomes and complications rates between EUS-guided drainage using a novel LAMS (n = 10) versus plastic stents (n = 18) from December 2013 to October 2016. Technical success was defined as successful stent placement without immediate complications. Clinical success was defined as resolution of the PC/WON and disappearance of symptoms., Results: Among 10 patients in LAMS group, 4 patients had complicated PC and 6 patients had WON. In the plastic stent group, 15 and 3 patients had PC and WON, respectively. The median fluid collection size before treatment was 82.5 (interquartile range [IQR], 60.75-118.25) mm and 92.0 (IQR, 75.75-130.25) mm in the LAMS and plastic stent groups, respectively. There were no statistically significant differences in technical success rates (90% vs. 94.4%; p = 0.999), clinical success rates (80% vs. 77.8%; p = 0.999), and complication rates (20% vs. 27.8%; p = 0.999) between the two groups., Conclusions: Treatment outcomes of EUS-guided drainage using a novel LAMS were feasible despite the significantly high proportion of WON. The LAMS allowed acceptable treatment outcomes for EUS-guided drainage., Competing Interests: The authors have declared that no competing interests exist.

Acute pancreatitis is a common diagnosis worldwide, with gallstone disease being the most prevalent cause (50%). The American College of Gastroenterology recommends urgent endoscopic retrograde cholangiopancreatography (ERCP) (within 24 h) for patients with biliary pancreatitis accompanied by cholangitis. Most international guidelines recommend that ERCP be performed within 72 h in patients with biliary pancreatitis and a bile duct obstruction without cholangitis, but the optimal timing for endoscopy is controversial. We investigated the optimal timing for ERCP in patients with biliary pancreatitis and a bile duct obstruction without cholangitis, and whether performing endoscopy within 24 h is superior to performing it after 24 h. We analyzed the clinical data of 505 patients with newly diagnosed acute pancreatitis, from January 1, 2005 to December 31, 2014. We divided the patients into two groups according to the timing of ERCP: < 24 h (urgent) and 24-72 h (early).Among the 505 patients, 73 were diagnosed with biliary pancreatitis and a bile duct obstruction without cholangitis. The mean age of the patients was 55 years (range: 26-90 years). Bile duct stones and biliary sludge were identified on endoscopy in 45 (61.6%) and 11 (15.0%) patients, respectively. The timing of ERCP within 72 h was not associated with ERCP-related complications (P = 0.113), and the total length of hospital stay was not different between urgent and early ERCP (5.9 vs. 5.7 days, P = 0.174). No significant differences were found in total length of hospitalization or procedural-related complications, in patients with biliary pancreatitis and a bile duct obstruction without cholangitis, according to the timing of ERCP (< 24 h vs. 24-72 h).

Purpose: Several studies reported the increased risk of second primary pancreatic ductal adenocarcinoma (2nd PDAC) in cancer survivors. However, data on the characteristics of 2nd PDAC are insufficient., Methods: This retrospective cohort study included 1759 patients with PDAC. They were classified as having 2nd PDAC or first primary PDAC (1st PDAC) according to a prior diagnosed cancer of different origin, at least 6 months before PDAC diagnosis., Results: There were 110 patients (6.4%) with 2nd PDAC and 1606 (93.6%) patients with 1st PDAC. Patients with 2nd PDAC presented with older age (66.5 vs. 62.2 years, p < 0.001) and higher rate of resectability (26.4% vs. 15.9%, p = 0.004) at diagnosis than those with 1st PDAC. Multivariate analysis without considering resectable status showed that 2nd PDAC (hazard ratio [HR] 0.73, 95% confidence interval [CI] 0.56-0.94, p = 0.016) was associated with better overall survival. After adjusting for resectable status, however, 2nd PDAC (HR 0.85, 95% CI 0.66-1.09, p = 0.198) was no longer associated with overall survival. When subgroups were separately analyzed according to initial treatment modality, the effectiveness of surgery and chemotherapy were similar between 2nd and 1st PDAC (33.1 vs. 28.5 months, p = 0.860 and 10.8 vs. 10.7 months, p = 0.952)., Conclusions: The proportion of resectable cases was significantly higher in 2nd PDAC. When surgery with curative aim was possible, the overall survival was increased even in patients with 2nd PDAC. These results suggest the importance of screening for second primary cancer in cancer survivors.

Objective: To differentiate smoking-related interstitial fibrosis (SRIF) from usual interstitial pneumonia (UIP) with emphysema on CT in combined pulmonary fibrosis and emphysema (CPFE) patients., Materials and Methods: This study was approved by the institutional review board and informed consent was waived. We included 65 patients who underwent lung biopsy under the suspicion of UIP pattern on HRCT, and after radiologic-pathologic correlation, they were divided into three groups: UIP without emphysema (n = 30), UIP with emphysema (n = 26), and SRIF (n = 9). The quantitative extent of emphysema in the entire lung was visually assessed and fibrotic patterns were qualitatively analyzed based on six characteristics (asymmetry, juxta-subpleural sparing, emphysema beside the honeycombing area, absence of ground grass attenuation/reticulation in honeycombing area, inhomogeneous honeycombing, and absence of honeycombing in the upper lobes). Kaplan-Meier analysis was used for survival analysis, and logistic regression with a receiver operating characteristic curve was used to predict the possibility of SRIF., Results: In qualitative analysis of fibrotic patterns, SRIF tended to exhibit more than three of six fibrotic features, whereas UIP with emphysema demonstrated about two of these characteristics (p = 0.035). In addition, SRIF had a higher extent of emphysema than UIP with emphysema when they have same amount of fibrosis (p = 0.014). In patients with SRIF, 5-year survival rate was 85.7%, while it was 40.7% in UIP with emphysema patients (p = 0.035)., Conclusion: Fibrotic CT patterns and survival rate differed between SRIF and UIP with emphysema among CPFE patients, which explains the variable prognosis of CPFE., Competing Interests: The authors have declared that no competing interests exist.

Angiogenesis is the process of new blood vessel formation, and it plays a key role in various physiological and pathological conditions. The β2-glycoprotein I (β2-GPI) is a plasma glycoprotein with multiple biological functions, some of which remain to be elucidated. This study aimed to identify the contribution of 2-GPI on the angiogenesis induced by vascular endothelial growth factor (VEGF), a pro-angiogenic factor that may regulate endothelial remodeling, and its underlying mechanism. Our results revealed that β2-GPI dose-dependently decreased the VEGF-induced increase in endothelial cell proliferation, using the 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) and the bromodeoxyuridine (BrdU) incorporation assays. Furthermore, incubation with both β2-GPI and deglycosylated β2-GPI inhibited the VEGF-induced tube formation. Our results suggest that the carbohydrate residues of β2-GPI do not participate in the function of anti-angiogenesis. Using in vivo Matrigel plug and angioreactor assays, we show that β2-GPI remarkably inhibited the VEGF-induced angiogenesis at a physiological concentration. Moreover, β2-GPI inhibited the VEGF-induced phosphorylation of extracellular signal-regulated kinase 1/2 (ERK1/2), Akt, and endothelial nitric oxide synthase (eNOS). In summary, our in vitro and in vivo data reveal for the first time that β2-GPI inhibits the VEGF-induced angiogenesis and highlights the potential for β2-GPI in anti-angiogenic therapy., Competing Interests: The authors have declared that no competing interests exist.

Background and Aims: Although thicker needles theoretically allow more tissue to be collected, their decreased flexibility can cause mechanical damage to the endoscope, technical failure, and sample blood contamination. The effects of needle gauge on diagnostic outcomes of endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) of pancreatic mass lesions remain unknown. This study compared procurement rates of histologic cores obtained from EUS-FNB of pancreatic masses using 25- and 22-gauge core biopsy needles., Patients and Methods: From March 2014 to July 2014, 66 patients with solid pancreatic mass underwent EUS-FNB with both 25- and 22-gauge core biopsy needles. Among them, 10 patients were excluded and thus 56 patients were eligible for the analyses. Needle sequences were randomly assigned, and two passes were made with each needle, consisting of 10 uniform to-and-fro movements on each pass with 10 mL syringe suction. A pathologist blinded to needle sequence evaluated specimens for the presence of histologic core., Results: The mean patient age was 65.8 ± 9.5 years (range, 44-89 years); 35 patients (62.5%) were men. The mean pancreatic mass size was 35.3 ± 17.1 mm (range 14-122.3 mm). Twenty-eight patients (50%) had tumors at the pancreas head or uncinate process. There were no significant differences in procurement rates of histologic cores between 25-gauge (49/56, 87.5%) and 22-gauge (46/56, 82.1%, P = 0.581) needles or diagnostic accuracy using only histologic cores (98% and 95%). There were no technical failures or procedure-related adverse events., Conclusions: The 25-gauge core biopsy needle could offer acceptable and comparable outcomes regarding diagnostic performance including histologic core procurement rates compared to the 22-gauge core biopsy needle, although the differences were not statistically significant., Trial Registration: ClinicalTrials.gov NCT01795066.

A fundamental challenge in robotics today is building robots that can learn new skills by observing humans and imitating human actions. We propose a new Bayesian approach to robotic learning by imitation inspired by the developmental hypothesis that children use self-experience to bootstrap the process of intention recognition and goal-based imitation. Our approach allows an autonomous agent to: (i) learn probabilistic models of actions through self-discovery and experience, (ii) utilize these learned models for inferring the goals of human actions, and (iii) perform goal-based imitation for robotic learning and human-robot collaboration. Such an approach allows a robot to leverage its increasing repertoire of learned behaviors to interpret increasingly complex human actions and use the inferred goals for imitation, even when the robot has very different actuators from humans. We demonstrate our approach using two different scenarios: (i) a simulated robot that learns human-like gaze following behavior, and (ii) a robot that learns to imitate human actions in a tabletop organization task. In both cases, the agent learns a probabilistic model of its own actions, and uses this model for goal inference and goal-based imitation. We also show that the robotic agent can use its probabilistic model to seek human assistance when it recognizes that its inferred actions are too uncertain, risky, or impossible to perform, thereby opening the door to human-robot collaboration.

The clinical significance of Mycobacterium kansasii respiratory isolates is uncertain. The aims of this study were to determine the clinical relevance of M. kansasii isolates and to identify the clinical features and outcomes of M. kansasii lung disease. We reviewed the medical records of 104 patients from whom at least one respiratory M. kansasii isolate was obtained from January 2003 to July 2014 at Samsung Medical Center, South Korea. Of these 104 patients, 54 (52%) met the diagnostic criteria for nontuberculous mycobacterial lung disease; among them, 41 (76%) patients received antibiotic treatment for a median time of 15.0 months (interquartile range [IQR], 7.0-18.0 months). The remaining 13 (24%) without overt disease progression were observed for a median period of 24.0 months (IQR, 5.0-34.5 months). Patients with M. kansasii lung disease exhibited various radiographic findings of lung disease, including the fibrocavitary form (n = 24, 44%), the nodular bronchiectatic form (n = 17, 32%), and an unclassifiable form (n = 13, 24%). The fibrocavitary form was more common in patients who received treatment (n = 23, 56%), while the nodular bronchiectatic form was more common in patients with M. kansasii lung disease who did not receive treatment (n = 9, 70%). None of the patients with a single sputum isolate (n = 18) developed M. kansasii disease over a median follow-up period of 12.0 months (IQR, 4.0-26.5 months). In total, 52% of all patients with M. kansasii respiratory isolates exhibited clinically significant disease. Moreover, patients with M. kansasii lung disease displayed diverse radiographic findings in addition to the fibrocavitary form. The nodular bronchiectatic form was more common in patients with M. kansasii lung disease with an indolent clinical course. Thus, since the clinical significance of a single M. kansasii respiratory isolate is not definite, strict adherence to recommended diagnostic criteria is advised.

Background: The importance of providing effective analgesia during sedation for complex endoscopic procedures has been widely recognized. However, repeated administration of opioids in order to achieve sufficient analgesia may carry the risk of delayed recovery after propofol based sedation. This study was done to compare recovery profiles and the satisfaction of the endoscopists and patients between conventional balanced propofol sedation and analgesia-oriented combination sedation for patients undergoing endoscopic retrograde cholangiopancreatography (ERCP)., Methods: Two hundred and two adult patients scheduled for ERCP were sedated by either the Conventional (initial bolus of meperidine with propofol infusion) or Combination (repeated bolus doses of fentanyl with propofol infusion) method. Recovery profiles, satisfaction levels of the endoscopists and patients, drug requirements and complications were compared between groups., Results: Patients of the Combination Group required significantly less propofol compared to the Conventional Group (135.0 ± 68.8 mg vs. 165.3 ± 81.7 mg, P = 0.005). Modified Aldrete scores were not different between groups throughout the recovery period, and recovery times were also comparable between groups. Satisfaction scores were not different between the two groups in both the endoscopists and patients (P = 0.868 and 0.890, respectively)., Conclusions: Considering the significant reduction in propofol dose, the non-inferiority of recovery profiles and satisfaction scores of the endoscopists and patients, analgesia oriented combination sedation may be a more safe yet effective sedative method compared to conventional balanced propofol sedation during ERCP.

Recently, the possibility of PD1 pathway-targeted therapy has been extensively studied in various human malignant tumors. However, no previous study has investigated their potential application for soft-tissue sarcomas (STS). In this study, we evaluated the clinical impact of intra-tumoral infiltration of PD1-positive lymphocytes and PD-L1 expression in tumor cells in 105 cases of STS. Intra-tumoral infiltration of PD1-positive lymphocytes and PD-L1 expression were seen in 65% and 58% of STS, respectively. Both PD1-positivity and PD-L1 expression were significantly associated with advanced clinicopathological parameters such as higher clinical stage, presence of distant metastasis, higher histological grade, poor differentiation of tumor, and tumor necrosis. Moreover, both PD1-positivity and PD-L1 positivity were independent prognostic indicators of overall survival (OS) and event-free survival (EFS) of STS by multivariate analysis. In addition, the combined pattern of PD1- and PD-L1-positivity was also an independent prognostic indicator for OS and EFS by multivariate analysis. The patents with a PD1(+)/PD-L1(+) pattern had the shortest survival time. In conclusion, this study is the first to demonstrate that the infiltration of PD1 positive lymphocytes and PD-L1 expression in STS cells could be used as novel prognostic indicators for STS. Moreover, the evaluation of PD1- and PD-L1-positivity in STS is also available as possible criteria for selection of patients suitable for PD1-based immunotherapy.

Unlabelled: Recently, the roles of SIRT1 and deleted in breast cancer 1 (DBC1) in human cancer have been extensively studied and it has been demonstrated that they are involved in many human carcinomas. However, their clinical significance for soft-tissue sarcomas has not been examined. In this study, we evaluated the expression and prognostic significance of the expression of SIRT1, DBC1, P53, β-catenin, cyclin D1, and KI67 in 104 cases of soft-tissue sarcomas., Results: Immunohistochemical expression of SIRT1, DBC1, P53, β-catenin, and cyclin D1 were seen in 71%, 74%, 53%, 48%, and 73% of sarcomas, respectively. The expression of SIRT1, DBC1, P53, β-catenin, and cyclin D1 were significantly correlated with advanced clinicopathological parameters such as higher clinical stage, higher histological grade, increased mitotic counts, and distant metastasis. The expression of SIRT1, DBC1, P53, β-catenin, cyclin D1, and KI67 were significantly correlated with each other and positive expression of all of these predicted shorter overall survival and event-free survival by univariate analysis. Multivariate analysis revealed the expression of SIRT1 as an independent prognostic indicator for overall survival and event-free survival of sarcoma patients. In conclusion, this study demonstrates that SIRT1- and DBC1-related pathways may be involved in the progression of soft-tissue sarcomas and can be used as clinically significant prognostic indicators for sarcoma patients. Moreover, the SIRT1- and DBC1-related pathways could be new therapeutic targets for the treatment of sarcomas.