Efficacy and safety of three-dimensional magnetically assisted capsule endoscopy for upper gastrointestinal and small bowel examination.

BACKGROUND: Magnetically assisted capsule endoscopy (MACE) showed the feasibility for upper gastrointestinal examination. To further enhance the performance of conventional MACE, it is necessary to provide quality-improved and three-dimensional images. The aim of this clinical study was to determine the efficacy and safety of novel three-dimensional MACE (3D MACE) for upper gastrointestinal and small bowel examination at once. METHODS: This was a prospective, single-center, non-randomized, and sequential examination study (KCT0007114) at Dongguk University Ilsan Hospital. Adult patients who visited for upper endoscopy were included. The study protocol was conducted in two stages. First, upper gastrointestinal examination was performed using 3D MACE, and a continuous small bowel examination was performed by conventional method of capsule endoscopy. Two hours later, an upper endoscopy was performed for comparison with 3D MACE examination. The primary outcome was confirmation of major gastric structures (esophagogastric junction, cardia/fundus, body, angle, antrum, and pylorus). Secondary outcomes were confirmation of esophagus and duodenal bulb, accuracy for gastric lesions, completion of small bowel examination, 3D image reconstruction of gastric lesion, and safety. RESULTS: Fifty-five patients were finally enrolled. The examination time of 3D MACE was 14.84 ± 3.02 minutes and upper endoscopy was 5.22 ± 2.39 minutes. The confirmation rate of the six major gastric structures was 98.6% in 3D MACE and 100% in upper endoscopy. Gastric lesions were identified in 43 patients during 3D MACE, and 40 patients during upper endoscopy (Sensitivity 0.97). 3D reconstructed images were acquired for all lesions inspected by 3D MACE. The continuous small bowel examination by 3D MACE was completed in 94.5%. 3D MACE showed better overall satisfaction (3D MACE 9.55 ± 0.79 and upper endoscopy 7.75 ± 2.34, p<0.0001). There were no aspiration or significant adverse event or capsule retention in the 3D MACE examination. CONCLUSIONS: Novel 3D MACE system is more advanced diagnostic modality than the conventional MACE. And it is possible to perform serial upper gastrointestinal and small bowel examination as a non-invasive and one-step test. It would be also served as a bridge to pan-endoscopy.

Transgelin-2, a novel cancer stem cell-related biomarker, is a diagnostic and therapeutic target for biliary tract cancer.

BACKGROUND: Biliary tract cancer (BTC) is a relatively rare but aggressive gastrointestinal cancer with a high mortality rate. Cancer stem cell (CSC) populations play crucial roles in tumor biology and are responsible for the low response to anti-cancer treatment and the high recurrence rate. This study investigated the role of Transgelin-2 (TAGLN2), overexpressed in CSC in BTC cells, and analyzed its expression in patient tissues and serum to identify potential new targets for BTC. METHODS: TAGLN2 expression was suppressed by small-interfering or short hairpin RNAs, and its effects on tumor biology were assessed in several BTC cell lines. Furthermore, the effects of TAGLN2 silencing on gemcitabine-resistant BTC cells, differentially expressed genes, proteins, and sensitivity to therapeutics or radiation were assessed. TAGLN2 expression was also assessed using western blotting and immunohistochemistry in samples obtained from patients with BTC to validate its clinical application. RESULTS: Suppression of TAGLN2 in BTC cell lines decreased cell proliferation, migration, invasion, and tumor size, in addition to a reduction in CSC features, including clonogenicity, radioresistance, and chemoresistance. TAGLN2 was highly expressed in BTC tissues, especially in cancer-associated fibroblasts in the stroma. Patients with a low stromal immunohistochemical index had prolonged disease-free survival compared to those with a high stromal immunohistochemical index (11.5 vs. 7.4 months, P = 0.013). TAGLN2 expression was higher in the plasma of patients with BTC than that in those with benign diseases. TAGLN2 had a higher area under the curve (0.901) than CA19-9, a validated tumor biomarker (0.799; P < 0.001). CONCLUSION: TAGLN2 plays a critical role in promoting BTC cell growth and motility and is involved in regulating BTC stemness. Silencing TAGLN2 expression enhanced cell sensitivity to radiation and chemotherapeutic drugs. The expression of TAGLN2 in patient tissue and plasma suggests its potential to serve as a secretory biomarker for BTC. Overall, targeting TAGLN2 could be an appropriate therapeutic strategy against advanced cancer following chemotherapy failure.

Automatic Classification of GI Organs in Wireless Capsule Endoscopy Using a No-Code Platform-Based Deep Learning Model.

The first step in reading a capsule endoscopy (CE) is determining the gastrointestinal (GI) organ. Because CE produces too many inappropriate and repetitive images, automatic organ classification cannot be directly applied to CE videos. In this study, we developed a deep learning algorithm to classify GI organs (the esophagus, stomach, small bowel, and colon) using a no-code platform, applied it to CE videos, and proposed a novel method to visualize the transitional area of each GI organ. We used training data (37,307 images from 24 CE videos) and test data (39,781 images from 30 CE videos) for model development. This model was validated using 100 CE videos that included "normal", "blood", "inflamed", "vascular", and "polypoid" lesions. Our model achieved an overall accuracy of 0.98, precision of 0.89, recall of 0.97, and F1 score of 0.92. When we validated this model relative to the 100 CE videos, it produced average accuracies for the esophagus, stomach, small bowel, and colon of 0.98, 0.96, 0.87, and 0.87, respectively. Increasing the AI score's cut-off improved most performance metrics in each organ (p < 0.05). To locate a transitional area, we visualized the predicted results over time, and setting the cut-off of the AI score to 99.9% resulted in a better intuitive presentation than the baseline. In conclusion, the GI organ classification AI model demonstrated high accuracy on CE videos. The transitional area could be more easily located by adjusting the cut-off of the AI score and visualization of its result over time.

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach.

Risk prediction requires comprehensive integration of clinical information and concurrent radiological findings. We present an upgraded chest radiograph (CXR) explainable artificial intelligence (xAI) model, which was trained on 241,723 well-annotated CXRs obtained prior to the onset of the COVID-19 pandemic. Mean area under the receiver operating characteristic curve (AUROC) for detection of 20 radiographic features was 0.955 (95% CI 0.938-0.955) on PA view and 0.909 (95% CI 0.890-0.925) on AP view. Coexistent and correlated radiographic findings are displayed in an interpretation table, and calibrated classifier confidence is displayed on an AI scoreboard. Retrieval of similar feature patches and comparable CXRs from a Model-Derived Atlas provides justification for model predictions. To demonstrate the feasibility of a fine-tuning approach for efficient and scalable development of xAI risk prediction models, we applied our CXR xAI model, in combination with clinical information, to predict oxygen requirement in COVID-19 patients. Prediction accuracy for high flow oxygen (HFO) and mechanical ventilation (MV) was 0.953 and 0.934 at 24 h and 0.932 and 0.836 at 72 h from the time of emergency department (ED) admission, respectively. Our CXR xAI model is auditable and captures key pathophysiological manifestations of cardiorespiratory diseases and cardiothoracic comorbidities. This model can be efficiently and broadly applied via a fine-tuning approach to provide fully automated risk and outcome predictions in various clinical scenarios in real-world practice.

Accurate auto-labeling of chest X-ray images based on quantitative similarity to an explainable AI model.

The inability to accurately, efficiently label large, open-access medical imaging datasets limits the widespread implementation of artificial intelligence models in healthcare. There have been few attempts, however, to automate the annotation of such public databases; one approach, for example, focused on labor-intensive, manual labeling of subsets of these datasets to be used to train new models. In this study, we describe a method for standardized, automated labeling based on similarity to a previously validated, explainable AI (xAI) model-derived-atlas, for which the user can specify a quantitative threshold for a desired level of accuracy (the probability-of-similarity, pSim metric). We show that our xAI model, by calculating the pSim values for each clinical output label based on comparison to its training-set derived reference atlas, can automatically label the external datasets to a user-selected, high level of accuracy, equaling or exceeding that of human experts. We additionally show that, by fine-tuning the original model using the automatically labelled exams for retraining, performance can be preserved or improved, resulting in a highly accurate, more generalized model.

MarkIt: A Collaborative Artificial Intelligence Annotation Platform Leveraging Blockchain For Medical Imaging Research.

Current research on medical image processing relies heavily on the amount and quality of input data. Specifically, supervised machine learning methods require well-annotated datasets. A lack of annotation tools limits the potential to achieve high-volume processing and scaled systems with a proper reward mechanism. We developed MarkIt, a web-based tool, for collaborative annotation of medical imaging data with artificial intelligence and blockchain technologies. Our platform handles both Digital Imaging and Communications in Medicine (DICOM) and non-DICOM images, and allows users to annotate them for classification and object detection tasks in an efficient manner. MarkIt can accelerate the annotation process and keep track of user activities to calculate a fair reward. A proof-of-concept experiment was conducted with three fellowship-trained radiologists, each of whom annotated 1,000 chest X-ray studies for multi-label classification. We calculated the inter-rater agreement and estimated the value of the dataset to distribute the reward for annotators using a crypto currency. We hypothesize that MarkIt allows the typically arduous annotation task to become more efficient. In addition, MarkIt can serve as a platform to evaluate the value of data and trade the annotation results in a more scalable manner in the future. The platform is publicly available for testing on https://markit.mgh.harvard.edu.

Early use of imipenem/cilastatin and vancomycin followed by de-escalation versus conventional antimicrobials without de-escalation for patients with hospital-acquired pneumonia in a medical ICU: a randomized clinical trial.

INTRODUCTION: Although early use of broad-spectrum antimicrobials in critically ill patients may increase antimicrobial adequacy, uncontrolled use of these agents may select for more-resistant organisms. This study investigated the effects of early use of broad-spectrum antimicrobials in critically ill patients with hospital-acquired pneumonia. METHODS: We compared the early use of broad-spectrum antimicrobials plus subsequent de-escalation (DE) with conventional antimicrobial treatment (non-de-escalation, NDE) in critically ill patients with hospital-acquired pneumonia (HAP). This open-label, randomized clinical trial was performed in patients in a tertiary-care center medical intensive care unit (MICU) in Korea. Patients (n=54) randomized to the DE group received initial imipenem/cilastatin plus vancomycin with subsequent de-escalation according to culture results, whereas patients randomized to the NDE group (n=55) received noncarbapenem, nonvancomycin empiric antimicrobials. RESULTS: Between November 2004 and October 2006, 109 MICU patients with HAP were enrolled. Initial antimicrobial adequacy was significantly higher in the DE than in the NDE group for Gram-positive organisms (100% versus 14.3%; P<0.001), but not for Gram-negative organisms (64.3% versus 85.7%; P=0.190). Mean intensive care unit (ICU) stay, and 14-day, 28-day, and overall mortality rates did not differ in the two groups. Among culture-positive patients, mortality from methicillin-resistant Staphylococcus aureus (MRSA) pneumonia was higher in the DE group, even after early administration of vancomycin. Multidrug-resistant organisms, especially MRSA, were more likely to emerge in the DE group (adjusted hazard ratio for emergence of MRSA, 3.84; 95% confidence interval, 1.06 to 13.91). CONCLUSIONS: The therapeutic advantage of early administration of broad-spectrum antimicrobials, especially with vancomycin, was not evident in this study.