The association between different physical activity (PA) patterns and cardiometabolic index (CMI) in US adult population from NHANES (2007-2016).

Background: Physical activity (PA) is widely recommended for preventing and combating obesity, but the most effective PA pattern for treating obesity remains unclear. Cardiometabolic index (CMI), derived from waist height ratio and triglycerides to high-density lipoprotein-cholesterol ratio, is a novel indicator for evaluating obesity. However, the relationship between different PA patterns and CMI remains unelucidated. Objective: This study aimed to explore the association between different PA patterns and CMI in U.S. adults. Methods: Participants with complete information in CMI, PA patterns, and other covariates in the National Health and Nutrition Examination Survey database (2007-2016) were included in this study. Multivariate linear regression models were utilized to explore the relationship between PA patterns and CMI. Moreover, stratified analyses, interaction tests and restricted cubic spline (RCS) regression analysis were used to investigate the stability and nonlinearity of the association, respectively. Results: A total of 16,442 adults were included in this study. After adjusting for all potential covariates, only the regularly active group was significantly associated with CMI reduction (ß = -0.13, 95% CI: 0.19 to -0.07, P < 0.0001), while the weekend warriors group did not achieve equivalent CMI reduction (ß = -0.09, 95% CI: 0.32 to 0.14, P = 0.4204). Subgroup analyses and interaction tests revealed that the CMI-PA association was more pronounced in the subgroup with age≤45 or >60, with higher education level, and who are current drinkers. Furthermore, RCS analysis indicated that total PA in a week was significantly, nonlinearly associated with CMI in non-inactive adults, and that a total of PA more than 330 min can reap favorable CMI reduction. Conclusion: Being regularly active is associated with significant CMI reduction, while being weekend warriors and insufficiently active do not achieve equivalent benefits. For non-inactive individuals, engaging in PA for more than 330 min weekly helps to reduce CMI effectively.

The effect of incorporating domain knowledge with deep learning in identifying benign and malignant gastric whitish lesions: A retrospective study.

BACKGROUND AND AIM: Early whitish gastric neoplasms can be easily misdiagnosed; differential diagnosis of gastric whitish lesions remains a challenge. We aim to build a deep learning (DL) model to diagnose whitish gastric neoplasms and explore the effect of adding domain knowledge in model construction. METHODS: We collected 4558 images from two institutions to train and test models. We first developed two sole DL models (1 and 2) using supervised and semi-supervised algorithms. Then we selected diagnosis-related features through literature research and developed feature-extraction models to determine features including boundary, surface, roundness, depression, and location. Then predictions of the five feature-extraction models and sole DL model were combined and inputted into seven machine-learning (ML) based fitting-diagnosis models. The optimal model was selected as ENDOANGEL-WD (whitish-diagnosis) and compared with endoscopists. RESULTS: Sole DL 2 had higher sensitivity (83.12% vs 68.67%, Bonferroni adjusted P = 0.024) than sole DL 1. Adding domain knowledge, the decision tree performed best among the seven ML models, achieving higher specificity than DL 1 (84.38% vs 72.27%, Bonferroni adjusted P < 0.05) and higher accuracy than DL 2 (80.47%, Bonferroni adjusted P < 0.001) and was selected as ENDOANGEL-WD. ENDOANGEL-WD showed better accuracy compared with 10 endoscopists (75.70%, P < 0.001). CONCLUSIONS: We developed a novel system ENDOANGEL-WD combining domain knowledge and traditional DL to detect gastric whitish neoplasms. Adding domain knowledge improved the performance of traditional DL, which provided a novel solution for establishing diagnostic models for other rare diseases potentially.

Discovery of sesquiterpene from Youngia japonica with antitumor effect.

Fourteen sesquiterpenes, including one undescribed sesquiterpene lactone, were isolated from Youngia japonica, and their structures were identified by NMR, HRESIMS, ECD and calculated ECD. Cytotoxic activities of all isolates against A549, HeLa, and 4 T1 cell lines were detected by CCK8 assay. Among them, 2 showed obvious cytotoxic activity against A549 cells. Subsequently, the production of ROS, and apoptosis of A549 cells treated with 2 were evaluated. The result showed that 2 distinctly increased the ROS level, and induced the apoptosis of A549 cells. Further anticancer mechanism studies showed that 2 increased the expression of cleaved caspase 3. Taken together, our results demonstrated that 2 might become potential leading compounds for the treatment of lung cancer.

An artificial intelligence system for chronic atrophic gastritis diagnosis and risk stratification under white light endoscopy.

BACKGROUND AND AIMS: The diagnosis and stratification of gastric atrophy (GA) predict patients' gastric cancer progression risk and determine endoscopy surveillance interval. We aimed to construct an artificial intelligence (AI) system for GA endoscopic identification and risk stratification based on the Kimura-Takemoto classification. METHODS: We constructed the system using two trained models and verified its performance. First, we retrospectively collected 869 images and 119 videos to compare its performance with that of endoscopists in identifying GA. Then, we included original image cases of 102 patients to validate the system for stratifying GA and comparing it with endoscopists with different experiences. RESULTS: The sensitivity of model 1 was higher than that of endoscopists (92.72% vs. 76.85 %) at image level and also higher than that of experts (94.87% vs. 85.90 %) at video level. The system outperformed experts in stratifying GA (overall accuracy: 81.37 %, 73.04 %, p = 0.045). The accuracy of this system in classifying non-GA, mild GA, moderate GA, and severe GA was 80.00 %, 77.42 %, 83.33 %, and 85.71 %, comparable to that of experts and better than that of seniors and novices. CONCLUSIONS: We established an expert-level system for GA endoscopic identification and risk stratification. It has great potential for endoscopic assessment and surveillance determinations.

A newly developed deep learning-based system for automatic detection and classification of small bowel lesions during double-balloon enteroscopy examination.

BACKGROUND: Double-balloon enteroscopy (DBE) is a standard method for diagnosing and treating small bowel disease. However, DBE may yield false-negative results due to oversight or inexperience. We aim to develop a computer-aided diagnostic (CAD) system for the automatic detection and classification of small bowel abnormalities in DBE. DESIGN AND METHODS: A total of 5201 images were collected from Renmin Hospital of Wuhan University to construct a detection model for localizing lesions during DBE, and 3021 images were collected to construct a classification model for classifying lesions into four classes, protruding lesion, diverticulum, erosion & ulcer and angioectasia. The performance of the two models was evaluated using 1318 normal images and 915 abnormal images and 65 videos from independent patients and then compared with that of 8 endoscopists. The standard answer was the expert consensus. RESULTS: For the image test set, the detection model achieved a sensitivity of 92% (843/915) and an area under the curve (AUC) of 0.947, and the classification model achieved an accuracy of 86%. For the video test set, the accuracy of the system was significantly better than that of the endoscopists (85% vs. 77 ± 6%, p < 0.01). For the video test set, the proposed system was superior to novices and comparable to experts. CONCLUSIONS: We established a real-time CAD system for detecting and classifying small bowel lesions in DBE with favourable performance. ENDOANGEL-DBE has the potential to help endoscopists, especially novices, in clinical practice and may reduce the miss rate of small bowel lesions.

A randomized controlled trial of standard vs customized graduated elastic compression stockings in patients with chronic venous disease.

OBJECTIVE: This study aimed to compare the efficacy of customized graduated elastic compression stockings (c-GECSs) based on lower leg parameter models with standard GECSs (s-GECSs) in patients with chronic venous disease (CVD). METHODS: In this randomized, single-blind, controlled trial, 79 patients with stage C2 or C3 CVD were assigned to one of two groups: c-GECSs or s-GECSs. The primary outcome was change to Venous Insufficiency Epidemiological and Economic Study Quality of Life (VEINES-QOL) scores at months 1, 3, and 6 as compared with baseline. Secondary outcomes included compliance with wearing ECSs, interface pressure at the smallest circumference of the ankle (point B) and the largest circumference of the calf (point C), and calf volume (CV). RESULTS: There were 13 pairs of s-GECS and 2 pairs of c-GECS that showed pressure values higher than the standard at either point B or C. The c-GECSs were significantly superior to s-GECSs in terms of score improvement at all three time points (month 1, 8.47 [95% confidence interval (CI), 7.47-9.45] vs 5.89 [95% CI, 5.00-6.78]; month 3, 9.60 [95% CI, 8.47-10.72] vs 6.72 [95% CI, 5.62-7.83]; month 6, 7.09 [95% CI, 5.93-8.24] vs 3.92 [95% CI, 2.67-5.18]; P < .0001). Besides, at month 1, the mean daily use time of the c-GECS and s-GECS groups was 10.7 and 9.5 hours, respectively (P < .05). Correlation analysis indicated a negative relationship between local high pressure and daily duration in the s-GECS group (rpb = -0.388; n = 38; P < .05). Variances in pressure were greater in the s-GECSs group. The c-GECSs showed advantage in maintaining pressure. Both c-GECSs and s-GECSs effectively reduced CV (mL), with no significant differences between groups (month 1, 90.0 [95% CI, 71.4-108.5] vs 85.0 [95% CI, 65.6-104.2]; month 3, 93.8 [95% CI, 69.7-117.8] vs 85.9 [95% CI, 65.5-106.2]; month 6, 70.8 [95% CI, 46.5-95.2]) vs 60.8 [95% CI, 44.1-77.5]). CONCLUSIONS: The c-GECSs based on individual leg parameter models significantly improved VEINES-QOL scores and provided stable and enduring pressure as compared with s-GECSs for patients with stage C2 or C3 CVD. Although both c-GECSs and s-GECSs effectively reduced CV, the superior fit and comfort of c-GECSs improved patient compliance. Hence, c-GECSs are a viable alternative for patients who have difficulty tolerating s-GECSs.

Glioblastoma behavior study under different frequency electromagnetic field.

The tumor-treating fields (TTFields) technology has revolutionized the management of recurrent and newly diagnosed glioblastoma (GBM) cases. To ameliorate this treatment modality for GBM and other oncological conditions, it is necessary to understand the biophysical principles of TTFields better. In this study, we further analyzed the mechanism of the electromagnetic exposure with varying frequencies and electric field strengths on cells in mitosis, specifically in telophase. In reference to previous studies, an intuitive finite element model of the mitotic cell was built for electromagnetic simulations, predicting a local increase in the cleavage furrow region, which may help explain TTFields' anti-proliferative effects. Cell experiments confirmed that the reduction in proliferation and migration of glioma cell by TTFields was in a frequency- and field-strength-dependent manner. This work provides unique insights into the selection of frequencies in the anti-proliferative effect of TTFields on tumors, which could improve the application of TTFields.

A case report of dermatomyositis mimicking myasthenia gravis.

RATIONALE: Patients who have myasthenia gravis or dermatomyositis show clinical signs of muscular weakening. Ocular muscle involvement is uncommon, and symmetrical proximal limb weakness is the typical presentation of dermatomyositis. However, the earliest and most noticeable sign in those with myasthenia gravis is extraocular muscular paralysis. Dermatomyositis is frequently complicated by malignancy, and the common malignancies associated with dermatomyositis vary by region and ethnicity, while thymoma is relatively rare. About 10% to 15% of people with myasthenia gravis have thymoma, which is involved in the etiology of the disease. PATIENT CONCERNS: A 68-year-old female presented with ocular muscle weakness for 10 days that manifested as bilateral blepharoptosis with the phenomenon of "light in the morning and heavy in the evening." Imaging examination showed anterior mediastinal thymic tumor with metastasis. DIAGNOSES: After a thorough physical examination, we discovered bilateral upper limbs with grade IV muscle strength and the typical rash of dermatomyositis. In combination with elevated serum kinase levels and electromyography suggesting myogenic damage, the patient was finally diagnosed as dermatomyositis with multiple metastases of thymoma. INTERVENTIONS: The patient received oral hydroxychloroquine sulfate, topical corticosteroids, and tacrolimus ointment, but these did not work very well. Subsequently, the patient underwent surgery combined with radiotherapy for the thymoma. OUTCOMES: Muscle weakness in the patient improved after effective treatment of tumor, and the rash mostly disappeared. CONCLUSION: Ocular muscle weakness and thymoma are more common in myasthenia gravis, but we cannot ignore the possibility of dermatomyositis. To further establish the diagnosis, a thorough physical examination and laboratory findings are required. Further tumor screening should be performed for patients with dermatomyositis. Early detection and management of possible tumors are essential to the treatment of dermatomyositis linked to malignancies.

[Imaging findings of carcinoma ex pleomorphic adenoma in minor salivary glands].

PURPOSE: To summarize the CT and MR imaging features of carcinoma ex pleomorphic adenoma(Ca-ex-PA) in minor salivary gland, and analyze the correlation between various features and pathological classification. METHODS: Forty-three patients with Ca-ex-PA in minor salivary gland were collected. The CT and MRI findings were retrospectively analyzed and correlated with their pathological types. Fisher's exact test was used to analyze the correlation between various imaging features (tumor morphology, boundary, internal structure, bone invasion, cervical lymph node metastasis) and pathological types with SPSS 25.0 software package. RESULTS: Among the 43 patients with Ca-ex-PA, 83.7%(36/43) of the tumors were lobulated; 81.4%(35/43) showed cystic degeneration or necrosis, with heterogeneous enhancement. Coarse calcification or mixed calcification was found in 37.2%(16/43), 25.6%(11/43) had compressive absorption of adjacent bone. 75%(12/16) of type Ⅰ/Ⅱ tumors had regular morphology (round or oval), and 77.8%(21/27) of type Ⅲ tumors had irregular morphology, 93.8%(15/16) of type Ⅰ/Ⅱ tumors had well-defined margin and 66.7%(18/27) of type Ⅲ tumors had ill-defined margin. Osteolytic bone resorption occurred in 59.3%(16/27) of type Ⅲ tumors. The average maximum diameter of type Ⅰ/Ⅱ tumors was significantly shorter than that of type Ⅲ(P＜0.05). Fisher's exact test showed the characteristics of tumor morphology, boundary and osteolytic bone resorption were related to pathological grouping(P＜0.001). CONCLUSIONS: Most Ca-ex-PA in minor salivary glands is characterized by lobular and heterogeneous enhanced neoplasm on CT and MR imaging. A round or oval tumor with well-defined margin usually correlates with typeⅠ and Ⅱ, contrarily, an irregular mass with ill-defined margin and osteolytic bone destruction usually correlates with type Ⅲ. Combining the three characteristics of morphology, boundary and osteolysis is more helpful to distinguish type Ⅰ/Ⅱ and type Ⅲ tumors.

Development and Evaluation of a Surveillance System for Follow-Up After Colorectal Polypectomy.

Importance: The adherence of physicians and patients to published colorectal postpolypectomy surveillance guidelines varies greatly, and patient follow-up is critical but time consuming. Objectives: To evaluate the accuracy of an automatic surveillance (AS) system in identifying patients after polypectomy, assigning surveillance intervals for different risks of patients, and proactively following up with patients on time. Design, Setting, and Participants: In this diagnostic/prognostic study, endoscopic and pathological reports of 47 544 patients undergoing colonoscopy at 3 hospitals between January 1, 2017, and June 30, 2022, were collected to develop an AS system based on natural language processing. The performance of the AS system was fully evaluated in internal and external tests according to 5 guidelines worldwide and compared with that of physicians. A multireader, multicase (MRMC) trial was conducted to evaluate use of the AS system and physician guideline adherence, and prospective data were collected to evaluate the success rate in contacting patients and the association with reduced human workload. Data analysis was conducted from July to September 2022. Exposures: Assistance of the AS system. Main Outcomes and Measures: The accuracy of the system in identifying patients after polypectomy, stratifying patient risk levels, and assigning surveillance intervals in internal (Renmin Hospital of Wuhan University), external 1 (Wenzhou Central Hospital), and external 2 (The First People's Hospital of Yichang) test sets; the accuracy of physicians and their time burden with and without system assistance; and the rate of successfully informed patients of the system were evaluated. Results: Test sets for 16 106 patients undergoing colonoscopy (mean [SD] age, 51.90 [13.40] years; 7690 females [47.75%]) were evaluated. In internal, external 1, and external 2 test sets, the system had an overall accuracy of 99.91% (95% CI, 99.83%-99.95%), 99.54% (95% CI, 99.30%-99.70%), and 99.77% (95% CI, 99.41%-99.91%), respectively, for identifying types of patients and achieved an overall accuracy of at least 99.30% (95% CI, 98.67%-99.63%) in the internal test set, 98.89% (95% CI, 98.33%-99.27%) in external test set 1, and 98.56% (95% CI, 95.86%-99.51%) in external test set 2 for stratifying patient risk levels and assigning surveillance intervals according to 5 guidelines. The system was associated with increased mean (SD) accuracy among physicians vs no AS system in 105 patients (98.67% [1.28%] vs 78.10% [18.01%]; P = .04) in the MRMC trial. In a prospective trial, the AS system successfully informed 82 of 88 patients (93.18%) and was associated with reduced burden of follow-up time vs no AS system (0 vs 2.86 h). Conclusions and Relevance: This study found that an AS system was associated with improved adherence to guidelines among physicians and reduced workload among physicians and nurses.

Associated factors with stimulation induced seizures and the relevance with surgical outcomes.

OBJECTIVE: To analyze the associated factors with stimulation-induced seizures (SIS) and the relevant factors in predicting surgical outcomes. METHODS: We analyzed 80 consecutive epilepsy patients explored by stereo-electroencephalography with routine electrical stimulation mapping (ESM). If seizures induced by ESM, patients were classified as SIS-positive (SIS-P); otherwise, SIS-negative (SIS-N). Patients received radical surgery were further classified as favorable (Engel I) and unfavorable (Engel II-IV) groups. RESULTS: Of the 80 patients included, we identified 44 (55.0%) and 36(45.0%) patients in the SIS-P and SIS-N groups, respectively. Multivariate analysis revealed that the seizure onset pattern (SOP) of preceding repetitive epileptiform discharges following LVFA (PRED→LVFA) (OR 3.319, 95% CI 1.200-9.183, P = 0.021) and pathology of focal cortical dysplasia (FCD) type II (OR 3.943, 95% CI 1.093-14.226, P = 0.036) were independent factors influencing whether the electrical stimulation can induce a seizure. Among the patients received radical surgery, there were 55 and 15 patients in the favorable and unfavorable groups separately. Multivariate analysis revealed that the SOP of PRED→LVFA induced seizures by stimulation (OR 11.409, 95% CI 1.182-110.161, P = 0.035) and bilateral implantation (OR 0.048, 95% CI 0.005-0.497, P = 0.011) were independent factors affecting surgical outcomes. The previous epilepsy surgery had a trend to be a negative factor with SIS (OR 0.156, 95% CI 0.028-0.880, P = 0.035) and surgical outcomes (OR 0.253, 95% CI 0.053-1.219, P = 0.087). CONCLUSION: ESM is a highly valuable method for localizing the seizure onset zone. The SOP of PRED→LVFA and FCD type II were associated with elicitation of SIS by ESM, whereas a previous epilepsy surgery showed a negative association. Furthermore, the SOP of PRED→LVFA together with SIS in the same patient predicted favorable surgical outcomes, whereas bilateral electrode implantation predicted unfavorable outcomes.

Exploring the challenge of early gastric cancer diagnostic AI system face in multiple centers and its potential solutions.

BACKGROUND: Artificial intelligence (AI) performed variously among test sets with different diversity due to sample selection bias, which can be stumbling block for AI applications. We previously tested AI named ENDOANGEL, diagnosing early gastric cancer (EGC) on single-center videos in man-machine competition. We aimed to re-test ENDOANGEL on multi-center videos to explore challenges applying AI in multiple centers, then upgrade ENDOANGEL and explore solutions to the challenge. METHODS: ENDOANGEL was re-tested on multi-center videos retrospectively collected from 12 institutions and compared with performance in previously reported single-center videos. We then upgraded ENDOANGEL to ENDOANGEL-2022 with more training samples and novel algorithms and conducted competition between ENDOANGEL-2022 and endoscopists. ENDOANGEL-2022 was then tested on single-center videos and compared with performance in multi-center videos; the two AI systems were also compared with each other and endoscopists. RESULTS: Forty-six EGCs and 54 non-cancers were included in multi-center video cohort. On diagnosing EGCs, compared with single-center videos, ENDOANGEL showed stable sensitivity (97.83% vs. 100.00%) while sharply decreased specificity (61.11% vs. 82.54%); ENDOANGEL-2022 showed similar tendency while achieving significantly higher specificity (79.63%, p < 0.01) making fewer mistakes on typical lesions than ENDOANGEL. On detecting gastric neoplasms, both AI showed stable sensitivity while sharply decreased specificity. Nevertheless, both AI outperformed endoscopists in the two competitions. CONCLUSIONS: Great increase of false positives is a prominent challenge for applying EGC diagnostic AI in multiple centers due to high heterogeneity of negative cases. Optimizing AI by adding samples and using novel algorithms is promising to overcome this challenge.

Facial Merkel cell carcinoma in a patient with diabetes and hepatitis B: A case report.

BACKGROUND: Patients with chronic inflammatory disorders are at a higher risk of developing aggressive Merkel cell carcinoma (MCC). Diabetes is a common chronic inflammatory disease that is possibly associated with MCC; however, there are still no reports on the association between hepatitis B virus (HBV) infection and MCC. Whether there is an association between these three diseases and the specific mechanisms behind their effects is worth further research in the future. CASE SUMMARY: We herein report a rare case of MCC with extracutaneous and nodal invasion in an Asian individual with type 2 diabetes mellitus and chronic HBV infection, but no immunosuppression or other malignancies. Such cases are uncommon and have rarely been reported in the literature. A 56-year-old Asian male presented with a significant mass on his right cheek and underwent extensive resection combined with parotidectomy, neck lymphadenectomy, and split-thickness skin grafting. Based on the histopathological findings, a diagnosis of MCC involving the adipose tissue, muscle, nerve, and parotid gland with lymphovascular invasion was made. Subsequently, he received radiotherapy with no adverse reactions. CONCLUSION: MCC is a rare, aggressive skin cancer with frequent local recurrence, nodal invasion, and metastasis, which usually arises in older people of the white race. Patients with chronic inflammatory disorders are at a higher risk of developing aggressive MCC. The diagnosis can be confirmed with histology and immunohistochemistry. For localized MCC, surgery is the preferred treatment option. However, for advanced MCC, radiotherapy and chemotherapy have proven to be effective. In cases where chemotherapy is not effective or in the advanced stages of MCC, immune therapy plays an important role in treatment. As with any rare disease, the management of MCC remains an enormous challenge for clinicians; thus, follow-up should be individualized and future progress needs multidisciplinary collaborative efforts. Furthermore, physicians should include MCC in their list of possible diagnoses when they come across painless, rapidly growing lesions, particularly in patients with chronic HBV infection or diabetes, as these patients are more susceptible to the development of this condition and it tends to be more aggressive in them.

The effectiveness of a computer-aided system in improving the detection rate of gastric neoplasm and early gastric cancer: study protocol for a multi-centre, randomized controlled trial.

BACKGROUND: This protocol is for a multi-centre randomised controlled trial to determine whether the computer-aided system ENDOANGEL-GC improves the detection rates of gastric neoplasms and early gastric cancer (EGC) in routine oesophagogastroduodenoscopy (EGD). METHODS: Study design: Prospective, single-blind, parallel-group, multi-centre randomised controlled trial. SETTINGS: The computer-aided system ENDOANGEL-GC was used to monitor blind spots, detect gastric abnormalities, and identify gastric neoplasms during EGD. PARTICIPANTS: Adults who underwent screening, diagnosis, or surveillance EGD. Randomisation groups: 1. Experiment group, EGD examinations with the assistance of the ENDOANGEL-GC; 2. Control group, EGD examinations without the assistance of the ENDOANGEL-GC. RANDOMISATION: Block randomisation, stratified by centre. PRIMARY OUTCOMES: Detection rates of gastric neoplasms and EGC. SECONDARY OUTCOMES: Detection rate of premalignant gastric lesions, biopsy rate, observation time, and number of blind spots on EGD. BLINDING: Outcomes are undertaken by blinded assessors. SAMPLE SIZE: Based on the previously published findings and our pilot study, the detection rate of gastric neoplasms in the control group is estimated to be 2.5%, and that of the experimental group is expected to be 4.0%. With a two-sided α level of 0.05 and power of 80%, allowing for a 10% drop-out rate, the sample size is calculated as 4858. The detection rate of EGC in the control group is estimated to be 20%, and that of the experiment group is expected to be 35%. With a two-sided α level of 0.05 and power of 80%, a total of 270 cases of gastric cancer are needed. Assuming the proportion of gastric cancer to be 1% in patients undergoing EGD and allowing for a 10% dropout rate, the sample size is calculated as 30,000. Considering the larger sample size calculated from the two primary endpoints, the required sample size is determined to be 30,000. DISCUSSION: The results of this trial will help determine the effectiveness of the ENDOANGEL-GC in clinical settings. TRIAL REGISTRATION: ChiCTR (Chinese Clinical Trial Registry), ChiCTR2100054449, registered 17 December 2021.

Explainable artificial intelligence incorporated with domain knowledge diagnosing early gastric neoplasms under white light endoscopy.

White light endoscopy is the most pivotal tool for detecting early gastric neoplasms. Previous artificial intelligence (AI) systems were primarily unexplainable, affecting their clinical credibility and acceptability. We aimed to develop an explainable AI named ENDOANGEL-ED (explainable diagnosis) to solve this problem. A total of 4482 images and 296 videos with focal lesions from 3279 patients from eight hospitals were used for training, validating, and testing ENDOANGEL-ED. A traditional sole deep learning (DL) model was trained using the same dataset. The performance of ENDOANGEL-ED and sole DL was evaluated on six levels: internal and external images, internal and external videos, consecutive videos, and man-machine comparison with 77 endoscopists in videos. Furthermore, a multi-reader, multi-case study was conducted to evaluate the ENDOANGEL-ED's effectiveness. A scale was used to compare the overall acceptance of endoscopists to traditional and explainable AI systems. The ENDOANGEL-ED showed high performance in the image and video tests. In man-machine comparison, the accuracy of ENDOANGEL-ED was significantly higher than that of all endoscopists in internal (81.10% vs. 70.61%, p < 0.001) and external videos (88.24% vs. 78.49%, p < 0.001). With ENDOANGEL-ED's assistance, the accuracy of endoscopists significantly improved (70.61% vs. 79.63%, p < 0.001). Compared with the traditional AI, the explainable AI increased the endoscopists' trust and acceptance (4.42 vs. 3.74, p < 0.001; 4.52 vs. 4.00, p < 0.001). In conclusion, we developed a real-time explainable AI that showed high performance, higher clinical credibility, and acceptance than traditional DL models and greatly improved the diagnostic ability of endoscopists.

An explainable artificial intelligence system for diagnosing Helicobacter Pylori infection under endoscopy: a case-control study.

Background: Changes in gastric mucosa caused by Helicobacter pylori (H. pylori) infection affect the observation of early gastric cancer under endoscopy. Although previous researches reported that computer-aided diagnosis (CAD) systems have great potential in the diagnosis of H. pylori infection, their explainability remains a challenge. Objective: We aim to develop an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) and giving diagnostic basis under endoscopy. Design: A case-control study. Methods: We retrospectively obtained 47,239 images from 1826 patients between 1 June 2020 and 31 July 2021 at Renmin Hospital of Wuhan University for the development of EADHI. EADHI was developed based on feature extraction combining ResNet-50 and long short-term memory networks. Nine endoscopic features were used for H. pylori infection. EADHI's performance was evaluated and compared to that of endoscopists. An external test was conducted in Wenzhou Central Hospital to evaluate its robustness. A gradient-boosting decision tree model was used to examine the contributions of different mucosal features for diagnosing H. pylori infection. Results: The system extracted mucosal features for diagnosing H. pylori infection with an overall accuracy of 78.3% [95% confidence interval (CI): 76.2-80.3]. The accuracy of EADHI for diagnosing H. pylori infection (91.1%, 95% CI: 85.7-94.6) was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3) in internal test. And it showed a good accuracy of 91.9% (95% CI: 85.6-95.7) in external test. Mucosal edema was the most important diagnostic feature for H. pylori positive, while regular arrangement of collecting venules was the most important H. pylori negative feature. Conclusion: The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. Plain language summary: An explainable AI system for Helicobacter pylori with good diagnostic performance Helicobacter pylori (H. pylori) is the main risk factor for gastric cancer (GC), and changes in gastric mucosa caused by H. pylori infection affect the observation of early GC under endoscopy. Therefore, it is necessary to identify H. pylori infection under endoscopy. Although previous research showed that computer-aided diagnosis (CAD) systems have great potential in H. pylori infection diagnosis, their generalization and explainability are still a challenge. Herein, we constructed an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) using images by case. In this study, we integrated ResNet-50 and long short-term memory (LSTM) networks into the system. Among them, ResNet50 is used for feature extraction, LSTM is used to classify H. pylori infection status based on these features. Furthermore, we added the information of mucosal features in each case when training the system so that EADHI could identify and output which mucosal features are contained in a case. In our study, EADHI achieved good diagnostic performance with an accuracy of 91.1% [95% confidence interval (CI): 85.7-94.6], which was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3%) in internal test. In addition, it showed a good diagnostic accuracy of 91.9% (95% CI: 85.6-95.7) in external tests. The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. However, we only used data from a single center to develop EADHI, and it was not effective in identifying past H. pylori infection. Future, multicenter, prospective studies are needed to demonstrate the clinical applicability of CADs.

MANF ameliorates DSS-induced mouse colitis via restricting Ly6ChiCX3CR1int macrophage transformation and suppressing CHOP-BATF2 signaling pathway.

Mesencephalic astrocyte-derived neurotrophic factor (MANF), an endoplasmic reticulum stress-inducible secreting protein, has evolutionarily conserved immune-regulatory function that contributes to the negative regulation of inflammation in macrophages. In this study, we investigated the profiles of MANF in the macrophages of the patients with active inflammatory bowel disease (IBD) and the mice with experimental colitis, which was induced in both myeloid cell-specific MANF knockout mice and wild-type mice by 3% dextran sodium sulfate (DSS) for 7 days. We found that MANF expression was significantly increased in intestinal macrophages from both the mice with experimental colitis and patients with active IBD. DSS-induced colitis was exacerbated in myeloid cell-specific MANF knockout mice. Injection of recombinant human MANF (rhMANF, 10 mg·kg-1·d-1, i.v.) from D4 to D6 significantly ameliorated experimental colitis in DSS-treated mice. More importantly, MANF deficiency in myeloid cells resulted in a dramatic increase in the number of Ly6ChiCX3CRint proinflammatory macrophages in colon lamina propria of DSS-treated mice, and the proinflammatory cytokines and chemokines were upregulated as well. Meanwhile, we demonstrated that MANF attenuated Th17-mediated immunopathology by inhibiting BATF2-mediated innate immune response and downregulating CXCL9, CXCL10, CXCL11 and IL-12p40; MANF functioned as a negative regulator in inflammatory macrophages via inhibiting CHOP-BATF2 signaling pathway, thereby protecting against DSS-induced mouse colitis. These results suggest that MANF ameliorates colon injury by negatively regulating inflammatory macrophage transformation, which shed light on a potential therapeutic target for IBD.

A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video).

BACKGROUND: White light (WL) and weak-magnifying (WM) endoscopy are both important methods for diagnosing gastric neoplasms. This study constructed a deep-learning system named ENDOANGEL-MM (multi-modal) aimed at real-time diagnosing gastric neoplasms using WL and WM data. METHODS: WL and WM images of a same lesion were combined into image-pairs. A total of 4201 images, 7436 image-pairs, and 162 videos were used for model construction and validation. Models 1-5 including two single-modal models (WL, WM) and three multi-modal models (data fusion on task-level, feature-level, and input-level) were constructed. The models were tested on three levels including images, videos, and prospective patients. The best model was selected for constructing ENDOANGEL-MM. We compared the performance between the models and endoscopists and conducted a diagnostic study to explore the ENDOANGEL-MM's assistance ability. RESULTS: Model 4 (ENDOANGEL-MM) showed the best performance among five models. Model 2 performed better in single-modal models. The accuracy of ENDOANGEL-MM was higher than that of Model 2 in still images, real-time videos, and prospective patients. (86.54 vs 78.85%, P = 0.134; 90.00 vs 85.00%, P = 0.179; 93.55 vs 70.97%, P < 0.001). Model 2 and ENDOANGEL-MM outperformed endoscopists on WM data (85.00 vs 71.67%, P = 0.002) and multi-modal data (90.00 vs 76.17%, P = 0.002), significantly. With the assistance of ENDOANGEL-MM, the accuracy of non-experts improved significantly (85.75 vs 70.75%, P = 0.020), and performed no significant difference from experts (85.75 vs 89.00%, P = 0.159). CONCLUSIONS: The multi-modal model constructed by feature-level fusion showed the best performance. ENDOANGEL-MM identified gastric neoplasms with good accuracy and has a potential role in real-clinic.

[MRI findings of parotid acinic cell carcinoma in 19 consecutive cases].

PURPOSE: To describe the MRI features of acinar cell carcinoma of parotid gland (AciCC) and to evaluate the diagnostic value of MR functional imaging. METHODS: A total of 269 cases of maxillofacial AciCC confirmed by surgery and pathology were analyzed. Among them, nineteen subjects with AciCC in the parotid gland underwent preoperative MRI examination (non-enhanced scan for one case, enhanced scan for 18 cases), seventeen patients underwent diffusion-weighted imaging scan, and 15 patients underwent dynamic contrast-enhanced scan. MRI findings of 19 patients were retrospectively analyzed. The lesion size, location, morphology, margin, internal composition, enhancement pattern and functional imaging characteristics were analyzed. SPSS 25.0 software package was used for statistical analysis. RESULTS: Among 269 cases of maxillofacial AciCC, there were 108 males and 161 females, male: female = 1:1.49, aged from 4 to 89 years, with a mean age of (45.95±17.33) years. 84.4% (227/269) were located in the parotid gland. On MRI images, 78.9% (15/19) had well-defined margin, 57.9% (11/19) were round or oval, and 36.8% (7/19) were lobed nodules. One case had irregular morphology and peripheral invasion. The range of maximum diameter was 6-56 mm, averaging (24.8±15.3) mm. Internal composition showed 57.9% (11/19) were cystic solid, 42.1% (8/19) were solid, 31.6% (6/19) had bleeding. T2-weighted MRI showed 52.6% (10/19) with envelope structure, 15.8% (3/19) with low signal separation inside, 38.9%(7/18) had uniform enhancement, and 61.1%(11/18) had uneven enhancement. Functional imaging showed the mean ADC value of tumor was (1.026±0.194)×10-3 mm2/s(n=17). 86.7%(13/15) TIC was type Ⅱ. CONCLUSIONS: Most maxillofacial AciCC are located in the parotid gland. It is difficult to distinguish AciCC from benign tumors with conventional MRI in morphology. The ADC value of AciCC is lower than that of benign tumors, and the type of TIC curve is mostly type Ⅱ. Combination of morphology and functional imaging can improve the diagnostic accuracy of this disease.