Effect of an artificial intelligence-assisted system on endoscopic diagnosis of superficial oesophageal squamous cell carcinoma and precancerous lesions: a multicentre, tandem, double-blind, randomised controlled trial.

BACKGROUND: Despite the usefulness of white light endoscopy (WLE) and non-magnified narrow-band imaging (NBI) for screening for superficial oesophageal squamous cell carcinoma and precancerous lesions, these lesions might be missed due to their subtle features and interpretation variations among endoscopists. Our team has developed an artificial intelligence (AI) system to detect superficial oesophageal squamous cell carcinoma and precancerous lesions using WLE and non-magnified NBI. We aimed to evaluate the auxiliary diagnostic performance of the AI system in a real clinical setting. METHODS: We did a multicentre, tandem, double-blind, randomised controlled trial at 12 hospitals in China. Eligible patients were aged 18 years or older and underwent sedated upper gastrointestinal endoscopy for screening, investigation of gastrointestinal symptoms, or surveillance. Patients were randomly assigned (1:1) to either the AI-first group or the routine-first group using a computerised random number generator. Patients, pathologists, and statistical analysts were masked to group assignment, whereas endoscopists and research assistants were not. The same endoscopist at each centre did tandem upper gastrointestinal endoscopy for each eligible patient on the same day. In the AI-first group, the endoscopist did the first examination with the assistance of the AI system and the second examination without it. In the routine-first group, the order of examinations was reversed. The primary outcome was the miss rate of superficial oesophageal squamous cell carcinoma and precancerous lesions, calculated on a per-lesion and per-patient basis. All analyses were done on a per-protocol basis. This trial is registered with the Chinese Clinical Trial Registry (ChiCTR2100052116) and is completed. FINDINGS: Between Oct 19, 2021, and June 8, 2022, 5934 patients were randomly assigned to the AI-first group and 5912 to the routine-first group, of whom 5865 and 5850 were eligible for analysis. Per-lesion miss rates were 1·7% (2/118; 95% CI 0·0-4·0) in the AI-first group versus 6·7% (6/90; 1·5-11·8) in the routine-first group (risk ratio 0·25, 95% CI 0·06-1·08; p=0·079). Per-patient miss rates were 1·9% (2/106; 0·0-4·5) in AI-first group versus 5·1% (4/79; 0·2-9·9) in the routine-first group (0·37, 0·08-1·71; p=0·40). Bleeding after biopsy of oesophageal lesions was observed in 13 (0·2%) patients in the AI-first group and 11 (0·2%) patients in the routine-first group. No serious adverse events were reported by patients in either group. INTERPRETATION: The observed effect of AI-assisted endoscopy on the per-lesion and per-patient miss rates of superficial oesophageal squamous cell carcinoma and precancerous lesions under WLE and non-magnified NBI was consistent with substantial benefit through to a neutral or small negative effect. The effectiveness and cost-benefit of this AI system in real-world clinical settings remain to be further assessed. FUNDING: National Natural Science Foundation of China, 1·3·5 project for disciplines of excellence, West China Hospital, Sichuan University, and Chengdu Science and Technology Project. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

Percutaneous contrast-enhanced ultrasound for localization and qualitative diagnosis of sentinel lymph nodes in cutaneous malignant melanoma of lower extremities: a preliminary study.

BACKGROUND: To explore the feasibility of sentinel lymph node (SLN) tracing by percutaneous contrast-enhanced ultrasound (pCEUS) in patients with cutaneous malignant melanoma (CMM) and the ability to enhance patterns of SLNs in diagnosing lymph nodes (LNs) metastases. METHODS: Fifty-three patients with CMM of the lower extremities treated at our hospital were included in the study. All the participants received pCEUS preoperatively. The enhanced lymphatic channels (LCs) and associated SLNs were observed and tracked in real-time. The number of enhanced LCs and enhancing patterns of SLNs were recorded. Subsequently, SLNs localized by pCEUS were pathologically examined. RESULTS: Of the 53 cases, SLNs were successfully localized by pCEUS in 48 cases. In total, there were 59 detected SLNs averaging 1.23±0.42 SLNs per case. The main lymphatic drainage patterns (LDPs) were the following: one enhanced LC pointed to one or more than one SLN, and multiple enhanced LCs pointed to one or multiple SLNs. There were four enhancing patterns of SLNs (uniform, annular, uneven, and no enhancement), among which the first two were considered benign nodes, while the latter two were considered metastatic nodes. With pathological results as the gold standard, the diagnostic sensitivity and specificity by pCEUS were 90.9% and 75.0%, respectively. CONCLUSIONS: Contrast-enhanced ultrasound (US) is a feasible approach for SLN identification in patients with CMM of the lower extremities. Enhancing patterns of SLNs may help predict metastasizing SLNs. This novel method may be a promising technique for clinical application.

Determination of reference ranges for normal upper trapezius elasticity during different shoulder abduction using shear wave elastography: a preliminary study.

The purpose of this study was to determine the reference ranges of normal upper trapezius (UT) elasticity during different shoulder abduction using shear wave elastography (SWE). Mean shear wave velocity (SWV) of UT elasticity in eighty healthy participants were measured at left and right shoulder 0° abduction and 90° passive abduction (L0°, R0°, L90°, R90°) with SWE. The effects of potential factors (gender, UT thickness, age, and body mass index) on UT elasticity were analyzed. The reference ranges of normal UT elasticity were calculated by using the normal distribution method. UT elasticity was significantly different among various shoulder abduction (P < 0.0001). UT elasticity was significantly higher in males at both L90° (P < 0.05) and R90° (P < 0.01) than in females. The reference ranges of normal UT elasticity were 2.90-4.01 m/s at L0° and 3.01-4.29 m/s at R0°, and were 4.90-6.40 m/s in males and 4.40-6.20 m/s in females at L90°, 5.20-7.02 m/s in males and 4.71-6.80 m/s in females at R90°. Our results suggest that gender should be considered when determining the reference ranges of normal UT elasticity at L90° and R90° with SWE. These values may provide quantitative baseline measurements for the assessment of UT muscle strain in the future.

Shear wave elastography evaluation of the median and tibial nerve in diabetic peripheral neuropathy.

BACKGROUND: To evaluate the value of shear wave elastography (SWE) in the detection of diabetic peripheral neuropathy (DPN) of the median and tibial nerves. METHODS: The study included 40 DPN patients, 40 diabetic mellitus (DM) patients without DPN, and 40 healthy subjects. High-resolution ultrasonography (US) and SWE were performed on the median nerve (MN) and tibial nerve (TN), and cross-sectional area (CSA) and nerve stiffness were measured. ROC analysis was also performed. RESULTS: The patients with DPN demonstrated higher stiffness of the median and tibial nerve compared with that of healthy volunteers and DM patients (P<0.001). Bilateral analysis showed that there was no significant difference in nerve stiffness between the left and right median nerves and tibial nerves in DPN patients (P>0.05). The stiffness of median nerve and tibial nerve in each one side also had no significant difference in patients with DPN (P>0.05). The CSA of the tibial nerve in the DPN group was significantly larger than that in the other groups (P<0.001), while there was no significant difference of median nerve CSA among the three groups (P>0.05). The area under curve (AUC) of SWE (MN: 0.899, TN: 0.927) to diagnose DPN was significantly greater than that of CSA (TN: 0.798). The optimal cut-off value in SWE of the tibial nerve and median nerve for diagnosis of DPN was 4.11 and 4.06 m/s, respectively, with a good sensitivity and specificity. CONCLUSIONS: Median and tibial nerve stiffness was significantly higher in patients with DPN. These findings suggest that SWE-based stiffness measurement of the nerve was a better method than CSA, and it can be used as another effective assistant method in the diagnosis of DPN.

[Hematological abnormality and clinical characteristics in systemic lupus erythematosus].

To investigate the hematological abnormality and clinical characteristics in systemic lupus erythematosus (SLE), the hematological data of 58 SLE and the curative effects of corticosteroid and immunosuppressive agents on SLE were retrospectively analysed by using SPSS/PC software. The results showed that the incidence of hematological abnormalities in 58 cases was as follows: 50 cases of hemogram abnormality (86.2%), 41 of anemia (70.7%), 34 of thrombocytopenia (58.7%), 37 of leukopenia (63.8%). Peripheral cytopenia of every cell lineage was common in SLE. The cell abnormalities of two or three lineages were seen in 41 cases (70.7%). The initial symptoms with hematological abnormality were found in 12 cases (20.7%), 7 out of 12 cases were erroneously diagnosed as hematology diseases (12.1%). In 30 out of 58 patients, the results of bone marrow examination showed that 23 had hyperplasia (76.7%) and 7 were hypoplasia. In 25 out of 38 cases, splenomegaly (65.8%) was found by B ultrasonography. In 25 patients with SLE receiving Coombs test, 3 were positive (12.0%). PAIg increased in 16 out of 22 cases of thrombocytopenia (72.7%). 26 cases of SLE with two or three lineage cytopenia in peripheral blood were treated by corticosteroid and immunosuppressive agent. The hemogram improved in all patients including 6 cases of bone marrow hypoplasia. It is concluded that the hematological abnormalities are frequent in SLE patients, which are short of specialty. The cytopenia of two or more lineage in peripheral blood is most common when bone marrow shows hyperplastic. The therapy with corticosteroid and immunosuppressive agents is efficacious.