Analysis of white-light imaging-based features predictive for determination of lesion depths of superficial flat esophageal squamous cell carcinoma: a retrospective multicenter study from China.

OBJECTIVES: Endoscopic diagnosis of invasion depth of superficial esophageal squamous cell carcinoma (SESCC) by white-light imaging (WLI) modality remains difficult. This study aims to clarify WLI-based features which are predictive for invasion depth of SESCC. METHODS: A two-phase study was performed by enrolling 1288 patients with 1396 SESCC lesions. Endoscopic appearances, clinical characteristics and post-operative pathological outcomes were collected and reviewed. The association between lesion features and invasion depth were analyzed. A predictive nomogram was constructed for prediction of invasion depth. RESULTS: Among 1396 lesions in derivation and validation cohort, 1139 (81.6%), 194 (13.9%) and 63 (4.5%) lesions were diagnosed as lesions confined into the intraepithelium or the lamina propria mucosa (T1a-EP/LPM), lesions invading the muscularis mucosa (T1a-MM) or superficial submucosa (T1b-SM1) and tumor with moderate invasion into the submucosa or deeper submucosal invasion (≥ T1b-SM2), respectively. Lesion length > 2 cm (p < 0.001), wider circumferential extension (p < 0.001, 0.002 and 0.048 for > 3/4, 1/2-3/4 and 1/4-1/2 circumferential extension, respectively), surface unevenness (p < 0.001 for both type 0-IIa/0-IIc lesions and mixed type lesions), spontaneous bleeding (p < 0.001), granularity (p < 0.001) and nodules (p < 0.001) were identified as significant factors predictive for lesion depth. A nomogram based on these factors was constructed and the values of area under the Receiver Operating Characteristics curve were 0.89 and 0.90 in the internal and external patient cohort. CONCLUSIONS: Our study provides six WLI-based morphological features predicting for lesion depth of SESCC. Our findings will make endoscopic evaluation of invasion depth for SESCC more convenient by assessing these profiles.

Artificial intelligence assisted detection of superficial esophageal squamous cell carcinoma in white-light endoscopic images by using a generalized system.

BACKGROUND: The use of artificial intelligence (AI) assisted white light imaging (WLI) detection systems for superficial esophageal squamous cell carcinoma (SESCC) is limited by training with images from one specific endoscopy platform. METHODS: In this study, we developed an AI system with a convolutional neural network (CNN) model using WLI images from Olympus and Fujifilm endoscopy platforms. The training dataset consisted of 5892 WLI images from 1283 patients, and the validation dataset included 4529 images from 1224 patients. We assessed the diagnostic performance of the AI system and compared it with that of endoscopists. We analyzed the system's ability to identify cancerous imaging characteristics and investigated the efficacy of the AI system as an assistant in diagnosis. RESULTS: In the internal validation set, the AI system's per-image analysis had a sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of 96.64%, 95.35%, 91.75%, 90.91%, and 98.33%, respectively. In patient-based analysis, these values were 90.17%, 94.34%, 88.38%, 89.50%, and 94.72%, respectively. The diagnostic results in the external validation set were also favorable. The CNN model's diagnostic performance in recognizing cancerous imaging characteristics was comparable to that of expert endoscopists and significantly higher than that of mid-level and junior endoscopists. This model was competent in localizing SESCC lesions. Manual diagnostic performances were significantly improved with the assistance by AI system, especially in terms of accuracy (75.12% vs. 84.95%, p = 0.008), specificity (63.29% vs. 76.59%, p = 0.017) and PPV (64.95% vs. 75.23%, p = 0.006). CONCLUSIONS: The results of this study demonstrate that the developed AI system is highly effective in automatically recognizing SESCC, displaying impressive diagnostic performance, and exhibiting strong generalizability. Furthermore, when used as an assistant in the diagnosis process, the system improved manual diagnostic performance.

Study protocol for artificial intelligence-assisted sponge cytology as pre-endoscopy screening for early esophegeal squmaous epithelial lesions in China.

BACKGROUND: Endoscopic screening is the widely accepted screening strategy for esophageal squmaous cell carcinoma (ESCC). However, massive endoscopic screening is expensive and not cost-efficient, and novel pre-endoscopy detection used as a preliminary screening method arouses new concerns. We are planning to launch an artificial intelligence (AI) assisted sponge cytology for detecting esophageal squmaous high-grade intraepithelial neoplasia (HGIN) and above lesions. The aim of this trail is to investigate the efficiency of AI-assisted sponge cytology in population-based screening of early esophageal squmaous epithelial lesions. METHODS: The study will be prospectively conducted in five regions with a high prevalence of ESCC. AI-assisted sponge cytology and endoscopic examination will be sequentially performed. Based on our previous data, at least 864 patients with esophageal HGIN and above lesions are needed to achieve enough statistical power. And, a calculated 112,500 individuals with high risks of ESCC will be recruited. In the first stage, each 24,000 participants who meet the inclusion criteria will be recruited on a voluntary basis. Setting pathological results as standard reference, diagnostic threshold and according performance of AI-assisted detection will be evaluated. A prediction model will be constructed by co-analyzing cytological results and relevant risk factors. Then, an external validation cohort will be used for validation of the model efficiency. Also, cost-efficiency analysis will be performed. This study protocol was registered on chineseclinicaltrial.gov (ChiCTR1900028524). DISCUSSION: Our study will determine whether this AI-assisted sponge cytology can be used as an effective pre-endoscopy detection tool for large-scale screening for ESCC in high-risk areas.

Efficacy and safety of a novel submucosal injection solution for endoscopic resection in porcine models.

OBJECTIVE: A submucosal injection is usually required to improve the efficacy and safety of endoscopic submucosal dissection (ESD) and endoscopic mucosal resection (EMR). This study aimed to evaluate the performance of 3.3% sodium carboxymethyl starch (Na-CMS) solution, a novel submucosal injection solution, for ESD and EMR. METHODS: Na-CMS, normal saline (NS) and two commercially available agents (sigMAVisc and Eleview) were injected into the esophageal submucosa of randomly grouped pigs. The level of submucosal elevation was examined. Subsequently, ESD or EMR procedures using 3.3% Na-CMS or NS as submucosal injections were performed in the gastrointestinal tract of the pigs. RESULTS: Submucosal elevation was significantly higher and more sustained in the 3.3% Na-CMS group than in the controls (P < 0.05). The volume required for ESD or EMR was significantly lower in the 3.3% Na-CMS group than in the NS group (ESD: 12.21 ± 4.09 mL vs 28.25 ± 8.02 mL, P < 0.001; EMR: 3.99 ± 1.98 mL vs 7.15 ± 3.67 mL, P = 0.001). The ESD resection time was significantly shorter in the 3.3% Na-CMS group than in the NS group (16.58 ± 7.30 min vs 25.29 ± 11.89 min, P = 0.004). Hemorrhage after ESD in the 3.3% Na-CMS group was less severe than that in the NS group (P = 0.006). CONCLUSION: 3.3% Na-CMS is an effective, safe and low-cost submucosal injection solution and holds promise as preferable agent for submucosal injection in ESD and EMR procedures.

MiR-26b regulates 5-FU-resistance in human colorectal cancer via down-regulation of Pgp.

Chemotherapy resistance frequently drives tumor progression. However, the underlying molecular mechanisms remain unclear. In this study, we found that the expression level of miR-26b was down-regulated in the human colorectal cancer tissues and the resistant cells strains: HT-29/5-FU and LOVO/5-FU cells. Meanwhile, we showed that miR-26b improved sensibility of colorectal cancer cells to 5-FU in vitro and enhanced the potency of 5-FU in the inhibition of tumor growth in vivo. We further demonstrated that the tumor suppressive role of miR-26b was mediated by negatively regulating P-glycoprotein (Pgp) protein expression. Furthermore, studies of colorectal cancer specimens indicated that the expression of miR-26b and Pgp had inverse correlation. Importantly, we found that CpG islands in the miR-26b promoter region were hypermethylated in 5-FU resistant cells. Our study is the first to identify the tumor suppressive role of over-expressed miR-26b in chemo-sensitivity. Identification of a novel miRNA-mediated pathway that regulates chemo-sensitivity in colorectal cancer will facilitate the development of novel therapeutic strategies in the future.

[Value of non-invasive continuous hemodynamic monitoring system in the differential diagnosis of the patients with dyspnea].

OBJECTIVE: To evaluate non-invasive continuous hemodynamic (IQ System) monitoring in the differential diagnosis of dyspnea. METHODS: According to the diagnosis on discharge, 48 patients diagnosed as pulmonary dyspnea were enrolled in control group and 38 patients with cardiac dyspnea were in heart failure group. Each patient underwent IQ monitoring on admission and after recovery. The difference in the diagnosis on admission and on discharge, and the difference in IQ index were analyzed. RESULTS: (1) Clinical diagnosis: 7 patients in heart failure group were missed on admission as 5 were diagnosed as pneumonia and 2 were diagnosed as chronic obstructive pulmonary disease (COPD). One patient with pneumothorax in control group was misdiagnosed as heart failure. (2) Indexes of cardiac function: base impedance (Zo), maximum value of dz/dt (dz/dt max) and Heather index (HI) of heart failure group were markedly lower than those of control group (all P<0.001). The respective values were (19.0+/-3.5) Omega vs. (28.8+/-5.5) Omega, (0.76+/-0.42) Omega/s vs. (1.40+/-0.72) Omega/s, and (7.04+/-4.25) Omega/s2 vs. (13.60+/-6.36) Omega/s2. If Zo value of patients with dyspnea was 22 omicron or less, the sensitivity in diagnosing heart failure was 79 percent, and its specificity was 94 percent. If Zo value was 18.0 omicron or less, the sensitivity in diagnosing heart failure was 47 percent, and its specificity was 100 percent. (3) Comparison within groups: Indexes of cardiac function of control group did not change obviously and Zo, dz/dt max, HI, stroke volume (SV) and acceleration contraction index (ACI) values of heart failure group rose significantly after recovery. (4) Pre-ejection period (PEP) and left ventricular ejection time (VET) in both groups had no statistical significance in differences. CONCLUSION: IQ System was valuable in differential diagnosis to judge if dyspnea is caused by heart failure. Zo, dz/dt max and HI, especially Zo, are reliable.