Multi-step validation of a deep learning-based system with visual explanations for optical diagnosis of polyps with advanced features.

Artificial intelligence (AI) has been found to assist in optical differentiation of hyperplastic and adenomatous colorectal polyps. We investigated whether AI can improve the accuracy of endoscopists' optical diagnosis of polyps with advanced features. We introduced our AI system distinguishing polyps with advanced features with more than 0.870 of accuracy in the internal and external validation datasets. All 19 endoscopists with different levels showed significantly lower diagnostic accuracy (0.410-0.580) than the AI. Prospective randomized controlled study involving 120 endoscopists into optical diagnosis of polyps with advanced features with or without AI demonstration identified that AI improved endoscopists' proportion of polyps with advanced features correctly sent for histological examination (0.960 versus 0.840, p < 0.001), and the proportion of polyps without advanced features resected and discarded (0.490 versus 0.380, p = 0.007). We thus developed an AI technique that significantly increases the accuracy of colorectal polyps with advanced features.

Hypoxia and low-glucose environments co-induced HGDILnc1 promote glycolysis and angiogenesis.

Small bowel vascular malformation disease (SBVM) commonly causes obscure gastrointestinal bleeding (OGIB). However, the pathogenetic mechanism and the role of lncRNAs in SBVM remain largely unknown. Here, we found that hypoxia and low-glucose environments co-augment angiogenesis and existed in SBVM. Mechanistically, hypoxia and low-glucose environments supported angiogenesis via activation of hypoxia and glucose deprivation-induced lncRNA (HGDILnc1) transcription by increasing binding of the NeuroD1 transcription factor to the HGDILnc1 promoter. Raised HGDILnc1 acted as a suppressor of α-Enolase 1 (ENO1) small ubiquitin-like modifier modification (SUMOylation)-triggered ubiquitination, and an activator of transcription of Aldolase C (ALDOC) via upregulation of Histone H2B lysine 16 acetylation (H2BK16ac) level in the promoter of ALDOC, and consequently promoting glycolysis and angiogenesis. Moreover, HGDILnc1 was clinically positively correlated with Neurogenic differentiation 1 (NeuroD1), ENO1, and ALDOC in SBVM tissues, and could function as a biomarker for SBVM diagnosis and therapy. These findings suggest that hypoxia and low-glucose environments were present in SBVM tissues, and co-augmented angiogenesis. Hypoxia and low-glucose environments co-induced HGDILnc1, which is higher expressed in SBVM tissue compared with normal tissue, could promoted glycolysis and angiogenesis.

Influence of early colorectal cancer component on the positive margins after endoscopic resection: a retrospective study.

BACKGROUND: Endoscopic treatment methods for early colorectal cancer (ECRC) mainly depend on the size and morphology. It is unclear whether different endoscopic resection methods could achieve curative resection for ECRC confined in the mucosa. The study was designed to compare the rate of positive vertical margin (VM) of ECRC with advanced adenomas (AAs) including adenoma > 1 cm, villous adenoma, high-grade intraepithelial neoplasia/dysplasia stratified by different endoscopic resection methods. METHODS: Rate of positive VM for 489 ECRCs including Intramucosal (pTis) and superficial submucosal invasion (pT1) carcinomas were compared with those of 753 AAs stratified by different endoscopic resection methods using Chi-squared test. Multivariate logistic model was performed to investigate the risk factors of positive VM for different endoscopic resection methods. RESULTS: The pTis ECRC exhibited a similar rate of positive VM as that of AAs for en bloc hot snare polypectomy (HSP, 0% Vs. 0.85%, P = 0.617), endoscopic mucosal resection (EMR, 0.81% vs. 0.25%, P = 0.375) and endoscopic submucosal dissection (ESD, 1.82% Vs. 1.02%, P = 0.659). The pTis carcinoma was not found to be a risk factor for positive VM by en bloc EMR (P = 0.349) or ESD (P = 0.368). The en bloc resection achieved for pT1a carcinomas exhibited similar to positive VM achieved through ESD (2.06% Vs. 1.02%, P = 1.000) for AAs. Nonetheless, EMR resulted in higher risk of positive VM (5.41% Vs. 0.25%, P < 0.001) for pT1a carcinomas as compared to AAs. The pT1a invasion was identified as a risk factor for positive VM in polyps with en bloc EMR (odds ratio = 23.90, P = 0.005) but not ESD (OR = 2.96, P = 0.396). CONCLUSION: Collectively, the pTis carcinoma was not found to be a risk factor for positive VM resected by en bloc HSP, EMR or ESD. Additionally, ESD may be preferred over EMR for pT1a carcinomas with lower rate of positive VM.

Customized Cellulose Fiber Paper Enabled by an In Situ Growth of Ultralong Hydroxyapatite Nanowires.

Cellulose fiber (CF) paper is a low-cost, sustainable, and flexible substrate, which has gained increasing interest recently. Before practical usage, the functionalization of the pristine CF paper is indispensable to meet requirements of specific applications. Different from conventional surface modification or physical mixing methods, we report in situ growth of ultralong hydroxyapatite nanowires (HAPNWs) with lengths larger than 10 µm on the CF paper. HAPNWs are radially aligned on the surface of CFs, creating a micro/nanoscale hierarchical structure. By means of the excellent ion exchange ability of HAP and the hierarchical structure, the functions of the CF paper can be easily customized. As a proof-of-concept, we demonstrate two kinds of functional CF paper: (1) the photoluminescent CF paper by doping Eu3+ and Tb3+ ions into the crystal lattice of HAPNWs and (2) the superhydrophobic CF paper by coating poly(dimethylsiloxane) on the HAPNW hierarchical structure, which can be applied for self-cleaning and oil/water separation. It is expected that an in situ growth of ultralong HAPNWs will provide an instructive guideline for designing a CF paper with specific functions.

Personalized four-category staging for predicting prognosis in patients with small bowel Adenocarcinoma: an international development and validation study.

BACKGROUND: Log odds of positive lymph nodes (LODDS) classification showed superiority over 8th edition N staging in predicting survival of small bowel adenocarcinoma (SBA) patients. The aim of this study was to develop and validate the Tumor, LODDS, and Metastasis (TLM) staging of SBA. METHODS: Totally 1789 SBA patients from the Surveillance, Epidemiology, and End Results (SEER) database between 1988-2010, 437 patients from SEER database between 2011-2013 and 166 patients from multicenters were categorized into development, validation and test cohort, respectively. The TLM staging was developed in the development cohort using Ensemble Algorithm for Clustering Cancer Data (EACCD) method. C-index was used to assess the performance of the TLM staging in predicting cancer-specific survival (CSS) and was compared with the traditional 8th edition TNM staging. FINDINGS: Four-category TLM staging designed for the development cohort showed higher discriminatory power than TNM staging in predicting CSS in the development cohort (0.682 vs. 0.650, P < 0.001), validation cohort (0.682 vs. 0.654, P = 0.022), and test cohort (0.659 vs. 0.611, P = 0.023), respectively. TLM staging continued to show its higher predictive efficacy than the 8th TNM in TNM stage II/III patients or in patients with lymph node yield less than 8. INTERPRETATION: TLM staging showed a better prognostic performance than the 8th TNM staging especially TNM stage II/III or patients with lymph node yield less than 8 and therefore, could serve to complement the TNM staging in patients with SBA. FUNDING: A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.