Artificial intelligence-aided diagnostic imaging: A state-of-the-art technique in precancerous screening.

BACKGROUND AND AIM: Chromoendoscopy with the use of indigo carmine (IC) dye is a crucial endoscopic technique to identify gastrointestinal neoplasms. However, its performance is limited by the endoscopist's skill, and no standards are available for lesion identification. Thus, we developed an artificial intelligence (AI) model to replace chromoendoscopy. METHODS: This pilot study assessed the feasibility of our novel AI model in the conversion of white-light images (WLI) into virtual IC-dyed images based on a generative adversarial network. The predictions of our AI model were evaluated against the assessments of five endoscopic experts who were blinded to the purpose of this study with a staining quality rating from 1 (unacceptable) to 4 (excellent). RESULTS: The AI model successfully transformed the WLI of polyps with different morphologies and different types of lesions in the gastrointestinal tract into virtual IC-dyed images. The quality ratings of the real IC-dyed and AI images did not significantly differ concerning surface structure (AI vs IC: 3.08 vs 3.00), lesion border (3.04 vs 2.98), and overall contrast (3.14 vs 3.02) from 10 sets of images (10 AI images and 10 real IC-dyed images). Although the score depended significantly on the evaluator, the staining methods (AI or real IC) and evaluators had no significant interaction (P > 0.05) with each other. CONCLUSION: Our results demonstrated the feasibility of employing AI model's virtual IC staining, increasing the possibility of being employed in daily practice. This novel technology may facilitate gastrointestinal lesion identification in the future.

[HCCR-2 enhances the division and proliferation of SMMC 7721 via PI3K/Akt pathway].

OBJECTIVE: To observe the biological changes of SMMC 7721 cell line which was stably transfected with HCCR-2 gene and to study the molecular mechanism of HCCR-2 expression in SMMC 7721 cell line. METHODS: SMMC7721 cells were transfected with HCCR-2-pEGFP-N1 and pEGFP-N1 by lipofectmine 2000 and the transfectants were selected and confirmed using Western-blot technique. Cell cycles were tested by flow cytometry. The reproductive activity was detected by MTT assay. SMMC 7721 cells were routinely cultured with treatment of increasing concentrations (0, 50, 100, 200 ng/ml) of EGF for 24 h. Cells were pretreated with the specific inhibitor of PI3K (LY294002) and then cultured with EGF (100 ng/ml) for 24h and the expression of HCCR protein in these cells were measured by Western blot. Another set of SMMC 7721 cells were transfected with DN-Akt-pcDNA3.1 (dominant negative Akt kinase) and pcDNA3.1 by lipofectmine 2000. The transfectants were selected and confirmed using Western-blot technique as before. HCCR-2 and bcl-2 were measured on protein level by Western blot. RESULTS: SMMC 7721 cells were stably transfected with HCCR-2 gene. HCCR-2 gene transfection can increase the proportion of S-phase cells (21.62%+/-1.33% vs 15.76%+/-0.73%, P<0.01) and decrease the cell apoptosis (1.28%+/-0.16% vs 7.72%+/-0.23%, P<0.01). MTT assay showed the growth of HCCR-2 gene transfected cells was faster than that of empty vecter transfected cells. The HCCR-2 protein was up-regulated in a dose-dependent manner in the cells cultured with different concentrations of EGF for 24 h. Treatment of SMMC 7721 cells with specific inhibitor of PI3K (LY294002) suppressed EGF-induced HCCR-2 expression. HCCR-2 protein was down-regulated in dominant negative Akt transfectants. CONCLUSIONS: EGF upregulated HCCR-2 protein expression in SMMC 7721 cell line via PI3K/Akt pathway. The overexpression of HCCR-2 could enhance the division and proliferation of SMMC 7721.