Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study.

Background: Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic polyps not requiring resection, potentially reducing cost. Objective: To evaluate the performance of real-time CAD with endocytoscopes (×520 ultramagnifying colonoscopes providing microvascular and cellular visualization of colorectal polyps after application of the narrow-band imaging [NBI] and methylene blue staining modes, respectively). Design: Single-group, open-label, prospective study. (UMIN [University hospital Medical Information Network] Clinical Trial Registry: UMIN000027360). Setting: University hospital. Participants: 791 consecutive patients undergoing colonoscopy and 23 endoscopists. Intervention: Real-time use of CAD during colonoscopy. Measurements: CAD-predicted pathology (neoplastic or nonneoplastic) of detected diminutive polyps (≤5 mm) on the basis of real-time outputs compared with pathologic diagnosis of the resected specimen (gold standard). The primary end point was whether CAD with the stained mode produced a negative predictive value (NPV) of 90% or greater for identifying diminutive rectosigmoid adenomas, the threshold required to "diagnose-and-leave" nonneoplastic polyps. Best- and worst-case scenarios assumed that polyps lacking either CAD diagnosis or pathology were true- or false-positive or true- or false-negative, respectively. Results: Overall, 466 diminutive (including 250 rectosigmoid) polyps from 325 patients were assessed by CAD, with a pathologic prediction rate of 98.1% (457 of 466). The NPVs of CAD for diminutive rectosigmoid adenomas were 96.4% (95% CI, 91.8% to 98.8%) (best-case scenario) and 93.7% (CI, 88.3% to 97.1%) (worst-case scenario) with stained mode and 96.5% (CI, 92.1% to 98.9%) (best-case scenario) and 95.2% (CI, 90.3% to 98.0%) (worst-case scenario) with NBI. Limitation: Two thirds of the colonoscopies were conducted by experts who had each experienced more than 200 endocytoscopies; 186 polyps not assessed by CAD were excluded. Conclusion: Real-time CAD can achieve the performance level required for a diagnose-and-leave strategy for diminutive, nonneoplastic rectosigmoid polyps. Primary Funding Source: Japan Society for the Promotion of Science.

Analysis of YAP1 and TAZ expression by immunohistochemical staining in malignant mesothelioma and reactive mesothelial cells.

[This retracts the article DOI: 10.3892/ol.2018.8225.].

Analysis of YAP1 and TAZ expression by immunohistochemical staining in malignant mesothelioma and reactive mesothelial cells.

Gene mutations are involved in the development of malignant mesothelioma. Important mutations have been identified in the genes for cyclin-dependent kinase inhibitor 2A (p16) alternative reading frame, breast cancer-associated protein 1 (BAP1) and neurofibromatosis type 2 (NF2). Previously, the utility of detecting the loss of BAP1 by immunohistochemistry (IHC) and p16-deletion by fluorescence in situ hybridization has been identified in several studies. However, NF2-associated examinations have not been performed. The present study aimed to evaluate the expression of yes-associated protein 1 (YAP1) and tafazzin (TAZ) protein, which are associated with NF2 gene mutations, in malignant mesothelioma (MM) and reactive mesothelial cells (RMCs). Formalin-fixed paraffin-embedded tissues from 31 MM and 33 RMC samples were analyzed. The expression of YAP1 and TAZ protein were examined by IHC. Positivity for YAP1 was identified 27/31 MM and 15/33 RMC samples. Positivity for TAZ was identified in 28/31 MM and 18/33 RMC samples. Using the optimal cutoff points determined by the receiver operating characteristic curve, a positive IHC result for YAP1 and TAZ was 74% sensitive and 94% specific for detecting MM. The results indicate that increased expression of YAP1 and TAZ may be associated with mesothelial tumorization, and aid in the diagnosis of MM.

Expression of matrix metalloproteinase-7 correlates with the invasion of T1 colorectal carcinoma.

T1 colorectal carcinomas (CRCs) are an initial site of metastatic spread. Various risk factors for lymph node metastasis have been investigated in T1 CRCs. However, the major step in the entire process of metastasis remains unclear. In terms of carcinoma invasion and metastasis, matrix metalloproteinases (MMPs) have recently gained increasing attention. Notably, MMP-7 is frequently overexpressed in CRCs, but its implication has not been determined in T1 CRCs yet. The present study aimed to clarify the associations between the pathological risk factors of T1 CRCs and MMP-7. In the current study, 211 lesions of T1 CRC that were resected endoscopically or surgically at Showa University Northern Yokohama Hospital (Yokohama, Japan) between April 2008 and December 2009 were retrospectively analyzed. MMP-7 was immunostained and evaluated by its frequency of expression. Pathological factors of T1 CRCs were analyzed in association with MMP-7 expression. Furthermore, the ultrastructural alterations of carcinoma invasion were examined using low vacuum-scanning electron microscopy (LV-SEM). MMP-7 expression was associated with venous invasion (P=0.005), and LV-SEM revealed the disappearance of the normal structure of collagen and elastic fibers of veins invaded by tumor cells expressing MMP-7. At the invasive front, MMP-7 has a vital role in carcinoma invasion, correlating with venous invasion of T1 CRCs.

The role of microvessel density, lymph node metastasis, and tumor size as prognostic factors of distant metastasis in colorectal cancer.

Angiogenesis is essential for tumor growth and metastasis. CD105 is reportedly a specific marker for tumor angiogenesis. It has been demonstrated that monoclonal antibodies to CD105 have high affinity for activated endothelial cells. A relationship between metastasis and microvessel density (MVD), as an indicator of neovascularization, has been identified in patients with colorectal cancer as shown by the presence of monoclonal antibodies to CD105. However, data on potentially confounding factors such as lymphatic and vascular infiltration and tumor size are lacking. We further investigated the relationship between MVD and distant metastasis, along with potentially confounding clinicopathological factors, to more precisely characterize this relationship. In this retrospective study, we analyzed colorectal cancer specimens surgically or endoscopically resected from January to September 2009. We defined MVD as the number of microvessels stained by monoclonal antibodies to CD105 per ×400 field. Selected clinicopathological factors were analyzed and stepwise multivariate logistic regression was performed to identify independent risk factors for distant metastasis. We analyzed 129 lesions. The median follow-up time was 34 months (range, 6-85 months) in patients with distant metastasis and 61 months (range, 60-86 months) in those without distant metastasis. At the time of resection or during subsequent follow-up, 32 patients had distant metastases. The MVD was significantly greater in patients with than without distant metastases (mean ± standard deviation: 10.4±4.9 vs. 7.6±3.3, P=0.008; Welch's t-test). Stepwise multivariate logistic regression indicated that MVD, regional lymph node metastasis, and tumor size were independent risk factors for distant metastases. Combining assessment of monoclonal antibodies to CD105-positive MVD with assessment of regional lymph node metastasis and tumor size may help to identify patients who need more intensive surveillance after surgery for colorectal cancer.