Comparing artificial intelligence to humans for endoscopic diagnosis of gastric neoplasia: An external validation study.

OBJECTIVES: Artificial intelligence (AI) uses deep learning functionalities that may enhance the detection of early gastric cancer during endoscopy. An AI-based endoscopic system for upper endoscopy was recently developed in Japan. We aim to validate this AI-based system in a Singaporean cohort. METHODS: There were 300 de-identified still images prepared from endoscopy video files obtained from subjects that underwent gastroscopy in National University Hospital (NUH). Five specialists and 6 non-specialists (trainees) from NUH were assigned to read and categorize the images into "neoplastic" or "non-neoplastic." Results were then compared with the readings performed by the endoscopic AI system. RESULTS: The mean accuracy, sensitivity, and specificity for the 11 endoscopists were 0.847, 0.525, and 0.872, respectively. These values for the AI-based system were 0.777, 0.591, and 0.791, respectively. While AI in general did not perform better than endoscopists on the whole, in the subgroup of high-grade dysplastic lesions, only 29.1% were picked up by the endoscopist rating, but 80% were classified as neoplastic by AI (P = 0.0011). The average diagnostic time was also faster in AI compared with endoscopists (677.1 s vs 42.02 s (P < 0.001). CONCLUSION: We demonstrated that an AI system developed in another health system was comparable in diagnostic accuracy in the evaluation of static images. AI systems are faster and not fatigable and may have a role in augmenting human diagnosis during endoscopy. With more advances in AI and larger studies to support its efficacy it would likely play a larger role in screening endoscopy in future.

Identification of molecular subtypes of gastric cancer with different responses to PI3-kinase inhibitors and 5-fluorouracil.

BACKGROUND & AIMS: Almost all gastric cancers are adenocarcinomas, which have considerable heterogeneity among patients. We sought to identify subtypes of gastric adenocarcinomas with particular biological properties and responses to chemotherapy and targeted agents. METHODS: We compared gene expression patterns among 248 gastric tumors; using a robust method of unsupervised clustering, consensus hierarchical clustering with iterative feature selection, we identified 3 major subtypes. We developed a classifier for these subtypes and validated it in 70 tumors from a different population. We identified distinct genomic and epigenomic properties of the subtypes. We determined drug sensitivities of the subtypes in primary tumors using clinical survival data, and in cell lines through high-throughput drug screening. RESULTS: We identified 3 subtypes of gastric adenocarcinoma: proliferative, metabolic, and mesenchymal. Tumors of the proliferative subtype had high levels of genomic instability, TP53 mutations, and DNA hypomethylation. Cancer cells of the metabolic subtype were more sensitive to 5-fluorouracil than the other subtypes. Furthermore, in 2 independent groups of patients, those with tumors of the metabolic subtype appeared to have greater benefits with 5-fluorouracil treatment. Tumors of the mesenchymal subtype contain cells with features of cancer stem cells, and cell lines of this subtype are particularly sensitive to phosphatidylinositol 3-kinase-AKT-mTOR inhibitors in vitro. CONCLUSIONS: Based on gene expression patterns, we classified gastric cancers into 3 subtypes, and validated these in an independent set of tumors. The subgroups have differences in molecular and genetic features and response to therapy; this information might be used to select specific treatment approaches for patients with gastric cancer.

Cathepsin S mediates gastric cancer cell migration and invasion via a putative network of metastasis-associated proteins.

Cancer progression is governed by multifaceted interactions of cancer cells with their microenvironment and one of these ways is through secreted compounds. Substances released by gastric cancer cells have not being profiled in a proteome-wide manner. ITRAQ-based tandem mass spectrometry was employed to quantify proteins secreted by HFE145 normal, MKN7 well-differentiated, and MKN45 poorly differentiated gastric cancer cell lines. The expression levels of 237 proteins were found to be significantly different between normal and cancer cells. Further examination of 16 gastric cell lines and 115 clinical samples validated the up-regulation of CTSS expression in gastric cancer. Silencing CTSS expression suppressed the migration and invasion of gastric cancer cells in vitro. Subsequent secretomics revealed that CTSS silencing resulted in changes in expression levels of 197 proteins, one-third of which are implicated in cellular movement. Proteome-wide comparative secretomes of normal and gastric cancer cells were produced that constitute a useful resource for gastric cancer research. CTSS was demonstrated to play novel roles in gastric cancer cell migration and invasion, putatively via a network of proteins associated with cell migration, invasion, or metastasis. Cathepsin S is member of a large group of extracellular proteases, which are attractive drug targets. The implicated role of CTSS in gastric cancer metastasis provides an opportunity to test existing compounds against CTSS for adjuvant therapy and/or treatment of metastatic gastric cancers.

PRL3-zumab as an immunotherapy to inhibit tumors expressing PRL3 oncoprotein.

Tumor-specific antibody drugs can serve as cancer therapy with minimal side effects. A humanized antibody, PRL3-zumab, specifically binds to an intracellular oncogenic phosphatase PRL3, which is frequently expressed in several cancers. Here we show that PRL3-zumab specifically inhibits PRL3+ cancer cells in vivo, but not in vitro. PRL3 antigens are detected on the cell surface and outer exosomal membranes, implying an 'inside-out' externalization of PRL3. PRL3-zumab binds to surface PRL3 in a manner consistent with that in classical antibody-dependent cell-mediated cytotoxicity or antibody-dependent cellular phagocytosis tumor elimination pathways, as PRL3-zumab requires an intact Fc region and host FcγII/III receptor engagement to recruit B cells, NK cells and macrophages to PRL3+ tumor microenvironments. PRL3 is overexpressed in 80.6% of 151 fresh-frozen tumor samples across 11 common cancers examined, but not in patient-matched normal tissues, thereby implicating PRL3 as a tumor-associated antigen. Targeting externalized PRL3 antigens with PRL3-zumab may represent a feasible approach for anti-tumor immunotherapy.

PRL3-zumab, a first-in-class humanized antibody for cancer therapy.

Novel, tumor-specific drugs are urgently needed for a breakthrough in cancer therapy. Herein, we generated a first-in-class humanized antibody (PRL3-zumab) against PRL-3, an intracellular tumor-associated phosphatase upregulated in multiple human cancers, for unconventional cancer immunotherapies. We focused on gastric cancer (GC), wherein elevated PRL-3 mRNA levels significantly correlated with shortened overall survival of GC patients. PRL-3 protein was overexpressed in 85% of fresh-frozen clinical gastric tumor samples examined but not in patient-matched normal gastric tissues. Using human GC cell lines, we demonstrated that PRL3-zumab specifically blocked PRL-3+, but not PRL-3-, orthotopic gastric tumors. In this setting, PRL3-zumab had better therapeutic efficacy as a monotherapy, rather than simultaneous combination with 5-fluorouracil or 5-fluorouracil alone. PRL3-zumab could also prevent PRL-3+ tumor recurrence. Mechanistically, we found that intracellular PRL-3 antigens could be externalized to become "extracellular oncotargets" that serve as bait for PRL3-zumab binding to potentially bridge and recruit immunocytes into tumor microenvironments for killing effects on cancer cells. In summary, our results document a comprehensive cancer therapeutic approach to specific antibody-targeted therapy against the PRL-3 oncotarget as a case study for developing antibodies against other intracellular targets in drug discovery.

Real-time Raman spectroscopy for in vivo, online gastric cancer diagnosis during clinical endoscopic examination.

Optical spectroscopic techniques including reflectance, fluorescence and Raman spectroscopy have shown promising potential for in vivo precancer and cancer diagnostics in a variety of organs. However, data-analysis has mostly been limited to post-processing and off-line algorithm development. In this work, we develop a fully automated on-line Raman spectral diagnostics framework integrated with a multimodal image-guided Raman technique for real-time in vivo cancer detection at endoscopy. A total of 2748 in vivo gastric tissue spectra (2465 normal and 283 cancer) were acquired from 305 patients recruited to construct a spectral database for diagnostic algorithms development. The novel diagnostic scheme developed implements on-line preprocessing, outlier detection based on principal component analysis statistics (i.e., Hotelling's T2 and Q-residuals) for tissue Raman spectra verification as well as for organ specific probabilistic diagnostics using different diagnostic algorithms. Free-running optical diagnosis and processing time of < 0.5 s can be achieved, which is critical to realizing real-time in vivo tissue diagnostics during clinical endoscopic examination. The optimized partial least squares-discriminant analysis (PLS-DA) models based on the randomly resampled training database (80% for learning and 20% for testing) provide the diagnostic accuracy of 85.6% [95% confidence interval (CI): 82.9% to 88.2%] [sensitivity of 80.5% (95% CI: 71.4% to 89.6%) and specificity of 86.2% (95% CI: 83.6% to 88.7%)] for the detection of gastric cancer. The PLS-DA algorithms are further applied prospectively on 10 gastric patients at gastroscopy, achieving the predictive accuracy of 80.0% (60/75) [sensitivity of 90.0% (27/30) and specificity of 73.3% (33/45)] for in vivo diagnosis of gastric cancer. The receiver operating characteristics curves further confirmed the efficacy of Raman endoscopy together with PLS-DA algorithms for in vivo prospective diagnosis of gastric cancer. This work successfully moves biomedical Raman spectroscopic technique into real-time, on-line clinical cancer diagnosis, especially in routine endoscopic diagnostic applications.