Background: Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading to better patient outcomes. Objective: We performed an umbrella review to summarize and critically evaluate the evidence for the AI-based imaging diagnosis of cancers. Methods: PubMed, Embase, Web of Science, Cochrane, and IEEE databases were searched for relevant systematic reviews from inception to June 19, 2024. Two independent investigators abstracted data and assessed the quality of evidence, using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Systematic Reviews and Research Syntheses. We further assessed the quality of evidence in each meta-analysis by applying the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria. Diagnostic performance data were synthesized narratively. Results: In a comprehensive analysis of 158 included studies evaluating the performance of AI algorithms in noninvasive imaging diagnosis across 8 major human system cancers, the accuracy of the classifiers for central nervous system cancers varied widely (ranging from 48% to 100%). Similarities were observed in the diagnostic performance for cancers of the head and neck, respiratory system, digestive system, urinary system, female-related systems, skin, and other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 reviews meta-analyzed sensitivity and specificity for esophageal cancer, showing ranges of 90%-95% and 80%-93.8%, respectively. In the case of breast cancer detection, 8 reviews calculated the pooled sensitivity and specificity within the ranges of 75.4%-92% and 83%-90.6%, respectively. Four meta-analyses reported the ranges of sensitivity and specificity in ovarian cancer, and both were 75%-94%. Notably, in lung cancer, the pooled specificity was relatively low, primarily distributed between 65% and 80%. Furthermore, 80.4% (127/158) of the included studies were of high quality according to the JBI Critical Appraisal Checklist, with the remaining studies classified as medium quality. The GRADE assessment indicated that the overall quality of the evidence was moderate to low. Conclusions: Although AI shows great potential for achieving accelerated, accurate, and more objective diagnoses of multiple cancers, there are still hurdles to overcome before its implementation in clinical settings. The present findings highlight that a concerted effort from the research community, clinicians, and policymakers is required to overcome existing hurdles and translate this potential into improved patient outcomes and health care delivery. Trial Registration: PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278

BACKGROUND:Differentiation of malignant from benign liver tumors remains a challenging problem. In recent years, mass spectrometry (MS) technique has emerged as a promising strategy to diagnose a wide range of malignant tumors. The purpose of this st...

Background: Oral squamous cell carcinoma (OSCC), a form of head and neck squamous cell carcinoma (HNSCC) has a poor 5-year survival rate. OSCC patients are often treated with cisplatin but resistance to chemotherapy is often observed. This makes it important identification of alternative therapeutic targets which will result in more favorable outcome in OSCC patients. The plant homeodomain (PHD)-containing protein Inhibitor of Growth family of tumor suppressor proteins (p33ING1b) has been indicated as a tumor suppressor in different cancers including OSCC. This protein has been shown to function by modulating transcriptional activity of p53; however, the exact mechanism(s) are not well defined. Methods: Expression of total and acetylated p53 and p33ING1b protein was determined in OSCC cell lines YD-9, YD-8, and YD-38 by immunoblot analysis. Effect of modulation of p33ING1b protein expression on acetylation of p53 and cell proliferation was determined by immunoblot and MTT assay. Effect of modulation of p33ING1b protein expression on transactivation of p53 was assessed by heterologous promoter-based reporter and chromatin immunoprecipitation. Effect of modulation of expression of p33ING1b on SIR2 mRNA and protein was determined by quantitative real-time PCR and immunoblot analyses. Impact of modulation of p33ING1b alone or in combination with SIR2 on chemosensitivity of YD-9 and YD-8 cells to cisplatin was determined in time and dose-dependent cell proliferation assays. Results: Here, using a panel of OSCC cell lines with wild type or mutant p53, we show that p33ING1b expression is correlated to acetylation of p53 at lysine 382 residue. Increased acetylation of p53 following overexpression of p33ING1b was associated with increased expression of the pro-apoptotic proteins BAX, p21, and cleaved-Caspase 3, and decreased cell proliferation. Reporter assays with p21 and BAX promoters showed that p33ING1b expression levels directly correlated to promoter activity of these 2 genes. Chromatin immunoprecipitation assay showed that transcriptional regulation of p21 and BAX by acetylated p53 is dependent on expression level of p33ING1b. Differential acetylation of p53 following modulation of p33ING1b expression was indirect. Expression of p33ING1b was found to be inversely correlated to the NAD-dependent deacetylase silent information regulator 2 (SIR2). SIR2 was transcriptionally regulated by p33ING1b. Relative expression of p33ING1b was found to dictate chemosensitivity of OSCC cell lines to cisplatin treatment. Concomitant overexpression of p33ING1b and knockdown of SIR2 had a synergistic effect on chemosensitivity of OSCC cell lines to cisplatin, compared to either overexpression of p33ING1b or knockdown of SIR2 alone. Conclusions: The results from the current study thus elucidate that p33ING1b regulates p53 acetylation irrespective of p53 mutation and subsequent transactivation by transcriptional regulation of SIR2 expression. The results also indicate that p33ING1b and SIR2 are potentially attractive therapeutic targets.

BACKGROUND Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading to better patient outcomes. OBJECTIVE We performed an umbrella review to summarize and critically evaluate the evidence for the AI-based imaging diagnosis of cancers. METHODS PubMed, Embase, Web of Science, Cochrane, and IEEE databases were searched for relevant systematic reviews from inception to June 19, 2024. Two independent investigators abstracted data and assessed the quality of evidence, using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Systematic Reviews and Research Syntheses. We further assessed the quality of evidence in each meta-analysis by applying the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria. Diagnostic performance data were synthesized narratively. RESULTS In a comprehensive analysis of 158 included studies evaluating the performance of AI algorithms in noninvasive imaging diagnosis across 8 major human system cancers, the accuracy of the classifiers for central nervous system cancers varied widely (ranging from 48% to 100%). Similarities were observed in the diagnostic performance for cancers of the head and neck, respiratory system, digestive system, urinary system, female-related systems, skin, and other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 reviews meta-analyzed sensitivity and specificity for esophageal cancer, showing ranges of 90%-95% and 80%-93.8%, respectively. In the case of breast cancer detection, 8 reviews calculated the pooled sensitivity and specificity within the ranges of 75.4%-92% and 83%-90.6%, respectively. Four meta-analyses reported the ranges of sensitivity and specificity in ovarian cancer, and both were 75%-94%. Notably, in lung cancer, the pooled specificity was relatively low, primarily distributed between 65% and 80%. Furthermore, 80.4% (127/158) of the included studies were of high quality according to the JBI Critical Appraisal Checklist, with the remaining studies classified as medium quality. The GRADE assessment indicated that the overall quality of the evidence was moderate to low. CONCLUSIONS Although AI shows great potential for achieving accelerated, accurate, and more objective diagnoses of multiple cancers, there are still hurdles to overcome before its implementation in clinical settings. The present findings highlight that a concerted effort from the research community, clinicians, and policymakers is required to overcome existing hurdles and translate this potential into improved patient outcomes and health care delivery. CLINICALTRIAL PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278