Dual primary gastric and colorectal cancer:The known hereditary causes and underlying mechanisms

In this editorial,I commented on the paper by Lin et al,published in this issue of the World Journal of Gastrointestinal Oncology.The work aimed at analysing the clinicopathologic characteristics and prognosis of synchronous and metachronous cancers in patients with dual primary gastric and colorectal cancer(CRC).The authors concluded the necessity for regular surveillance for metachronous cancer during postoperative follow-up and reported the prognosis is influenced by the gastric cancer(GC)stage rather than the CRC stage.Although surveillance was recommended in the conclusion,the authors did not explore this area in their study and did not include tests used for such surveillance.This editorial focuses on the most characterized gastrointestinal cancer susceptibility syndromes concerning dual gastric and CRCs.These include hereditary diffuse GC,familial adenomatous polyposis,hereditary nonpolyposis colon cancer,Lynch syndrome,and three major hamartomatous polyposis syndromes associated with CRC and GC,namely Peutz-Jeghers syndrome,juvenile polyposis syndrome,and PTEN hamartoma syndrome.Careful assessment of these syndromes/conditions,including inheritance,risk of gastric and colorectal or other cancer development,genetic mutations and recommended genetic investigations,is crucial for optimum management of these patients.

Deep learning with convolutional neural networks for identification of liver masses and hepatocellular carcinoma: A systematic review

BACKGROUND Artificial intelligence,such as convolutional neural networks(CNNs),has been used in the interpretation of images and the diagnosis of hepatocellular cancer(HCC)and liver masses.CNN,a machine-learning algorithm similar to deep learning,has demonstrated its capability to recognise specific features that can detect pathological lesions.AIM To assess the use of CNNs in examining HCC and liver masses images in the diagnosis of cancer and evaluating the accuracy level of CNNs and their performance.METHODS The databases PubMed,EMBASE,and the Web of Science and research books were systematically searched using related keywords.Studies analysing pathological anatomy,cellular,and radiological images on HCC or liver masses using CNNs were identified according to the study protocol to detect cancer,differentiating cancer from other lesions,or staging the lesion.The data were extracted as per a predefined extraction.The accuracy level and performance of the CNNs in detecting cancer or early stages of cancer were analysed.The primary outcomes of the study were analysing the type of cancer or liver mass and identifying the type of images that showed optimum accuracy in cancer detection.RESULTS A total of 11 studies that met the selection criteria and were consistent with the aims of the study were identified.The studies demonstrated the ability to differentiate liver masses or differentiate HCC from other lesions(n=6),HCC from cirrhosis or development of new tumours(n=3),and HCC nuclei grading or segmentation(n=2).The CNNs showed satisfactory levels of accuracy.The studies aimed at detecting lesions(n=4),classification(n=5),and segmentation(n=2).Several methods were used to assess the accuracy of CNN models used.CONCLUSION The role of CNNs in analysing images and as tools in early detection of HCC or liver masses has been demonstrated in these studies.While a few limitations have been identified in these studies,overall there was an optimal level of accuracy of the CNNs used in segmentation and classification of liver cancers images.

Inflammatory bowel disease: An evaluation of health information on the internet

AIM To evaluate the quality and accuracy of websites written to the public on inflammatory bowel disease(IBD)(Crohn's disease and ulcerative colitis) and assess their readability level.METHODS Google?, Bing?, and Yahoo? search engines were searched independently by three researchers in December 2014. Only English-language websites were selected on the basis of predetermined inclusion and exclusion criteria. Researchers independently evaluated the quality of each website by using the DISCERN and the HONcode instruments. The readability levels were calculated using two formulas; the Flesch-Kincaid Grade Level Index, and the Coleman-Liau Readability Index. The agreement between the evaluators was calculated using Cohen kappa coefficient.RESULTS Eighty-four websites were finally identified. Scores varied from a minimum DISCERN score of 18 to a maximum of 68 [mean ± SD, 42.2 ± 10.7; median = 41.5, interquartile range, interquartile range (IQR) = 15.8] and a minimum score of HONcode of 0.14 and a maximum of 0.95 (mean ± SD, 0.16 ± 0.19; median = 0.45, IQR = 0.29). Most of these websites were reviewed in 2014 and 2015 (n = 51). The creators of these websites were: universities and research centers(n = 25, 30%), foundations and associations (n = 15, 18%), commercial and pharmaceutical companies(n =25, 30%), charities and volunteer work(n = 9, 10%), and non-university educational bodies (n = 10, 12%). The Flesch-Kincaid Grade Level readability score(mean ± SD) was 11.9 ± 2.4 and the Coleman-Liau Readability Index score was 12.6 ± 1.5. Significant correlation was found between the two readability scores (R2 = 0.509, P = 0.001). The overall agreement between evaluators measured by Cohen kappa coefficient was in the range of 0.804-0.876; rated as "Good".CONCLUSION The DISCERN and the HONcode scores of websites varied and the readability levels of most websites were above the public readability level. The study highlights the areas that need further improvement and development in patient education online materials about IBD.