TWTang Wong

Tang Wong

*This is an algorithmically generated author record based on publicly available information.

Tang Wong has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-Class Gastroesophageal Reflux Disease Classification System Using Deep Learning Techniques

    by Tang Wong, Pak Kin Wong, Tao Yan, In Weng Chan, Hao Ren, Chon In Chan

    Gastroesophageal reflux disease (GERD) has been a ubiquitous health problem for centuries. Its symptoms are hard to distinguish and endoscopists with less experience usually find it difficult to diagnose the severity of GERD, and this disease might progress to more severe diseases like Barrett’s esophagus without adequate treatment. Therefore, we proposed a multi-class classification system, which comprised a deep learning (DL) model and graphical user interface (GUI), to classify GERD grading from endoscopic images so as to provide finer predictions on erosive esophagus and easier assessment to the system. The Los Angeles Classification system (LACS) was selected as the standard for severity grading. We collected 3,654 white light (WL) esophagoscopic images from the database engine of Xiangyang Centre Hospital. We built the DL model using pre-trained convolutional neural network (CNN) model as the backbone, and different pre-trained models were used and compared. We also evaluated the effectiveness of applying data resampling and attention map to the DL model for optimizing model performance. Besides, data augmentation was also employed. After the best model was selected, we built the GUI using HuggingFace. Experimental results showed that DenseNet121 with oversampling and attention map achieved the best results with an accuracy of 0.7469, recall of 0.7057 and Cohen’s kappa of 0.7757. It was also discovered that the experimental groups using both techniques outperformed the others, while using DenseNet121 obtained better results considering all experimental groups. The model outputs were displayed in terms of the predicted label, probabilities for each grade and a heatmap containing highlighted attention. In conclusion, a multi-class DL classification system was developed for GERD grading classification, and it exhibited its potentially acceptable efficacy for GERD diagnosis based on the LACS.


  • Open Access

    MEN4, the MEN1 Mimicker: A Case Series of three Phenotypically Heterogenous Patients With Unique CDKN1B Mutations

    by Amanda Seabrook, Ayanthi Wijewardene, Sunita De Sousa, Tang Wong, Nisa Sheriff, Anthony J Gill, Rakesh Iyer, Michael Field, Catherine Luxford, Roderick Clifton-Bligh, et al.

    Context Germline CDKN1B pathogenic variants result in multiple endocrine neoplasia type 4 (MEN4), an autosomal dominant hereditary tumor syndrome variably associated with primary hyperparathyroidism, pituitary adenoma, and duodenopancreatic neuroendocrine tumors. Objective To report the phenotype of 3 unrelated cases each with a unique germline CDKN1B variant (of which 2 are novel) and compare these cases with those described in the current literature. Design/Methods Three case studies, including clinical presentation, germline, and tumor genetic analysis and family history. Setting Two tertiary University Hospitals in Sydney, New South Wales, and 1 tertiary University Hospital in Canberra, Australian Capital Territory, Australia. Outcome Phenotype of the 3 cases and their kindred; molecular analysis and tumor p27kip1 immunohistochemistry. Results Family A: The proband developed multiglandular primary hyperparathyroidism, a microprolactinoma and a multifocal nonfunctioning duodenopancreatic neuroendocrine tumor. Family B: The proband was diagnosed with primary hyperparathyroidism from a single parathyroid adenoma. Family C: The proband was diagnosed with a nonfunctioning pituitary microadenoma and ectopic Cushing’s syndrome from an atypical thymic carcinoid tumor. Germline sequencing in each patient identified a unique variant in CDKN1B, 2 of which are novel (c.179G > A, p.Trp60*; c.475G > A, p.Asp159Asn) and 1 previously reported (c.374_375delCT, p.Ser125*). Conclusions Germline CDKN1B pathogenic variants cause the syndrome MEN4. The phenotype resulting from the 3 pathogenic variants described in this series highlights the heterogenous nature of this syndrome, ranging from isolated primary hyperparathyroidism to the full spectrum of endocrine manifestations. We report the first described cases of a prolactinoma and an atypical thymic carcinoid tumor in MEN4.