ALAlbert S. M. Li

Albert S. M. Li

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Albert S. M. Li has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    AI Deployment on GBM Diagnosis: A Novel Approach to Analyze Histopathological Images Using Image Feature-Based Analysis

    by Eva Y. W. Cheung, Ricky W. K. Wu, Albert S. M. Li, Ellie S. M. Chu

    Background: Glioblastoma (GBM) is one of the most common malignant primary brain tumors, which accounts for 60–70% of all gliomas. Conventional diagnosis and the decision of post-operation treatment plan for glioblastoma is mainly based on the feature-based qualitative analysis of hematoxylin and eosin-stained (H&E) histopathological slides by both an experienced medical technologist and a pathologist. The recent development of digital whole slide scanners makes AI-based histopathological image analysis feasible and helps to diagnose cancer by accurately counting cell types and/or quantitative analysis. However, the technology available for digital slide image analysis is still very limited. This study aimed to build an image feature-based computer model using histopathology whole slide images to differentiate patients with glioblastoma (GBM) from healthy control (HC). Method: Two independent cohorts of patients were used. The first cohort was composed of 262 GBM patients of the Cancer Genome Atlas Glioblastoma Multiform Collection (TCGA-GBM) dataset from the cancer imaging archive (TCIA) database. The second cohort was composed of 60 GBM patients collected from a local hospital. Also, a group of 60 participants with no known brain disease were collected. All the H&E slides were collected. Thirty-three image features (22 GLCM and 11 GLRLM) were retrieved from the tumor volume delineated by medical technologist on H&E slides. Five machine-learning algorithms including decision-tree (DT), extreme-boost (EB), support vector machine (SVM), random forest (RF), and linear model (LM) were used to build five models using the image features extracted from the first cohort of patients. Models built were deployed using the selected key image features for GBM diagnosis from the second cohort (local patients) as model testing, to identify and verify key image features for GBM diagnosis. Results: All five machine learning algorithms demonstrated excellent performance in GBM diagnosis and achieved an overall accuracy of 100% in the training and validation stage. A total of 12 GLCM and 3 GLRLM image features were identified and they showed a significant difference between the normal and the GBM image. However, only the SVM model maintained its excellent performance in the deployment of the models using the independent local cohort, with an accuracy of 93.5%, sensitivity of 86.95%, and specificity of 99.73%. Conclusion: In this study, we have identified 12 GLCM and 3 GLRLM image features which can aid the GBM diagnosis. Among the five models built, the SVM model proposed in this study demonstrated excellent accuracy with very good sensitivity and specificity. It could potentially be used for GBM diagnosis and future clinical application.


  • Thin-Layer Cytology Findings of Small Cell Carcinoma of the Lower Female Genital Tract

    by Wai-Kuen Ng, Leslie K. N. Cheung, Albert S. M. Li, Simon K. M. Tse, Siu-Wah Pang, Janson C. Y. Chow

    To describe the thin-layer cytology findings of small cell carcinoma of the low female genital tract, with histologic correlation and human papillomavirus (HPV) genotyping. The authors reviewed the clinical findings, thin-layer cytology and histologic features of small cell carcinoma of the lower female genital tract (cervix or vagina) occurring in three postmenopausal Chinese women at Pamela Youde Nethersole Eastern Hospital, Hong Kong, over a four-year period, from January 1998 to December 2001. Molecular techniques for HPV screening and genotyping using the polymerase chain reaction and restriction fragment length polymorphism were employed on the cytologic specimens. The thin-layer preparations were of moderate to high cellularity. There were loose aggregates of or isolated small round cells with a high nuclear/cytoplasmic ratio, thin but irregular nuclear membrane, hyperchromatic nuclei, inconspicuous nucleoli and scanty cytoplasm. Tumor cell cannibalism was commonly found. Small groups of tumor cells with nuclear molding were noted. There was also obvious tumor diathesis in the background. The necrotic debris was admixed with isolated small round cells, apoptotic bodies and nuclear dust. Associated koilocytosis or squamous intraepithelial lesions were not seen. Histologic examination of the tumor biopsies showed classic features of small cell carcinoma associated with squashing artifacts and vascularized stroma. Molecular analysis revealed the presence of HPV DNA (either type 18 or 16) in all the three liquid-based cytology samples. While the cytomorphologic features of small cell carcinoma of the cervix or vagina in thin-layer preparations are slightly different from those in conventional smears, due mainly to the absence of smearing effect, recognition of the subtle but characteristic appearance can enhance the accuracy of the cytologic diagnosis. The association between HPV and primary small cell carcinoma of the lower female genital tract was confirmed by this study.