Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster viewing 06

408P - Machine learning for glioblastoma screening from histopathology whole slide imaging


03 Dec 2022


Poster viewing 06


Secondary Prevention/Screening;  Cancer Diagnostics

Tumour Site

Central Nervous System Malignancies


Eva Yi Wah Cheung


Annals of Oncology (2022) 33 (suppl_9): S1598-S1618. 10.1016/annonc/annonc1135


E.Y.W. Cheung1, E.S.M. Chu2, A.S.M. Li3, F. Tang3, R.W. Wu4

Author affiliations

  • 1 Mhs Department, TWC - Tung Wah College - King's Park Campus, 00852 - Kowloon/HK
  • 2 School Of Medical And Health Sciences, Tung Wah College, 852 - Hong Kong/HK
  • 3 Mhs, TWC - Tung Wah College - King's Park Campus, 00852 - Kowloon/HK
  • 4 Department Of Biological And Biomedical Sciences, School Of Health And Life Sciences, Glasgow Caledonian University, Glasgow/GB

Abstract 408P


Glioblastoma (GBM) is one of the most common malignant primary brain tumours, which accounts for 60-70% of all glioma. Conventional diagnosis and post-operation treatment plan for glioblastoma is mainly based on the identification of tumor cells on haematoxylin and eosin stained (H&E) histopathological slides by both experienced medical technologist and pathologist. The recent development of digital whole slide scanners allows the histopathological image analysis feasible. This study aimed to build an image feature based model using histopathology whole slide images to differentiate patients with GBM from healthy control (HC).


628 H&E images were collected from 30 GBM patients, obtained from public database the Cancer Image Archive. Another 554 images were collected from 30 HC. 22 Gray level Co-occurrence Matrix (GLCM) image features were retrieved from the collected images by an in-house developed software. Both the GBM and HC groups were divided into a training and a validation group on 70:30 basis. A random forest algorithm was used to build the model using training set, and validated by the validation set by R software.


The receiver operating characteristics (ROC) curve showed that the average class and overall accuracy achieved 94.6%. The area under the curve (AUC) was 0.98, with sensitivity of 94.1% and sensitivity of 95.1%.


The machine learning model can accurately differentiate GBM from HC in histopathology whole slide imaging. The application can be fully automatic and it is practical in applying for GBM screening.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

The authors.


College Research Grant (CRG) - Tung Wah College.


All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.