Using statistical methods to grade cancer severity in histopathology images

Faculty Mentor: Ana-Maria Staicu
Prerequisites: Probability, statistical computing.

Outline: Cancer detection and progression have been revolutionized by the development of modern medical imaging techniques. Typically, scanning via computed tomography (CT), magnetic resonance imaging (MRI), or ultrasound is used to identify cancer with high accuracy, while histopathological imaging is employed to further understand cancer growth. Histopathology images are acquired through a complex procedure that involves staining the tissue specimens with specific stains, which are meant to increase the contrast between the normal and cancer cells. Examination and interpretation of the histopathology images are generally performed by highly trained anatomic pathologists; although recent methods in machine learning have shown great promise to automatize the latter step.

Research objectives: In this project we will review and compare a few popular methods to automatically grade cancer type with the goal to develop a new approach that leverages the advantages of existing methods.

Outcomes: The project examines the performance of statistical methods to grade cancer types for specified cancers, using histopathology images.


  • Ayyad, Sarah M., Mohamed Shehata, Ahmed Shalaby, Abou El-Ghar, Mohammed Ghazal, Moumen El-Melegy, Nahla B. Abdel-Hamid, Labib M. Labib, H. Arafat Ali, and Ayman El-Baz. “Role of AI and Histopathological Images in Detecting Prostate Cancer: A Survey.” Sensors 21, no. 8 (2021): 2586.
  • Bulten, Wouter, Péter Bándi, Jeffrey Hoven, Rob van de Loo, Johannes Lotz, Nick Weiss, Jeroen van der Laak, Bram van Ginneken, Christina Hulsbergen-van de Kaa, and Geert Litjens. “Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard.” Scientific reports 9, no. 1 (2019): 1-10.
  • He, L., Long, L. R., Antani, S., & Thoma, G. R. (2012). Histology image analysis for carcinoma detection and grading. Computer methods and programs in biomedicine, 107(3), 538-556.
  • Hu, Z., Tang, J., Wang, Z., Zhang, K., Zhang, L., & Sun, Q. (2018). Deep learning for image-based cancer detection and diagnosis− A survey. Pattern Recognition, 83, 134-149.