Computational Pathology for improved cancer management and better human sustainability
According to Cancer Research UK, there are around One Million cancer deaths every year between 2016-2018. Cancer accounts for more than a quarter (28%) of all deaths during 2018. Medical experts distinguish over 100 different types of cancer. However, it is increasingly accepted that every single type of cancer is a heterogeneous disease requiring ‘personalized and precise’ treatment tailored to an individual’s genetic makeup and to the very specific features of his or her cancer.
Quantitative spatial profiling of the tumor microenvironment coupled with genomic profiling of cancer is the key to objective selection of optimal treatment for cancer patients. Moreover, it will also help the pathologists better understand that how the immune system responds to the growth and spread of cancer and/or to a particular treatment.
Main research theme in computational pathology
- To develop computer vision-based techniques for detecting and segmentation tissue structures in digital histology images to better understand and quantifysegmentation of tissue structures in digital histology images, to better understand and quantifyunderstanding and quantification of tumor micro-environment.
- To develop novel AI-based techniques for the discovery of new diagnostic, prognostic, and predictive digital biomarkers. These biomarkers are based on tissue morphology and architecture, tumor-immune microenvironment, and spatial signatures of a combination of the tumor, peri-tumor, and even some of the non-tumor regions in digital pathology images.
- To develop AI-based processing pipelines for histological and medical data with the aim to predict the overall survival, specific survival, event-free survival, or recurrence-free survival of patients. This can eventually lead to the development of tailor-made preventive diagnostics, therapeutics, and disease management strategies based on an individual’s omics profiles in a “big data” approach by exploiting the complex relationships and hidden patterns in the available “data”, of histological images as well as in genomics. The “big data” is analyzed for estimating pre-malignancy diagnosis, quantifying therapy response, disease stage, survival prediction, and precision medicine techniques.
In big picture, we envision to develop next generation of Computational Pathology based tools and technologies that can be used in clinical practice enabling improved diagnosis, grading, prognosis, and treatment planning of cancer patients.
- Sajid Javed, A. Mahmood, M. M. Fraz, , NA Koohbanani, K. Benes, Yee-Wah Tsang, K. Hewitt, D, Epstein, D. Snead, NM Rajpoot , “Cellular community detection for tissue phenotyping in colorectal cancer histology images”, Medical Image Analysis, Vol. 63 , No. 1, Jul, 2020. IF: 8.88
- M. Shaban, R. Awan, M.M. Fraz , A. Azam, Y. Tsang, D. Snead, N.M. Rajpoot , “Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images”, IEEE Transactions on Medical Imaging, Vol. 21 , No. 1, Feb, 2020. IF: 7.81
- M.M. Fraz , S. A. Khurran, S. Graham, M. Shaban, Asif Loya, N.M. Rajpoot , “FABnet: Feature attention based network for simultaneous segmentation of microvessels and nerves in routine histology images of oral cancer”, Neural Computing and Applications, Vol. 20 , No. 1, Nov, 2019. IF: 4.66
- M. Shaban, S.A. Khurram, M. M. Fraz , N. Alsubaie, I. Masood, S. Mushtaq, M. Hassan, A. Loya & N. M. Rajpoot , “A Novel Digital Score for Abundance of Tumour Infiltrating Lymphocytes Predicts Disease Free Survival in Oral Squamous Cell Carcinoma”, Nature Scientific Reports, Vol. 9 , No. 1, PP. 13341 (2019) , Sep, 2019. IF: 4.525
- R.M.S. Bashir, H. Mahmood, M. Shaban, SEA Raza, M. M. Fraz, , S.A. Khurram, N. M. Rajpoot , “Automated grade classification of oral epithelial dysplasia using morphometric analysis of histology images”, Proceedings of the Medical Imaging 2020: Digital Pathology, Feb, 2020, Houston, Texas , USA.
- M.M.Fraz, M.Shaban, S.Graham, S.A.Khurram, N.M.Rajpoot , , “Uncertainty Driven Pooling Network for Microvessel Segmentation in Routine Histology Images”, Proceedings of COMPAY workshop in 21st International Conference on Medical Image Computing and Computer Assisted Intervention, Sep, 2018, Granada , Spain.
- Sajid Javed, M.M. Fraz, David Epstein, David Snead, and Nasir M. Rajpoot , , “Cellular Community Detection for Tissue Classification”, Proceedings of COMPAY workshop in 21st International Conference on Medical Image Computing and Computer Assisted Intervention, Sep, 2018, Granada, Spain.