Biomedical engineering researchers at Case Western Reserve University are using computerized imaging to provide new tools in better diagnosing and treating cancers, specifically prostate and estrogen receptor positive (ER+) breast cancers.
Preliminary computerized imagine reveals the shape of the prostate and a compartment within the gland—called the transitional zone—consistently differ in men with prostate cancer than in those without the disease, according to new research led by Anant Madabhushi, the F. Alex Nason professor II of biomedical engineering and director of the university’s Center for Computational Imaging and Personalized Diagnostics (CCIPD).
The findings, published in Scientific Reports, may provide a new avenue to diagnose the disease—perhaps even the cancer’s aggressiveness.
Madabhushi also led a research team that discovered the number of tubules in tumors may predict which women with estrogen receptor positive (ER+) breast cancer will benefit from hormone therapy alone and which require chemotherapy.
Tubules represent the tumor’s vasculature, providing tumors with oxygen and nutrition. The more of them there are, the more likely a patient will need chemotherapy.
In the study, also published in Scientific Reports, the researchers developed a computer program to automatically count the number of tubules found in whole slide images of breast cancer tissue specimens. They found the number of tubules correlated with the scores produced by the current best test differentiating between indolent and aggressive ER+ cancers.
In addition to the published findings, CCIPD researchers have been awarded four patents related to computational imaging technology:
- U.S. patent 9,483,822 for technology capturing intra-tumoral heterogeneity on radiographic imaging.
- U.S. patent 9,424,460 entitled “Tumor Plus Adjacent Benign Signature (TABS) for Quantitative Histomophometry,” which describes methods, apparatus and other embodiments associate with predicting prostate cancer progression
- U.S. patent 9,430,829 entitled “Automatic Detection of Mitosis Using Handcrafted and Convolutional Neural Network Features," which describes the apparatus associated with detecting mitosis in breast cancer pathology images by combining handcrafted and convolutional neural network features in a cascaded architecture.
- U.S. patent 9,430,830 entitled "Spatially Aware Cell Cluster (SpACCl) Graphs for Quantitative Histomorphometry," which describes the methods, apparatus, and other embodiments associated with objectively predicting disease aggressiveness using Spatially Aware Cell Cluster (SpACCl) graphs.
- U.S. patent 20150254494 for for capturing cancer architecture in digital pathology images.