Hyperspectral Imaging to Discern Malignant and Benign Canine Mammary Tumors A Thesis Proposal Submitted to the Temple University Graduate Board

Hyperspectral imaging is an emerging technology in the field of biomedical engineering which may be used as a non-invasive modality for cancer characterization. In this project, we propose to investigate near-infrared (NIR) hyperspectral imaging for the characterization of canine mammary cancer. Nearinfrared hyperspectral imaging has been used for the detection of various kinds of human cancer; breast, gastric, prostate and tongue. A research group has also investigated the use of NIR reflectance imaging to detect canine cancer using fluorescent dyes. The use of NIR hyperspectral imaging, however, has been limited for the characterization of canine cancer. In this project, we have already acquired hyperspectral images of 22 canine mammary tumors. Preliminary results of 2 canine patients show that the spectra of canine cancer tissue differ from those of benign tissue. The malignant tissue has relatively low reflectance intensity compared to the benign tissue; in the wavelength range between 650nm to 1100nm.The decreased reflectance intensity observed for malignant tumors is due to the increased microvasculature and therefore higher blood content of cancerous tissue relative to benign tissue. In the future, we will normalize and preprocess the spectral dataset. We propose to apply various algorithms such as Support Vector Machine, Linear Discriminant Analysis, Principal Component Analysis and Tissue Optical Methods on the spectral data to discern the malignant and benign tumors. The advantage of cancer detection using hyperspectral imaging is that it is non-invasive and less time consuming than traditional methods like biopsy.