Main Content

Biomedical Imaging to Distinguish Normal, Precancerous and Cancerous Cells

In the area of biomedical imaging, hyperspectral imaging (HIS) is an emerging imaging modality for medical applications, especially in disease diagnosis and image-guided surgery.

At UMMC, we have begun to investigate the HSI technique to study cancer cells in liquid-based Pap test slides. HIS can combine conventional imaging and spectrophotometry and be employed to collect optical spectra from separate positions in a 2-dimensional spatial array, thus yielding another dimension of data, which together with the spatial and spectral dimensions can probe more completely for light interactions with pathology. The objective of our first project was to test the hypothesis that the cytologic diagnosis of cancer cells can be enhanced by the technique of hyperspectral imaging (HSI).

We employed HSI to obtain hyperspectrum from a normal human fibroblast, as well as its telomerase-immortalized and SV40-transformed derivatives. Novel algorithms were developed to differentiate among these cell models based on spectral and spatial differences. Using the same technique with modified algorithms, we were able to differentiate among normal and precancerous (low-grade [LG] and high-grade [HG]) cervical cells and squamous cell carcinoma (SCC) on liquid-based Papanicolaou (Pap) test slides.

The specificity for identifying normal fibroblast cell type based on spatial and spectral algorithms was 74.2%. The sensitivity for identifying telomeraseimmortalized and SV40-transformed cells was 100% and 90.3%, respectively. We were able to identify normal cervical cells with a specificity of 95.8%. With regard to LG precancerous cells and HG precancerous cells, the sensitivity was 66.7% and 93.5%, respectively. The sensitivity detected for SCC was 98.6%.

From this study, we were able to conclude that HSI can be utilized in prescreening liquid-based Pap test slides to improve efficiency in Pap test diagnoses with the goal of ultimately reducing the mortality from cervical cancer while reducing health care costs.

UMMC is now currently seeking funding support also to investigate the usefulness of HIS in detecting other cancer cells. We would like to develop an automated system to recognize cancer stages utilizing a HIS library.