Project

Machine Learning for Combined Classification of Fluorescent Biomarkers and Expert Annotations Using White Light Images

Biomarker imaging provides non-invasive indicators of disease and is used by human experts to augment disease diagnosis. It is, however, often expensive and reliant on experts to interpret the resulting images. We have developed a process for learning associations between standard white light images and both biomarkers and expert annotations of disease. Oral imaging is one particular example of biomarker imaging that can supplement expert knowledge; the biomarker porphyrin is associated with poor oral health and oral cancer. We report that our process learns to accurately predict the presence of porphyrin and expert-annotated conditions.

Why is this work important?

Biomarker imaging provides non-invasive indicators of disease and is used by human experts to augment disease diagnosis. Capturing biomarker images requires specialized and often expensive hardware, annotations, and analyses by experts, resulting in substantial diagnosis delays.

What has been done before?

Even when biomarker imaging is available, experts are often needed to interpret the resulting images. There is a rich literature on medical image segmentation,… View full description

Biomarker imaging provides non-invasive indicators of disease and is used by human experts to augment disease diagnosis. It is, however, often expensive and reliant on experts to interpret the resulting images. We have developed a process for learning associations between standard white light images and both biomarkers and expert annotations of disease. Oral imaging is one particular example of biomarker imaging that can supplement expert knowledge; the biomarker porphyrin is associated with poor oral health and oral cancer. We report that our process learns to accurately predict the presence of porphyrin and expert-annotated conditions.

Why is this work important?

Biomarker imaging provides non-invasive indicators of disease and is used by human experts to augment disease diagnosis. Capturing biomarker images requires specialized and often expensive hardware, annotations, and analyses by experts, resulting in substantial diagnosis delays.

What has been done before?

Even when biomarker imaging is available, experts are often needed to interpret the resulting images. There is a rich literature on medical image segmentation, but many approaches—especially deep learning—require large amounts of images and operate on information from only a single given imaging modality.

What are our contributions?

We successfully learn assocations between images and union signatures of biomarker presence and expert disease annotations. By transforming the image-level segmentation problem into a region-based problem, we are able to learn from far fewer images than other approaches. We specifically test our approach on detecting the biomarker porphyrin and associated conditions in millions of image patches. Once trained, the classifiers predict the location of porphyrin in images without requiring specialized biomarker imaging devices or expert intervention.

What are the next steps?

We are developing processes incorporating numerous other biomarkers, conditions, and imaging modalities.

Related projects

  1. Biomarker Imaging with Mobile Phones