Multi-view 3D second harmonic generation(SHG) imaging and texture analysis for ovarian cancer classification
We are interested in developing imaging techniques to understand how the extracellular matrix is remodeled in ovarian cancer. Under the direction of Paul Campagnola and Rock Mackie, we have developed imaging techniques to acquire 3D extracellular matrix imaging by directing laser focus from four different directions for reconstruction. To quantitate remodeling, we implement a 3D texture analysis to delineate the collagen fibrillar morphology observed in second harmonic generation microscopy images of human normal and high grade malignant ovarian tissues. In the learning stage, a dictionary of “textons”—frequently occurring texture features that are identified by measuring the image response to a filter bank of various shapes, sizes, and orientations—is created. By calculating a representative model based on the texton distribution for each tissue type using a training set of respective second harmonic generation images, we then perform classification between images of normal and high grade malignant ovarian tissues. For 3D texture, we did classification based on the area under receiver operating characteristic curves (true positives versus false positives). The local analysis algorithm is a more general method to probe rapidly changing fibrillar morphologies than global analyses such as FFT. It is also more versatile than other texture approaches as the filter bank can be highly tailored to specific applications (e.g., different disease states) by creating customized libraries based on common image features.