Multispectral band selection and spatial characterization: Application to mitosis detection in breast cancer histopathology.

Breast cancer is the second most frequent cancer. The reference process for breast cancer prognosis is Nottingham grading system. According to this system, mitosis detection is one of the three important criteria required for grading process and quantifying the locality and prognosis of a tumor. Multispectral imaging, as relatively new to the field of histopathology, has the advantage, over traditional RGB imaging, to capture spectrally resolved information at specific frequencies, across the electromagnetic spectrum. This study aims at evaluating the accuracy of mitosis detection on histopathological multispectral images. The proposed framework includes: selection of spectral bands and focal planes, detection of candidate mitotic regions and computation of morphological and multispectral statistical features. A state-of-the-art of the methods for mitosis classification is also provided. This framework has been evaluated on MITOS multispectral dataset and achieved higher detection rate (67.35%) and F-Measure (63.74%) than the best MITOS contest results (Roux et al., 2013). Our results indicate that the selected multispectral bands have more discriminant information than a single spectral band or all spectral bands for mitotic figures, validating the interest of using multispectral images to improve the quality of the diagnostic in histopathology.

VARIATIONAL LEVEL-SET WITH GAUSSIAN SHAPE MODEL FOR CELL SEGMENTATION.

In analysis of microscopy based images, a major challenge lies in splitting apart cells that appear to overlap because they are too densely packed. This task is complicated by the physics of the image acquisition that causes large variations in pixel intensities. Each image typically contains thousands of cells with each cell having a different orientation, size and intensity histogram. In this paper, a spatial intensity model of a nucleus is incorporated into [1] to aid cell segmentation from microscopy datasets. An energy functional is defined and with it the spatial intensity distribution of a nuclei is modeled as a Gaussian distribution with constant intensity background. Experimental results on a variety of microscopic data validate its effectiveness.

TISSUE LEVEL SEGMENTATION AND TRACKING OF BIOLOGICAL STRUCTURES IN MICROSCOPIC IMAGES BASED ON DENSITY MAPS.

During embryogenesis, cells coordinate to form geometric arrangements. These arrangements are initially noticed as stereotypical clumps of cells that further divide to form a rigorous structure with a high density of cells. In this work, we explore density-based segmentation and tracking of cellular structures as observed in microscopy images. Using a new modified form of the Mumford-Shah energy functional, we derived a variational level-set for density-based segmentation. The novelty of the work lies in evolving an initialized contour that represents a salient structure on density maps to automatically generate novel cell structures upon convergence. We validate our methods and show results on confocal ear images of the zebrafish embryo.