Segmentation of Crypts and Classification of Diseases in a Biopsy using Novel Active Contour Algorithm and the Crypt Architecture

In this talk we introduce a novel method for detection and segmentation of crypts in colon biopsies. Most of the approaches proposed in the literature try to segment the crypts using only the biopsy image without understanding the meaning of each pixel. The proposed method differs in that we segment the crypts using an automatically generated pixel-level classification image of the original biopsy image and handle the artifacts due to the sectioning process and variance in color, shape and size of the crypts. The biopsy image pixels are classified to nuclei, immune system, lumen, cytoplasm, stroma and goblet cells. The crypts are then segmented using a novel active contour approach, where the external force is determined by the semantics of each pixel and the model of the crypt. The active contour is applied for every lumen candidate detected using the pixel-level classification. Finally, a false positive crypt elimination process is performed to remove segmentation errors. This is done by measuring their adherence to the crypt model using the pixel level classification results.

 

The results of this work are used as input for our biopsy segmentation algorithm into benign and cancerous regions using the architecture of the biopsy. We first calculate the crypt architecture using Delaunay triangulation on the crypt centroids and use this architecture to retrieve those crypts that were incorrectly removed in the crypt classification step. In the final step, we use the segmented crypts to construct a more accurate architecture and classify each triangle as healthy or cancerous using the classification of the crypts as healthy or cancerous. The method was tested on 54 colon biopsy images: 109 healthy sub-images containing 4944 healthy crypts and 91 cancerous sub-images containing 2236 cancerous crypts. It achieved 92% accuracy in crypt classification and 94% in biopsy region classification.