Abstract
Whole-slide imaging of tissue microarrays (TMAs) holds the promise of automated image analysis of a large number of histopathological samples from a single slide. This demands high-throughput image processing to enable analysis of these tissue samples for diagnosis of cancer and other conditions. In this paper, we present a completely automated method for the accurate detection and localization of tissue cores that is based on geometric restoration of the core shapes without placing any assumptions on grid geometry. The method relies on hierarchical clustering in conjunction with the Davies-Bouldin index for cluster validation in order to estimate the number of cores in the image wherefrom we estimate the core radius and refine this estimate using morphological granulometry. The final stage of the algorithm reconstructs circular discs from core sections such that these discs cover the entire region of each core regardless of the precise shape of the core. The results show that the proposed method is able to reconstruct core locations without any evidence of localization. Furthermore, the algorithm is more efficient than existing methods based on the Hough transform for circle detection. The algorithm’s simplicity, accuracy, and computational efficiency allow for automated high-throughput analysis of microarray images.
Highlights
Tissue microarrays [13] (TMAs) allow pathologists to study hundreds of tissue samples on a single slide
We find a preliminary estimate of the number of cores by varying the number of clusters K, whereby for every value of K, the clustering result is assessed by the Davies-Bouldin index which is an ideal metric for circular cluster validation
We tested our method on over 2300 cores belonging to 32 tissue microarray images
Summary
Tissue microarrays [13] (TMAs) allow pathologists to study hundreds of tissue samples on a single slide. When imaged as one slide, these tissue arrays hold the promise of high-throughput, automated analysis and staging of cancer and other illnesses. The preparation of tissue microarrays is carried out manually. Human error, and acquisition conditions, microarray layouts often contain a number of irregularities in the 2D grid geometry [6] such as rotations, geometric distortions, and variations in inter-core spacing. In addition non-uniformities may arise in the foreground and background intensity distributions due to the slide preparation procedure or the acquisition process. Tissue microarrays present a challenging task for automated image analysis. In this paper we focus on what is referred to as gridding, namely to localize the center and extent of each tissue core in a slide
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
