Robust Segmentation of Overlapping Cells in Histopathology Specimens Using Parallel Seed Detection and Repulsive Level Set

Abstract

Automated image analysis of histopathology specimens could potentially provide support for early detection and improved characterization of breast cancer. Automated segmentation of the cells comprising imaged tissue microarrays (TMA) is a prerequisite for any subsequent quantitative analysis. Unfortunately, crowding and overlapping of cells present significant challenges for most traditional segmentation algorithms. In this paper, we propose a novel algorithm which can reliably separate touching cells in hematoxylin stained breast TMA specimens which have been acquired using a standard RGB camera. The algorithm is composed of two steps. It begins with a fast, reliable object center localization approach which utilizes single-path voting followed by mean-shift clustering. Next, the contour of each cell is obtained using a level set algorithm based on an interactive model. We compared the experimental results with those reported in the most current literature. Finally, performance was evaluated by comparing the pixel-wise accuracy provided by human experts with that produced by the new automated segmentation algorithm. The method was systematically tested on 234 image patches exhibiting dense overlap and containing more than 2200 cells. It was also tested on whole slide images including blood smears and tissue microarrays containing thousands of cells. Since the voting step of the seed detection algorithm is well suited for parallelization, a parallel version of the algorithm was implemented using graphic processing units (GPU) which resulted in significant speed-up over the C/C++ implementation.

Novel image markers for non-small cell lung cancer classification and survival prediction

“…We have compared the proposed voting method (SPV) presented in [22] and the phase-coded hough transform (HT) based on quantitative measurement. In our evaluation a positive detection is counted if a detected seed locates within a 8-pixel circle around a ground truth seed; otherwise, a miss is counted.…”

“…Motivated by [22], we have proposed a multi-scale distance map-based voting algorithm for cell detection. The newly developed method can efficiently handle relatively large cell size and shape variation.…”

“…A vast variety of algorithms based on watershed and its variants [15–17], graph cut [18, 19], and active contour models [20–22] have been proposed. However, none of these methods could robustly handle touching cell segmentation challenges exhibited in lung cancer images.…”

Hybrid multi-GPU computing: accelerated kernels for segmentation and object detection with medical image processing applications

“…To identify breast cancer biomarkers an algorithm was proposed in 2012. This method can detect separating touching cells using their geometry and segmentation techniques using GPUs efficiently [44]; a real-time solution for camera calibration and lens distortion correction in medical endoscopy was proposed in 2012 [34,35]. An aberrant crypt foci segmentation algorithm on GPU was proposed in 2013, in order identify and categorize irregularities [33] of the intestinal tract.…”

“…), facial feature extraction, medical imaging among many others [21,25,28,38,40,51]. Some of the applications of image segmentation in medical context consist of locating tumors, pulmonary nodules, locating Aberrant Crypt Foci (ACF), vessel segmentation or cervical vertebra segmentation, organs and bones segmentation [4,20,22,31,33,36,44].…”