Selective Hole Filling of Red Blood Cells for Improved Marker-Controlled Watershed Segmentation

Abstract

Manual counting and evaluation of red blood cells with the presence of malaria parasites is a tiresome, time-consuming process that can be altered by environmental conditions and human error. Many algorithms were presented to segment red blood cells for subsequent parasitemia evaluation by machine learning algorithms. However, the segmentation of overlapping red blood cells always has been a challenge. Marker-controlled watershed segmentation is one of the methods that was implemented to separate overlapping red blood cells. However, a high number of overlapped red blood cells were still an issue. We propose a novel approach to improve the segmentation efficiency of marker-controlled watershed segmentation. Local minimum histogram background segmentation with a selective hole filling algorithm was introduced to improve segmentation efficiency of marker-controlled watershed segmentation on a high number of overlapping red blood cells. The local minimum was selected on the smoothed histogram for background segmentation. The combination of selective filling, convex hull, and Hough circle detection algorithms was utilized for the intact segmentation of red blood cells. The markers were computed from the resulted mask, and finally, marker-controlled watershed segmentation was applied to separate overlapping red blood cells. As a result, the proposed algorithm achieved higher background segmentation accuracy compared to popular background segmentation algorithms, and the inclusion of corner details improved watershed segmentation efficiency.

Accurate and fast extraction of adhesive cells based on concave points detection and matching

“…Through the image preprocessing algorithm including grayscale transformation, binarization, hole filling, adhesive cell recognition, and median filtering, the image noise can be filtered out while preserving the cell regions correctly. As for References [6,8,13,22], we programmed the algorithm and tested it using the same datasets constructed in this article. For References [19,20], due to the lack of core algorithm programming and specified dataset support, we directly cited the detection accuracy results for comparison.…”

“…However, the SP value of this method is higher than others, reaching about 126, meaning that it is prone to segment a single cell into multiple cells. Reference [8] introduced the selective hole filling algorithm for local background segmentation based on minimum histogram, and combined selective filling, convex hull, and hough circle detection together for the complete segmentation of red blood cells. The label controlled watershed segmentation algorithm is utilized to separate the overlapping red blood cells.…”

“…Lim et al 7 utilized gradient magnitude computing, thresholding, morphological operations, and watershed transform to perform cell segmentation, but faced with the drawback of incomplete localization of each overlapping cell. Nurçin et al 8 used selective hole filling algorithm for local minimum histogram background segmentation, and then combine selective filling, convex hull, and Hough circle detection algorithms for complete segmentation of red blood cells. The above morphology‐based segmentation is prone to produce over‐segmentation and mis‐segmentation, which cannot identify the severely adhesive cells.…”

“…Cell segmentation and extraction results of each method:(A) original image; (B-E) are the segmentation results of,6,8,13,22 respectively; (F) is the extraction results of the proposed method.…”

An intelligent neural network model to detect red blood cells for various blood structure classification in microscopic medical images

“…In working towards automatic detection of red blood cells, assessments of blood smears play a key role in diagnosis. Microscopic images can be utilized for the early detection, investigation, and measurement of several blood illnesses when specific parasites like Babesia and Malaria directly infect red blood cells (RBCs) [2] . Nonetheless, manually or visually assessing WBCs in leukemia and parasitemia in thinner blood films is a tiresome process that is susceptible to errors in counting [3] .…”