Segmenting Neuroblastoma Tumor Images and Splitting Overlapping Cells Using Shortest Paths between Cell Contour Convex Regions

Tafavogh, Siamak; Navarro, Karla Félix; Catchpoole, Daniel; Kennedy, Paul J.

doi:10.1007/978-3-642-38326-7_26

Cited by 7 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these approaches fail, when deal with long chains. To handle these issues, concavity regions are detected to split the rouleauxed RBCs through lines cuts or circles drawing (Gurcan et al, ; Kumarasamy, Ong, & Tan, ; LaTorre, Alonso‐Nanclares, Muelas, Peña, & DeFelipe, ; Mughal, Muhammad, Sharif, Saba, & Rehman, ; Saba, ; Tafavogh, Navarro, Catchpoole, & Kennedy, ; Zhang, Sun, Su, & Pham, ).…”

Section: Research Backgroundmentioning

confidence: 99%

Rouleaux red blood cells splitting in microscopic thin blood smear images via local maxima, circles drawing, and mapping with original RBCs

Rehman

Abbas

Saba

et al. 2018

Microscopy Res & Technique

View full text Add to dashboard Cite

Splitting the rouleaux RBCs from single RBCs and its further subdivision is a challenging area in computer-assisted diagnosis of blood. This phenomenon is applied in complete blood count, anemia, leukemia, and malaria tests. Several automated techniques are reported in the state of art for this task but face either under or over splitting problems. The current research presents a novel approach to split Rouleaux red blood cells (chains of RBCs) precisely, which are frequently observed in the thin blood smear images. Accordingly, this research address the rouleaux splitting problem in a realistic, efficient and automated way by considering the distance transform and local maxima of the rouleaux RBCs. Rouleaux RBCs are splitted by taking their local maxima as the centres to draw circles by mid-point circle algorithm. The resulting circles are further mapped with single RBC in Rouleaux to preserve its original shape. The results of the proposed approach on standard data set are presented and analyzed statistically by achieving an average recall of 0.059, an average precision of 0.067 and F-measure 0.063 are achieved through ground truth with visual inspection.

show abstract

Section: Research Backgroundmentioning

confidence: 99%

Rouleaux red blood cells splitting in microscopic thin blood smear images via local maxima, circles drawing, and mapping with original RBCs

Rehman

Abbas

Saba

et al. 2018

Microscopy Res & Technique

View full text Add to dashboard Cite

show abstract

“…Segmentation techniques are used to locate and extract these numerical patterns. Because the main focus of this paper is not segmentation, we use the segmentation approach in [13] which deploys the well known, simple, yet efficient adaptive thresholding approach based on the Otsu method [14] for segmenting the cellular and neuropil regions. The Otsu method efficiently and accurately determines a different range of intensity values using the grey-level histogram of the pixels in the images with low range of intensity variation.…”

Section: Segmentationmentioning

confidence: 99%

Automated Quantitative and Qualitative Analysis of Whole Neuroblastoma Tumour Images for Prognosis

Tafavogh

Meng

Catchpoole

et al. 2014

Biomedical Engineering / 817: Robotics Applications

Self Cite

View full text Add to dashboard Cite

Manual quantitative and qualitative microscopic analysis of cancerous tumours is subject to inter-intra observer variability in pathology. Neuroblastoma is an infant cancer with one of the lowest survival rates. Choosing a proper therapeutic regime for the tumour is highly dependent on determining the tumour aggressiveness level which requires an extensive microscopic analysis. There is an urgent demand from pathologists for reducing the role of microscopic analysis in the process of prognosis and using an automated system to determine the tumour aggressiveness. In this paper, we develop an automated system to address this demand. We propose a novel fourstage hybrid algorithm. First, we develop novel whole slide image partitioning and zooming techniques. Second, we introduce an image enhancement technique to reduce the intensity variation within the tissue images. Third, we deploy a thresholding technique for segmenting the regions of interest. Fourth, we develop a prognosis decision making engine based on a robust clinical prognosis scheme to classify the aggressiveness level using the segmented regions of interest. The performance of the system is evaluated by a pathologist. The system is compared against a state-of-the-art system, and the results indicate a superiority for our system in grading the tumour with average F-measure 86.77%.

show abstract

“…Concavity-based approaches deal the problems in such a way so as to discover concavity regions and in some cases to find concavity points and to split the clustered Red Blood Cells through linear cuts or circular drawing or elliptical drawing, as stated in the studies of (LaTorre et al, 2013;Tafavogh et al, 2013;Zhang et al, 2012;Wang et al, 2011;Kumarasamy et al, 2011;Wen et al, 2009;Makkapati & Naik 2009;Gurcan et al, 2009;Cloppet & Boucher, 2008;Abbas & Mohamad, 2014b;Abbas & Mohamad, 2015c). The concavity-based approaches give good results, but in some cases, they are computationally very expensive.…”

Section: Introductionmentioning

confidence: 99%

Clustered Red Blood Cells Splitting via Boundary Analysis in Microscopic Thin Blood Smear Digital Images

Abbas

Abdullah²,

Mohamad

et al. 2015

IJTech

View full text Add to dashboard Cite

Clustered Red Blood Cells are observed very frequently in the thin blood smear digital images. Separating clustered Red Blood Cells from the single Red Blood Cells and splitting of clustered Red Blood Cells into single Red Blood Cells is a challenging job in the computer-assisted diagnosis of blood for any disorder in many diseases like Complete Blood Count Test, Anemia, Leukemia and Malaria etc. The mentioned problems are highly laborious in manual microscopy for the hematologists. Many techniques currently existing for the solution suffer from both under-and over-splitting problems when highly complex clusters of Red Blood Cells occur. In addition, the existing techniques are not computationally efficient. In this paper, we address the aforementioned problems, firstly by considering the boundaries of the convex hulls of clustered Red Blood Cells and secondly, by splitting the boundaries according to the number of Red Blood Cells in relation to distance measures. Furthermore, we draw circles using a mid-point circle algorithm at each boundary cleavage to give an illusion of the Red Blood Cells. The test results of the proposed technique on a standard online dataset are presented in two ways. Statistically first of all by achieving an average recall of 0.964 and precision of 0.970 while their F-measure achieved is 0.962 as well as secondly through ground truth data with visual inspections.

show abstract

Segmenting Neuroblastoma Tumor Images and Splitting Overlapping Cells Using Shortest Paths between Cell Contour Convex Regions

Cited by 7 publications

References 7 publications

Rouleaux red blood cells splitting in microscopic thin blood smear images via local maxima, circles drawing, and mapping with original RBCs

Rouleaux red blood cells splitting in microscopic thin blood smear images via local maxima, circles drawing, and mapping with original RBCs

Automated Quantitative and Qualitative Analysis of Whole Neuroblastoma Tumour Images for Prognosis

Clustered Red Blood Cells Splitting via Boundary Analysis in Microscopic Thin Blood Smear Digital Images

Contact Info

Product

Resources

About