Image processing-based identification of dicentric chromosomes in slide images

Galloway, Sarah; Coetzer, Johannes; Muller, Neil

doi:10.1109/saupec/robmech/prasa48453.2020.9040926

Cited by 1 publication

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In literature, conventional identification algorithms passed chromosome cross-sectional pixel information 5 before iterating skeletonization techniques 12 to find the medial axis of chromosome using various curve fitting methods [6][7][8] , handwritten word recognition 9 , or skeleton trimming techniques 10,11 . Finally, the locations of centromeres are determined by the convexity 10,12 and pixel information 6,7,13 of the chromosomes.…”

Section: Time Efficiency Of the Novel Methodmentioning

confidence: 99%

“…Conventional methods for dicentric chromosome identification firstly extracts the medial axis of the chromosome image and then identifies the centromeres based on the morphological properties of the chromosome. The commonly used medial axis extraction methods rely on chromosome cross-section pixel information 5 and various curve fitting methods [6][7][8] , while some medial axis extraction methods implement handwritten word recognition 9 , skeleton pruning techniques 10,11 and iterative skeletonisation technique 12 . For the identification of the centromere, the centromere positions can be calculated by convex and concave property 10,12 , and the pixel information of the chromosomes 6,7,13 .…”

mentioning

confidence: 99%

“…The commonly used medial axis extraction methods rely on chromosome cross-section pixel information 5 and various curve fitting methods [6][7][8] , while some medial axis extraction methods implement handwritten word recognition 9 , skeleton pruning techniques 10,11 and iterative skeletonisation technique 12 . For the identification of the centromere, the centromere positions can be calculated by convex and concave property 10,12 , and the pixel information of the chromosomes 6,7,13 . The centromere can also be detected by applying multicolor fluorescence in situ hybridization images [14][15][16][17] .…”

mentioning

confidence: 99%

See 2 more Smart Citations

High-precision automatic identification method for dicentric chromosome images using two-stage convolutional neural network

Shen

Li³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Dicentric chromosome analysis is the gold standard for biological dose assessment. To enhance the efficiency of biological dose assessment in large-scale radiation catastrophes, automatic identification of dicentric chromosome images is a promising and objective method. In this paper, an automatic identification method for dicentric chromosome images using two-stage convolutional neural network is proposed based on Giemsa-stained automatic microscopic imaging. To automatically segment the adhesive chromosome masses, a k-means based adaptive image segmentation and watershed segmentation algorithm is applied. The first-stage CNN is used to identify the dicentric chromosome images from all the images and the second-stage CNN works to specifically identify the dicentric chromosome images. This two-stage CNN identification method can effectively detects chromosome images with concealed centromeres, poorly expanded and long-armed entangled chromosomes, and tricentric chromosomes. The novel two-stage CNN method has a chromosome identification accuracy of 99.4%, a sensitivity of 85.8% sensitivity, and a specificity of 99.6%, effectively reducing the false positive rate of dicentric chromosome. The analysis speed of this automatic identification method can be 20 times quicker than manual detection, providing a valuable reference for other image identification situations with small target rates.

show abstract