Year-end Sale % OFF 
Abstract
Chromosome analysis is an essential task in a cytogenetics lab, where cytogeneticists can diagnose whether there are abnormalities or not. Karyotyping is a standard technique in chromosome analysis that classifies metaphase image to 24 chromosome classes. The main two categories of chromosome abnormalities are structural abnormalities that are changing in the structure of chromosomes and numerical abnormalities which include either monosomy (missing one chromosome) or trisomy (extra copy of the chromosome). Manual karyotyping is complex and requires high domain expertise, as it takes an amount of time. With these motivations, in this research, we used deep learning to automate karyotyping to recognize the common numerical abnormalities on a dataset containing 147 non-overlapped metaphase images collected from the Center of Excellence in Genomic Medicine Research at King Abdulaziz University. The metaphase images went through three stages. The first one is individual chromosomes detection using YOLOv2 Convolutional Neural Network followed by some chromosome post-processing. This step achieved 0.84 mean IoU, 0.9923 AP, and 100% individual chromosomes detection accuracy. The second stage is feature extraction and classification where we fine-tune VGG19 network using two different approaches, one by adding extra fully connected layer(s) and another by replacing fully connected layers with the global average pooling layer. The best accuracy obtained is 95.04%. The final step is detecting abnormality and this step obtained 96.67% abnormality detection accuracy. To further validate the proposed classification method, we examined the Biomedical Imaging Laboratory dataset which is publicly available online and achieved 94.11% accuracy.
Highlights
Chromosomes are organized structures that contain the genetic information of the human body
We propose to automatically detect the individual chromosomes on the metaphase image and classify the chromosomes based on Convolutional Neural Network (CNN) deep learning
2) FINE-TUNING You Only Look Once (YOLO) v2 YOLO v2 object detection is used to localize every chromosome on metaphase image and after conducting different experiments, we found the best training parameters are need to save the results on disk as in offline augmentation
Summary
Chromosomes are organized structures that contain the genetic information of the human body. ResNet and VGG19 are examples of pre-trained models that have been trained on more than a million of images and can classify them into 1000 objects (such as coffee mug, pencil, keyboard, and many animals) They have been learned huge feature representations from these images [16]. It starts by loading the pre-trained model where the convolutional layers (earlier layers) extract features. We attempt in this article to automate karyotyping steps (segmentation and classification) by detecting and extracting chromosome objects from the metaphase feeding the chromosome images into CNN for feature extraction and classification. 2. Inspired by transfer learning, we fine-tuned YOLO v2 for individual chromosomes detection on a metaphase image with ResNet backbone for feature extraction.
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
