슈퍼픽셀 이미지 분할을 이용한 ResNet 기반 백혈구 감별 알고리즘 개발
Development of ResNet-based WBC Classification Algorithm Using Super-pixel Image Segmentation
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.
Abstract
In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.
참고문헌 (24)
- I. Goodfellow, "Deep Learning" (2016), MIT Press
- "Pattern Recognition, Pattern Analysis"[URL]
- Shlee, "White blood cell image Retrieving & Clustering System", The Korean Institute of Information Scientists and Engineers, 26(2), pp.530~532 (1999)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition, Vol. 6", pp.1~14 (2015)
- M. D. Zeiler, "Visualizing and understanding convolutional networks", European conference on computer vision, pp.818~833 (2014)
- A. Krizhevsky, "ImageNet Classification with Deep Convolutional Neural Networks", NIPS, 1, pp.1097~1105 (2012)
- S. Ioffe, "Batch Normalization: Acceler ating Deep Network Training by Reducing Internal Covariate Shift", NIPS, 3, pp.1~11 (2015)
- Y. Tang, "Deep Learning using Linear Support Vector Machines", ICML 2013, 4 (2015)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2015)
- K. He, "Identity Mappings in Deep Residual Networks", Computer Vision and Pattern Recognition, 3, pp.1~15 (2016)
- 최종문, "Image Analysis Software를 이용한 변형적혈구 측정법 개발", Laboratory Medicine Online, 3(1), pp.6~14 (2013), 대한진단검사의학회
- M. Habibzadeh, "Comparati ve study of shape, intensity and texture features and support vector machine for white blood cell classification", Journal of Theoretical and Applied Computer Science, 7(1), pp.20~35 (2013)
- Y. M. Alomari, , Computational and Mathematical Methods in Medicine, pp.1~17 (2014)
- N. Ghane, "Segmentation of White Blood Cells From Microscopic Images Using a Novel Combination of K-Means Clustering and Modified Watershed Algorithm", J Med Signals Sens, 7(2), pp.92~101 (2017)
- M. I. Razzak, "Microscopic Blood Smear Segmentation and Classification using Deep Contour Aware CNN and Extreme Machine Learning", Computer Vision and Pattern Recognition Workshops (CVPRW), pp.49~55 (2017)
- R. Sorgedrager, "Automated malaria diagnosis using convolutional neural networks in an on-field setting", pp.2018
- M. Xu, "A deep convolutional neural network for classification of red blood cells in sickle cell anemia", PLoS Comput Biol, 13(10), pp.1~27 (2017)
- 현정환, "객체 검출 시스템 개발을 위한 Tracking-Learning-Detection 알고리즘과 학습알고리즘에 관한 연구", 한국정보기술학회논문지, 15(12), pp.139~145 (2017), 한국정보기술학회[DOI]
- H. N. Mhaskar, "A Deep Learning Approach to Diabetic Blood Glucose Prediction", Frontiers in Applied Mathematics and Statistics, 3(14), pp.1~11 (2017)
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Neural Information Processing Systems (NIPS), pp.1097~1105 (2012)
- Jsyoo, "Deep learning based image recognition technology trend", pp.17~24 (2017), Information and Society
- "Identity Mappings in Deep Residual Networks Review"[URL]
- R. Achanta, "SLIC Superpixels Compared to State-of-the-Art Superpixel Methods", IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), pp.2274~2282 (2012), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- M. Liu, "Entropy rate superpixel segmentation", IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.1~14 (2014)