Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Previous works on segmentation of SEM (scanning electron microscope) blood cell image ignore the semantic segmentation approach of whole-slide blood cell segmentation. In the proposed work, we address the problem of whole-slide blood cell segmentation using the semantic segmentation approach. We design a novel convolutional encoder-decoder framework along with VGG-16 as the pixel-level feature extraction model. The proposed framework comprises 3 main steps: First, all the original images along with manually generated ground truth masks of each blood cell type are passed through the preprocessing stage. In the preprocessing stage, pixel-level labeling, RGB to grayscale conversion of masked image and pixel fusing, and unity mask generation are performed. After that, VGG16 is loaded into the system, which acts as a pretrained pixel-level feature extraction model. In the third step, the training process is initiated on the proposed model. We have evaluated our network performance on three evaluation metrics. We obtained outstanding results with respect to classwise, as well as global and mean accuracies. Our system achieved classwise accuracies of 97.45%, 93.34%, and 85.11% for RBCs, WBCs, and platelets, respectively, while global and mean accuracies remain 97.18% and 91.96%, respectively.

[1]  Jennifer C. Dela Cruz,et al.  Leukocyte segmentation and counting based on microscopic blood images using HSV saturation component with blob analysis , 2018, 2018 3rd International Conference on Control and Robotics Engineering (ICCRE).

[2]  Vincenzo Piuri,et al.  All-IDB: The acute lymphoblastic leukemia image database for image processing , 2011, 2011 18th IEEE International Conference on Image Processing.

[3]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[4]  Changyan Xiao,et al.  Simultaneous Segmentation of Leukocyte and Erythrocyte in Microscopic Images Using a Marker-Controlled Watershed Algorithm , 2018, Comput. Math. Methods Medicine.

[5]  Keerthana Prasad,et al.  Development of a Robust Algorithm for Detection of Nuclei and Classification of White Blood Cells in Peripheral Blood Smear Images , 2018, Journal of Medical Systems.

[6]  V G Nikitaev,et al.  Research of the Leukocytes Segmentation Method in the Blood Cells Recognition Systems , 2018 .

[7]  Muhammad Imran Razzak,et al.  Automated Pathology Image Analysis , 2018 .

[8]  Julius Stuller.  Ordered modified Gram-Schmidt orthogonalization revised , 1995 .

[9]  Chandan Chakraborty,et al.  Automated identification of normoblast cell from human peripheral blood smear images , 2018, Journal of microscopy.

[10]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Emad A. Mohammed,et al.  Toward leveraging big value from data: chronic lymphocytic leukemia cell classification , 2017, Network Modeling Analysis in Health Informatics and Bioinformatics.

[12]  Yang Wang,et al.  Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation , 2016, ISVC.

[13]  Rahul Khanna,et al.  Support Vector Machines for Classification , 2015 .

[14]  Gabriela Csurka,et al.  What is a good evaluation measure for semantic segmentation? , 2013, BMVC.

[15]  Chunhua Shen,et al.  Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Cecilia Di Ruberto,et al.  A leucocytes count system from blood smear images , 2016, Machine Vision and Applications.

[17]  Xiaomei Li,et al.  Segmentation of White Blood Cells through Nucleus Mark Watershed Operations and Mean Shift Clustering , 2015, Sensors.

[18]  Hong Liu,et al.  A novel algorithm for segmentation of leukocytes in peripheral blood , 2018, Biomed. Signal Process. Control..

[19]  Hao Chen,et al.  Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation , 2019, AAAI.

[20]  Lixin Zheng,et al.  Combining Convolutional Neural Network With Recursive Neural Network for Blood Cell Image Classification , 2018, IEEE Access.

[21]  Bahram Javidi,et al.  Cell morphology-based classification of red blood cells using holographic imaging informatics. , 2016, Biomedical optics express.

[22]  Yoginath R. Kalshetty,et al.  Review on Blood Cell Image Segmentation and Counting , 2014 .

[23]  Yanhui Guo,et al.  A novel white blood cells segmentation algorithm based on adaptive neutrosophic similarity score , 2018, Health Inf. Sci. Syst..

[24]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[25]  Alexander Kihm,et al.  Classification of red blood cell shapes in flow using outlier tolerant machine learning , 2018, PLoS Comput. Biol..

[26]  Jos B. T. M. Roerdink,et al.  The Watershed Transform: Definitions, Algorithms and Parallelization Strategies , 2000, Fundam. Informaticae.

[27]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[28]  Nancy M. Salem,et al.  A Comparative Study of White Blood cells Segmentation using Otsu Threshold and Watershed Transformation , 2016 .

[29]  Muhammad Imran Razzak,et al.  Extreme learning machine based microscopic red blood cells classification , 2018, Cluster Computing.

[30]  Nuhman Ul Haq,et al.  Efficient Enhancement and Segmentation of Leukocytes From Microscopic Images , 2016 .

[31]  Sung Wook Baik,et al.  Leukocytes Classification and Segmentation in Microscopic Blood Smear: A Resource-Aware Healthcare Service in Smart Cities , 2017, IEEE Access.