3D Semantic Deep Learning Networks for Leukemia Detection

作     者：Javaria Amin Muhammad Sharif Muhammad Almas Anjum Ayesha Siddiqa Seifedine Kadry Yunyoung Nam Mudassar Raza 

作者机构：University of WahWah CanttPakistan COMSATS University IslamabadWah CampusPakistan National University of Technology(NUTECH)IJP Road IslamabadPakistan Faculty of Applied Computing and TechnologyNoroff University CollegeKristiansandNorway Department of Computer Science and EngineeringSoonchunhyang UniversityAsan31538Korea 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2021年第69卷第10期

页      面：785-799页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

基　　金：This research was supported by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0012724,The Competency Development Program for Industry Specialist) the Soonchunhyang University Research Fund 

主　　题：YOLOv2 darknet53 Bhattacharyya separately criteria ONNX 

摘      要：White blood cells(WBCs)are a vital part of the immune system that protect the body from different types of bacteria and *** cell growth destroys the body’s immune system,and computerized methods play a vital role in detecting abnormalities at the initial *** this research,a deep learning technique is proposed for the detection of *** proposed methodology consists of three *** I uses an open neural network exchange(ONNX)and YOLOv2 to localize *** localized images are passed to Phase II,in which 3D-segmentation is performed using deeplabv3 as a base network of the pre-trained Xception *** segmented images are used in Phase III,in which features are extracted using the darknet-53 model and optimized using Bhattacharyya separately criteria to classify *** proposed methodology is validated on three publically available benchmark datasets,namely ALL-IDB1,ALL-IDB2,and LISC,in terms of different metrics,such as precision,accuracy,sensitivity,and dice *** results of the proposed method are comparable to those of recent existing methodologies,thus proving its effectiveness.