An efficient deep Convolutional Neural Network based detection and classification of Acute Lymphoblastic Leukemia

被引:98
作者
Das, Pradeep Kumar [1 ]
Meher, Sukadev [1 ]
机构
[1] Natl Inst Technol Rourkela, Dept Elect & Commun Engn, Rourkela 769008, Odisha, India
关键词
Acute Lymphoblastic Leukemia; Classification; Deep learning; Hematological disorder; Transfer learning; HUMAN ACTIVITY RECOGNITION; FEATURE-EXTRACTION; DIAGNOSIS; TRACKING; SYSTEM;
D O I
10.1016/j.eswa.2021.115311
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automated and accurate diagnosis of Acute Lymphoblastic Leukemia (ALL), blood cancer, is a challenging task. Nowadays, Convolutional Neural Networks (CNNs) have become a preferred approach for medical image analysis. However, for achieving excellent performance, classical CNNs usually require huge databases for proper training. This paper proposes an efficient deep CNNs framework to mitigate this issue and yield more accurate ALL detection. The salient features: depthwise separable convolutions, linear bottleneck architecture, inverted residual, and skip connections make it a faster and preferred approach. In this proposed method, a novel probability-based weight factor is suggested, which has a significant role in efficiently hybridizing MobilenetV2 and ResNet18 with preserving the benefits of both approaches. Its performance is validated using public benchmark datasets: ALLIDB1 and ALLIDB2. The experimental results display that the proposed approach yields the best accuracy (with 70% training and 30% testing) 99.39% and 97.18% in ALLIDB1 and ALLIDB2 datasets, respectively. Similarly, it also achieves the best accuracy (with 50% training and 50% testing) 97.92% and 96.00% in ALLIDB1 and ALLIDB2 datasets, respectively. Moreover, it also achieves the best performance compared to the recent transfer learning-based techniques in both the datasets, in terms of sensitivity, specificity, accuracy, precision, F1 score, and receiver operating characteristic (ROC) in most of the cases.
引用
收藏
页数:14
相关论文
共 73 条
[1]  
Abdeldaim AM, 2018, STUD COMPUT INTELL, V730, P131, DOI 10.1007/978-3-319-63754-9_7
[2]  
Ahmed A, 2020, INT BHURBAN C APPL S, P290, DOI [10.1109/IBCAST47879.2020.9044545, 10.1109/ibcast47879.2020.9044545]
[3]   A Novel Statistical Method for Scene Classification Based on Multi-Object Categorization and Logistic Regression [J].
Ahmed, Abrar ;
Jalal, Ahmad ;
Kim, Kibum .
SENSORS, 2020, 20 (14) :1-20
[4]   Acute lymphoblastic leukemia segmentation using local pixel information [J].
Al-jaboriy, Saif S. ;
Sjarif, Nilam Nur Amir ;
Chuprat, Suriayati ;
Abduallah, Wafaa Mustafa .
PATTERN RECOGNITION LETTERS, 2019, 125 :85-90
[5]   An Automatic Nucleus Segmentation and CNN Model based Classification Method of White Blood Cell [J].
Banik, Partha Pratim ;
Saha, Rappy ;
Kim, Ki-Doo .
EXPERT SYSTEMS WITH APPLICATIONS, 2020, 149
[6]   Telemonitoring of Daily Activity Using Accelerometer and Gyroscope in Smart Home Environments [J].
Batool, Mouazma ;
Jalal, Ahmad ;
Kim, Kibum .
JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2020, 15 (06) :2801-2809
[7]   Xception: Deep Learning with Depthwise Separable Convolutions [J].
Chollet, Francois .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1800-1807
[8]  
Das Pradeep Kumar, 2021, Machine Learning, Deep Learning and Computational Intelligence for Wireless Communication. Proceedings of MDCWC 2020. Lecture Notes in Electrical Engineering (LNEE 749), P425, DOI 10.1007/978-981-16-0289-4_32
[9]  
Das P.K., 2020, IEEE HYDCON, P1, DOI DOI 10.1109/HYDCON48903.2020.9242745
[10]   An Efficient Blood-Cell Segmentation for the Detection of Hematological Disorders [J].
Das, Pradeep Kumar ;
Meher, Sukadev ;
Panda, Rutuparna ;
Abraham, Ajith .
IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (10) :10615-10626