Open Access

ARTICLE

3D Semantic Deep Learning Networks for Leukemia Detection

Javaria Amin¹, Muhammad Sharif², Muhammad Almas Anjum³, Ayesha Siddiqa¹, Seifedine Kadry⁴, Yunyoung Nam^5,*, Mudassar Raza²
1 University of Wah, Wah Cantt, Pakistan
2 COMSATS University Islamabad, Wah Campus, Pakistan
3 National University of Technology (NUTECH), IJP Road Islamabad, Pakistan
4 Faculty of Applied Computing and Technology, Noroff University College, Kristiansand, Norway
5 Department of Computer Science and Engineering, Soonchunhyang University, Asan, 31538, Korea
* Corresponding Author: Yunyoung Nam. Email:
(This article belongs to this Special Issue: AI, IoT, Blockchain Assisted Intelligent Solutions to Medical and Healthcare Systems)

Computers, Materials & Continua 2021, 69(1), 785-799. https://doi.org/10.32604/cmc.2021.015249

Received 12 November 2020; Accepted 13 February 2021; Issue published 04 June 2021

Abstract

White blood cells (WBCs) are a vital part of the immune system that protect the body from different types of bacteria and viruses. Abnormal cell growth destroys the body’s immune system, and computerized methods play a vital role in detecting abnormalities at the initial stage. In this research, a deep learning technique is proposed for the detection of leukemia. The proposed methodology consists of three phases. Phase I uses an open neural network exchange (ONNX) and YOLOv2 to localize WBCs. The localized images are passed to Phase II, in which 3D-segmentation is performed using deeplabv3 as a base network of the pre-trained Xception model. The 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 WBCs. The 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 scores. The results of the proposed method are comparable to those of recent existing methodologies, thus proving its effectiveness.

---

Keywords

YOLOv2; darknet53; Bhattacharyya separately criteria; ONNX

---

Citations