The state of the art of deep learning models in medical science and their challenges

  • PDF / 3,281,455 Bytes
  • 15 Pages / 595.276 x 790.866 pts Page_size
  • 74 Downloads / 147 Views




The state of the art of deep learning models in medical science and their challenges Chandradeep Bhatt1 · Indrajeet Kumar1 · V. Vijayakumar2 · Kamred Udham Singh3 · Abhishek Kumar4 

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract With time, AI technologies have matured well and resonated in various domains of applied sciences and engineering. The sub-domains of AI, machine learning (ML), deep learning (DL), and associated statistical tools are getting more attention. Therefore, various machine learning models are being created to take advantage of the data available and accomplish tasks, such as automatic prediction, classification, clustering, segmentation and anomaly detection, etc. Tasks like classification need labeled data used to train the models to achieve a reliable accuracy. This study shows the systematic review of promising research areas and applications of DL models in medical diagnosis and medical healthcare systems. The prevalent DL models, their architectures, and related pros, cons are discussed to clarify their prospects. Many deep learning networks have been useful in the field of medical image processing for prognosis and diagnosis of life-threatening ailments (e.g., breast cancer, lung cancer, and brain tumor, etc.), which stand as an error-prone and tedious task for doctors and specialists when performed manually. Medical images are processed using these DL methods to solve various tasks like prediction, segmentation, and classification with accuracy bypassing human abilities. However, the current DL models have some limitations that encourage the researchers to seek further improvement. Keywords  Artificial intelligence · Machine learning · Deep learning models · Medical healthcare system

1 Introduction

* Abhishek Kumar [email protected] Chandradeep Bhatt [email protected] Indrajeet Kumar [email protected] V. Vijayakumar [email protected] Kamred Udham Singh [email protected] 1

Department of Computer Science and Engineering, Graphic Era Hill University, Dehradun, UK 248002, India


School of Computer Science and Engineering, The University of New South Wales, Sydney, NSW 2052, Australia


School of Computing, Graphic Era Hill University, Dehradun, UK 248002, India


Department of Computer Science, Banaras Hindu University, UP, Varanasi 221005, India

Since the last decades, the simulation of the human brain efficiently is considered a challenging task for everyone. However, various attempts made by different groups have enabled the possibilities of implementing such simulation that has led to the development of a variety of concepts like a virtual assistant (Alexa, Siri, Cortana), language translation Chatbot, Image colorization, facial recognition and so on using deep learning networks [1–5]. The deep learning approach is a subset of machine learning stimulated by the human brain’s data processing pattern [1, 3–8, 13–16]. The Venn diagram in Fig. 1 shows the logical relationship bet