A Survey on Deep Learning Approaches to Medical Images and a Systematic Look up into Real-Time Object Detection

• Published in: Archives of computational methods in engineering 2022-06, Vol.29 (4), p.2071-2111
• Main Authors: Kaur, Amrita, Singh, Yadwinder, Neeru, Nirvair, Kaur, Lakhwinder, Singh, Ashima
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Artificial neural networks; Computer vision; Data processing; Deep learning; Engineering; Image classification; Machine learning; Mathematical and Computational Engineering; Medical electronics; Medical imaging; Natural language processing; Object recognition; Real time; Review Article; Target detection; Vision systems
• ISSN: 1134-3060; 1886-1784
• DOI: 10.1007/s11831-021-09649-9

The article focuses on the gentle introduction of Artificial Intelligence and the concepts of machine learning (ML) and deep learning (DL). The rapid developments made in DL techniques has motivated us to delve into this study. The concept of DL flourishing from basics theoretical concepts to applications. Deep neural networks are now state-of-the-art ML models commonly used in academia and industry in several fields, from image recognition to natural language processing. These advances have an immense potential for medical imaging technology, medical data processing, medical diagnostics and general healthcare. Our aim is two-fold: (1) the survey on DL approaches to medical images (2) the DL-based object detection approaches. The article delivers an effective description of the recent advances, advanced learning technologies and the platforms used for DL approaches. Object detection is the most explored and challenging concept in the field of computer vision systems. This field is receiving greater attention among the researchers since it covers real-time applications such as the face, pedestrian, text etc. The role of object detection is to detect the target objects presented in the image (or) video frames by appropriately classifying into their relevant classes. The review study of object detection begins with the recent works, the datasets used, and the real-time applications are explored from the learning strategies. Finally, the article investigates the challenges of the DL models and discusses promising future directions in both the research areas.