Introduction to deep learning: minimum essence required to launch a research
- PDF / 2,672,771 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 98 Downloads / 166 Views
INVITED REVIEW
Introduction to deep learning: minimum essence required to launch a research Tomohiro Wataya1 · Katsuyuki Nakanishi1 · Yuki Suzuki2 · Shoji Kido2 · Noriyuki Tomiyama3 Received: 11 March 2020 / Accepted: 2 June 2020 © Japan Radiological Society 2020
Abstract In the present article, we provide an overview on the basics of deep learning in terms of technical aspects and steps required to launch a deep learning research. Deep learning is a branch of artificial intelligence, which has been attracting interest in many domains. The essence of deep learning can be compared to teaching an elementaryschool student how to differenti‑ ate magnetic resonance images, and we first explain the concept using this analogy.Deep learning models are composed of many layers including input, hidden, and output ones. Convolutional neural networks are suitable for image processing as convolutional and pooling layers allow successfully performing extraction of image features. The process of conducting a research work with deep learning can be divided into the nine following steps: computer preparation, software installation, specifying the function, data collection, data edits, dataset creation, programming, program execution, and verification of results. Concerning widespread expectations, deep learning cannot be applied to solve tasks other than those set in specifi‑ cation; moreover, it requires a large amount of data to train and has difficulties with recognizing unknown concepts. Deep learning cannot be considered as a universal tool, and researchers should have thorough understanding of the features of this technique. Keywords Deep learning · Convolutional neural network (CNN) · Artificial intelligence (AI) · Machine learning (ML) · Representation learning (RL)
Introduction Artificial intelligence (AI) has been attracting greater atten‑ tion in recent years. Successful research works are reported constantly in a variety of complex tasks, including image classification, object detection, speech recognition, play‑ ing games [1], and drawing pictures [2]. Related research in the medical field has been also progressing, including such research questions as analyzing electrocardiograms
* Tomohiro Wataya wataya‑[email protected] 1
Department of Diagnostic and Interventional Radiology, Osaka International Cancer Institute, 3‑1‑69 Otemae, Chuo‑ku, Osaka 541‑8567, Japan
2
Department of Artificial Intelligence Diagnostic Radiology, Osaka University Graduate School of Medicine, 2‑2 Yamadaoka, Suita, Osaka 565‑0871, Japan
3
Department of Radiology, Osaka University Graduate School of Medicine, 2‑2 Yamadaoka, Suita, Osaka 565‑0871, Japan
[3], detecting polyps from colonoscopy [4], and extracting features from pathological images [5]. Radiological image analysis and interpretation are the fundamental cognitive tasks in the field of radiology, which historically have been difficult to resolve despite technical advances in computer vision [6]. However, owing to the advancement of deep learning and other AI techniques
Data Loading...
