Deep Learning Approaches for Automatic Localization in Medical Images

Abstract

Recent revolutionary advances in deep learning (DL) have fueled several breakthrough achievements in various complicated computer vision tasks. The remarkable successes and achievements started in 2012 when deep learning neural networks (DNNs) outperformed the shallow machine learning models on a number of significant benchmarks. Significant advances were made in computer vision by conducting very complex image interpretation tasks with outstanding accuracy. These achievements have shown great promise in a wide variety of fields, especially in medical image analysis by creating opportunities to diagnose and treat diseases earlier. In recent years, the application of the DNN for object localization has gained the attention of researchers due to its success over conventional methods, especially in object localization. As this has become a very broad and rapidly growing field, this study presents a short review of DNN implementation for medical images and validates its efficacy on benchmarks. This study presents the first review that focuses on object localization using the DNN in medical images. The key aim of this study was to summarize the recent studies based on the DNN for medical image localization and to highlight the research gaps that can provide worthwhile ideas to shape future research related to object localization tasks. It starts with an overview on the importance of medical image analysis and existing technology in this space. The discussion then proceeds to the dominant DNN utilized in the current literature. Finally, we conclude by discussing the challenges associated with the application of the DNN for medical image localization which can drive further studies in identifying potential future developments in the relevant field of study.

Construction of diagnostic and prognostic models based on gene signatures of nasopharyngeal carcinoma by machine learning methods

“…With the selection of appropriate input and output layers, functional relationships with infinitely close correlations between the input and output layers can be discovered by learning and debugging large amounts of clinical data through network models ( 39 ). The network model is trained by providing the neural network with input and output layers and the connection weights can be adjusted during iterations to match the output with the actual output until the desired result is obtained ( 40 ). Based on these advantages, we chose a random forest combined with an ANN approach to construct a diagnostic prediction model for NPC.…”

The Establishment of Hypertrophic Cardiomyopathy Diagnosis Model via Artificial Neural Network and Random Decision Forest Method

“…Unlike traditional regression analysis, neural networks can analyze nonlinear data because of their data processing ability. As long as appropriate input and output layers are selected, and a large amount of clinical data are learned and debugged through the network model, a functional relationship between the input and the output layers with an association relationship that is infinitely close to reality can be found [28,29]. The use of successfully trained network models has a great role in promoting clinical prediction and treatment.…”

An Integrated Multimodal Deep Learning Framework for Accurate Skin Disease Classification

“…DNNs are neural networks with multiple layers that are specifically designed to learn complex patterns and relationships from structured data. The DNN accepts clinical data as input and utilizes a series of hidden layers with nonlinear activation functions to convert the clinical data into valuable, useful feature representations [26]. The DNN formulation can be represented as:…”