An introduction to deep learning in medical physics: advantages, potential, and challenges

Abstract

As one of the most popular approaches in artificial intelligence, deep learning (DL) has attracted a lot of attention in the medical physics field over the past few years. The goals of this topical review article are twofold. First, we will provide an overview of the method to medical physics researchers interested in DL to help them start the endeavor. Second, we will give in-depth discussions on the DL technology to make researchers aware of its potential challenges and possible solutions. As such, we divide the article into two major parts. The first part introduces general concepts and principles of DL and summarizes major research resources, such as computational tools and databases. The second part discusses challenges faced by DL, present available methods to mitigate some of these challenges, as well as our recommendations.

Artificial Intelligence and the Medical Physicist: Welcome to the Machine

“…Deep learning (DL) is a group of methods, which can be employed for supervised or unsupervised learning on any type of data, image, or signal. DL employs models with multiple stacks of neural layers to learn inherent patterns from input data and generate comprehensive representations, in contrast to classical ML methods, which use hand-crafted features manually extracted as input [2].…”

“…To reduce overfitting in DL, data augmentation (e.g., by the affine transformation of the images) during training is commonly implemented [10], and layers in the networks are specialized in reducing overfitting, such as dropout layers [108]. On the other side, DL suffers from other sources of uncertainties (e.g., the presence of many local minima in the loss function and the stochastic nature of training algorithms), so that repeating model training multiple times does not necessarily produce the same model [2]. Besides, the class imbalance problem, in which some classes have a significantly higher number of samples, is detrimental for ML performance, if not properly accounted for [109,110].…”

“…Interpretability is the level of understanding of the information that the model extracts from input data, why it is extracted, and how it arrives at its output [2]. ML models are usually perceived as black boxes by the users and clinicians, meaning that they have a low level of interpretability.…”

“…Artificial intelligence (AI) is a branch of computer science dedicated to giving machines or computers the ability to perform human-like cognitive functions, such as learning, problem-solving, and decision making [1,2]. AI-based systems have shown performance superior to experienced human beings in tasks, such as image classification and analysis, speech recognition, and decision-making [3].…”

Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance

“…AI is characterized as a collection of algorithms that perform tasks correlated with human thinking or intelligence [4] with machine learning (ML) and deep learning (DL) as subdomains [5]. Several review papers have been published on the use of AI, ML and DL in radiotherapy [6][7][8][9][10][11][12]. However, not much is written on clinical implementation of these new techniques [13,14].…”