Shallow and deep learning classifiers in medical image analysis

Abstract

An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians' decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between "shallow" learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and "deep" learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence.Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics).• Deep classifiers implement automatic feature extraction and classification.• The classifier selection is based on data and computational resources availability, task, and explanation needs.

Keywords: Artificial intelligence; Deep learning; Explainable AI; Machine learning classifiers; Shallow learning.

Fig. 1

Graphical representation of hard and soft margin of a support vector machine. With the soft margin, some misclassifications (double circles) are allowed

Fig. 2

a The data on the x-axis are the original non-separable data. b Application of a second-degree polynomial function to make the two classes separable

Fig. 3

Application of the random forest algorithm. Each decision tree in the forest calculates its own prediction: 250 trees predicted the analyzed sample as benign and 36 as malignant. It is shown that the result is the most frequent prediction made by the entire forest (benign tumor)

Fig. 4

Representation of how the k-nearest neighbors algorithm works. Considering the new point to classify (?), the category is assigned based on the five nearest neighbors (k = 5). In this case, three triangles versus one circle versus one rectangle

Fig. 5

Representation of the multilayer perceptron, composed of one input layer, one hidden layer, and one output layer. Each individual unit of the hidden layer and output layer is a single perceptron, represented in the box

Fig. 6

Example of convolutional operation between an input image (a T1-weighted magnetic resonance image of the brain) and the Sobel filter for edge detection

Fig. 7

Example of convolutional neural network architecture. The input images are fed into the convolutional and pooling layers for feature extraction. In the end, the resulting flattened feature vector is fed into the dense layer to perform the classification task