Radiomics, machine learning, and artificial intelligence—what the neuroradiologist needs to know

Abstract

Purpose Artificial intelligence (AI) is playing an ever-increasing role in Neuroradiology. Methods When designing AI-based research in neuroradiology and appreciating the literature, it is important to understand the fundamental principles of AI. Training, validation, and test datasets must be defined and set apart as priorities. External validation and testing datasets are preferable, when feasible. The specific type of learning process (supervised vs. unsupervised) and the machine learning model also require definition. Deep learning (DL) is an AI-based approach that is modelled on the structure of neurons of the brain; convolutional neural networks (CNN) are a commonly used example in neuroradiology. Results Radiomics is a frequently used approach in which a multitude of imaging features are extracted from a region of interest and subsequently reduced and selected to convey diagnostic or prognostic information. Deep radiomics uses CNNs to directly extract features and obviate the need for predefined features. Conclusion Common limitations and pitfalls in AI-based research in neuroradiology are limited sample sizes (“small-n-large-p problem”), selection bias, as well as overfitting and underfitting.

Neuroimaging in the Era of Artificial Intelligence: Current Applications

“…60 Neuroradiology, particularly with uncommon, advanced imaging methods, has a smaller number of available studies. 61 Even with more prevalent imaging modalities, such as head CT, the work of collecting training scans from patients with the prerequisite disease processes, particularly if these processes are rare, can limit the number of datapoints collected. Neuroradiologists should understand how an AI tool was generated, including the size and variety of the training dataset used, to best gauge the clinical applicability and fitness of the system.…”

Hemodynamic Imaging in Cerebral Diffuse Glioma—Part B: Molecular Correlates, Treatment Effect Monitoring, Prognosis, and Future Directions

“…The new development of radiomics allows for the extraction of a high number of quantitative features to identify relations in the data that are not appreciable through traditional analytical methods [ 207 , 208 ]. Radiomics, and the possibility to combine it with machine learning algorithms, have shown considerable potential in terms of improving the diagnostic, prognostic, and predictive accuracy of conventional imaging analysis [ 207 , 208 , 209 , 210 ]. For example, every year, the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) challenge serves as a platform for developing better algorithms aimed at brain tumor segmentation.…”

Differential diagnosis of thyroid nodules by the Demetics ultrasound‐assisted diagnosis system and contrast‐enhanced ultrasound combined with thyroid image reporting and data systems

“…And its applications in computed tomography, magnetic resonance imaging and ultrasound have been studied a lot. [9][10][11][12][13][14] At present, the application of AI to thyroid nodules is still under investigation. 13 The Demetics system is a new technology for AI-CAD.…”

“…The AI‐CAD system based on deep learning has developed rapidly in recent years. And its applications in computed tomography, magnetic resonance imaging and ultrasound have been studied a lot 9–14 . At present, the application of AI to thyroid nodules is still under investigation 13 .…”