Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

Abstract

The discipline of radiology and diagnostic imaging has evolved greatly in recent years. We have observed an exponential increase in the number of exams performed, subspecialization of medical fields, and increases in accuracy of the various imaging methods, making it a challenge for the radiologist to “know everything about all exams and regions”. In addition, imaging exams are no longer only qualitative and diagnostic, providing now quantitative information on disease severity, as well as identifying biomarkers of prognosis and treatment response. In view of this, computer-aided diagnosis systems have been developed with the objective of complementing diagnostic imaging and helping the therapeutic decision-making process. With the advent of artificial intelligence, “big data”, and machine learning, we are moving toward the rapid expansion of the use of these tools in daily life of physicians, making each patient unique, as well as leading radiology toward the concept of multidisciplinary approach and precision medicine. In this article, we will present the main aspects of the computational tools currently available for analysis of images and the principles of such analysis, together with the main terms and concepts involved, as well as examining the impact that the development of artificial intelligence has had on radiology and diagnostic imaging.

Radiomics Assessment of SPAIR and STIR MRI Sequences to Predict Axial and Peripheral Spondyloarthritis

“…There is great difficulty in diagnosing SpA because of its various forms of presentation, requiring several clinical and laboratory assessments that may not be able to be visually performed on the MRI [Lambert et al 2016]. Radiomics, by contrast, can capture additional information from the MRI that can predict clinical outcomes [Gillies et al 2016, Santos et al 2019. Radiomics could be a tool to aid physicians in clinical decisions because it can identify fine texture details on medical images.…”

“…One alternative to it is deep learning and convolutional neural networks. Deep learning features are extracted directly from MRI pixels/voxels without relying on image segmentation and handcrafted feature extraction methods [Santos et al 2019, LeCun et al 2015. Deep convolutional neural networks have been shown an efficient method in medical image analysis and radiomics [Litjens et al 2017, Lee et al 2017, and hence, they are intended to be used in future works and compared with the developed RBFN models.…”

Deep Learning for Locally Advanced Nasopharyngeal Carcinoma Prognostication Based on Pre- and Post-treatment MRI

“…With the increasing subspecialization of medical elds, the demand for more accurate and informative image reports is booming, challenging radiologists, and medical imaging specialists to know everything about all exams and regions (28). The purpose of image examination today is not only qualitative diagnosis but also obtaining rich quantitative information such as the severity of the disease, prognosis, therapeutic effect of drugs, etc.…”

Arcabouço para Classificação, Recuperação por Conteúdo e Radiômica de Imagens Médicas: uma investigação de biomarcadores quantitativos para o câncer de pulmão

“…Após a revolução tecnológica naárea de diagnóstico por imagem com a estruturação de ambientes radiológicos totalmente digitalizados, houve a integração destes ambientes com outros sistemas de informação em saúde. O principal exemplo desta integraçãoé o sistema de arquivamento e comunicação de imagens médicas (PACS -Picture Archiving and Communication System), responsável por receber, armazenar e disponibilizar as imagens no padrão de comunicação de imagem digital em medicina (DICOM -Digital Imaging and Communications in Medicine) dos diversos dispositivos de aquisição [Santos et al 2019].…”

“…A integração dos dados clínicosé ainda mais importanteà medicina de precisão devido o potencial preditivo da mineração dos dados do paciente na atual "Era Big Data". Neste contexto, a radiômica pode ser entendida como a translação dos conceitos de Big Data e medicina de precisão para o ecossistema do diagnóstico por imagem e está focada no desenvolvimento de ferramentas e bases de apoioà tomada de decisão clínica, que possam potencialmente melhorar o diagnóstico, o prognóstico e a precisão de uma previsão de resposta terapêutica [Santos et al 2019].…”