Artificial intelligence and radiomics in pulmonary nodule management: current status and future applications

Abstract

Artificial intelligence (AI) has been present in some guise within the field of radiology for over 50 years. The first studies investigating computer-aided diagnosis in thoracic radiology date back to the 1960s, and in the subsequent years, the main application of these techniques has been the detection and classification of pulmonary nodules. In addition, there have been other less intensely researched applications, such as the diagnosis of interstitial lung disease, chronic obstructive pulmonary disease, and the detection of pulmonary emboli. Despite extensive literature on the use of convolutional neural networks in thoracic imaging over the last few decades, we are yet to see these systems in use in clinical practice. The article reviews current state-of-the-art applications of AI and in detection, classification, and follow-up of pulmonary nodules and how deep-learning techniques might influence these going forward. Finally, we postulate the impact of these advancements on the role of radiologists and the importance of radiologists in the development and evaluation of these techniques.

Künstliche Intelligenz in der Bildgebung der Lunge

“…Da eine manuelle Segmentation nur beschränkt reproduzierbar ist, sollten Rundherde (semi)-automatisch segmentiert werden. Neue Ansätze der automatischen Segmentierung, die auf ConvNets beruhen, sind hier deutlich genauer als bisher verwendete Algorithmen [29].…”

“…Jedoch ist die Zahl der für die Entwick-lung dieser Modelle herangezogenen Datenpunkte in der Regel relativ klein. Dieser Umstand, zusammen mit der ausgeprägten Heterogenität der Daten, führt zu einer schlechten Übertragbarkeit dieser Modelle auf Routinedaten [29].…”

“…Die Klassifikation von Lungenrundherden kann jedoch durch ConvNets deutlich verbessert werden. Erste Studien konnten zeigen, dass sich durch ConvNets vor allem die Zahl der falschpositiven Resultate reduzieren lässt, was gerade im Lungenkrebs-Screening von wesentlicher Bedeutung ist [29].…”

Application of artificial intelligence image-assisted diagnosis system in chest CT examination of COVID-19

“…The application of AI in the medical eld has also been reported [3]. It has made important progress in the screening, positioning and analysis of pulmonary nodules [4], thyroid nodules [5], intracranial aneurysms [6] and other diseases. During the in-depth cooperation between Hefei Binhu Hospital and IFLYTEK CO.,LTD., the AI image-assisted diagnosis system was used in the early screening and review evaluation of COVID-19.…”

From hype to hope to hard work: developing responsible AI for radiology

“…As clinical radiologists, we also need to grapple with many new research methodologies, a whole new lexicon, unfamiliar research protocols, new fluid ways to publish results prior to peer-review and a whole world of openaccess information which provides a landscape for rapid development. In this special edition, some of these new concepts are explored by experts in their field who have applied AI to the humble but ubiquitous chest radiograph, 4 pulmonary nodules, 5 and high-volume breast imaging, 6 through to complex analysis of brain lesions 7,8 and the moving heart. 9 However, we must return to more traditional "diagnostic test accuracy" methods for the clinical validation of tools that will be used for patient care.…”