Artificial Intelligence in Lung Cancer Imaging: Unfolding the Future

Abstract

Lung cancer is one of the malignancies with higher morbidity and mortality. Imaging plays an essential role in each phase of lung cancer management, from detection to assessment of response to treatment. The development of imaging-based artificial intelligence (AI) models has the potential to play a key role in early detection and customized treatment planning. Computer-aided detection of lung nodules in screening programs has revolutionized the early detection of the disease. Moreover, the possibility to use AI approaches to identify patients at risk of developing lung cancer during their life can help a more targeted screening program. The combination of imaging features and clinical and laboratory data through AI models is giving promising results in the prediction of patients’ outcomes, response to specific therapies, and risk for toxic reaction development. In this review, we provide an overview of the main imaging AI-based tools in lung cancer imaging, including automated lesion detection, characterization, segmentation, prediction of outcome, and treatment response to provide radiologists and clinicians with the foundation for these applications in a clinical scenario.

Artificial Intelligence in Brain Tumor Imaging: A Step toward Personalized Medicine

“…The proper tuning of CAD tools is essential to ensure diagnostic accuracy, lowering the risk of overdiagnosis, overtreatment, and unreasonable concern in patients [ 23 ]. Generally speaking, if the threshold sensibility is too low, the model can be affected by a high false-positive rate, for example, including vascular structures instead of small metastases; on the other hand, when the threshold is high, the model can fail to detect small (in particular, <3 mm) lesions [ 45 ].…”

“…Segmentation is also an essential step in the radiomics workflow since lesion delimitation is preliminary to the extraction of radiomics features [ 23 ].…”

“…It includes some well-established steps for image acquisition (or data collection), post-processing/reconstruction, segmentation (definition of the area/volume of interest), feature extraction and harmonization, and data mining/model building. The last phase consists of the effective extraction of valuable information from imaging data, essentially through machine learning (ML) methods that need to be trained, validated, and tested to ensure reliability and clinical applicability [ 22 , 23 ].…”

Artificial Intelligence in Emergency Radiology: Where Are We Going?

“…There are four main ML approaches (supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning), which differ in the level of data pretreatment required, the algorithmic strategies adopted to map the relationships between the data, and the problems they can solve: the first three are the most used in radiology, and each can adapt to different clinical tasks [ 10 ].…”

Onkologie im Aufbruch: Wie KI und Digitalisierung die Zukunft gestalten

“…In jenen Bereichen der Medizin, die mit bildgebenden Informationen umgehen, kann sicherlich heute bereits eine deutliche Überlegenheit der künstlichen Intelligenz im Vergleich zur humanen Intelligenz festgestellt werden. KI-Bilderkennung bezieht sich hierbei nicht nur auf die Bereiche der Pathologie, der Dermatologie oder der klassischen Radiologie, in denen die KI-Systeme selbst im Vergleich mit erfahrenen Spezialistinnen und Spezialisten eine beeindruckend verbesserte Sensitivität und Spezifität in der Befundung erreichen [1, 2, 3, 4, 5]. KI-Systeme werden nicht nur darauf trainiert, maligne Tumoren zu erkennen.…”