Use of Artificial Intelligence in Non-Oncologic Interventional Radiology: Current State and Future Directions

Artificial intelligence in interventional radiology: state of the art

Artificial intelligence (AI) has demonstrated great potential in a wide variety of applications in interventional radiology (IR). Support for decision-making and outcome prediction, new functions and improvements in fluoroscopy, ultrasound, computed tomography, and magnetic resonance imaging, specifically in the field of IR, have all been investigated. Furthermore, AI represents a significant boost for fusion imaging and simulated reality, robotics, touchless software interactions, and virtual biopsy. The procedural nature, heterogeneity, and lack of standardisation slow down the process of adoption of AI in IR. Research in AI is in its early stages as current literature is based on pilot or proof of concept studies. The full range of possibilities is yet to be explored.Relevance statement Exploring AI's transformative potential, this article assesses its current applications and challenges in IR, offering insights into decision support and outcome prediction, imaging enhancements, robotics, and touchless interactions, shaping the future of patient care.Key points• AI adoption in IR is more complex compared to diagnostic radiology.• Current literature about AI in IR is in its early stages.• AI has the potential to revolutionise every aspect of IR.

Artificial Intelligence, Augmented Reality, and Virtual Reality Advances and Applications in Interventional Radiology

Artificial intelligence (AI) uses computer algorithms to process and interpret data as well as perform tasks, while continuously redefining itself. Machine learning, a subset of AI, is based on reverse training in which evaluation and extraction of data occur from exposure to labeled examples. AI is capable of using neural networks to extract more complex, high-level data, even from unlabeled data sets, and better emulate, or even exceed, the human brain. Advances in AI have and will continue to revolutionize medicine, especially the field of radiology. Compared to the field of interventional radiology, AI innovations in the field of diagnostic radiology are more widely understood and used, although still with significant potential and growth on the horizon. Additionally, AI is closely related and often incorporated into the technology and programming of augmented reality, virtual reality, and radiogenomic innovations which have the potential to enhance the efficiency and accuracy of radiological diagnoses and treatment planning. There are many barriers that limit the applications of artificial intelligence applications into the clinical practice and dynamic procedures of interventional radiology. Despite these barriers to implementation, artificial intelligence in IR continues to advance and the continued development of machine learning and deep learning places interventional radiology in a unique position for exponential growth. This review describes the current and possible future applications of artificial intelligence, radiogenomics, and augmented and virtual reality in interventional radiology while also describing the challenges and limitations that must be addressed before these applications can be fully implemented into common clinical practice.

Quantitative Automated Segmentation of Lipiodol Deposits on Cone Beam CT Imaging acquired during Transarterial Chemoembolization for Liver Tumors: A Deep Learning Approach

PURPOSE

The purpose of this study was to show that a deep learning-based, automated model for Lipiodol segmentation on CBCT after cTACE performs closer to the "ground truth segmentation" than a conventional thresholding-based model.

MATERIALS & METHODS

This post-hoc analysis included 36 patients with a diagnosis of HCC or other solid liver tumor who underwent cTACE with an intra-procedural CBCT. Semi-automatic segmentation of Lipiodol were obtained. Then, a convolutional U-net model was used to output a binary mask that predicts Lipiodol deposition. A threshold value of signal intensity on CBCT was used to obtain a Lipiodol mask for comparison. Dice similarity coefficient (DSC), Mean-squared error (MSE), and Center of Mass (CM), and fractional volume ratios for both masks were obtained by comparing them to the ground truth (radiologist segmented Lipiodol deposits) to obtain accuracy metrics for the two masks. These results were used to compare the model vs. the threshold technique.

RESULTS

For all metrics, the U-net outperformed the threshold technique: DSC (0.65±0.17 vs. 0.45±0.22,p<0.001) and MSE (125.53±107.36 vs. 185.98±93.82,p=0.005). Difference between the CM predicted, and the actual CM was (15.31±14.63mm vs. 31.34±30.24mm,p<0.001), with lesser distance indicating higher accuracy. The fraction of volume present ([predicted Lipiodol volume]/[ground truth Lipiodol volume]) was 1.22±0.84vs.2.58±3.52,p=0.048 for our model's prediction and threshold technique, respectively.

CONCLUSION

This study showed that a deep learning framework could detect Lipiodol in CBCT imaging and was capable of outperforming the conventionally used thresholding technique over several metrics. Further optimization will allow for more accurate, quantitative predictions of Lipiodol depositions intra-procedurally.