Abstract
Simple SummaryArtificial intelligence (AI) is gaining more and more attention in radiology. The efficiency of AI-based algorithms to solve specific problems is, in some cases, far superior compared to human-driven approaches. This is particularly evident in some repetitive tasks, such as segmentation, where AI usually outperforms manual approaches. AI may be also used in quantification where it can provide, for example, fast and efficient longitudinal follow up in liver tumour burden. AI, thanks to the association with radiomic and big data, may also suggest a diagnosis. Finally, AI algorithms can also reduce scan time, increase image quality and, in the case of computed tomography, reduce patient dose.Artificial intelligence (AI) is one of the most promising fields of research in medical imaging so far. By means of specific algorithms, it can be used to help radiologists in their routine workflow. There are several papers that describe AI approaches to solve different problems in liver and pancreatic imaging. These problems may be summarized in four different categories: segmentation, quantification, characterization and image quality improvement. Segmentation is usually the first step of successive elaborations. If done manually, it is a time-consuming process. Therefore, the semi-automatic and automatic creation of a liver or a pancreatic mask may save time for other evaluations, such as quantification of various parameters, from organs volume to their textural features. The alterations of normal liver and pancreas structure may give a clue to the presence of a diffuse or focal pathology. AI can be trained to recognize these alterations and propose a diagnosis, which may then be confirmed or not by radiologists. Finally, AI may be applied in medical image reconstruction in order to increase image quality, decrease dose administration (referring to computed tomography) and reduce scan times. In this article, we report the state of the art of AI applications in these four main categories.
Highlights
Artificial intelligence (AI) is one of the most promising fields of research to date.The applications of AI-based algorithms in medicine include drug development, health monitoring, disease diagnosis, and personalized medical treatment [1,2,3,4]
In regard to the pancreas, the importance of detecting a possible pancreatic adenocarcinoma [46] as soon as possible is well known, and developing a comevaluated the performance of deep learning (DL) applied to the Liver Imaging Reporting and Data System (LI-RADS) [42]
Shi et al found that the three-phase dynamic contrast enhanced CT (DCE-CT) protocol, combined with a convolutional dense network, had an area under the curve (AUC) of 0.920 in differentiating hepatocellular carcinoma (HCC) from other focal liver lesions compared to an AUC
Summary
Artificial intelligence (AI) is one of the most promising fields of research to date. In modern ANNs, multiple artificial neurons are organized in several layers, called hidden layers to form a DL network [7,8]. This structure creates a feedforward stream from the ANN input to the output. The training set contains examples of network input and corresponding expected output (typically a classification label, a regression value and/or a binary segmentation of an image). Supervised learning provides high quality networks but requires an annotated input that may be time-consuming to set up, especially for radiology applications. We refer the interested reader to a survey on deep learning in medical images [13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
