Artificial intelligence (AI) is the most revolutionizing development in the health care industry in the current decade, with diagnostic imaging having the greatest share in such development. Machine learning and deep learning (DL) are subclasses of AI that show breakthrough performance in image analysis. They have become the state of the art in the field of image classification and recognition. Machine learning deals with the extraction of the important characteristic features from images, whereas DL uses neural networks to solve such problems with better performance. In this review, we discuss the current applications of machine learning and DL in the field of diagnostic radiology. Deep learning applications can be divided into medical imaging analysis and applications beyond analysis. In the field of medical imaging analysis, deep convolutional neural networks are used for image classification, lesion detection, and segmentation. Also used are recurrent neural networks when extracting information from electronic medical records and to augment the use of convolutional neural networks in the field of image classification. Generative adversarial networks have been explicitly used in generating high-resolution computed tomography and magnetic resonance images and to map computed tomography images from the corresponding magnetic resonance imaging. Beyond image analysis, DL can be used for quality control, workflow organization, and reporting. In this article, we review the most current AI models used in medical imaging research, providing a brief explanation of the various models described in the literature within the past 5 years. Emphasis is placed on the various DL models, as they are the most state-of-art in imaging analysis.

Hepatocellular carcinoma (HCC) is the most common primary liver neoplasm, and its incidence has doubled over the past two decades owing to increasing risk factors. Despite surveillance, most HCC cases are diagnosed at advanced stages and can only be treated using transarterial chemo-embolization (TACE) or systemic therapy. TACE failure may occur with incidence reaching up to 60% of cases, leaving patients with a financial and emotional burden. Radiomics has emerged as a new tool capable of predicting tumor response to TACE from pre-procedural computed tomography (CT) studies. This data report defines the HCC-TACE data collection of confirmed HCC patients who underwent TACE and have pre- and post-procedure CT imaging studies and available treatment outcomes (time-to-progression and overall survival). Clinically curated segmentation of pre-procedural CT studies was done for the purpose of algorithm training for prediction and automatic liver tumor segmentation.

The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. We identified 56 articles published from 2015 to 2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50 %), followed by image-synthesis (13 %), and multiple applications simultaneously (11 %). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32 %). Imaging data was used in 91 % of studies, while only 13 % incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60 %), with Monte Carlo dropout being the most commonly implemented UQ method (32 %) followed by ensembling (16 %). 55 % of studies did not share code or datasets. Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, we identified a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

The treatment times of laser induced thermal therapies (LITT) guided by computational prediction are determined by the convergence behavior of partial differential equation (PDE)-constrained optimization problems. In this paper, we investigate the convergence behavior of a bioheat transfer constrained calibration problem to assess the feasibility of applying to real-time patient specific data. The calibration techniques utilize multiplanar thermal images obtained from the nondestructive in vivo heating of canine prostate. The calibration techniques attempt to adaptively recover the biothermal heterogeneities within the tissue on a patient-specific level and results in a formidable PDE constrained optimization problem to be solved in real time. A comprehensive calibration study is performed with both homogeneous and spatially heterogeneous biothermal model parameters with and without constitutive nonlinearities. Initial results presented here indicate that the calibration problems involving the inverse solution of thousands of model parameters can converge to a solution within three minutes and decrease the ||·||_{L 2} ² _{(0,T;L 2 (¿))} norm of the difference between computational prediction and the measured temperature values to a patient-specific regime.

To evaluate the accuracy of computer simulation in predicting the thermal damage region produced by a radiofrequency (RF) ablation procedure in an in vitro perfused bovine liver model. The thermal dose end point in the liver model is used to assess quantitatively computer prediction for use in prospective treatment planning of RF ablation procedures. Geometric details of the tri-cooled tip electrode were modeled. The resistive heating of a pulsed voltage delivery was simulated in four dimensions using finite element models (FEM) implemented on high-performance parallel computing architectures. A range of physically realistic blood perfusion parameters, 3.6-53.6 kg/sec/m(3), was considered in the computer model. An Arrhenius damage model was used to predict the thermal dose. Dice similarity coefficients (DSC) were the metric of comparison between computational predictions and T1-weighted contrast-enhanced images of the damage obtained from a RF procedure performed on an in vitro perfused bovine liver model. For a perfusion parameter greater than 16.3 kg/sec/m(3), simulations predict the temporal evolution of the damaged volume is perfusion limited and will reach a maximum value. Over a range of physically meaningful perfusion values, 16.3-33.1 kg/sec/m(3), the predicted thermal dose reaches the maximum damage volume within 2 minutes of the delivery and is in good agreement (DSC > 0.7) with experimental measurements obtained from the perfused liver model. As measured by the computed volumetric DSC, computer prediction accuracy of the thermal dose shows good correlation with ablation lesions measured in vitro in perfused bovine liver models over a range of physically realistic perfusion values.