Digital twins are virtual replicas of physical objects or systems. This new technology is increasingly being adopted in industry to improve the monitoring and efficiency of products and organizations. In healthcare, digital human twins (DHTs) represent virtual copies of patients, including tissues, organs, and physiological processes. Their application has the potential to transform patient care in the direction of increasingly personalized data-driven medicine. The use of DHTs can be integrated with digital twins of healthcare institutions to improve organizational management processes and resource allocation. By modeling the complex multi-omics interactions between genetic and environmental factors, DHTs help monitor disease progression and optimize treatment plans. Through digital simulation, DHT models enable the selection of the most appropriate molecular therapy and accurate 3D representation for precision surgical planning, together with augmented reality tools. Furthermore, they allow for the development of tailored early diagnosis protocols and new targeted drugs. Furthermore, digital twins can facilitate medical training and education. By creating virtual anatomy and physiology models, medical students can practice procedures, enhance their skills, and improve their understanding of the human body. Overall, digital twins have immense potential to revolutionize healthcare, improving patient care and outcomes, reducing costs, and enhancing medical research and education. However, challenges such as data security, data quality, and data interoperability must be addressed before the widespread adoption of digital twins in healthcare. We aim to propose a narrative review on this hot topic to provide an overview of the potential applications of digital twins to improve treatment and diagnostics, but also of the challenges related to their development and widespread diffusion.

Background and purpose: Accurate instance segmentation of teeth in panoramic dental X-rays is a challenging task due to variations in tooth morphology and overlapping regions. In this study, we propose a new algorithm, for instance, segmentation of the different teeth in panoramic dental X-rays. Methods: An instance segmentation model was trained using the architecture of a Mask Region-based Convolutional Neural Network (Mask-RCNN). The data for the training, validation, and testing were taken from the Tuft dental database (1000 panoramic dental radiographs). The number of the predicted label was 52 (20 deciduous and 32 permanent). The size of the training, validation, and test sets were 760, 190, and 70 images, respectively, and the split was performed randomly. The model was trained for 300 epochs, using a batch size of 10, a base learning rate of 0.001, and a warm-up multistep learning rate scheduler (gamma = 0.1). Data augmentation was performed by changing the brightness, contrast, crop, and image size. The percentage of correctly detected teeth and Dice in the test set were used as the quality metrics for the model. Results: In the test set, the percentage of correctly classified teeth was 98.4%, while the Dice score was 0.87. For both the left mandibular central and lateral incisor permanent teeth, the Dice index result was 0.91 and the accuracy was 100%. For the permanent teeth right mandibular first molar, mandibular second molar, and third molar, the Dice indexes were 0.92, 0.93, and 0.78, respectively, with an accuracy of 100% for all three different teeth. For deciduous teeth, the Dice indexes for the right mandibular lateral incisor, right mandibular canine, and right mandibular first molar were 0.89, 0.91, and 0.85, respectively, with an accuracy of 100%. Conclusions: A successful instance segmentation model for teeth identification in panoramic dental X-ray was developed and validated. This model may help speed up and automate tasks like teeth counting and identifying specific missing teeth, improving the current clinical practice.

Objectives: Artificial intelligence (AI) methods can be applied to enhance contrast in diagnostic images beyond that attainable with the standard doses of contrast agents (CAs) normally used in the clinic, thus potentially increasing diagnostic power and sensitivity. Deep learning–based AI relies on training data sets, which should be sufficiently large and diverse to effectively adjust network parameters, avoid biases, and enable generalization of the outcome. However, large sets of diagnostic images acquired at doses of CA outside the standard-of-care are not commonly available. Here, we propose a method to generate synthetic data sets to train an “AI agent” designed to amplify the effects of CAs in magnetic resonance (MR) images. The method was fine-tuned and validated in a preclinical study in a murine model of brain glioma, and extended to a large, retrospective clinical human data set. Materials and Methods: A physical model was applied to simulate different levels of MR contrast from a gadolinium-based CA. The simulated data were used to train a neural network that predicts image contrast at higher doses. A preclinical MR study at multiple CA doses in a rat model of glioma was performed to tune model parameters and to assess fidelity of the virtual contrast images against ground-truth MR and histological data. Two different scanners (3 T and 7 T, respectively) were used to assess the effects of field strength. The approach was then applied to a retrospective clinical study comprising 1990 examinations in patients affected by a variety of brain diseases, including glioma, multiple sclerosis, and metastatic cancer. Images were evaluated in terms of contrast-to-noise ratio and lesion-to-brain ratio, and qualitative scores. Results: In the preclinical study, virtual double-dose images showed high degrees of similarity to experimental double-dose images for both peak signal-to-noise ratio and structural similarity index (29.49 dB and 0.914 dB at 7 T, respectively, and 31.32 dB and 0.942 dB at 3 T) and significant improvement over standard contrast dose (ie, 0.1 mmol Gd/kg) images at both field strengths. In the clinical study, contrast-to-noise ratio and lesion-to-brain ratio increased by an average 155% and 34% in virtual contrast images compared with standard-dose images. Blind scoring of AI-enhanced images by 2 neuroradiologists showed significantly better sensitivity to small brain lesions compared with standard-dose images (4.46/5 vs 3.51/5). Conclusions: Synthetic data generated by a physical model of contrast enhancement provided effective training for a deep learning model for contrast amplification. Contrast above that attainable at standard doses of gadolinium-based CA can be generated through this approach, with significant advantages in the detection of small low-enhancing brain lesions.

The reproducibility of contrast-enhanced ultrasound (CEUS) and standard B-mode ultrasound in the assessment of radiofrequency-ablated volume of benign thyroid nodules was compared. A preliminary study was conducted on consecutive patients who underwent radiofrequency ablation (RFA) of benign thyroid nodules between 2014 and 2016, with available CEUS and B-mode post-ablation checks. CEUS and B-mode images were retrospectively evaluated by two radiologists to assess inter- and intra-observer agreement in the assessment of ablated volume (Bland–Altman test). For CEUS, the mean inter-observer difference (95% limits of agreement) was 0.219 mL (-0.372–0.809 mL); for B-mode, the mean difference was 0.880 mL (-1.655–3.414 mL). Reproducibility was significantly higher for CEUS (85%) than for B-mode (27%). Mean intra-observer differences (95% limits of agreement) were 0.013 mL (0.803–4.097 mL) for Reader 1 and 0.031 mL (0.763–3.931 mL) for Reader 2 using CEUS, while they were 0.567 mL (-2.180–4.317 mL, Reader 1) and 0.759 mL (-2.584–4.290 mL, Reader 2) for B-mode. Intra-observer reproducibility was significantly higher for CEUS (96% and 95%, for the two readers) than for B-mode (21% and 23%). In conclusion, CEUS had higher reproducibility and inter- and intra-observer agreement compared to conventional B-mode in the assessment of radiofrequency-ablated volume of benign thyroid nodules.