Program

Efficient resource monitoring and organizational strategies are crucial for improving healthcare processes. Digital twins have been applied in many healthcare applications, and offer promising solutions. In our paper, we present a new digital twins-based approach that helps to improve the entire operating block management. We developed a prototype that allows for easy tracking of patients among the block, monitoring key areas: entrances, exits, and operating and recovery rooms. The system provides helpful services to medical staff, including statistical reports and scheduling assistance. Our solution was developed in partnership with the local hospital in Parma, and it seamlessly integrates with the existing legacy system to simplify healthcare operations.

In healthcare, Digital Twins (DTs) promise to personalize treatment plans, simulate surgeries, and forecast individual responses to particular therapies. By adopting Machine Learning methodologies, it is possible to figure out some insights hidden among the features for enhancing medical diagnosis. Our contribution leverages the role of intraoperative ultrasound in liver surgery in building a Bayesian Network (BN) model for enabling the early localisation of hepatic cancer. Under this premise, we aim to determine how this change could be affected by other factors (such as age, gender, and before-surgery treatment) by modelling a BN that allows the early diagnosis of hepatic cancer. This is the first step toward the DT definition of a patient affected by a hepatic cancer, in charge of continuously monitoring his/her health status.

As healthcare applications of Artificial Intelligence are growing more and more, the necessity of building universal and transparent models in healthcare is of a paramount importance. Defining approaches able to combine the flexibility of data-driven and the explainability of model-based methods is still an open and promising challenge. This paper proposes an approach to combine mathematical modelling, based on Ordinary Differential Equations, Machine Learning and Fluid Stochastic Petri Nets. By adopting the proposed method and tools, a user could understand the effects of drugs and other treatments on a patient in an interpretable manner. The paper also presents a preliminary application of the approach on the human heartbeat.

This study presents a comparative analysis of segmentation models based on the YOLO (You Only Look Once) architecture for the task of vocal cord detection in laryngoscopic images. The yolov5, yolov8, and yolov9 architectures were evaluated using images obtained from laryngoscopic videos recorded during standard examinations at ORL clinics. The primary objective was to assess the efficiency of different model sizes and architectures in accurately identifying the position of vocal cords within the images. Our findings reveal that all evaluated architectures demonstrate proficiency in vocal cord detection, with comparable results across the models. However, there is a discernible difference in mean Average Precision (mAP) metrics (at IoU thresholds ranging from 0.5 to 0.95). Notably, yolov8 exhibits the highest mAP scores, followed by yolov5 and yolov9, indicating superior performance in identifying vocal cord regions. This comparative analysis provides valuable insights into the effectiveness of YOLO-based segmentation models for vocal cord detection, highlighting the importance of model size and architecture selection in medical image analysis applications. 

Accurate localization of vocal cords is crucial in medical imaging applications for diagnostic and therapeutic purposes. In this study, we evaluated the performance of state-of-the-art object detection models, including YOLO, EfficientDet D1, Faster R-CNN, and Single Shot Detectors architectures, for the task of vocal cord detection. Utilizing a dataset of annotated medical images, we conducted comprehensive experiments to compare the models in terms of mean average precision (mAP) and inference time. Our results indicate that YOLOv8m achieved the highest performance, with a mAP@[0.5:0.95] of 0.778 and an inference time of 4.7 milliseconds. EfficientDet D1, Faster R-CNNs, and Single Shot Detectors trailed behind with slightly lower mAP scores. These findings highlight the efficacy of YOLOv8m for vocal cord localization on the utilized dataset. Moreover, our study provides valuable insights for the selection of suitable object detection models in medical imaging applications, facilitating improved diagnosis and treatment planning in laryngology and otolaryngology. 

Human Digital Twin is an emerging technology that could revolutionise the current healthcare system by enabling the delivery of Personalised Health Services through the use of tools such as artificial intelligence. However, the considerable complexity of the structure of the human body, brought about by continuous molecular and physiological changes, makes it extremely difficult to process medical data extracted by artificial intelligence techniques. The latter requires a large amount of data for reliable performance, which is often difficult to obtain due to limited quality and availability. In this paper, we propose a methodology to generate artificial medical data. In detail, we focus on generating artificial voice signals of healthy individuals and patients suffering with dysphonia. The analysis of voice recordings is fundamental to diagnose specific pneumo-articulatory apparatus diseases, such as dysphonia. The generative neural network employed is based on the WaveNet model, due to its autoregressive sampling, which enables generating recordings of variable length. We propose a setup which enables to generate artificial samples of required gender and pathology to balance and augment the dataset using only one generative network. The quality of the generative network is assessed by balancing the training dataset by generated data and training a convolutional classifier, which is tested on a dataset which was not introduced to the generative network during training. We achieved reasonable improvements in classification accuracy, particularly for the under-represented gender in terms of accuracy, arguing that this approach is worthy of future research.