An intensity-based self-supervised domain adaptation method for intervertebral disc segmentation in magnetic resonance imaging.

BACKGROUND AND OBJECTIVE: Accurate IVD segmentation is crucial for diagnosing and treating spinal conditions. Traditional deep learning methods depend on extensive, annotated datasets, which are hard to acquire. This research proposes an intensity-based self-supervised domain adaptation, using unlabeled multi-domain data to reduce reliance on large annotated datasets. METHODS: The study introduces an innovative method using intensity-based self-supervised learning for IVD segmentation in MRI scans. This approach is particularly suited for IVD segmentations due to its ability to effectively capture the subtle intensity variations that are characteristic of spinal structures. The model, a dual-task system, simultaneously segments IVDs and predicts intensity transformations. This intensity-focused method has the advantages of being easy to train and computationally light, making it highly practical in diverse clinical settings. Trained on unlabeled data from multiple domains, the model learns domain-invariant features, adeptly handling intensity variations across different MRI devices and protocols. RESULTS: Testing on three public datasets showed that this model outperforms baseline models trained on single-domain data. It handles domain shifts and achieves higher accuracy in IVD segmentation. CONCLUSIONS: This study demonstrates the potential of intensity-based self-supervised domain adaptation for IVD segmentation. It suggests new directions for research in enhancing generalizability across datasets with domain shifts, which can be applied to other medical imaging fields.

On the use of contrastive learning for standard-plane classification in fetal ultrasound imaging.

BACKGROUND: To investigate the effectiveness of contrastive learning, in particular SimClr, in reducing the need for large annotated ultrasound (US) image datasets for fetal standard plane identification. METHODS: We explore SimClr advantage in the cases of both low and high inter-class variability, considering at the same time how classification performance varies according to different amounts of labels used. This evaluation is performed by exploiting contrastive learning through different training strategies. We apply both quantitative and qualitative analyses, using standard metrics (F1-score, sensitivity, and precision), Class Activation Mapping (CAM), and t-Distributed Stochastic Neighbor Embedding (t-SNE). RESULTS: When dealing with high inter-class variability classification tasks, contrastive learning does not bring a significant advantage; whereas it results to be relevant for low inter-class variability classification, specifically when initialized with ImageNet weights. CONCLUSIONS: Contrastive learning approaches are typically used when a large number of unlabeled data is available, which is not representative of US datasets. We proved that SimClr either as pre-training with backbone initialized via ImageNet weights or used in an end-to-end dual-task may impact positively the performance over standard transfer learning approaches, under a scenario in which the dataset is small and characterized by low inter-class variability.

Generalizability and robustness evaluation of attribute-based zero-shot learning.

In the field of deep learning, large quantities of data are typically required to effectively train models. This challenge has given rise to techniques like zero-shot learning (ZSL), which trains models on a set of "seen" classes and evaluates them on a set of "unseen" classes. Although ZSL has shown considerable potential, particularly with the employment of generative methods, its generalizability to real-world scenarios remains uncertain. The hypothesis of this work is that the performance of ZSL models is systematically influenced by the chosen "splits"; in particular, the statistical properties of the classes and attributes used in training. In this paper, we test this hypothesis by introducing the concepts of generalizability and robustness in attribute-based ZSL and carry out a variety of experiments to stress-test ZSL models against different splits. Our aim is to lay the groundwork for future research on ZSL models' generalizability, robustness, and practical applications. We evaluate the accuracy of state-of-the-art models on benchmark datasets and identify consistent trends in generalizability and robustness. We analyze how these properties vary based on the dataset type, differentiating between coarse- and fine-grained datasets, and our findings indicate significant room for improvement in both generalizability and robustness. Furthermore, our results demonstrate the effectiveness of dimensionality reduction techniques in improving the performance of state-of-the-art models in fine-grained datasets.

In the Direction of an Artificial Intelligence-Enabled Monitoring Platform for Concrete Structures.

In a seismic context, it is fundamental to deploy distributed sensor networks for Structural Health Monitoring (SHM). Indeed, regularly gathering data from a structure/infrastructure gives insight on the structural health status, and Artificial Intelligence (AI) technologies can help in exploiting this information to generate early warnings useful for decision-making purposes. With a perspective of developing a remote monitoring platform for the built environment in a seismic context, the authors tested self-sensing concrete beams in loading tests, focusing on the measured electrical impedance. The formed cracks were objectively assessed through a vision-based system. Also, a comparative analysis of AI-based and statistical prediction methods, including Prophet, ARIMA, and SARIMAX, was conducted for predicting electrical impedance. Results show that the real part of electrical impedance is highly correlated with the applied load (Pearson's correlation coefficient > 0.9); hence, the piezoresistive ability of the manufactured specimens has been confirmed. Concerning prediction methods, the superiority of the Prophet model over statistical techniques was demonstrated (Mean Absolute Percentage Error, MAPE < 1.00%). Thus, the exploitation of electrical impedance sensors, vision-based systems, and AI technologies can be significant to enhance SHM and maintenance needs prediction in the built environment.

A3CarScene: An audio-visual dataset for driving scene understanding.

Accurate perception and awareness of the environment surrounding the automobile is a challenge in automotive research. This article presents A3CarScene, a dataset recorded while driving a research vehicle equipped with audio and video sensors on public roads in the Marche Region, Italy. The sensor suite includes eight microphones installed inside and outside the passenger compartment and two dashcams mounted on the front and rear windows. Approximately 31 h of data for each device were collected during October and November 2022 by driving about 1500 km along diverse roads and landscapes, in variable weather conditions, in daytime and nighttime hours. All key information for the scene understanding process of automated vehicles has been accurately annotated. For each route, annotations with beginning and end timestamps report the type of road traveled (motorway, trunk, primary, secondary, tertiary, residential, and service roads), the degree of urbanization of the area (city, town, suburban area, village, exurban and rural areas), the weather conditions (clear, cloudy, overcast, and rainy), the level of lighting (daytime, evening, night, and tunnel), the type (asphalt or cobblestones) and moisture status (dry or wet) of the road pavement, and the state of the windows (open or closed). This large-scale dataset is valuable for developing new driving assistance technologies based on audio or video data alone or in a multimodal manner and for improving the performance of systems currently in use. The data acquisition process with sensors in multiple locations allows for the assessment of the best installation placement concerning the task. Deep learning engineers can use this dataset to build new baselines, as a comparative benchmark, and to extend existing databases for autonomous driving.

Generating depth images of preterm infants in given poses using GANs.

BACKGROUND AND OBJECTIVES: The use of deep learning for preterm infant's movement monitoring has the potential to support clinicians in early recognizing motor and behavioural disorders. The development of deep learning algorithms is, however, hampered by the lack of publicly available annotated datasets. METHODS: To mitigate the issue, this paper presents a Generative Adversarial Network-based framework to generate images of preterm infants in a given pose. The framework consists of a bibranch encoder and a conditional Generative Adversarial Network, to generate a rough image and a refined version of it, respectively. RESULTS: Evaluation was performed on the Moving INfants In RGB-D dataset which has 12.000 depth frames from 12 preterm infants. A low Fréchet inception distance (142.9) and an inception score (2.8) close to that of real-image distribution (2.6) are obtained. The results achieved show the potentiality of the framework in generating realistic depth images of preterm infants in a given pose. CONCLUSIONS: Pursuing research on the generation of new data may enable researchers to propose increasingly advanced and effective deep learning-based monitoring systems.

Addressing Gaps in Small-Scale Fisheries: A Low-Cost Tracking System.

During the last decade vessel-position-recording devices, such as the Vessel Monitoring System and the Automatic Identification System, have increasingly given accurate spatial and quantitative information of industrial fisheries. On the other hand, small-scale fisheries (vessels below 12 m) remain untracked and largely unregulated even though they play an important socio-economic and cultural role in European waters and coastal communities and account for most of the total EU fishing fleet. The typically low-technological capacity of these small-scale fishing boats-for which space and power onboard are often limited-as well their reduced operative range encourage the development of efficient, low-cost, and low-burden tracking solutions. In this context, we designed a cost-effective and scalable prototypic architecture to gather and process positional data from small-scale vessels, making use of a LoRaWAN/cellular network. Data collected by our first installation are presented, as well as its preliminary processing. The emergence of a such low-cost and open-source technology coupled to artificial intelligence could open new opportunities for equipping small-scale vessels, collecting their trajectory data, and estimating their fishing effort (information which has historically not been present). It enables a new monitoring strategy that could effectively include small-scale fleets and support the design of new policies oriented to inform coastal resource and fisheries management.

A Synergic Integration of AIS Data and SAR Imagery to Monitor Fisheries and Detect Suspicious Activities.

Maritime traffic and fishing activities have accelerated considerably over the last decade, with a consequent impact on the environment and marine resources. Meanwhile, a growing number of ship-reporting technologies and remote-sensing systems are generating an overwhelming amount of spatio-temporal and geographically distributed data related to large-scale vessels and their movements. Individual technologies have distinct limitations but, when combined, can provide a better view of what is happening at sea, lead to effectively monitor fishing activities, and help tackle the investigations of suspicious behaviors in close proximity of managed areas. The paper integrates non-cooperative Synthetic Aperture Radar (SAR) Sentinel-1 images and cooperative Automatic Identification System (AIS) data, by proposing two types of associations: (i) point-to-point and (ii) point-to-line. They allow the fusion of ship positions and highlight "suspicious" AIS data gaps in close proximity of managed areas that can be further investigated only once the vessel-and the gear it adopts-is known. This is addressed by a machine-learning approach based on the Fast Fourier Transform that classifies single sea trips. The approach is tested on a case study in the central Adriatic Sea, automatically reporting AIS-SAR associations and seeking ships that are not broadcasting their positions (intentionally or not). Results allow the discrimination of collaborative and non-collaborative ships, playing a key role in detecting potential suspect behaviors especially in close proximity of managed areas.

A Decision Support System for Diabetes Chronic Care Models Based on General Practitioner Engagement and EHR Data Sharing.

Objective Decision support systems (DSS) have been developed and promoted for their potential to improve quality of health care. However, there is a lack of common clinical strategy and a poor management of clinical resources and erroneous implementation of preventive medicine. Methods To overcome this problem, this work proposed an integrated system that relies on the creation and sharing of a database extracted from GPs' Electronic Health Records (EHRs) within the Netmedica Italian (NMI) cloud infrastructure. Although the proposed system is a pilot application specifically tailored for improving the chronic Type 2 Diabetes (T2D) care it could be easily targeted to effectively manage different chronic-diseases. The proposed DSS is based on EHR structure used by GPs in their daily activities following the most updated guidelines in data protection and sharing. The DSS is equipped with a Machine Learning (ML) method for analyzing the shared EHRs and thus tackling the high variability of EHRs. A novel set of T2D care-quality indicators are used specifically to determine the economic incentives and the T2D features are presented as predictors of the proposed ML approach. Results The EHRs from 41237 T2D patients were analyzed. No additional data collection, with respect to the standard clinical practice, was required. The DSS exhibited competitive performance (up to an overall accuracy of 98%±2% and macro-recall of 96%±1%) for classifying chronic care quality across the different follow-up phases. The chronic care quality model brought to a significant increase (up to 12%) of the T2D patients without complications. For GPs who agreed to use the proposed system, there was an economic incentive. A further bonus was assigned when performance targets are achieved. Conclusions The quality care evaluation in a clinical use-case scenario demonstrated how the empowerment of the GPs through the use of the platform (integrating the proposed DSS), along with the economic incentives, may speed up the improvement of care.

Sharing health data among general practitioners: The Nu.Sa. project.

Today, e-health has entered the everyday work flow in the form of a variety of healthcare providers. General practitioners (GPs) are the largest category in the public sanitary service, with about 60,000 GPs throughout Italy. Here, we present the Nu.Sa. project, operating in Italy, which has established one of the first GP healthcare information systems based on heterogeneous data sources. This system connects all providers and provides full access to clinical and health-related data. This goal is achieved through a novel technological infrastructure for data sharing based on interoperability specifications recognised at the national level for messages transmitted from GP providers to the central domain. All data standards are publicly available and subjected to continuous improvement. Currently, the system manages more than 5,000 GPs with about 5,500,000 patients in total, with 4,700,000 pharmacological e-prescriptions and 1,700,000 e-prescriptions for laboratory exams per month. Hence, the Nu.Sa. healthcare system that has the capacity to gather standardised data from 16 different form of GP software, connecting patients, GPs, healthcare organisations, and healthcare professionals across a large and heterogeneous territory through the implementation of data standards with a strong focus on cybersecurity. Results show that the application of this scenario at a national level, with novel metrics on the architecture's scalability and the software's usability, affect the sanitary system and on GPs' professional activities.

Embedded Vision Sensor Network for Planogram Maintenance in Retail Environments.

A planogram is a detailed visual map that establishes the position of the products in a retail store. It is designed to supply the best location of a product for suppliers to support an innovative merchandising approach, to increase sales and profits and to better manage the shelves. Deviating from the planogram defeats the purpose of any of these goals, and maintaining the integrity of the planogram becomes a fundamental aspect in retail operations. We propose an embedded system, mainly based on a smart camera, able to detect and to investigate the most important parameters in a retail store by identifying the differences with respect to an "approved" planogram. We propose a new solution that allows concentrating all the surveys and the useful measures on a limited number of devices in communication among them. These devices are simple, low cost and ready for immediate installation, providing an affordable and scalable solution to the problem of planogram maintenance. Moreover, over an Internet of Things (IoT) cloud-based architecture, the system supplies many additional data that are not concerning the planogram, e.g., out-of-shelf events, promptly notified through SMS and/or mail. The application of this project allows the realization of highly integrated systems, which are economical, complete and easy to use for a large number of users. Experimental results have proven that the system can efficiently calculate the deviation from a normal situation by comparing the base planogram image with the images grabbed.