This study presents an interdisciplinary approach to monitoring vulnerable Mediterranean coastal dune habitats by integrating robotic and artificial intelligence technologies into traditional monitoring methods. The unstructured nature of coastal dunes presents a challenge for monitoring activities, leading to expensive and time-consuming actions from the human operators. Our solution uses a quadruped robotic platform, ANYmal C, to navigate unstable, irregular, and rough terrain and to adapt to dune conditions. The effectiveness and efficiency of the proposed method are demonstrated through the autonomous replication of monitoring missions, which mirrors the criteria used by human operators to acquire data. The data collected can be used to draw conclusions about the conservation status of the habitats by estimating biomass and vegetation cover, and to train artificial intelligence algorithms to detect target species. When paired with traditional phytosociological surveys performed by botanists, this robotics-assisted protocol not only streamlines field operations but also enhances data acquisition, storage, and usage. This pilot framework demonstrates how legged robots can improve data acquisition efficiency and support human experts in habitat monitoring, increasing the frequency and consistency of field observations while maintaining expert oversight. The result is a proactive and scalable framework for monitoring Mediterranean dune habitats that integrates agile legged robots and artificial intelligence to assist and strengthen traditional ecological monitoring.

This paper presents a novel approach to forest habitat monitoring using robotics and advanced data analysis techniques. We introduce a quadrupedal robot with LiDAR and onboard cameras to collect detailed data about forest structure and composition. The data is then processed using a combination of data analysis techniques and machine learning algorithms to perform a comprehensive dendrometric and floristic survey. Our approach provides an efficient and accurate method for assessing the ecological health of forest ecosystems. This work contributes to the ongoing efforts in habitat conservation and offers a promising tool for future environmental monitoring tasks.

Object identification has been widely used in several applications, utilising the annotated data with bounding boxes to specify each object's exact location and category in images and videos. However, relatively little research has been conducted on identifying plant species in their natural environments. Natural habitats play a crucial role in preserving biodiversity, ecological balance, and overall ecosystem health. So, effective monitoring of habitats is necessary for safeguarding them, and one way of doing this is by identifying the typical and early warning plant species. Our study quantitatively evaluates the performance of six popular object detection models on our dataset collected in the wild, comprising various plant species from four habitats: screes, dunes, grasslands, and forests. The dataset employed in this work includes the data collected by human operators and the quadrupedal robot ANYmal C. The pre-trained object detection models have been chosen for experiments, and they are fine-tuned on our dataset to achieve better performance. These models incorporate two one-stage (RetinaNet and YOLOv8n), two two-stage (Faster RCNN and Cascade RCNN), and two transformer-based detectors (DETR and Deformable DETR). Extensive experimentation has been performed on the four habitat datasets by applying class balancing and hyperparameter tuning, and the obtained results are discussed.

According to the European Union’s Habitat Directive, habitat monitoring plays a critical role in response to the escalating problems posed by biodiversity loss and environmental degradation. Scree habitats, hosting unique and often endangered species, face severe threats from climate change due to their high-altitude nature. Traditionally, their monitoring has required highly skilled scientists to conduct extensive fieldwork in remote, potentially hazardous locations, making the process resource-intensive and time-consuming. This paper presents a novel approach for scree habitat monitoring using a legged robot to assist botanists in data collection and species identification. Specifically, we deployed the ANYmal C robot in the Italian Alpine bio-region in two field campaigns spanning two years and leveraged deep learning to detect and classify key plant species of interest. Our results demonstrate that agile legged robots can navigate challenging terrains and increase the frequency and efficiency of scree monitoring. When paired with traditional phytosociological surveys performed by botanists, this robotics-assisted protocol not only streamlines field operations but also enhances data acquisition, storage, and usage. The outcomes of this research contribute to the evolving landscape of robotics in environmental science, paving the way for a more comprehensive and sustainable approach to habitat monitoring and preservation.

Purpose To evaluate the diagnostic performance of artificial intelligence (AI) models in detecting and classifying aortic dissection (AD) from CT images through a systematic review and meta-analysis. Materials and Methods PubMed, Web of Science, Embase, and Medline were searched for articles published from January 2010 to October 2023. All primary studies were included. Quality of evidence was assessed using a composite tool based on the METhodological RadiomICs Score (ie, METRICS) and Checklist for Artificial Intelligence in Medical Imaging (ie, CLAIM) checklists, and risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (ie, QUADAS-2) tool. Univariate and bivariate meta-analyses were performed assessing individual and joint estimates of sensitivity and specificity. Results Thirteen studies were identified, with most using contrast-enhanced CT (CECT) imaging (n = 9) and the remainder using noncontrast CT (NCCT) imaging as their model input. Only three studies presented algorithms classifying AD by Stanford criteria. Univariate analysis of AI detection performance estimated sensitivity at 94% (95% CI: 88, 97; P = .049) and specificity at 88% (95% CI: 79, 94; P < .001). Bivariate analysis showed good overall model performances (area under the receiver operating characteristic curve [AUC], 0.97 [95% CI: 0.95, 0.99]; P = .49). Subgroup analyses revealed good performance for models using CECT images (sensitivity, 97% [95% CI: 81, 100; P = .007]; specificity, 93% [95% CI: 87, 97; P < .001]; AUC, 0.98 [95% CI: 0.93, 0.99; P = .09]) and NCCT images (sensitivity, 91% [95% CI: 83, 96; P = .33); specificity, 84% [95% CI: 69, 93; P < .001); AUC, 0.95 [95% CI: 0.90, 0.99; P = .14]). Most studies were of low quality and had high risk of bias. Conclusion AI can feasibly detect AD but does not demonstrate clinical applicability in its current form. Keywords: CT, Vascular, Cardiac, Aorta, Computer-aided Diagnosis (CAD), Meta-Analysis Supplemental material is available for this article. © RSNA, 2025.

BACKGROUND:The global prevalence of diabetes is rising, alongside costs and workload associated with screening for diabetic eye disease (diabetic retinopathy). Automated retinal image analysis systems (ARIAS) could replace primary human grading of images for diabetic retinopathy. We evaluated multiple ARIAS in a real-life screening programme. METHODS:Eight of 25 invited and potentially eligible CE-marked systems for diabetic retinopathy detection from retinal images agreed to participate. From 202 886 screening encounters at the North East London Diabetic Eye Screening Programme (between Jan 1, 2021, and Dec 31, 2022) we curated a database of 1·2 million images and sociodemographic and grading data. Images were manually graded by up to three graders according to a standard national protocol. ARIAS performance overall and by subgroups of age, sex, ethnicity, and index of multiple deprivation (IMD) were assessed against the reference standard, defined as the final human grade in the worst eye for referable diabetic retinopathy (primary outcome). Vendor algorithms did not have access to human grading data. FINDINGS:Sensitivity across vendors ranged from 83·7% to 98·7% for referable diabetic retinopathy, from 96·7% to 99·8% for moderate-to-severe non-proliferative diabetic retinopathy, and from 95·8% to 99·5% for proliferative diabetic retinopathy. Sensitivity was largely consistent for moderate-to-severe non-proliferative and proliferative diabetic retinopathy by subgroups of age, sex, ethnicity, and IMD for all ARIAS. For mild-to-moderate non-proliferative diabetic retinopathy with referable maculopathy, sensitivity across vendors ranged from 79·5% to 98·3%, with greater variability across population subgroups. False positive rates for no observable diabetic retinopathy ranged from 4·3% to 61·4% and within vendors varied by 0·5 to 44 percentage points across population subgroups. INTERPRETATION:ARIAS showed high sensitivity for medium-risk and high-risk diabetic retinopathy in a real-world screening service, with equitable performance across population subgroups. ARIAS could provide a cost-effective solution to deal with the rising burden of screening for diabetic retinopathy by safely triaging for human grading, substantially increasing grading capacity and rapid diabetic retinopathy detection. FUNDING:NHS Transformation Directorate, The Health Foundation, and The Wellcome Trust.

This paper presents a novel approach to forest habitat monitoring using robotics and advanced data analysis techniques. We introduce a quadrupedal robot with LiDAR and onboard cameras to collect detailed data about forest structure and composition. The data is then processed using a combination of data analysis techniques and machine learning algorithms to perform a comprehensive dendrometric and floristic survey. Our approach provides an efficient and accurate method for assessing the ecological health of forest ecosystems. This work contributes to the ongoing efforts in habitat conservation and offers a promising tool for future environmental monitoring tasks.

Retinal imaging offers a non-invasive means to assess the circulatory system, with morphological features of retinal vessels serving as biomarkers for systemic disease. QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) is a fully automated artificial intelligence-enabled retinal vasculometry system designed to process large-scale retinal image datasets to obtain quantitative measures of vessel morphology for use in epidemiological studies. Previously reliant on traditional image processing and machine learning, QUARTZ has now transitioned to a deep learning pipeline. Currently individually trained versions are tailored to specific datasets. Evaluation using the UK Biobank retinal dataset shows improvements in performance metrics: the F1 score for vessel segmentation increased from 0.7753 to 0.8472, accuracy for the A/V segment-level decision increased from 0.8524 to 0.9022, the detection rate for optic disc localization increased from 0.9760 to 0.9933, and the F1 score for image quality classification increased from 0.8872 to 0.9750. QUARTZ distinguishes itself from other deep learning based retinal vasculometry systems through its efficient use of data, extracting valuable information despite issues such as low levels of illumination. The high performance of QUARTZ is consistent across two other extensive retinal datasets, namely the Canadian Longitudinal Study on Aging (CLSA) and the North East London Diabetic Eye Screening Programme (NEL DESP). Evaluation on subsets was preceded by the automatic processing of entire retinal datasets by QUARTZ, processing over 1.4 million images. These retinal vasculometry outputs will serve as a valuable resource for epidemiological studies.

We propose methods to automatically assess the conservation status of a habitat. Habitat monitoring is usually performed by botanists and other specialists in their field work, searching for the presence or lack of typical plant species (Evans D, Arvela M (2011) Assessment and reporting under Article 17 of the Habitats Directive. Explanatory Notes & Guidelines for the period 2007–2012. European Commission, Brussels.) and other elements (such as vegetation cover) that might indicate the degradation of a habitat. We present preliminary work that makes use of a robotic platform employed to help botanists in their tasks. Three methods are proposed. First a color segmentation method, to detect the amount of green in a given area, a detection method to automatically detect the presence of a given plant, and finally a classification method used to identify a plant in a single image.

Recently, object recognition and image segmentation have gained much attention in the computer vision field and image processing for effective object localisation and identification. Researchers have applied semantic segmentation and instance segmentation in diverse application areas. However, the least research has been performed in natural habitat monitoring or plant species identification in natural environments/surroundings. For this study, we composed a real image dataset from four habitats: forests, dunes, grasslands, and screes from various locations in Italy. Habitat expert botanists annotated the data using bounding box annotations which have been further utilised to generate the plant species masks using the recently proposed Segment Anything Model (SAM) for segmentation, localisation, and identification tasks. Extensive experimentation has been performed on habitat data with bounding boxes and masks using YOLOv8 detection and segmentation models. Comparative analysis of models, model training with different train data percentages, and the importance of masks over bounding boxes have been studied and discussed.

Objective: To describe the development of a platform for image collection and annotation that resulted in a multi-sourced international image dataset of oral lesions to facilitate the development of automated lesion classification algorithms. Materials and Methods: We developed a web-interface, hosted on a web server to collect oral lesions images from international partners. Further, we developed a customised annotation tool, also a web-interface for systematic annotation of images to build a rich clinically labelled dataset. We evaluated the sensitivities comparing referral decisions through the annotation process with the clinical diagnosis of the lesions. Results: The image repository hosts 2474 images of oral lesions consisting of oral cancer, oral potentially malignant disorders and other oral lesions that were collected through MeMoSA (R) UPLOAD. Eight-hundred images were annotated by seven oral medicine specialists on MeMoSA (R) ANNOTATE, to mark the lesion and to collect clinical labels. The sensitivity in referral decision for all lesions that required a referral for cancer management/surveillance was moderate to high depending on the type of lesion (64.3%-100%). Conclusion: This is the first description of a database with clinically labelled oral lesions. This database could accelerate the improvement of AI algorithms that can promote the early detection of high-risk oral lesions.

In this paper, we first discuss the challenges related to habitat monitoring and review possible robotic solutions. Then, we propose a framework to perform terrestrial habitat monitoring exploiting the mobility of legged robotic systems. The idea is to provide the robot with the Natural Intelligence introduced as the combination of the environment in which it moves, the intelligence embedded in the design of its body, and the algorithms composing its mind. This approach aims to solve the challenges of deploying robots in real natural environments, such as irregular and rough terrains, long-lasting operations, and unexpected collisions, with the final objective of assisting humans in assessing the habitat conservation status. Finally, we present examples of robotic monitoring of habitats in four different environments: forests, grasslands, dunes, and screes.

We propose a new method for simulating pedestrian crowd movement in a virtual environment. A crowd consists of groups of different number of people with different attributes such as gender, age, position, velocity, and energy. Each group has its own intention used to generate a trajectory for each pedestrian navigating in the virtual environment. Additionally, an agent -based model is introduced to simulate pedestrian behaviours in the groups, where various steering behaviours are introduced and combined into a single steering force to allow pedestrians in each group to walk toward their destination point. Based on the proposed method, every single pedestrian in each group can continuously adjust their attributes. Moreover, pedestrians optimize their path independently toward the desired goals, while avoiding obstacles and other pedestrians in the scene. This method takes into account the safety-space around each pedestrian to avoid collisions among pedestrians. The proposed method was implemented for several simulation scenarios under various conditions for a wide range of different parameters. Statistical analysis is carried out to evaluate the performance of the proposed method for simulating the crowd movement in the virtual environment. Results indicate that our method can generate each pedestrian's trajectories in each group independently to reach several goal points within a reasonable computational time. Moreover, the obtained results reveal that the mean value of the computational time is not increased significantly with the increasing of the number of pedestrians in the crowd. (c) 2021 Elsevier Inc. All rights reserved.

This chapter presents the main results of the MONICA project, one of the five large-scale pilot projects funded by the European Commission. MONICA focuses on the adoption of wearable IoT solutions for the management of safety and security in large open-air events as well as on the reduction of noise level for neighbours. The project addresses several challenges in eleven pilots of six major European cities using a large number of IoT wearables and sensors. The chapter first introduces all MONICA challenges in the context of large open-air events and then presents the corresponding adopted technical solutions, the defined IoT architecture and the perspective in integrating a wide range of heterogeneous sensors. On one side, the focus is on the solutions that have been adopted to improve the crowd management, crowd safety

This paper investigates a new method to simulate pedestrian crowd movement in a large and complex virtual environment, representing a public space such as a shopping mall. To demonstrate pedestrian dynamics, we consider groups of pedestrians of different size, sharing a crowded environment. A pedestrian has its own characteristics, such as gender , age , position , velocity , and energy . The proposed method uses a multi-group microscopic model to generate real-time trajectories for all people moving in the defined virtual environment. Additionally, a dynamic model is introduced for modelling group behaviour. Based on the proposed method, all pedestrians in each group can continuously adjust their attributes and optimize their path towards the desired visiting targets, while avoiding obstacles and other pedestrians. Simulation results show that the proposed method can describe a realistic simulation of dynamic behaviour.

One common issue of object detection in aerial imagery is the small size of objects in proportion to the overall image size. This is mainly caused by high camera altitude and wide-angle lenses that are commonly used in drones aimed to maximize the coverage. State-of-the-art general purpose object detector tend to under-perform and struggle with small object detection due to loss of spatial features and weak feature representation of the small objects and sheer imbalance between objects and the background. This paper aims to address small object detection in aerial imagery by offering a Convolutional Neural Network (CNN) model that utilizes the Single Shot multi-box Detector (SSD) as the baseline network and extends its small object detection performance with feature enhancement modules including super-resolution, deconvolution and feature fusion. These modules are collectively aimed at improving the feature representation of small objects at the prediction layer. The performance of the proposed model is evaluated using three datasets including two aerial images datasets that mainly consist of small objects. The proposed model is compared with the state-of-the-art small object detectors. Experiment results demonstrate improvements in the mean Absolute Precision (mAP) and Recall values in comparison to the state-of-the-art small object detectors that investigated in this study.

Purpose To establish an oral lesion image database that could accelerate the development of artificial intelligence systems for lesion recognition and referral decision. Materials and Methods We describe the establishment of a multi-sourced image dataset through the development of a platform for the collection and annotation of images. Further, we developed a used-friendly tool (MeMoSA® ANNOTATE) for systematic annotation to collect a rich dataset associated with the images. We evaluated the sensitivities comparing referral decisions through the annotation process with the clinical diagnosis of the lesions to identify lesions that are challenging to identify through images alone. Results The image repository hosts 2474 images of oral lesions consisting of oral cancer, oral potentially malignant disorders, benign lesions, normal anatomical variants and normal mucosa that were collected through our platform, MeMoSA® UPLOAD. Over 800 images were annotated by seven oral medicine specialists on MeMoSA®ANNOTATE, to mark the lesion and to collect clinical labels. The sensitivity in referral decision for all lesions that required a referral for cancer management/surveillance was moderate to high depending on the type of lesion (64.3–100%). Conclusion This is the first description of a database with well-annotated oral lesions. This database has already been used for the development of AI algorithm for classifying oral lesions. Further expansion of this database could accelerate the improvement in AI algorithms that can facilitate the early detection of oral potentially malignant disorders and oral cancer.

Oral cancer disproportionately affects low- and middle-income countries, where a lack of access to appropriate medical care contributes towards late disease presentation. Using artificial intelligence to facilitate the automated identification of high-risk oral lesions can improve patient survival rates. With image classification using oral cavity images and other forms of medical images, the information to be classified can often be extremely localized. To address this problem, we propose the use of convolutional neural networks with trainable soft attention. Further to this, we incorporate the use of localization loss to penalize the difference between attention maps and clinically annotated mask. This effectively allows clinicians to help guide soft attention. Improvements to the baseline were made, with an accuracy of 0.8333 and a ROC AUC of 0.8632, which equates to increases of 0.0245 and 0.0394, respectively. This accuracy corresponds to a sensitivity of 0.8469 and a specificity of 0.8208. Perhaps of more importance, is a model that demonstrates better capability at paying attention to the lesions in its decision making. Furthermore, visualizing resulting attention maps can help to strengthen clinical confidence in AI decision making.

Oral cancer is a major health issue among low- and middle-income countries due to the late diagnosis. Automated algorithms and tools have the potential to identify oral lesions for early detection of oral cancer. In this paper, we aim to develop a novel deep learning framework named D'OraCa to classify oral lesions using photographic images. We are the first to develop a mouth landmark detection model for the oral images and incorporate it into the oral lesion classification model as a guidance to improve the classification accuracy. We evaluate the performance of five different deep convolutional neural networks and MobileNetV2 was chosen as the feature extractor for our proposed mouth landmark detection model. Quantitative and qualitative results demonstrate the effectiveness of the mouth landmark detection model in guiding the classification model to classify the oral lesions into four different referral decision classes. We train our proposed mouth landmark model on a combination of five datasets, containing 221,565 images. Then, we train and evaluate our proposed classification model with mouth landmark guidance using 2,455 oral images. The results are consistent with clinicians and the $$F_1$$ score of the classification model is improved to 61.68%.