Image Processing & Applications

Appearance-based gaze estimation frequently relies on deep Convolutional Neural Networks (CNNs). These models are accurate, but computationally expensive and act as ‘‘black boxes'', offering little interpretability. Geometric methods based on facial landmarks are lightweight alternatives. However, their performance limits and generalization capabilities remain underexplored in modern benchmarks. In this study, we conduct a comprehensive evaluation of the landmark-based gaze estimation. We introduce a standardized pipeline to extract and normalize landmarks from three large-scale datasets (Gaze360, ETH-XGaze, and GazeGene) and train lightweight regression models, specifically extreme gradient boosted trees and two neural architectures: a holistic multilayer perceptron (MLP) and a Siamese MLP designed to capture binocular geometry. We find that landmark-based models exhibit lower performance in the within-domain evaluation, likely due to noise introduced into the datasets by the landmark detector. Never-theless, in the cross-domain evaluation, the proposed MLP architectures show generalization capabilities comparable to those of the ResNet18 baselines. These findings suggest that sparse geometric features encode sufficient information for robust gaze estimation, paving the way for efficient, interpretable, and privacy-friendly edge applications. The source code and generated landmark-based datasets are available at: https://github.com/daniele-agostinelli/LandmarkGaze.git.

Keywords: Deep learning , Facial landmarks , Gaze estimation , Machine learning , Pattern recognition

Background and Objective: Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, accounting for approximately 20.5 million deaths annually, nearly one-third of all global deaths. Despite its central role in cardiology, echocardiographic assessment remains subject to significant inter- and intra-observer variability, particularly based on manual frame selection and segmentation. This limitation has driven increasing interest in Deep Learning (DL) solutions capable of enabling more objective, reproducible, and efficient analyses. Methods: This paper introduces CardioSmartAssist, a deep learning framework for automatic left ventricular segmentation and multi-cycle ejection fraction estimation relying solely on echocardiographic videos. The system integrates frame-by-frame segmentation visualisation, anomaly detection, and volume tracking to enhance clinical usability. Moreover, a key feature is its continuous learning mechanism, which allows clinician-corrected segmentations to be stored and used for progressive model refinement. Results: The framework is based on a MultiResUNet architecture, trained on public (EchoNet-Dynamic) and proprietary (CardioSmartSet) datasets, achieving Dice Coefficient Scores of 0.9328 and 0.9189, respectively. On the held-out test set, the EF estimated by the system showed a mean absolute difference of 10% compared with clinically reported EF values, which is lower than the typical inter-operator variability of approximately 13%. Conclusion: CardioSmartAssist resulted to be a promising tool for consistent cardiac evaluations, improving access to diagnostics, and enhancing clinical decision-making through smart assistance.

Keywords: AI-assisted diagnosis , Artificial intelligence , Clinical decision support systems , Computer-aided diagnosis , Deep learning , Left ventricular ejection fraction

Italian hand gestures constitute a distinctive and widely recognized form of nonverbal communication, deeply embedded in everyday interaction and cultural identity. Despite their prominence, these gestures are rarely formalized or systematically taught, posing challenges for foreign speakers and visitors seeking to interpret their meaning and pragmatic use. Moreover, their ephemeral and embodied nature complicates traditional preservation and transmission approaches, positioning them within the broader domain of intangible cultural heritage. This paper introduces a machine learning–based framework for recognizing iconic Italian hand gestures, designed to support cultural learning and engagement among foreign speakers and visitors. The approach combines RGB–D sensing with depth-enhanced geometric feature extraction, employing interpretable classification models trained on a purpose-built dataset. The recognition system is integrated into a non-immersive virtual reality application simulating an interactive digital totem conceived for public arrival spaces, providing tutorial content, real-time gesture recognition, and immediate feedback within a playful and accessible learning environment. Three supervised machine learning pipelines were evaluated, and Random Forest achieved the best overall performance. Its integration with an Isolation Forest module was further considered for deployment, achieving a macro-averaged accuracy and F1-score of 0.82 under a 5-fold cross-validation protocol. An experimental user study was conducted with 25 subjects to evaluate the proposed interactive system in terms of usability, user engagement, and learning effectiveness, obtaining favorable results and demonstrating its potential as a practical tool for cultural education and intercultural communication.

Keywords: gesture recognition , human–computer interaction , intangible cultural heritage , Italian culture , machine learning , virtual reality

Augmented Reality (AR) is increasingly being adopted in surgical procedures. Identifying accurate and reliable tracking systems can enhance the effectiveness of AR assisted surgery. The study presents a benchmarking platform to evaluate the performance of different optical surgical tools tracking systems for AR applications, addressing the need for standardized comparison of tracking systems' accuracy, repeatability, and reliability. A custom-built, cost-effective benchmarking platform was developed, and different quantitative evaluation metrics were employed to assess performances of Marker-Based (MB) tracking systems. Two types of measurements were performed: static, where metrics such as Target Registration Error (TRE) and tip stability as a measure of jitter were estimated, and dynamic, involving a measure of the deviation between the tracked tooltip trajectory and its GT. Three AR MB-tracking methods were tested: method 1, mono-RGB sensor tracking a planar image target; method 2, RGB-depth sensor tracking passive spherical markers; and method 3, mono-IR sensor tracking IR active markers. Significant performance differences were observed. Method 3 achieved the lowest TRE value of Method 1 exhibited the best tip stability with a jitter value of Method 2 obtained the minimum trajectory distance in dynamic tests. The benchmarking platform demonstrated its effectiveness in evaluating and comparing different AR tracking methods. This study enables the optimization of tracking system selection for use in the operating room, and facilitating the integration of AR as a supportive technology in surgical practice.

Keywords: Augmented reality , Augmented surgery , Marker-based , Pose estimation , RealSense , Tooltip tracking

During operation, turbomachinery blades are subjected to dynamic excitations, which are the primary drivers of high-cycle fatigue, the leading cause of failure in bladed disks. Therefore, accurate measurement of their dynamic response under resonance is critical for reliable design. Traditional contact-based measurement techniques suffer from drawbacks such as added mass, limited lifespan, and complex data transmission, prompting interest in non-contact alternatives. This paper explores the application of digital image correlation (DIC) for analyzing synchronous vibrations in bladed disks. The proposed approach employs low-speed, high-resolution cameras combined with downsampling strategies to enable cost-effective, full-field, high-resolution measurements. A signal processing technique, the circumferential harmonic fit (CHF), is proposed and applied to extract system parameters from downsampled displacement data. The methodology is applied on a simplified bladed disk mounted on a spinning rig, demonstrating successful identification of operational deflection shapes at resonance.

Keywords: Bladed disks , DIC , Downsampling , Optical technique , Spinning test , Vibrations

Immune checkpoint inhibitors (ICIs) have substantially improved outcomes in advanced melanoma but are frequently linked to immune-related adverse events (irAEs). Vitiligo is a common cutaneous irAE and has been consistently associated with improved patient outcome, including prolonged progression-free and overall survival. It also represents significant visual stigma, particularly when the face is involved. Traditional treatment comprises topical steroids, calcineurin inhibitors, laser, and phototherapy which often have insufficient effects. Since 2023, the first approved drug for non-segmental vitiligo (NSV) with facial involvement, the topical Janus kinase inhibitor ruxolitinib, has been available. However, experience with its use in ICI-induced vitiligo remains limited. In this exploratory analysis, three patients who developed facial vitiligo following ICI therapy applied 1.5% ruxolitinib cream to affected facial areas twice daily. After six (two patients), and twelve months (one patient), extensive repigmentation was observed, quantified at 95.7%, 78.9%, and 99.1% using a novel semi-automatic tool. Quality-of-life questionnaires showed mean reductions of 57.6% (Vitiligo DLQI) and 68.2% (Vitiligo-specific Quality of Life) in disease burden. Treatment was associated with substantial repigmentation without observed side effects. Further evaluation in larger, prospective cohorts is warranted to better define treatment effects, clinical applicability, and long-term safety.

Keywords: immune checkpoint inhibitor , immune-related adverse event , JAK inhibitor , melanoma , ruxolitinib , vitiligo

Background: Adherence to movement precautions following sternotomy is essential for sternal healing, but patients often find it difficult to maintain the correct behavior. Methods: This study introduces a real-time computer vision-based system to evaluate movement compliance with the post-sternotomy precautions protocol. A YOLOv11 object detection model was trained using a dataset comprising real images and AI-generated images. A secondary monitoring algorithm was developed to use YOLO inference results to classify the whole action rather than a single frame. Results: The integration of synthetic data significantly enhanced YOLO model performance, achieving a mAP50 of 80.3%. In real-time validation, the monitoring algorithm correctly classified 85% of non-compliant actions without misclassifying any compliant actions. Conclusion: This work demonstrates the feasibility of a low-cost, non-invasive solution for monitoring post-sternotomy precautions. Furthermore, the use of Generative AI proved effective in overcoming data scarcity.

Keywords: Cardiac Rehabilitation , Generative Artificial Intelligence , Sternotomy

Background: Serious games (SGs) with hand-tracking solutions are increasingly adopted in neurological rehabilitation. The Leap Motion Controller (LMC) is widely used in clinical and research contexts, while software-based systems, such as MediaPipe (MP), are emerging. Objectives: This study compared the usability of MP- and LMC-based SGs. Methods: Seven SGs were developed to evaluate Grasp and Pinch gestures and tested with fifty healthy volunteers. Usability was assessed with the System Usability Scale (SUS) after each device, and an ad-hoc comparative questionnaire (LMC, MP, Neutral) collected preferences on several aspects. Results: Both systems achieved excellent SUS scores (MP: 88/100; LMC: 90/100), with no statistical difference in usability. The comparative questionnaire showed a stronger preference for LMC (63%) versus MP (17%), with 20% neutral. Conclusion: Although both solutions demonstrated high usability, LMC was more frequently preferred in direct comparison. The SUS results of MP encourage further investigation, including large-scale tests with neurological patients.

Keywords: Comparative Study , Exergaming , Hand , Motion Capture , Neurological Rehabilitation

In this retrospective study, the diagnostic performance of an individualized apparent diffusion coefficient (ADC) signal intensity (SI) scale for differentiating prostate cancer (PCa) from benign simplified Prostate Imaging Reporting and Data System (S-PI-RADS) 4 lesions detected on biparametric magnetic resonance imaging (bpMRI) was evaluated. A total of 102 patients with biopsy-confirmed PCa and 79 patients with benign lesions (inflammation, HGPIN, ASAP) presenting as S-PI-RADS 4 were included. An individualized ADC SI scale was generated for each patient using maximum and minimum ADC values from the bladder and femoral head, respectively. The midpoint (ADC_mean) and the percentage difference (PD) between ADC_mean and lesion intensity (ADC_lesion) were calculated. Differences and diagnostic performance were assessed using Mann-Whitney U tests and receiver operating characteristic (ROC) analysis. PCa lesions demonstrated significantly lower ADC values and higher PDs compared with benign lesions (P<0.001). ROC analysis of PD yielded an area under the curve (AUC) of 0.798. Using a PD cut-off of 14.67%, sensitivity and specificity for detecting PCa were 73.5% and 94.9%, respectively. Intra-reader repeatability was high [intraclass correlation coefficient (ICC) 0.92–0.94], and PD values remained robust across variations in ADC fitting. The individualized ADC SI scale provides a patient-specific quantitative measure that effectively distinguishes malignant from benign S-PI-RADS 4 lesions. This approach complements visual bpMRI assessment, demonstrates high specificity, and has the potential to reduce unnecessary biopsies. Further prospective studies are warranted to validate its clinical utility.

Keywords: apparent diffusion coefficient (ADC) , Prostate cancer (PCa) , quantitative magnetic resonance imaging (quantitative MRI)

This paper addresses the crucial aspect of position error modeling and compensation in industrial servomechanisms with the aim to achieve accurate control and high-performance operation in industrial robots and automated production systems. The inherent complexity and nonlinear behavior of these modules, usually consisting of a servomotor and a speed reducer, often challenge traditional analytical modeling approaches. In response, the study extensively explores the design and implementation of Machine Learning (ML) algorithms to obtain a comprehensive model of the Transmission Error (TE) in rotating vector reducers, which is a main source of robot motion accuracy errors. The ML models are trained with experimental data obtained from a special purpose test rig, where the reducer is tested under different combinations of input speed, applied load and oil temperature. In the second part of the work, the resulting predictive model, tailored to capture the intricate dynamics of the analyzed reducer, is imported into a programmable logic controller to enable online compensation strategies during the execution of custom motion profiles. Experimental tests are conducted using two distinct motion profiles: one generated with a cycloidal law, typical of industrial machinery, and the other extrapolated from the joints of an industrial robot during a pick-and-place task. The results demonstrate the effectiveness of the proposed approach, enabling accurate prediction and substantial reductions (over 90%) in the overall reducer TE through the implemented predictive model.

Keywords: Compensation approach , Machine learning , Predictive modeling , Servomechanism , Test rig , Transmission error

Developing accurate methods for differentiating benign vs. malignant pulmonary nodules on CT is crucial for the correct management of patients referred for suspicious lung cancer. In this context deep learning by convolutional neural networks (CNN) has been gaining ground as an alternative to conventional methods based on feature engineering, although the use of CNN is often hampered by the lack of sufficiently large datasets for training. Herein we explore the effectiveness of deep features from pre-trained convolutional networks ‘off-the-shelf' to discriminate benign vs. malignant lung nodules from CT images. To this end we compare three approaches (two classic, one novel) for pseudo-colour image generation which allow the grey-scale CT data to be fed into CNN models designed for and trained on colour images. The classification performance was estimated by internal and cross-validation using two independent datasets (LIDC-IDRI and LUNGx), giving four experimental conditions altogether. Conventional radiomics features were used as baseline reference. The best accuracy achieved by deep features in the four experimental conditions was respectively 88.5%, 69.6%, 68.9% and 65.2%, that obtained through conventional features 85.5%, 60.9%, 65.2% and 63.8%.

Keywords: Convolutional neural networks , Lung cancer , Pseudo-colours , Transfer learning

Background and objective: Accurately measuring cervical vertebrae dimensions is crucial for diagnosing conditions, planning surgeries, and studying morphological variations related to gender, age, and ethnicity. However, traditional manual measurement methods, due to their labour-intensive nature, time-consuming process, and susceptibility to operator variability, often fall short in providing the objectivity required for reliable measurements. This study addresses these limitations by introducing a novel computer-based method for automatically identifying the dimensional features of human cervical vertebrae, leveraging 3D geometric models obtained from CT or 3D scanning. Methods: The proposed approach involves defining a local coordinate system and establishing a set of rules and parameters to evaluate the typical dimensional features of the vertebral body, foramen, and spinous process in the sagittal and coronal planes of the high-density point cloud of the cervical vertebra model. This system provides a consistent measurement reference frame, improving the method's reliability and objectivity. Based on this reference system, the method automates the traditional standard protocol, typically performed manually by radiologists, through an algorithmic approach. Results: The performance of the computer-based method was compared with the traditional manual approach using a dataset of nine complete cervical tracts. Manual measurements were conducted following a defined protocol. The manual method demonstrated poor repeatability and reproducibility, with substantial differences between the minimum and maximum values for the measured features in intra- and inter-operator evaluations. In contrast, the measurements obtained with the proposed computer-based method were consistent and repeatable. Conclusions: The proposed computer-based method provides a more reliable and objective approach for measuring the dimensional features of cervical vertebrae. It establishes a procedural standard for deducing the morphological characteristics of cervical vertebrae, with significant implications for clinical applications, such as surgical planning and diagnosis, as well as for forensic anthropology and spinal anatomy research. Further refinement and validation of the algorithmic rules and investigations into the influence of morphological abnormalities are necessary to improve the method's accuracy.

Keywords: Biomedical engineering , Cervical vertebrae , CT measures standardization

An effective method to enable the enjoyment of works of art by the blind is to reproduce tactile copies of the work, to facilitate tactile exploration. This is even more important when it comes to paintings, which are inherently not accessible to the blind unless they are transformed into 3D models. Today, artificial intelligence techniques are rapidly growing and represent a paramount method for solving a variety of previously hard-to-solve tasks. It is, therefore, presumable that the translation from 2D images to 3D models using such methods will be also in continuous development. Unfortunately, reconstructing a 3D model from a single image, especially when it comes to painting-based images, is an ill-posed problem due to the depth ambiguity and the lack of a ground truth for the 3D model. To confront this issue, this paper proposes an overview of artificial intelligence-based methods for reconstructing 3D geometry from a single image is provided. The survey explores the potentiality of Convolutional Neural Networks, Generative Adversarial Networks, Variational Autoencoders, and zero-shot methods. Through a small set of case studies, the capabilities and limitations of CNNs in creating a 3D-scene model from artworks are also encompassed. The findings suggest that, while deep learning models demonstrate that they are effective for 3D retrieval from paintings, they also call for post-processing and user interaction to improve the accuracy of the 3D models.

Keywords: 3D printing , blind people , CNNs , GANs , paintings , VAEs

Quality control is considered one of the most important tasks by manufacturing industries, as being able to guarantee certain quality levels is necessary in order to meet customer expectations, reduce waste and costs. Requiring an inspection for each of the products manufactured, being able to have a tool capable of automating the detection of possible defects would simplify this procedure, making it faster and more optimised. This is the specific case of the company Esaote, which carries out accurate quality control for each of its ultrasound probes. In particular, concerning the inspection of the shell, that is currently carried out manually by the staff. To create a tool capable of automating this inspection, a defect detection algorithm based on machine learning is proposed. The algorithm processes the images according to a patch-based strategy, following three steps: splits the image in patches, classifies and localizes the defects in the patches, and finally combines the results to obtain the complete list of all the defects present. Performance was analysed for different configurations related to the three steps, with particular emphasis on the percentage of overlap between patches, the total number of patches to be analysed, and the voting algorithm used to combine results between several patches. The best configuration identified an accuracy of 83.63%, an f-score of 89.87%, a precision of 81.60%, a recall of 88.97%, an AP of 77.63% and finally an AUC of 83.48%.

Keywords: Artificial Intelligence , Computer vision , Convolutional neural network , Image Processing , Visual inspection

This study explores the application of fuzzy soft classification techniques combined with vegetation indices to address spectral overlap and heterogeneity in agricultural image processing. The methodology focuses on the integration of three key vegetation indices: Soil-Adjusted Vegetation Index (SAVI), Modified Soil-Adjusted Vegetation Index (MSAVI), and Modified Chlorophyll Absorption in Reflectance Index (MCARI), with Modified Possibilistic C-Means (MPCM) clustering. The analysis involves preprocessing the image data, calculating the vegetation indices, and applying the MPCM algorithm to perform soft classification, allowing pixels to belong to multiple classes with varying degrees of membership. A quantitative assessment is conducted to evaluate the accuracy of the classification results. Methodological approach: • Integrating advanced image processing techniques and vegetative band ratios with the fuzzy classification method MPCM to handle the inherent complexities in agricultural image analysis, such as spectral overlap and mixed boundaries. • Quantitative assessment of classification accuracy using Fuzzy Error Matrices (FERM). This approach provides a robust framework for analyzing spectral overlaps among the crops and weeds and improving the accuracy of crop classification, particularly in heterogeneous environments.

Keywords: Chlorophyll absorption ratio index (CARI) , Digital image processing , Fuzzy logic , Modified possibilistic C-means (MPCM) , Modified soil adjusted vegetation index (MSAVI) , Soft-classification , Soil adjusted vegetation index (SAVI)

Oral Squamous Cell Carcinoma is characterized by significant mortality and morbidity. Dental professionals can play an important role in its early detection, thanks to the availability of embedded smart cameras for oral photos and remote screening supported by Deep Learning (DL). Despite the promising results of DL for automated detection and classification of oral lesions, its effectiveness is based on a clearly defined protocol, on the explainability of results, and on periodic cases collection. This paper proposes a novel method, combining DL and Case-Based Reasoning (CBR), to allow the post-hoc explanation of the system answer. The method uses explainability tools organized in a protocol defined in the Business Process Model and Notation (BPMN) to allow its experimental validation. A redesign of the Faster-R-CNN Feature Pyramid Networks (FPN) + DL architecture is also proposed for lesions detection and classification, fine-tuned on 160 cases belonging to three classes of oral ulcers. The DL system achieves state-of-the-art performance, i.e., 83% detection and 92% classification rate (98% for neoplastic vs. non-neoplastic binary classification). A preliminary experimentation of the protocol involved both resident and specialized doctors over selected difficult cases. The system and cases have been publicly released to foster collaboration between research centers.

Keywords: Case-based reasoning , Convolutional neural network , Explainable artificial intelligence , Medical imaging , Oral cancer , OSCC

This paper describes a new methodology that expands the capabilities of low-frame, high-resolution stereo-camera systems in studying the dynamic behavior of components in the presence of nonlinear phenomena. A new downsampling technique called the Smoothed Harmonics Analysis (SHA) is proposed. This technique addresses the limitations due to the low-frame rate cameras for the study of high-frequency periodic steady-state nonlinear oscillations. SHA enables accurate reconstruction of downsampled signals, thus opening up numerous potential applications. The feasibility of this technique is demonstrated by analyzing the motion of a beam with nonlinear behavior. The nonlinearity is caused by intermittent contact while the beam is subjected to harmonic excitation.

Keywords: Digital image correlation , Downsampling , Full-field measurements , Nonlinear dynamics

Digital Image Correlation (DIC) is a promising noncontact method for measuring the full-field dynamics of vibrating structures. This method needs one or two cameras to measure 2D or 3D dynamics. The frames of the recorded videos are then postprocessed to correlate the structure points at different times and obtain displacement information. A plethora of cameras is available—in terms of frame rate, resolution, versatility, and overall quality—the choice of which depends on the specific application and spending constraints. The idea behind this work is to evaluate the feasibility of making DIC-ready videos using cameras built into a device that is part of everyday life: the smartphone. The proposed approach is an easy-to-handle procedure, suitable for teaching purposes or an early qualitative investigation. This chapter discusses a simple experiment students or beginners can perform on simple vibrating structures. First, a simple 2D dynamics was investigated. The vibration of a clamped beam with moving constraints was recorded with a single smartphone. The beam had an L-type cross section to emphasize in-plane motion. The frames were postprocessed with open-source DIC software and the first modal shape was extracted. The goal of this assignment was to introduce students to the basics of DIC. Second, the 3D dynamics of a beam was studied with a single smartphone. The image of the beam was reflected by two mirrors, and the reflected images were recorded by a single smartphone. A tool was developed to split the recorded frame into two independent images. The images were postprocessed to obtain the full 3D dynamics of the beam. Third, the 3D dynamics of a beam was studied with two smartphones. © The Society for Experimental Mechanics, Inc.

Keywords: DIC , Dynamics , Educational , Pseudo 3D-DIC , Smartphone

Skin ulcers are open wounds on the skin characterized by the loss of epidermal tissue. Skin ulcers can be acute or chronic, with chronic ulcers persisting for over six weeks and often being difficult to heal. Treating chronic wounds involves periodic visual inspections to control infection and maintain moisture balance, with edge and size analysis used to track wound evolution. This condition mostly affects individuals over 65 years old and is often associated with chronic conditions such as diabetes, vascular issues, heart diseases, and obesity. Early detection, assessment, and treatment are crucial for recovery. This study introduces a method for automatically detecting and segmenting skin ulcers using a Convolutional Neural Network and two-dimensional images. Additionally, a three-dimensional image analysis is employed to extract key clinical parameters for patient assessment. The developed system aims to equip specialists and healthcare providers with an objective tool for assessing and monitoring skin ulcers. An interactive graphical interface, implemented in Unity3D, allows healthcare operators to interact with the system and visualize the extracted parameters of the ulcer. This approach seeks to address the need for precise and efficient monitoring tools in managing chronic wounds, providing a significant advancement in the field by automating and improving the accuracy of ulcer assessment.

Keywords: 3D analysis , automatic segmentation , chronic wound , clinical parameters , convolutional neural network , edge detection , interactive interface

Targeted Radionuclide Therapy (TRT) is a medical technique exploiting radionuclides to combat cancer growth and spread. TRT requires a supply of radionuclides that are currently produced by either cyclotrons or nuclear research reactors. In this context, the ISOLPHARM project investigates the production of innovative radionuclides for medical applications. This production will be based on the forthcoming SPES facility at the Legnaro National Laboratories (LNL) of the National Institute for Nuclear Physics (INFN), an ISOL facility where high-purity radioactive beams will be used to produce carrier-free radiopharmaceuticals. Previous studies demonstrated that a significant amount of 111Ag, an innovative β/γ emitter suitable for TRT with theranostic applications, can be obtained at the SPES facility. The present work describes the first imaging study on phantoms with 111Ag performed by the ISOLPHARM collaboration. This is a fundamental step to pave the way for the upcoming in vivo studies on the 111Ag-based radiopharmaceutical currently being developed. The imaging potential of this radionuclide was investigated by acquiring phantom images with Cerenkov Luminescence Imaging (CLI) and digital autoradiography

Keywords: ¹¹¹Ag , ⁶⁸Ga , Autoradiography , Cerenkov luminescence imaging , ISOLPHARM , Radiopharmaceuticals , Targeted radionuclide therapy