Explore the vast range of titles available.

The interpretation of thoracic radiographs is a challenging and error-prone task for veterinarians. Despite recent advancements in machine learning and computer vision, the development of computer-aided diagnostic systems for radiographs remains a challenging and unsolved problem, particularly in the context of veterinary medicine. In this study, a novel method, based on multi-label deep convolutional neural network (CNN), for the classification of thoracic radiographs in dogs was developed. All the thoracic radiographs of dogs performed between 2010 and 2020 in the institution were retrospectively collected. Radiographs were taken with two different radiograph acquisition systems and were divided into two data sets accordingly. One data set (Data Set 1) was used for training and testing and another data set (Data Set 2) was used to test the generalization ability of the CNNs. Radiographic findings used as non mutually exclusive labels to train the CNNs were: unremarkable, cardiomegaly, alveolar pattern, bronchial pattern, interstitial pattern, mass, pleural effusion, pneumothorax, and megaesophagus. Two different CNNs, based on ResNet-50 and DenseNet-121 architectures respectively, were developed and tested. The CNN based on ResNet-50 had an Area Under the Receive-Operator Curve (AUC) above 0.8 for all the included radiographic findings except for bronchial and interstitial patterns both on Data Set 1 and Data Set 2. The CNN based on DenseNet-121 had a lower overall performance. Statistically significant differences in the generalization ability between the two CNNs were evident, with the CNN based on ResNet-50 showing better performance for alveolar pattern, interstitial pattern, megaesophagus, and pneumothorax.

Skull segmentation from MR images is a complex yet highly desirable task in modern computational medicine. The main challenges are associated with the fact that MRI focuses more on the soft tissues rather than bone structures. While skull segmentation is well-established in CT imaging, the need for MRI-based segmentation arises from the risks associated with CT radiation exposure. In this work, we explore unsupervised skull segmentation by leveraging modality translation methods, transforming the challenge of direct MR segmentation into a more manageable task of modality translation followed by CT-based segmentation. A broad spectrum of deep generative networks is investigated, including generative adversarial networks, denoising diffusion models, and contrastive learning methods, leading to the development of a novel methodology of MRI-based skull segmentation. In this study, we also address the challenge that MR images typically have lower resolution than CT images, while high-resolution CT images are often required for clinical segmentation tasks, hence we additionally employ a robust super-resolution approach. The methodology proposed in this work offers fast inference for volumetric data and outperforms traditional supervised segmentation methods. Additionally, it surpasses a novel foundation medical segmentation model and delivers superior results compared to other modality translation techniques.

The structure and topology of the pulmonary arteries is crucial to understand, plan, and conduct medical treatment in the thorax area. Due to the complex anatomy of the pulmonary vessels, it is not easy to distinguish between the arteries and veins. The pulmonary arteries have a complex structure with an irregular shape and adjacent tissues, which makes automatic segmentation a challenging task. A deep neural network is required to segment the topological structure of the pulmonary artery. Therefore, in this study, a Dense Residual U-Net with a hybrid loss function is proposed. The network is trained on augmented Computed Tomography volumes to improve the performance of the network and prevent overfitting. Moreover, the hybrid loss function is implemented to improve the performance of the network. The results show an improvement in the Dice and HD95 scores over state-of-the-art techniques. The average scores achieved for the Dice and HD95 scores are 0.8775 and 4.2624 mm, respectively. The proposed method will support physicians in the challenging task of preoperative planning of thoracic surgery, where the correct assessment of the arteries is crucial.

This study explores an innovative approach to early Parkinson’s disease (PD) detection by analyzing speech data collected using a mixed reality (MR) system. A total of 57 Polish participants, including PD patients and healthy controls, performed five speech tasks while using an MR head-mounted display (HMD). Speech data were recorded and analyzed to extract acoustic and linguistic features, which were then evaluated using machine learning models, including logistic regression, support vector machines (SVMs), random forests, AdaBoost, and XGBoost. The XGBoost model achieved the best performance, with an F1-score of 0.90 ± 0.05 in the story-retelling task. Key features such as MFCCs (mel-frequency cepstral coefficients), spectral characteristics, RASTA-filtered auditory spectrum, and local shimmer were identified as significant in detecting PD-related speech alterations. Additionally, state-of-the-art deep learning models (wav2vec2, HuBERT, and WavLM) were fine-tuned for PD detection. HuBERT achieved the highest performance, with an F1-score of 0.94 ± 0.04 in the diadochokinetic task, demonstrating the potential of deep learning to capture complex speech patterns linked to neurodegenerative diseases. This study highlights the effectiveness of combining MR technology for speech data collection with advanced machine learning (ML) and deep learning (DL) techniques, offering a non-invasive and high-precision approach to PD diagnosis. The findings hold promise for broader clinical applications, advancing the diagnostic landscape for neurodegenerative disorders.

Breast-conserving surgery requires supportive radiotherapy to prevent cancer recurrence. However, the task of localizing the tumor bed to be irradiated is not trivial. The automatic image registration could significantly aid the tumor bed localization and lower the radiation dose delivered to the surrounding healthy tissues. This study proposes a novel image registration method dedicated to breast tumor bed localization addressing the problem of missing data due to tumor resection that may be applied to real-time radiotherapy planning. We propose a deep learning-based nonrigid image registration method based on a modified U-Net architecture. The algorithm works simultaneously on several image resolutions to handle large deformations. Moreover, we propose a dedicated volume penalty that introduces the medical knowledge about tumor resection into the registration process. The proposed method may be useful for improving real-time radiation therapy planning after the tumor resection and, thus, lower the surrounding healthy tissues’ irradiation. The data used in this study consist of 30 computed tomography scans acquired in patients with diagnosed breast cancer, before and after tumor surgery. The method is evaluated using the target registration error between manually annotated landmarks, the ratio of tumor volume, and the subjective visual assessment. We compare the proposed method to several other approaches and show that both the multilevel approach and the volume regularization improve the registration results. The mean target registration error is below 6.5 mm, and the relative volume ratio is close to zero. The registration time below 1 s enables the real-time processing. These results show improvements compared to the classical, iterative methods or other learning-based approaches that do not introduce the knowledge about tumor resection into the registration process. In future research, we plan to propose a method dedicated to automatic localization of missing regions that may be used to automatically segment tumors in the source image and scars in the target image.

The aim of this study was to develop and test an artificial intelligence (AI)-based algorithm for detecting common technical errors in canine thoracic radiography. The algorithm was trained using a database of thoracic radiographs from three veterinary clinics in Italy, which were evaluated for image quality by three experienced veterinary diagnostic imagers. The algorithm was designed to classify the images as correct or having one or more of the following errors: rotation, underexposure, overexposure, incorrect limb positioning, incorrect neck positioning, blurriness, cut-off, or the presence of foreign objects, or medical devices. The algorithm was able to correctly identify errors in thoracic radiographs with an overall accuracy of 81.5% in latero-lateral and 75.7% in sagittal images. The most accurately identified errors were limb mispositioning and underexposure both in latero-lateral and sagittal images. The accuracy of the developed model in the classification of technically correct radiographs was fair in latero-lateral and good in sagittal images. The authors conclude that their AI-based algorithm is a promising tool for improving the accuracy of radiographic interpretation by identifying technical errors in canine thoracic radiographs.

Explainable Artificial Intelligence (XAI) encompasses a broad spectrum of methods that aim to enhance the transparency of deep learning models, with Class Activation Mapping (CAM) methods widely used for visual interpretability. However, systematic evaluations of these methods in veterinary radiography remain scarce. This study presents a comparative analysis of eleven CAM methods, including GradCAM, XGradCAM, ScoreCAM, and EigenCAM, on a dataset of 7362 canine and feline X-ray images. A ResNet18 model was chosen based on the specificity of the dataset and preliminary results where it outperformed other models. Quantitative and qualitative evaluations were performed to determine how well each CAM method produced interpretable heatmaps relevant to clinical decision-making. Among the techniques evaluated, EigenGradCAM achieved the highest mean score and standard deviation (SD) of 2.571 (SD = 1.256), closely followed by EigenCAM at 2.519 (SD = 1.228) and GradCAM++ at 2.512 (SD = 1.277), with methods such as FullGrad and XGradCAM achieving worst scores of 2.000 (SD = 1.300) and 1.858 (SD = 1.198) respectively. Despite variations in saliency visualization, no single method universally improved veterinarians’ diagnostic confidence. While certain CAM methods provide better visual cues for some pathologies, they generally offered limited explainability and didn’t substantially improve veterinarians’ diagnostic confidence.

Devices and systems secured by biometric factors became a part of our lives because they are convenient, easy to use, reliable, and secure. They use information about unique features of our bodies in order to authenticate a user. It is possible to enhance the security of these devices by adding supplementary modality while keeping the user experience at the same level. Palm vein systems are based on infrared wavelengths used for capturing images of users’ veins. It is both convenient for the user, and it is one of the most secure biometric solutions. The proposed system uses IR and UV wavelengths; the images are then processed by a deep convolutional neural network for extraction of biometric features and authentication of users. We tested the system in a verification scenario that consisted of checking if the images collected from the user contained the same biometric features as those in the database. The True Positive Rate (TPR) achieved by the system when the information from the two modalities were combined was 99.5% by the threshold of acceptance set to the Equal Error Rate (EER).

The analysis of veterinary radiographic imaging data is an essential step in the diagnosis of many thoracic lesions. Given the limited time that physicians can devote to a single patient, it would be valuable to implement an automated system to help clinicians make faster but still accurate diagnoses. Currently, most of such systems are based on supervised deep learning approaches. However, the problem with these solutions is that they need a large database of labeled data. Access to such data is often limited, as it requires a great investment of both time and money. Therefore, in this work we present a solution that allows higher classification scores to be obtained using knowledge transfer from inter-species and inter-pathology self-supervised learning methods. Before training the network for classification, pretraining of the model was performed using self-supervised learning approaches on publicly available unlabeled radiographic data of human and dog images, which allowed substantially increasing the number of images for this phase. The self-supervised learning approaches included the Beta Variational Autoencoder, the Soft-Introspective Variational Autoencoder, and a Simple Framework for Contrastive Learning of Visual Representations. After the initial pretraining, fine-tuning was performed for the collected veterinary dataset using 20% of the available data. Next, a latent space exploration was performed for each model after which the encoding part of the model was fine-tuned again, this time in a supervised manner for classification. Simple Framework for Contrastive Learning of Visual Representations proved to be the most beneficial pretraining method. Therefore, it was for this method that experiments with various fine-tuning methods were carried out. We achieved a mean ROC AUC score of 0.77 and 0.66, respectively, for the laterolateral and dorsoventral projection datasets. The results show significant improvement compared to using the model without any pretraining approach.

Parkinson’s disease (PD) alters both speech and movement, yet most automated assessments still treat these signals separately. We examined whether combining voice with head motion improves discrimination between patients and healthy controls (HC). Synchronous measurements of acoustic and inertial signals were collected using a HoloLens 2 headset. Data were obtained from 165 participants (72 PD/93 HC), following a standardized mixed-reality (MR) protocol. We benchmarked single-modality models against fusion strategies under 5-fold stratified cross-validation. Voice alone was robust (pooled AUC ≈ 0.865), while the inertial channel alone was near chance (AUC ≈ 0.497). Fusion provided a modest but repeatable improvement: gated early-fusion achieved the highest AUC (≈0.875), cross-attention fusion was comparable (≈0.873). Gains were task-dependent. While speech-dominated tasks were already well captured by audio, tasks that embed movement benefited from complementary inertial data. Proposed MR capture proved feasible within a single session and showed that motion acts as a conditional improvement factor rather than a sole predictor. The results outline a practical path to multimodal screening and monitoring for PD, preserving the reliability of acoustic biomarkers while integrating kinematic features when they matter.