Objectives: The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Methods: Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. Results: The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96. For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. Conclusions: The study concludes that AI-based models can augment radiologists’ capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particularly for sclerotic lesion segmentation. The annotated CT dataset produced and shared in this research serves as a valuable resource for future advancements.

The choice of technique for the creation of a 3D digital human bone model from natural specimens has a critical impact on the final result and usability of the obtained model. The cornerstone factor in 3D modeling is the number of faces of polygon mesh, along with topological accuracy, as well as resolution and level of detail of the texture map. Three different techniques (3D scanning, photogrammetry, and micro-computed tomography) have been used to create a digital 3D model of the human zygomatic bone. As implementation and use of 3D models can be divided into three main categories—visualization, simulation, and physical replication to obtain a functioning model (implant or prothesis)—the obtained models have been evaluated by the density and topological accuracy of the polygonal mesh, as well as by visual appearance by inspecting the obtained texture map. The obtained data indicate that for biomedical applications and computer biomechanical simulation the most appropriate technique of 3D model obtainment is micro-computed tomography, in its turn for visualization and educational purposes, the photogrammetry technique is a more preferable choice.

The integration of artificial intelligence (AI), particularly through machine learning (ML) and deep learning (DL) algorithms, marks a transformative progression in medical imaging diagnostics. This technical note elucidates a novel methodology for semantic segmentation of the vertebral column in CT scans, exemplified by a dataset of 250 patients from Riga East Clinical University Hospital. Our approach centers on the accurate identification and labeling of individual vertebrae, ranging from C1 to the sacrum–coccyx complex. Patient selection was meticulously conducted, ensuring demographic balance in age and sex, and excluding scans with significant vertebral abnormalities to reduce confounding variables. This strategic selection bolstered the representativeness of our sample, thereby enhancing the external validity of our findings. Our workflow streamlined the segmentation process by eliminating the need for volume stitching, aligning seamlessly with the methodology we present. By leveraging AI, we have introduced a semi-automated annotation system that enables initial data labeling even by individuals without medical expertise. This phase is complemented by thorough manual validation against established anatomical standards, significantly reducing the time traditionally required for segmentation. This dual approach not only conserves resources but also expedites project timelines. While this method significantly advances radiological data annotation, it is not devoid of challenges, such as the necessity for manual validation by anatomically skilled personnel and reliance on specialized GPU hardware. Nonetheless, our methodology represents a substantial leap forward in medical data semantic segmentation, highlighting the potential of AI-driven approaches to revolutionize clinical and research practices in radiology.

According to the EU statistics1 skin cancer melanoma is the one of most deadly cancers. At the same time, it has up to 95% chance2 for curing if detected on the early stage. The early diagnostics is obstructed by low availability of dermatology specialists and low percentage of patients that are taking regular diagnostics.To deal with the early diagnostics unavailability we propose implementing portable automated diagnostic device, available to wide range of medical institutions. Automated diagnostic systems are not yet capable for providing final diagnosis, but are enough for detecting threats of skin cancer. Therefore, by bringing automatic tools to primary care physicians and other medical personal a lot persons could save their lives by detecting cancer on the early stage.To provide automated diagnostic tool, it is needed to solve multiple tasks including: skin images acquisition, image processing, calculating disease probability and delivering diagnosis result. These tasks have existing solutions as a commercial tool or as scientific methods, but there is a lack of ready to use service. Each paper author has specialization in one the fields, that will be used to implement proposed system in ongoing EU project.

As the incidence of skin cancer is still increasing worldwide, there is a high demand for early, non-invasive and inexpensive skin lesion diagnostics. In this article we describe and combine two skin imaging methods: skin autofluorescence (AF) and multispectral criterion p’. To develop this method, we used custom made prototype with 405 nm, 526 nm, 663 nm and 964 nm LED illuminations, perpendicular positioned linear polarizers, 515 nm filter and IDS camera. Our aim is to develop a skin lesion diagnostic device for primary care physicians who do not have experience in dermatology or skin oncology. In this study we included such common benign lesion groups as seborrheic keratosis, hyperkeratosis, melanocytic nevi and hemangiomas, as well two types of skin cancers: basal cell carcinoma and melanoma. By combining skin AF and multispectral p’ imaging methods, we achieved 100% sensitivity and 100% specificity for distinguishing melanoma (3 histologically confirmed cases) from seborrheic keratosis (13 dermatologically confirmed cases), hyperkeratosis (8 histologically and 1 dermatologically confirmed case), melanocytic nevi (23 dermatologically confirmed cases ), basal cell carcinomas (2 histologically and 16 dermatologically confirmed cases) and hemangiomas (8 dermatologically confirmed cases). Unfortunately, currently this method cannot distinguish the basal cell carcinoma group from benign lesion groups.