Human bacterial infections significantly contribute to the increase in healthcare-related burdens. This scenario drives the study of novel techniques for the early and precise diagnosis of infectious processes. Some alternatives include Nuclear Medicine- and Molecular Imaging-based strategies. However, radiopharmaceuticals that are available for routine assessments are not specific to differentiating infectious from aseptic inflammatory processes. In this context, [68Ga]Ga-DOTA-Ubiquicidin29-41 was synthesized using an automated module and radiochemical; in vivo and in vitro studies were performed. The radiopharmaceutical remained stable in saline (up to 180 min) and in rodent serum (up to 120 min) with radiochemical purities > 99 and 95%, respectively. Partition coefficient and serum protein binding at 60 min were determined (−3.63 ± 0.17 and 44.06 ± 1.88%, respectively). Ex vivo biodistribution, as well as in vivo microPET/CT images in mice, showed rapid blood clearance with renal excretion and reduced uptake in other organs in Staphylococcus aureus-infected animals. Higher uptake was observed in the target as compared to the non-target tissue (p < 0.0001) at 60 min post administration. The presented in-human clinical case demonstrates uptake of the radiopharmaceutical by Staphyloccocus aureus bacteria. These results indicate the potential of [68Ga]Ga-DOTA-Ubiquicidin29-41 as a radiopharmaceutical that can be obtained in a hospital radiopharmacy for the diagnosis of infectious processes using PET/CT.
This paper outlines the protocol for the deployment of a cloud-based universal medical image repository system. The proposal aims not only at the deployment but also at the automatic expansion of the platform, incorporating Artificial Intelligence (AI) for the analysis of medical image examinations. The methodology encompasses efficient data management through a universal database, along with the deployment of various AI models designed to assist in diagnostic decision-making. By presenting this protocol, the goal is to overcome technical challenges and issues that impact all phases of the workflow, from data management to the deployment of AI models in the healthcare sector. These challenges include ethical considerations, compliance with legal regulations, establishing user trust, and ensuring data security. The system has been deployed, with a tested and validated proof of concept, possessing the capability to receive thousands of images daily and to sustain the ongoing deployment of new AI models to expedite the analysis process in medical image exams.
Molecular imaging markers can be used to differentiate between infection and aseptic inflammation, determine the severity of infection, and monitor treatment responses. One of these markers is ubiquicidin(29-41) (UBI), a cationic peptide fragment that binds to the bacterial membrane wall and is labeled with gallium-68 (68Ga), a positron emitter radioisotope. The use of UBI in positron emission tomography (PET)/computed tomography (CT) for improved detection of lesions has been receiving considerable attention recently. Herein, we report the first case of
This paper proposes the use of artificial intelligence techniques, specifically the nnU-Net convolutional neural network, to improve the identification of left ventricular walls in images of myocardial perfusion scintigraphy, with the objective of improving the diagnosis and treatment of coronary artery disease. The methodology included data collection in a clinical environment, followed by data preparation and analysis using the 3D Slicer Platform for manual segmentation, and subsequently, the application of artificial intelligence models for automated segmentation, focusing on the efficiency of identifying the walls of the left ventricular. A total of 83 clinical routine exams were collected, each exam containing 50 slices, which is 4,150 images. The results demonstrate the efficiency of the proposed artificial intelligence model, with a Dice coefficient of 87% and an average Intersection over Union of 0.8, reflecting high agreement with the manual segmentations produced by experts and surpassing traditional interpretation methods. The internal and external validation of the model corroborates its future applicability in real clinical scenarios, offering a new perspective in the analysis of myocardial perfusion scintigraphy images. The integration of artificial intelligence into the process of analyzing myocardial perfusion scintigraphy images represents a significant advancement in diagnostic accuracy, promoting substantial improvements in the interpretation of medical images, and establishing a foundation for future research and clinical applications, such as artifact correction.
This work proposes a methodology for segmenting structures and brain tissues in computed tomography scans using unsupervised deep learning. The methodology involves extracting features from the CT scans and applying similarity and continuity constraints, creating segmentation maps of intracranial structures and observable tissues. This approach can assist experts in diagnosis by identifying specific regions with anomalies. The method is applied to a database of real scans and uses a spatial continuity evaluation function directly related to the desired quantity of structures. Results demonstrate that the proposed unsupervised methodology achieves segmentation of the desired number of labels and allows for a reduction in effort compared to supervised segmentation models.