ABSTRACT
We present a possible method of Artificial Intelligence (AI) based applications that can effectively filter noise-sensitive bone scintigraphy images. The use of special AI, based on preliminary examinations, allows us to significantly reduce study time or activity administered to the patient, thus reducing the patient, assistant, and physician radiation. We present the features of the AI filtering application, its teaching process, which is important to understand, so that the physician can safely take the processed image of the AI as a "secondary reliable opinion" to help them make a more accurate diagnosis. We also examine the robustness of the algorithm, the specificities and challenges of complex clinical control.
Subject(s)
Algorithms , Artificial Intelligence , Radionuclide Imaging , Humans , IntelligenceABSTRACT
Regenerative medicine using human or porcine ß-cells or islets has an excellent potential to become a clinically relevant method for the treatment of type-1 diabetes. High-resolution imaging of the function and faith of transplanted porcine pancreatic islets and human stem cell-derived beta cells in large animals and patients for testing advanced therapy medicinal products (ATMPs) is a currently unmet need for pre-clinical/clinical trials. The iNanoBIT EU H2020 project is developing novel highly sensitive nanotechnology-based imaging approaches allowing for monitoring of survival, engraftment, proliferation, function and whole-body distribution of the cellular transplants in a porcine diabetes model with excellent translational potential to humans. We develop and validate the application of single-photon emission computed tomography (SPECT) and optoacoustic imaging technologies in a transgenic insulin-deficient pig model to observe transplanted porcine xeno-islets and in vitro differentiated human beta cells. We are progressing in generating new transgenic reporter pigs and human-induced pluripotent cell (iPSC) lines for optoacoustic imaging and testing them in transplantable bioartificial islet devices. Novel multifunctional nanoparticles have been generated and are being tested for nuclear imaging of islets and beta cells using a new, high-resolution SPECT imaging device. Overall, the combined multidisciplinary expertise of the project partners allows progress towards creating much needed technological toolboxes for the xenotransplantation and ATMP field, and thus reinforces the European healthcare supply chain for regenerative medicinal products.
Subject(s)
Biotechnology/methods , Diabetes Mellitus, Type 1/therapy , Islets of Langerhans Transplantation/methods , Islets of Langerhans/surgery , Nanotechnology/methods , Animals , Animals, Genetically Modified , Humans , Regenerative Medicine/methods , SwineABSTRACT
Gold standard bone scintigraphy workflow contains acquisition of planar anterior and posterior images and if necessary, additional SPECTs as well. Planar acquisitions are time consuming and not enough for accurately locating hotspots. Current paper proposes a novel workflow for fast whole body bone SPECT scintigraphy. We present a novel stitching method to generate a whole body SPECT based on the SPECT projections. Our stitching method is performed on the projection series not on the reconstructed SPECTs, thus stitching artifacts are greatly reduced. Our workflow does not require any anterior-posterior image pairs, since these images are derived from the reconstructed whole body SPECT automatically. Our stitching method has been validated on real clinical data performed by medical physicians. Results show that our method is very effective for whole body SPECT generations leaving no signs of artifacts. Our workflow required overall 16 minutes to acquire a whole body SPECT which is comparable to the 60 minutes acquisition time required for gold standard techniques including planar images and additional SPECT acquisitions.
