RESUMO
We propose a deep learning (DL) model and a hyperparameter optimization strategy to reconstruct T1 and T2 maps acquired with the magnetic resonance fingerprinting (MRF) methodology. We applied two different MRF sequence routines to acquire images of ex vivo rat brain phantoms using a 7-T preclinical scanner. Subsequently, the DL model was trained using experimental data, completely excluding the use of any theoretical MRI signal simulator. The best combination of the DL parameters was implemented by an automatic hyperparameter optimization strategy, whose key aspect is to include all the parameters to the fit, allowing the simultaneous optimization of the neural network architecture, the structure of the DL model, and the supervised learning algorithm. By comparing the reconstruction performances of the DL technique with those achieved from the traditional dictionary-based method on an independent dataset, the DL approach was shown to reduce the mean percentage relative error by a factor of 3 for T1 and by a factor of 2 for T2 , and to improve the computational time by at least a factor of 37. Furthermore, the proposed DL method enables maintaining comparable reconstruction performance, even with a lower number of MRF images and a reduced k-space sampling percentage, with respect to the dictionary-based method. Our results suggest that the proposed DL methodology may offer an improvement in reconstruction accuracy, as well as speeding up MRF for preclinical, and in prospective clinical, investigations.
Assuntos
Aprendizado Profundo , Processamento de Imagem Assistida por Computador , Processamento de Imagem Assistida por Computador/métodos , Encéfalo/diagnóstico por imagem , Estudos Prospectivos , Imageamento por Ressonância Magnética/métodos , Imagens de Fantasmas , Espectroscopia de Ressonância MagnéticaRESUMO
Amyotrophic Lateral Sclerosis (ALS) is a complex pathology: (i) the neurodegeneration is chronic and progressive; it starts focally in specific central nervous system (CNS) areas and spreads to different districts; (ii) multiple cell types further than motor neurons (i.e., glial/immune system cells) are actively involved in the disease; (iii) both neurosupportive and neurotoxic neuroinflammatory responses were identified. Microglia cells (a key player of neuroinflammation in the CNS) attracted great interest as potential target cell population that could be modulated to counteract disease progression, at least in preclinical ALS models. However, the heterogeneous/multifaceted microglia cell responses occurring in different CNS districts during the disease represent a hurdle for clinical translation of single-drug therapies. To address this issue, over the past ten years, several studies attempted to dissect the complexity of microglia responses in ALS. In this review, we shall summarize these results highlighting how the heterogeneous signature displayed by ALS microglia reflects not only the extent of neuronal demise in different regions of the CNS, but also variable engagement in the attempts to cope with the neuronal damage. We shall discuss novel avenues opened by the advent of single-cell and spatial transcriptomics technologies, underlining the potential for discovery of novel therapeutic targets, as well as more specific diagnostic/prognostic not-invasive markers of neuroinflammation.