Bem vindo ao Grupo de Física Estatística, Neurociências e Inteligência Artificial Aplicados à Saúde da USP de Ribeirão Preto

Pesquisas voltadas para auxiliar o diagnóstico clínico de doenças neurodegenerativas

Sobre nós


O Grupo de Física Estatística, Neurociências e Inteligência Artificial Aplicados à Saúde é uma iniciativa colaborativa que reúne pesquisadores de diversas áreas anteriormente consideradas distantes, como Física, Farmácia, Computação, Psicologia, Biologia e Neurologia. Este grupo tem como objetivo principal integrar conceitos multidisciplinares no diagnóstico e tratamento de doenças neurodegenerativas, como a doença de Alzheimer e Parkinson.

Nossa missão é avançar no entendimento das complexidades das doenças neurodegenerativas e desenvolver abordagens inovadoras para melhorar o diagnóstico precoce, o tratamento e a qualidade de vida dos pacientes afetados por essas condições.

Acreditamos na importância da colaboração entre diferentes disciplinas para enfrentar os desafios complexos da saúde cerebral. Por meio de uma abordagem integrada que combina expertise em física estatística, neurociências e inteligência artificial, estamos empenhados em impulsionar a pesquisa e inovação na área da saúde, visando contribuir significativamente para o avanço científico e o bem-estar da comunidade.

Um pouco sobre nossas

Linhas de Pesquisa

Física Estatística



Saiba mais!

Neurociências



Saiba mais!

Inteligência Artificial



Saiba mais!

Últimas

Publicações

Journal of Medical Artificial Intelligence

The impact of the orientation of MRI slices on the accuracy of Alzheimer’s disease classification using convolutional neural networks (CNNs)

Bruno A. C. Ramalho, Lara R. Bortolato, Naomy D. Gomes, Lauro Wichert-Ana, Fernando Eduardo Padovan-Neto, Marco Antonio A. da Silva, Kleython José C. C. de Lacerda
Background: Alzheimer’s disease (AD) is the leading cause of major neurocognitive disorders, affecting approximately 50 million people worldwide. Due to its high prevalence, AD significantly impacts patients’ quality of life and poses a substantial challenge to healthcare systems. Diagnosis is intricate, with specificity and sensitivity rates falling below the ideal. Early identification of AD is essential to increase the effectiveness of pharmacotherapeutic treatment and improve quality of life. Consequently, there is a quest for innovative methods, such as machine learning and deep learning, to automate the diagnosis of AD in its early stages. Methods: We developed and validated a convolutional neural network (CNN) algorithm using the Keras Sequential API in Python to investigate the impact of slicing T1-weighted magnetic resonance images on the classification of patients with mild cognitive impairment (MCI) and healthy patients (NC), grouped based on scores on the Mini-Mental State Examination (MMSE). We selected 318 patients (250 healthy and 68 MCI) with a minimum of 16 years of education (equivalent to a completed undergraduate degree). The training, testing, and validation datasets were split in a 70/15/15 ratio for each slice. Results: The CNN achieved high accuracy values in classifying healthy and MCI groups, ranging between 97% and 99% depending on the slice, the number of training epochs, and batch size. In addition to precision, the F1-score, recall, and precision parameters were also evaluated, with values above 91%. Generally, the coronal slice produced the best results, followed by the axial and the sagittal slices, which nevertheless showed high performance, standing out individually in different evaluation parameters. Notably, the choice of batch size and the number of epochs also influenced the network’s classification. Conclusions: Our study findings indicate that utilizing CNN in conjunction with selecting a coronal slice proves to be a promising tool for facilitating the early-stage diagnosis of neurodegen as AD, through magnetic resonance imaging analysis, enabling more effective treatments and appropriate future planning. Moving forward, we aim to investigate whether these results replicate across other imaging modalities, such as positron emission tomography, and explore additi
Journal of Neuroscience Methods

Automating behavioral analysis in neuroscience: Development of an open-source python software for more consistent and reliable results

A.J.D.O. Cerveira, B.A.C. Ramalho, C.C.B. de Souza, A.P. Spadaro, B.A. Ramos, L. Wichert-Ana, F.E. Padovan-Neto, K.J.C.C. de Lacerda
Background: The application of automated analyses in neuroscience has become a practical approach. With automation, the algorithms and tools employed perform fast and accurate data analysis. It minimizes the inherent errors of manual analysis performed by a human experimenter. It also reduces the time required to analyze a large amount of data and the need for human and financial resources. Methods: In this work, we describe a protocol for the automated analysis of the Morris Water Maze (MWM) and the Open Field (OF) test using the OpenCV library in Python. This simple protocol tracks mice navigation with high accuracy. Results: In the MWM, both automated and manual analysis revealed similar results regarding the time the mice stayed in the target quadrant (p = 0.109). In the OF test, both automated and manual analysis revealed similar results regarding the time the mice stayed in the center (p = 0.520) and in the border (p = 0.503) of the field. Conclusions: The automated analysis protocol has several advantages over manual analysis. It saves time, reduces human errors, can be customized, and provides more consistent information about animal behavior during tests. We conclude that the automated protocol described here is reliable and provides consistent behavioral analysis in mice. This automated protocol could lead to deeper insight into behavioral neuroscience.

Contato

GFENIAAS - USP

Pesquisas voltadas para auxiliar o diagnóstico clínico de doenças neurodegenerativas

gfeniaas@gmail.com | @gfeniaas

Powered by @kleythonlacerda