Design and Application of Automated Algorithms for Diagnosis and Treatment Optimization in Neurodegenerative Diseases

Estella, Francisco; Suárez, Emma; Lozano, Beatriz Rodríguez; Santamarta, Elena; Sáiz, Antonio; Rojas, Fernando; Rojas, Ignacio; Blázquez, Marta; Nader, Lydia; Sol, Javier; Seijo, F.

doi:10.1007/s12021-022-09578-3

Cited by 3 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…El objetivo principal es reducir el tiempo de cicatrización. En otras disciplinas médicas se ha demostrado que adoptando este tipo de algoritmos y de protocolos se mejora la eficiencia (24). También se busca mejorar el proceso diagnóstico, aumentar las cifras de cicatrización efectiva, mejorar la calidad de vida de los pacientes, reducir las recidivas y reducir el consumo de recursos y el gasto sanitario.…”

Section: Discussionunclassified

Protocol and algorithm for diagnosis, treatment and early referral of lower limb ulcers

Martín¹,

Assunção²,

Mompó³

et al. 2023

Angiologia

View full text Add to dashboard Cite

Protocolo y algoritmo de diagnóstico, tratamiento y derivación ágil de las úlceras de la extremidad inferior Protocol and algorithm for diagnosis, treatment and early referral of lower limb ulcers 10.20960/angiologia.00435 01/23/2023 Protocolo y algoritmo de diagnóstico, tratamiento y derivación ágil de las úlceras de la extremidad inferior Protocol and algorithm for diagnosis, treatment and early referral of lower limb ulcers

show abstract

Section: Discussionunclassified

Protocol and algorithm for diagnosis, treatment and early referral of lower limb ulcers

Martín¹,

Assunção²,

Mompó³

et al. 2023

Angiologia

View full text Add to dashboard Cite

show abstract

“…Recent advancements in functional neuroimaging, including Resting-state functional magnetic resonance imaging (rs-fMRI), have led to reliable biomarkers for detecting the risky stages of AD (Albert et al 2011). Due to the high caregiving costs and the progressive nature of AD (Estella et al 2022), it would be highly beneficial to develop state-of-the-art frameworks for early diagnosis and efficient recognition of brain dysfunction (Platero 2022).…”

Section: Introductionmentioning

confidence: 99%

A novel framework for the diagnosis of Alzheimer's continuum using embedded features of brain networks

Poury

Masoudnia

Ameri

2022

Preprint

View full text Add to dashboard Cite

This study aims to develop a novel framework for efficient diagnosis of Alzheimer’s disease (AD) and those with mild cognitive impairment (MCI) based on functional connectivity (FC). The FCs are utilized to construct the brain graph, on which the node2vec method is applied to produce the node embeddings. The embedding of each region is considered as the corresponding feature vector, which is finally fed into a separate support vector machine (SVM) classifier to evaluate its discriminative score and use it as the weighted selection score. Accordingly, we propose a novel ensemble voting algorithm for the classification of well-defined stages of AD (Alzheimer’s (AD), converting MCI (MCIc), stable MCI (MCIs), and Healthy controls (HC)), based on a weighted voting scheme. Data were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Three binary classification tasks, i.e., MCIs vs. HC and MCIs vs. MCIc, and MCIc vs.AD were examined and the classification accuracies of 96.7%, and 92.1%, and 95.6% were achieved, respectively. Beyond this, our framework evaluates impaired FCs in various stages of the disease in order to assess the quantitative role of each altered region in brain networks for the classification tasks. The most discriminative features in the classification tasks suggest a cascading neurophysiologic procedure for the progression of failures in the functional organization of the brain during the AD spectrum. The functional deterioration patterns in the disease continuum from healthy to AD (based on our discriminative data-driven approach) are also found correlated to neuropsychiatric symptoms of Alzheimer’s and also compatible with neuropathology literature.

show abstract

A Skin Cancer Detector Based on Transfer Learning and Feature Fusion

Lan

Cai

Hussin

et al. 2023

CBIO

View full text Add to dashboard Cite

Background: With the rapid development of advanced artificial intelligence technologies which have been applied in varying types of applications, especially in the medical field. Cancer is one of the biggest problems in medical sciences. If cancer can be detected and treated early, the possibility of a cure will be greatly increased. Malignant skin cancer is one of the cancers with the highest mortality rate, which cannot be diagnosed in time only through doctors’ experience. We can employ artificial intelligence algorithms to detect skin cancer at an early stage, for example, patients are determined whether suffering from skin cancer by detecting skin damage or spots. Objective: We use the real HAM10000 image dataset to analyze and predict skin cancer. Methods: (1) We introduce a lightweight attention module to discover the relationships between features, and we fine-tune the pre-trained model (i.e., ResNet-50) on the HAM10000 dataset to extract the hidden high-level features from the images; (2) we integrate these high-level features with generic statistical features, and use the SMOTE oversampling technique to augment samples from the minority classes; and (3) we input the augmented samples into the XGBoost model for training and predicting. Results: The experimental results show that the accuracy, sensitivity, and specificity of the proposed SkinDet (Skin cancer detector based on transfer learning and feature fusion) model reached 98.24%, 97.84%, and 98.13%. The proposed model has stronger classification capability for the minority classes, such as dermato fibroma and actinic keratoses. result: The experimental results show that the accuracy, sensitivity and specificity of the proposed SkinDet (Skin cancer detector based on transfer learning and feature fusion) model reached 98.24%, 97.84% and 98.13%. The proposed model has stronger classification capability for the minority classes, such as dermato fibroma and actinic keratoses. Conclusion: SkinDet contains a lightweight attention module and can extract the hidden high-level features of the images by fine-tuning the pretrained model on the skin cancer dataset. In particular, SkinDet integrates high-level features with statistical features and augments samples of these minority classes. Importantly, SkinDet can be applied to classify the samples into minority classes.

show abstract

Design and Application of Automated Algorithms for Diagnosis and Treatment Optimization in Neurodegenerative Diseases

Cited by 3 publications

References 21 publications

Protocol and algorithm for diagnosis, treatment and early referral of lower limb ulcers

Protocol and algorithm for diagnosis, treatment and early referral of lower limb ulcers

A novel framework for the diagnosis of Alzheimer's continuum using embedded features of brain networks

A Skin Cancer Detector Based on Transfer Learning and Feature Fusion

Contact Info

Product

Resources

About