Luan Oliveira Silva

Luan Oliveira Silva

Auto-generated profile, based on publicly available information

Luan Oliveira Silva

Hospital Israelita Albert Einstein, São Paulo, Brazil

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
LSLuan Oliveira da Silva
Luan Oliveira da Silva
MSMaria Carolina Bueno da Silva
Maria Carolina Bueno da Silva
GRGuilherme Alberto Sousa Ribeiro
Guilherme Alberto Sousa Ribeiro
TCThiago Fellipe Ortiz de Camargo
Thiago Fellipe Ortiz de Camargo
PSPaulo Victor Dos Santos
Paulo Victor Dos Santos
WCWesley Pacheco Calixto
Wesley Pacheco Calixto
This paper presents an artificial intelligence-based classification model for the detection of pulmonary embolism in computed tomography angiography. The proposed model, developed from public data and validated on a large dataset from a tertiary hospital, uses a two-dimensional approach that integrates temporal series to classify each slice of the examination and make predictions at both slice and examination levels. The training process consists of two stages: first using a convolutional neural network InceptionResNet V2 and then a recurrent neural network long short-term memory model. This approach achieved an accuracy of 93% at the slice level and 77% at the examination level. External validation using a hospital dataset resulted in a precision of 86% for positive pulmonary embolism cases and 69% for negative pulmonary embolism cases. Notably, the model excels in excluding pulmonary embolism, achieving a precision of 73% and a recall of 82%, emphasizing its clinical value in reducing unnecessary interventions. In addition, the diverse demographic distribution in the validation dataset strengthens the model’s generalizability. Overall, this model offers promising potential for accurate detection and exclusion of pulmonary embolism, potentially streamlining diagnosis and improving patient outcomes.

4 September 2020
Verified
Conference Paper
Open access
PDF file
VSVictor Souza
Victor Souza
LSLuan Silva
Luan Silva
ASAdam Santos
Adam Santos
LALeandro Araújo
Leandro Araújo
This paper aims to compare the convolutional neural networks (CNNs): ResNet50, InceptionV3, and InceptionResNetV2 tested with and without pre-trained weights on the ImageNet database in order to solve the scene recognition problem. The results showed that the pre-trained ResNet50 achieved the best performance with an average accuracy of 99.82% in training and 85.53% in the test, while the worst result was attributed to the ResNet50 without pre-training, with 88.76% and 71.66% of average accuracy in training and testing, respectively. The main contribution of this work is the direct comparison between the CNNs widely applied in the literature, that is, to enable a better selection of the algorithms in the various scene recognition applications.

29 August 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
VGViviane M. Gomes
Viviane M. Gomes
JPJoselisa Peres Queiroz Paiva
Joselisa Peres Queiroz Paiva
BFBrunna Carolinne Rocha Silva Furriel
Brunna Carolinne Rocha Silva Furriel
PSPaulo Victor Santos
Paulo Victor Santos
JJJosé Raniery Ferreira Junior
José Raniery Ferreira Junior
WCWesley Pacheco Calixto
Wesley Pacheco Calixto
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.

30 June 2021 in Learning and Nonlinear Models
Verified
Journal Article
Closed access
LSLuan Oliveira Silva
Luan Oliveira Silva
UUUniversidade Federal do Sul e Sudeste do Pará - UNIFESSPA
Universidade Federal do Sul e Sudeste do Pará - UNIFESSPA
LALeandro dos Santos Araújo
Leandro dos Santos Araújo
VSVictor Ferreira Souza
Victor Ferreira Souza
RNRaimundo Matos Barros Neto
Raimundo Matos Barros Neto
ASAdam Santos
Adam Santos
Pneumonia is one of the most common medical problems in clinical practice and is the leading fatal infectious disease worldwide. According to the World Health Organization, pneumonia kills about 2 million children under the age of 5 and is constantly estimated to be the leading cause of infant mortality, killing more children than AIDS, malaria, and measles combined. A key element in the diagnosis is radiographic data, as chest x-rays are routinely obtained as a standard of care and can aid to differentiate the types of pneumonia. However, a rapid radiological interpretation of images is not always available, particularly in places with few resources, where childhood pneumonia has the highest incidence and mortality rates. As an alternative, the application of deep learning techniques for the classification of medical images has grown considerably in recent years. This study presents five implementations of convolutional neural networks (CNNs): ResNet50, VGG-16, InceptionV3, InceptionResNetV2, and ResNeXt50. To support the diagnosis of the disease, these CNNs were applied to solve the classification problem of medical radiographs from people with pneumonia. InceptionResNetV2 obtained the best recall and precision results for the Normal and Pneumonia classes, 93.95% and 97.52% respectively. ResNeXt50 achieved the best precision and f1-score results for the Normal class (94.62% and 94.25% respectively) and the recall and f1-score results for the Pneumonia class (97.80% and 97.65%, respectively).