Identification of thyroid nodules in infrared images by convolutional neural networks

Morán, Maira Beatriz Hernández; Conci, Aura; González, José Ramón García; Araujo, Adriel S.; Fiirst, W. G.; Damião, Charbel; Lima, Giovanna Aparecida Balarini; Filho, Rubens Antunes da Cruz

doi:10.1109/ijcnn.2018.8489032

Cited by 26 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os resultados encontrados ao longo deste estudo foram apresentados em diversos artigos publicados em meios cientifícos de grande alcance [Moran et al 2018b, Moran et al 2018a, González et al 2018. Agradeço a fundação CAPES pelo apoio financeiro a mim concedido que me permitiu realizar este trabalho…”

Section: Resultados Obtidos E Discussãounclassified

Metodologia para localização de nódulos malignos da tireoide a partir de imagens infravermelhas

Morán¹,

Conci²

2019

Anais Estendidos Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2019)

View full text Add to dashboard Cite

Thyroid anomalies have high prevalence and their early identification is crucial for a more effective treatment. Thermograms can be used in this process, since nodules tend to be more vascularized, resulting in a temperature increase. This work presents a methodology for determining thyroid nodules. We evaluate parameters that would allow to segment possibly nodular regions in thermographs. Convolutional neural networks (CNN) are used to classify these regions, identifying which ones refer to nodules. The good results of CNN in the classification (with 96% accuracy), show that the viability of the proposed methodology depends on the success of the segmentation.Resumo. Anomalias na tireoide têm alta prevalência e sua identificação precoceé essencial para um tratamento mais eficaz. Termogramas podem ser usados nesse processo, já que nódulos tendem a ser mais vascularizados, resultando num aumento de temperatura na região. Este trabalho apresenta uma metodologia para localizar nódulos na tireoide. São estudados parâmetros que permitiriam segmentar regiões possivelmente nodulares em termografias. Redes neurais convolucionais (CNN) são usadas para classificação dessas regiões, identificando quais se referem a nódulos. Os resultados obtidos apontam que, devido ao bom resultado da CNN na classificação (com acurácia de 96%), a viabilidade da metodologia proposta depende do sucesso da segmentação.

show abstract

Section: Resultados Obtidos E Discussãounclassified

Metodologia para localização de nódulos malignos da tireoide a partir de imagens infravermelhas

Morán¹,

Conci²

2019

Anais Estendidos Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2019)

View full text Add to dashboard Cite

show abstract

“…It should be noted that although these possibly abnormal regions have similar shapes, there are still some characteristics that can be used to classify them and indicate which regions refer to nodular regions. In this study, ResNet 28 CNNs were used in the classification process (but AlexNet and GoogLeNet have been investigated in previous work 36 ).…”

Section: Study 2: Identification Of Thyroid Nodules By Thermographymentioning

confidence: 99%

On the possibility of using temperature to aid in thyroid nodule investigation

Damião

Montero²,

Morán³

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Thyroid nodules are common, and their investigation is very important to exclude the possibility of cancer. The increase in blood vessels of malignant tumours may be related to local temperature augmentation detectable on the skin surface. The objective of this paper is to evaluate the feasibility of Infrared Thermography for cancer identification. For this purpose, two studies were performed. One used numerical modelling to simulate regional metabolic temperature propagation to evaluate whether a nodule is perceptible on the skin surface. A second study considered thyroid nodule identification by using convolutional neural networks (CNNs). First, variations in nodular size and fat thickness were investigated, showing that the fat layer has an important role in regional heat transfer. In the second study, the training process achieved accuracy of 96% for in-sample and 95% for validation. In the testing phase, 92% accuracy, 100% precision and 80% recall were achieved. Thus, the presented studies suggest the feasibility of using Infrared Thermography with the CNN Artificial Intelligence technique as additional information in the investigation of thyroid nodules for patients without a very thick subcutaneous fat layer.

show abstract

“…They perform object recognition and classification tasks [16] well. Object detection [17], diseases detection [18], and fault diagnosis [6, 10] are three examples of applications that use CNNs. Their basic structure consists of an input layer, alternating blocks of convolutional and pooling layers, which are followed by fully connected layers, and an output layer [16].…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes

Monteiro

Cerrada

Cabrera

et al. 2019

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Gearboxes are mechanical devices that play an essential role in several applications, e.g., the transmission of automotive vehicles. Their malfunctioning may result in economic losses and accidents, among others. The rise of powerful graphical processing units spreads the use of deep learning-based solutions to many problems, which includes the fault diagnosis on gearboxes. Those solutions usually require a significant amount of data, high computational power, and a long training process. The training of deep learning-based systems may not be feasible when GPUs are not available. This paper proposes a solution to reduce the training time of deep learning-based fault diagnosis systems without compromising their accuracy. The solution is based on the use of a decision stage to interpret all the probability outputs of a classifier whose output layer has the softmax activation function. Two classification algorithms were applied to perform the decision. We have reduced the training time by almost 80% without compromising the average accuracy of the fault diagnosis system.

show abstract

Identification of thyroid nodules in infrared images by convolutional neural networks

Cited by 26 publications

References 14 publications

Metodologia para localização de nódulos malignos da tireoide a partir de imagens infravermelhas

Metodologia para localização de nódulos malignos da tireoide a partir de imagens infravermelhas

On the possibility of using temperature to aid in thyroid nodule investigation

Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes

Contact Info

Product

Resources

About