The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening

Yan, Rongkai; Ashrafinia, Saeed; Park, Seyoun; Lee, Junghoon; Chu, Linda C.; Lin, Cheng Ting; Hussien, Amira; Malguria, Nagina; Steingrimsson, Jon A.; Rahmim, Arman; Huang, Peng

doi:10.1109/nssmic.2017.8532656

Cited by 2 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yan et al 43 used a database from the NLST composed of 186 biopsy‐confirmed control and lung cancer cases with a diameter between 4 and 20 mm. First, the samples were randomly split into training (70 benign + 70 malignant) and validation (26 benign + 20 malignant) sets.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Toward classifying small lung nodules with hyperparameter optimization of convolutional neural networks

Lima

Ferreira

Oliveira

2020

Computational Intelligence

View full text Add to dashboard Cite

Among all cancer‐related deaths, lung cancer leads all indicators, accounting for approximately 20% of all types. Patients diagnosed in the early stages have a 1‐year survival rate of 81% to 85%, while in an advanced stage have 15% to 19% chances of survival. The primary manifestation of this cancer is through pulmonary nodule on computed tomography images. In the early stages, it is a complex task even for experienced specialists and presents some challenges to classify these nodules in benign or malignant. So, to assist specialists, computer‐aided diagnosis systems have been used to improve the accuracy in the diagnosis. In this article, we explored and compared the use of random search, simulating annealing, and Tree‐of‐Parzen‐estimators algorithms of hyperparameter tuning to find the best architecture of a convolutional neural network to classify small pulmonary nodules in benign or malignant with a diameter of 5 to 10 mm. Our best model used result was the model using the simulating annealing algorithm and yielded an area under the receiver operating characteristic curve of 0.95, the sensitivity of 82%, the specificity of 94%, and accuracy of 88% using a balanced data set of nodules. Therefore, our model is capable of classifying early lung nodules, where the patients have bigger chances of survival.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Some works faced the problem of classifying small lung nodules, but the AUC‐ROC was not satisfactory 9,42,43 . So this problem, which is few explored, is opened in the literature and needs to be further investigated.…”

Section: Introductionmentioning

confidence: 99%

Toward classifying small lung nodules with hyperparameter optimization of convolutional neural networks

Lima

Ferreira

Oliveira

2020

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Some works faced the problem of classifying small lung nodules, but the AUC-ROC was not satisfactory [Felix et al 2016, Reeves et al 2015, Yan and et 2018. So this problem, which is a few explored, is opened in the literature and needs to be further investigated.…”

mentioning

confidence: 99%

Using Support Vector Machine and Features Selection on Classification of Early Lung Nodules

Lima¹,

Vieira²,

Costa³

et al. 2020

Anais Principais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2020)

View full text Add to dashboard Cite

O cancer de pulmão é o câncer que mais mata no mundo. No entanto, se o diagnóstico for feito no início da doença, as taxas de sobrevida em 1 ano são de aproximadamente 81-85%. Ferramentas de Auxílio ao Diagnóstico por Computador tem um grande potencial para auxiliar os especialistas na determinação da malignidade de um nódulo pulmonar. Neste trabalho, foram utilizados 4 grupos de atributos: Textura 3D, Nitidez da margem 3D, Forma 3D e Intensidade 3D; dois algoritmos de aprendizado de máquina: Support Vector Machine (SVM) e Multilayer Perceptron; e duas técnicas para selecionar os recursos mais relevantes: Relief e Algoritmo Genético Evolucionário (AGE). A classificação com SVM, Relief e AGE alcançou a melhor AUC de 0,856.

show abstract

The Use of Low-Dose CT Intra- and Extra-Nodular Image Texture Features to Improve Small Lung Nodule Diagnosis in Lung Cancer Screening

Cited by 2 publications

References 11 publications

Toward classifying small lung nodules with hyperparameter optimization of convolutional neural networks

Toward classifying small lung nodules with hyperparameter optimization of convolutional neural networks

Using Support Vector Machine and Features Selection on Classification of Early Lung Nodules

Contact Info

Product

Resources

About