Lung nodule classification using artificial crawlers, directional texture and support vector machine

Froz, Bruno Rodrigues; Filho, Antônio Oséas de Carvalho; Silva, Aristófanes Corrêa; Paiva, Anselmo Cardoso de; Nunes, Rodolfo Acatauassú; Gattass, Marcelo

doi:10.1016/j.eswa.2016.10.039

Cited by 58 publications

(29 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By visual inspection of the ROC curves, HSCNN performs better than the traditional 3D CNN model. The area under the ROC curve (AUC) quantitatively compares the overall performance of a classification model and is frequently used as a metric to access performance in nodule classification [15,17,26,30,31]. Table 5 summarizes the mean AUC score, accuracy, sensitivity, and specificity for both models.…”

Section: Model Trainingmentioning

confidence: 99%

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

Shen

Han

Aberle

et al. 2019

Expert Systems with Applications

203

141

View full text Add to dashboard Cite

While deep learning methods are increasingly being applied to tasks such as computer-aided diagnosis, these models are difficult to interpret, do not incorporate prior domain knowledge, and are often considered as a "black-box." The lack of model interpretability hinders them from being fully understood by target users such as radiologists. In this paper, we present a novel interpretable deep hierarchical semantic convolutional neural network (HSCNN) to predict whether a given pulmonary nodule observed on a computed tomography (CT) scan is malignant. Our network provides two levels of output: 1) low-level radiologist semantic features; and 2) a high-level malignancy prediction score. The low-level semantic outputs quantify the diagnostic features used by radiologists and serve to explain how the model interprets the images in an expert-driven manner. The information from these low-level tasks, along with the representations learned by the convolutional layers, are then combined and used to infer the high-level task of predicting nodule malignancy. This unified architecture is trained by optimizing a global loss function including both low-and high-level tasks, thereby learning all the parameters within a joint framework. Our experimental results using the Lung Image Database Consortium (LIDC) show that the proposed method not only produces interpretable lung cancer predictions but also achieves significantly better results compared to common 3D CNN approaches.

show abstract

Section: Model Trainingmentioning

confidence: 99%

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

Shen

Han

Aberle

et al. 2019

Expert Systems with Applications

203

141

View full text Add to dashboard Cite

show abstract

“…To assess the performance of the proposed algorithm, we performed a large set of experiments on a standard lung CT dataset. The performance is objectively computed and the results are also compared with 10 existing similar techniques, including [11,21,[29][30][31]36,[53][54][55][56]. In the region-growing algorithm, the maximum intensity distance was set to 0.18.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…We also compared the results of our method with ten existing similar nodule detection algorithms. The list of compared methods includes [11,21,[29][30][31]36,[53][54][55][56]. Although it is difficult to compare their performance because it depends on the image datasets and detection parameters, it is still important to attempt making a relative comparison.…”

Section: Performance Comparisonmentioning

confidence: 99%

“…Although it is difficult to compare their performance because it depends on the image datasets and detection parameters, it is still important to attempt making a relative comparison. The Sensitivity measure is widely used to report such results, as can be found in [11,21,[29][30][31]36,[53][54][55][56], therefore we also used a sensitivity metric to present the comparison. The results of the comparison are presented in Table 2.…”

Section: Performance Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Lung Nodule Detection in CT Images Using Statistical and Shape-Based Features

et al. 2020

View full text Add to dashboard Cite

The lung tumor is among the most detrimental kinds of malignancy. It has a high occurrence rate and a high death rate, as it is frequently diagnosed at the later stages. Computed Tomography (CT) scans are broadly used to distinguish the disease; computer aided systems are being created to analyze the ailment at prior stages productively. In this paper, we present a fully automatic framework for nodule detection from CT images of lungs. A histogram of the grayscale CT image is computed to automatically isolate the lung locale from the foundation. The results are refined using morphological operators. The internal structures are then extracted from the parenchyma. A threshold-based technique is proposed to separate the candidate nodules from other structures, e.g., bronchioles and blood vessels. Different statistical and shape-based features are extracted for these nodule candidates to form nodule feature vectors which are classified using support vector machines. The proposed method is evaluated on a large lungs CT dataset collected from the Lung Image Database Consortium (LIDC). The proposed method achieved excellent results compared to similar existing methods; it achieves a sensitivity rate of 93.75%, which demonstrates its effectiveness.

show abstract

“…The work of [10] proposes a methodology to classify lung nodule and non-nodule using texture features, artificial crawlers and the rose diagram.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Fuzzy-SVM classifier for automated lung diseases diagnosis

Hassen

Zakour

Taleb

2016

Polish Journal of Medical Physics and Engineering

View full text Add to dashboard Cite

A novel scheme for lesions classification in chest radiographs is presented in this paper. Features are extracted from detected lesions from lung regions which are segmented automatically. Then, we needed to eliminate redundant variables from the subset extracted because they affect the performance of the classification. We used Stepwise Forward Selection and Principal Components Analysis. Then, we obtained two subsets of features. We finally experimented the Stepwise/FCM/SVM classification and the PCA/FCM/SVM one. The ROC curves show that the hybrid PCA/FCM/SVM has relatively better accuracy and remarkable higher efficiency. Experimental results suggest that this approach may be helpful to radiologists for reading chest images.

show abstract

Lung nodule classification using artificial crawlers, directional texture and support vector machine

Cited by 58 publications

References 17 publications

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification

Lung Nodule Detection in CT Images Using Statistical and Shape-Based Features

A Hybrid Fuzzy-SVM classifier for automated lung diseases diagnosis

Contact Info

Product

Resources

About