Self-Supervised Transfer Learning Based on Domain Adaptation for Benign-Malignant Lung Nodule Classification on Thoracic CT

Hong, Huixiao; Wu, Ruoyu; Li, Yuan; Peng, Chao

doi:10.1109/jbhi.2022.3171851

Cited by 41 publications

(10 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is challenging to obtain feature information in 3D data for deep learning methods that require large amounts of data. Based on this, Huang et al 36 . proposed domain‐based adaptive self‐supervised transfer learning.…”

Section: Discussionmentioning

confidence: 99%

“…However, it is challenging to obtain feature information in 3D data for deep learning methods that require large amounts of data. Based on this, Huang et al 36 proposed domain-based adaptive self -supervised transfer learning. Although this method solves the problem of learning 3D data from scratch in deep learning models, it still has the problem of high computational cost compared to general transfer learning models.…”

Section: Binary Classification Ternary Classification Acc (%)mentioning

confidence: 99%

See 1 more Smart Citation

3D multi‐view squeeze‐and‐excitation convolutional neural network for lung nodule classification

Yang

et al. 2023

Medical Physics

View full text Add to dashboard Cite

Early screening is crucial to improve the survival rate and recovery rate of lung cancer patients. Computer-aided diagnosis system (CAD) is a powerful tool to assist clinicians in early diagnosis. Lung nodules are characterized by spatial heterogeneity.However,many attempts use the two-dimensional multiview (MV) framework to learn and simply integrate multiple view features. These methods suffer from the problems of not capturing the spatial characteristics effectively and ignoring the variability of multiple views. In this paper, we propose a three-dimensional MV convolutional neural network (3D MVCNN) framework and embed the squeeze-and-excitation (SE) module in it to further address the variability of each view in the MV framework. Methods: First, the 3D multiple view samples of lung nodules are extracted by the spatial sampling method, and a 3D CNN is established to extract 3D abstract features. Second, build a 3D MVCNN framework according to the 3D multiple view samples and 3D CNN. This framework can learn more features of different views of lung nodules, taking into account the characteristics of spatial heterogeneity of lung nodules. Finally, to further address the variability of each view in the MV framework, a 3D MVSECNN model is constructed by introducing a SE module in the feature fusion stage. For training and testing purposes we used independent subsets of the public LIDC-IDRI dataset. Results: For the LIDC-IDRI dataset, this study achieved 96.04% accuracy and 98.59% sensitivity in the binary classification, and 87.76% accuracy in the ternary classification, which was higher than other state-of -the-art studies. The consistency score of 0.948 between the model predictions and pathological diagnosis was significantly higher than that between the clinician's annotations and pathological diagnosis. Conclusions:The results show that our proposed method can effectively learn the spatial heterogeneity of nodules and solve the problem of multiple view variability. Moreover, the consistency analysis indicates that our method can provide clinicians with more accurate results of benign-malignant lung nodule classification for auxiliary diagnosis, which is important for assisting clinicians in clinical diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Binary Classification Ternary Classification Acc (%)mentioning

confidence: 99%

3D multi‐view squeeze‐and‐excitation convolutional neural network for lung nodule classification

Yang

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Lung cancer being the important health concern needs to be predicted as early as possible. There is a lot of work done in determining the presence of cancer [3] and deciding whether the cells are malignant or benign [4]. There several publications made on detection of early stages in cancer [5] [6].…”

Section: Literature Surveymentioning

confidence: 99%

Supervised learning techniques for detection of Lung Carcinoma

Jalall,

Harsha,

Dutta

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Lung diseases are the most common ailments seen among people with the history of smoking. Prompt and timely recognition and diagnosis may help in saving many lives. In order to detect cancer at early stages machine learning algorithms can be employed. Use of simple machine learning algorithms will help identify the carcinoma faster with high accuracy and lesser expense. This work shows the use three of simple machine learning (ML) algorithms like Logistic Regression, Support Vector Machine (SVM), and K-Nearest Neighbours (KNN). ML models were built using lung cancer patients’ dataset. The dataset was used to train the model as well as test the model. The three classifiers will detect the presence of lung cancer. For each classifier the Accuracy, Mean Square Error(MSE), precision, and Recall (R2) was calculated. A comparative study of the classifiers was done to identify which among the three was the best one. The main objective of the paper is to identify the best efficient machine-learning algorithm in terms of confusion matrices, accuracy, and precision for the prediction and diagnosis of lung cancer

show abstract

“…In 2022, Hong Huang et al proposed domain-adaptive selfsupervised transfer learning for chest CT classification of benign and malignant lung nodules and developed a data preprocessing strategy called adaptive slice selection to eliminate redundant noise in input samples with lung nodules (21). Ruoyu Wu et al proposed a self-supervised transfer learning framework driven by visual attention (STLFVA) for benign and malignant recognition of nodules on chest CT Then, they used the multiview aggregate attention module to comprehensively recalibrate the multilayer feature map from multiple attention angles, which can strengthen the anti-interference ability of background information (22).…”

Section: Introductionmentioning

confidence: 99%

“…In 2022, Hong Huang et al. proposed domain-adaptive self-supervised transfer learning for chest CT classification of benign and malignant lung nodules and developed a data preprocessing strategy called adaptive slice selection to eliminate redundant noise in input samples with lung nodules ( 21 ). Ruoyu Wu et al.…”

Section: Introductionmentioning

confidence: 99%

RAD-UNet: Research on an improved lung nodule semantic segmentation algorithm based on deep learning

Zuo

2023

Front. Oncol.

View full text Add to dashboard Cite

ObjectiveDue to the small proportion of target pixels in computed tomography (CT) images and the high similarity with the environment, convolutional neural network-based semantic segmentation models are difficult to develop by using deep learning. Extracting feature information often leads to under- or oversegmentation of lesions in CT images. In this paper, an improved convolutional neural network segmentation model known as RAD-UNet, which is based on the U-Net encoder-decoder architecture, is proposed and applied to lung nodular segmentation in CT images.MethodThe proposed RAD-UNet segmentation model includes several improved components: the U-Net encoder is replaced by a ResNet residual network module; an atrous spatial pyramid pooling module is added after the U-Net encoder; and the U-Net decoder is improved by introducing a cross-fusion feature module with channel and spatial attention.ResultsThe segmentation model was applied to the LIDC dataset and a CT dataset collected by the Affiliated Hospital of Anhui Medical University. The experimental results show that compared with the existing SegNet [14] and U-Net [15] methods, the proposed model demonstrates better lung lesion segmentation performance. On the above two datasets, the mIoU reached 87.76% and 88.13%, and the F1-score reached 93.56% and 93.72%, respectively. Conclusion: The experimental results show that the improved RAD-UNet segmentation method achieves more accurate pixel-level segmentation in CT images of lung tumours and identifies lung nodules better than the SegNet [14] and U-Net [15] models. The problems of under- and oversegmentation that occur during segmentation are solved, effectively improving the image segmentation performance.

show abstract

Self-Supervised Transfer Learning Based on Domain Adaptation for Benign-Malignant Lung Nodule Classification on Thoracic CT

Cited by 41 publications

References 53 publications

3D multi‐view squeeze‐and‐excitation convolutional neural network for lung nodule classification

3D multi‐view squeeze‐and‐excitation convolutional neural network for lung nodule classification

Supervised learning techniques for detection of Lung Carcinoma

RAD-UNet: Research on an improved lung nodule semantic segmentation algorithm based on deep learning

Contact Info

Product

Resources

About