An efficient multi-path 3D convolutional neural network for false-positive reduction of pulmonary nodule detection

Yuan, Haiying; Fan, Zhongwei; Wu, Yanrui; Cheng, Junpeng

doi:10.1007/s11548-021-02478-y

Cited by 14 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the training set and validation set, the false-positive rate dropped from 30.9 to 30.4% based solely on the doctor's diagnosis to 9.1 and 5.4%, respectively ( 37 ). Some scholars used a multipath 3D CNN to build a model based on the suspicious nodules' size, shape, and background information, which significantly reduced the false-positive rate ( 38 ). Their research shows that the false-positive rate can be reduced when AI is combined with medical imaging.…”

Section: Application Of Ai To Diagnosismentioning

confidence: 99%

The value of AI in the Diagnosis, Treatment, and Prognosis of Malignant Lung Cancer

Wang

Cai

et al. 2022

Front. Radio

View full text Add to dashboard Cite

Malignant tumors is a serious public health threat. Among them, lung cancer, which has the highest fatality rate globally, has significantly endangered human health. With the development of artificial intelligence (AI) and its integration with medicine, AI research in malignant lung tumors has become critical. This article reviews the value of CAD, computer neural network deep learning, radiomics, molecular biomarkers, and digital pathology for the diagnosis, treatment, and prognosis of malignant lung tumors.

show abstract

Section: Application Of Ai To Diagnosismentioning

confidence: 99%

The value of AI in the Diagnosis, Treatment, and Prognosis of Malignant Lung Cancer

Wang

Cai

et al. 2022

Front. Radio

View full text Add to dashboard Cite

show abstract

“…By adopting and concatenating three routes representing three receptive field widths into the network model, the feature information was fully retrieved and fused to dynamically adapt to the differences in shape, size, and context across the pulmonary nodules. Sensitivities of 0.952 and 0.962 were achieved at 4 and 8 false positives per scan, respectively, demonstrating exceptional performance 71 . The effective methods proposed are summarized in Table 3.…”

Section: Nodule Detectionmentioning

confidence: 99%

“…Sensitivities of 0.952 and 0.962 were achieved at 4 and 8 false positives per scan, respectively, demonstrating exceptional performance. 71 The effective methods proposed are summarized in Table 3.…”

Section: False Positive Reductionmentioning

confidence: 99%

Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis

Quanyang,

Yao,

Sicong

et al. 2024

Cancer Medicine

View full text Add to dashboard Cite

BackgroundThe exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies based on deep learning, particularly the advent of convolutional neural networks (CNNs), AI presents an expanded horizon of applications in lung cancer screening, including lung segmentation, nodule detection, false‐positive reduction, nodule classification, and prognosis.MethodologyThis review initially analyzes the current status of AI technologies. It then explores the applications of AI in lung cancer screening, including lung segmentation, nodule detection, and classification, and assesses the potential of AI in enhancing the sensitivity of nodule detection and reducing false‐positive rates. Finally, it addresses the challenges and future directions of AI in lung cancer screening.ResultsAI holds substantial prospects in lung cancer screening. It demonstrates significant potential in improving nodule detection sensitivity, reducing false‐positive rates, and classifying nodules, while also showing value in predicting nodule growth and pathological/genetic typing.ConclusionsAI offers a promising supportive approach to lung cancer screening, presenting considerable potential in enhancing nodule detection sensitivity, reducing false‐positive rates, and classifying nodules. However, the universality and interpretability of AI results need further enhancement. Future research should focus on the large‐scale validation of new deep learning‐based algorithms and multi‐center studies to improve the efficacy of AI in lung cancer screening.

show abstract

“…Yuan et al constructed a 3D CNN model extracting spatial information through the hierarchical architecture. They adopted three paths corresponding to three receptive field sizes and fused them to actively learn the changes of nodules [8]. Sun et al proposed a novel attention-embedded complementary-stream convolutional neural network for false positive reduction [9].…”

Section: Introductionmentioning

confidence: 99%

Lung nodule false positive reduction using a central attention convolutional neural network on imbalanced data

Hao

Cai

Feng

et al. 2023

Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

Computer-aided detection systems for lung nodules play an important role in the early diagnosis and treatment process. False positive reduction is a significant component in pulmonary nodule detection. To address the visual similarities between nodules and false positives in CT images and the problem of two-class imbalanced learning, we propose a central attention convolutional neural network on imbalanced data (CACNNID) to distinguish nodules from a large number of false positive candidates. To solve the imbalanced data problem, we consider density distribution, data augmentation, noise reduction, and balanced sampling for making the network well-learned. During the network training, we design the model to pay high attention to the central information and minimize the influence of irrelevant edge information for extracting the discriminant features. The proposed model has been evaluated on the public dataset LUNA16 and achieved a mean sensitivity of 92.64%, specificity of 98.71%, accuracy of 98.69%, and AUC of 95.67%. The experimental results indicate that our model can achieve satisfactory performance in false positive reduction.

show abstract

An efficient multi-path 3D convolutional neural network for false-positive reduction of pulmonary nodule detection

Cited by 14 publications

References 26 publications

The value of AI in the Diagnosis, Treatment, and Prognosis of Malignant Lung Cancer

The value of AI in the Diagnosis, Treatment, and Prognosis of Malignant Lung Cancer

Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis

Lung nodule false positive reduction using a central attention convolutional neural network on imbalanced data

Contact Info

Product

Resources

About