MD-NDNet: a multi-dimensional convolutional neural network for false-positive reduction in pulmonary nodule detection.

Published on Dec 5, 2020in Physics in Medicine and Biology3.609
路 DOI :10.1088/1361-6560/ABA87C
Zhan Wu (SEU: Southeast University), Rongjun Ge6
Estimated H-index: 6
(SEU: Southeast University)
+ 5 AuthorsHengyong Yu39
Estimated H-index: 39
(University of Massachusetts Lowell)
Sources
Abstract
Pulmonary nodule false positive reduction is of great significance for automated nodule detection in clinical diagnosis of low-dose computerized tomography (LDCT) lung cancer screening. Due to individual intra-nodule variations and visual similarities between true nodules and false positives as soft tissues in the LDCT images, the current clinical practices remain subject to shortcomings of potential high-risk and time-consumption issues. In this paper, we propose a multi-dimension nodule detection network (MD-NDNet) for automatic nodule false positive reduction using deep convolutional neural network (DCNNs). The underlying method collaboratively integrates multi-dimension nodule information to complementarily and comprehensively extract nodule inter-plane volumetric correlation features using three-dimension CNNs (3D CNNs) and spatial nodule correlation features from sagittal, coronal, and axial planes using two-dimension CNNs (2D CNNs) with attention module. To encompass different sizes and shapes of nodule candidates, a multi-scale ensemble strategy is employed for probability aggregation with weights. The proposed method is evaluated on the LUNA16 challenge dataset in ISBI 2016 with ten-fold cross-validation. Experiment results show that the proposed framework achieves classification performance with a CPM score of 0.9008. All of these indicate that our method enables an efficient, accurate and reliable pulmonary nodule detection for clinical diagnosis.
馃摉 Papers frequently viewed together
2018
4 Authors (Nannan Sun, ..., Hongtao Xie)
2018ICGSP: International Conference Graphics and Signal Processing
3 Authors (Zhengwei Hu, ..., Ming Zhu)
References40
Newest
#1Chung-Feng Jeffrey Kuo (NTUST: National Taiwan University of Science and Technology)H-Index: 26
#2Chang-Chiun Huang (NTUST: National Taiwan University of Science and Technology)H-Index: 8
Last. Hsian-He Hsu (NDMC: National Defense Medical Center)H-Index: 1
view all 7 authors...
Abstract Diagnosing and treating lung cancer at an early stage can improve the survival rate of patients. This study attempted to develop a computer-aided detection (CAD) system. In order to include all nodule types in the detection, this study proposes an image processing method for detecting ground glass opacity (GGO), part solid, and solid nodules in chest computed tomography. The process comprises image preprocessing, lung segmentation, nodule enhancement, candidate detection, and reduction ...
Source
#1Yanli Zhu (PKU: Peking University)H-Index: 2
#2Yuntao Song (PKU: Peking University)H-Index: 2
Last. Wenhao Ren (PKU: Peking University)H-Index: 2
view all 5 authors...
Objective FNA is a simple, safe, cost-effective and accurate diagnostic tool for the initial screening of patients with thyroid nodules. The aims of this study were to determine the diagnostic utility of FNAC performed in our institution, assess the cytomorphologic features that contribute to diagnostic errors and propose improvement measures.
Source
#1Dianlin Hu (SEU: Southeast University)H-Index: 5
#2Weiwen Wu (Chongqing University)H-Index: 13
Last. Gouenou Coatrieux (IMT: Institut Mines-T茅l茅com)H-Index: 28
view all 9 authors...
Multi-energy computed tomography (MCT) has a great potential in material decomposition, tissue characterization, lesion detection, and other applications. However, the severe noise that exists within projections makes it difficult to obtain high-quality MCT images. To overcome this limitation, we propose a method termed Spectral-Image Similarity-based Tensor with Enhanced-sparsity Reconstruction (SISTER) method. SISTER utilizes the non-local feature similarity in the spatial-spectral domain by c...
Source
#1Shuai Li (Beihang University)H-Index: 60
#2Yuting Guo (Beihang University)H-Index: 2
Last. Hong Qin (SBU: Stony Brook University)H-Index: 52
view all 7 authors...
Thyroid nodule classification in ultrasound images has gained great momentum based on deep convolutional neural networks in recent years. Nevertheless, it is still challenging to intelligently classify the fine-grained thyroid nodules, which is significant for the subsequent clinical treatments. The difficulties mainly stem from four aspects: few fine-grained training dataset, highly-variable appearances of intra-class nodules, overall-similar characteristics of inter-class nodules, and the low ...
Source
#1Jingya Liu (CCNY: City College of New York)H-Index: 5
#2Liangliang Cao (UMass: University of Massachusetts Amherst)H-Index: 39
Last. Yingli Tian (CCNY: City College of New York)H-Index: 64
view all 4 authors...
Accurate detection of pulmonary nodules with high sensitivity and specificity is essential for automatic lung cancer diagnosis from CT scans. Although many deep learning-based algorithms make great progress for improving the accuracy of nodule detection, the high false positive rate is still a challenging problem which limited the automatic diagnosis in routine clinical practice. In this paper, we propose a novel pulmonary nodule detection framework based on a 3D Feature Pyramid Network (3DFPN) ...
Source
#1Xiaoqing Guo (CityU: City University of Hong Kong)H-Index: 6
#2Yixuan Yuan (CityU: City University of Hong Kong)H-Index: 20
Accurate detection of abnormal regions in Wireless Capsule Endoscopy (WCE) images is crucial for early intestine cancer diagnosis and treatment, while it still remains challenging due to the relatively low contrasts and ambiguous boundaries between abnormalities and normal regions. Additionally, the huge intra-class variances, alone with the high degree of visual similarities shared by inter-class abnormalities prevent the network from robust classification. To tackle these dilemmas, we propose ...
Source
#2Laxman M. WaghmareH-Index: 15
Last. Subrahmanyam Murala (IIT-RPR: Indian Institute of Technology Ropar)H-Index: 23
view all 4 authors...
Abstract A novel image indexing algorithm for Content Based Image Retrieval (CBIR) using Local Energy Oriented Patterns (LEOP) is proposed in this paper. LEOP encodes pixel level energy orientations to find minute spatial features of an image whereas existing methods use neighborhood relationship. LEOP maps four pixel progression orientations to find top two maximum energy changes for each reference pixel in the image i.e. for each reference 3 脳 3 grid, two more 3 脳 3 grids out of four pixel pro...
Source
#1Shulong Li (Southern Medical University)H-Index: 6
#2Panpan XuH-Index: 2
Last. Jing Wang (UTSW: University of Texas Southwestern Medical Center)H-Index: 106
view all 12 authors...
To predict lung nodule malignancy with a high sensitivity and specificity for low dose CT (LDCT) lung cancer screening, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine HF, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM). We then trained 3D CNNs modified from thr...
Source
Jun 15, 2019 in CVPR (Computer Vision and Pattern Recognition)
#1Jun Fu (CAS: Chinese Academy of Sciences)H-Index: 10
#2Jing Liu (CAS: Chinese Academy of Sciences)H-Index: 34
Last. Hanqing LuH-Index: 64
view all 7 authors...
In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the self-attention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respec...
Source
#1Zifeng Wu (University of Adelaide)H-Index: 16
#2Chunhua Shen (University of Adelaide)H-Index: 94
Last. Anton van den Hengel (University of Adelaide)H-Index: 66
view all 3 authors...
Abstract The community has been going deeper and deeper in designing one cutting edge network after another, yet some works are there suggesting that we may have gone too far in this dimension. Some researchers unravelled a residual network into an exponentially wider one, and assorted the success of residual networks to fusing a large amount of relatively shallow models. Since some of their early claims are still not settled, we in this paper dig more on this topic, i.e., the unravelled view of...
Source
Cited By5
Newest
#1Bingbing Zheng (ECUST: East China University of Science and Technology)H-Index: 4
#2Dawei Yang (Fudan University)H-Index: 15
Last. Chunxue Bai (Fudan University)H-Index: 59
view all 6 authors...
PURPOSE Early detection is significant to reduce lung cancer-related death. Computer-aided detection system (CADs) can help radiologists to make an early diagnosis. In this paper, we propose a novel 3D gray density coding feature (3D GDC) and fuse it with extracted geometric features. The fusion feature and random forest are used for benign-malignant pulmonary nodule classification on Chest CT. METHODS First, a dictionary model is created to acquire codebook. It is used to obtain feature descrip...
Source
#1Shaohua Zheng (FZU: Fuzhou University)H-Index: 1
#2Zhiqiang Shen (FZU: Fuzhou University)H-Index: 1
Last. Liqin Huang (FZU: Fuzhou University)H-Index: 4
view all 9 authors...
Abstract null null Background and Objective: Computer-aided diagnosis (CAD) systems promote accurate diagnosis and reduce the burden of radiologists. A CAD system for lung cancer diagnosis includes nodule candidate detection and nodule malignancy evaluation. Recently, deep learning-based pulmonary nodule detection has reached satisfactory performance ready for clinical application. However, deep learning-based nodule malignancy evaluation depends on heuristic inference from low-dose computed tom...
Source
#2Jo茫o Mario Clementin de Andrade (UFPR: Federal University of Paran谩)
Last. Lucas Ferrari de Oliveira (UFPR: Federal University of Paran谩)H-Index: 7
view all 4 authors...
Cancer is one of the leading causes of mortality worldwide, specifically lung cancer. Computer-Aided Detection (CADe) systems are being proposed to assist radiologists in the task of pulmonary nodule detection. In this paper, we propose a CADe system that uses Deep Convolutional Neural Network (DCNN). In the Nodule Candidate Detection (NCD) step, we used Mask Region-Convolutional Neural Network (Mask R-CNN) to detect bounding boxes in 2D slices of low-dose Computed Tomography (CT) scans. In the ...
Source
#1Dongdong Gu (Hunan University)H-Index: 2
#2Guocai Liu (Hunan University)H-Index: 2
Last. Zhong XueH-Index: 23
view all 3 authors...
Abstract Computed tomography (CT) screening is an effective way for early detection of lung cancer in order to improve the survival rate of such a deadly disease. For more than two decades, image processing techniques such as nodule detection, segmentation, and classification have been extensively studied to assist physicians in identifying nodules from hundreds of CT slices to measure shapes and HU distributions of nodules automatically and to distinguish their malignancy. Thanks to new paralle...
Source
#1Shaohua ZhengH-Index: 1
#2Zhiqiang ShenH-Index: 1
view all 9 authors...
Background and Objective:Computer-aided diagnosis (CAD) systems promote diagnosis effectiveness and alleviate pressure of radiologists. A CAD system for lung cancer diagnosis includes nodule candidate detection and nodule malignancy evaluation. Recently, deep learning-based pulmonary nodule detection has reached satisfactory performance ready for clinical application. However, deep learning-based nodule malignancy evaluation depends on heuristic inference from low-dose computed tomography volume...
#1Rajesh Kumar (University of Electronic Science and Technology of China)H-Index: 11
#2Wenyong Wang (University of Electronic Science and Technology of China)H-Index: 4
Last. Ikram Ali (University of Electronic Science and Technology of China)H-Index: 8
view all 7 authors...
Abstract Deep learning, for image data processing, has been widely used to solve a variety of problems related to medical practices. However, researchers are constantly struggling to introduce ever efficient classification models. Recent studies show that deep learning can perform better and generalize well when trained using a large amount of data. Organizations such as hospitals, testing labs, research centers, etc. can share their data and collaboratively build a better learning model. Every ...
Source
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.