Multi-Scale Prediction Network for Lung Segmentation

Gu, Yanfeng; Lai, Yaoming; Xie, Peiliang; Wei, Jun; Lu, Yao

doi:10.1109/isbi.2019.8759207

Cited by 11 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has recently performed well in natural image segmentation [7], medical image segmentation [8], and video segmentation [9][10][11]. In medical imaging, deep learning not only excels in tissue and organ segmentation, such as pancreas segmentation [12][13][14], lung segmentation [15][16][17][18][19], and brain segmentation [20,21] but also exhibits superior performance in the segmentation of lesions, such as brain tumor segmentation [22][23][24], brain glioma segmentation [25], and microcalcification segmentation [26]. However, no studies regarding deep learning for rib segmentation have been reported.…”

Section: Introductionmentioning

confidence: 99%

MDU-Net: A Convolutional Network for Clavicle and Rib Segmentation from a Chest Radiograph

Wang

Feng

et al. 2020

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Automatic bone segmentation from a chest radiograph is an important and challenging task in medical image analysis. However, a chest radiograph contains numerous artifacts and tissue shadows, such as trachea, blood vessels, and lung veins, which limit the accuracy of traditional segmentation methods, such as thresholding and contour-related techniques. Deep learning has recently achieved excellent segmentation of some organs, such as the pancreas and the hippocampus. However, the insufficiency of annotated datasets impedes clavicle and rib segmentation from chest X-rays. We have constructed a dataset of chest X-rays with a raw chest radiograph and four annotated images showing the clavicles, anterior ribs, posterior ribs, and all bones (the complete set of ribs and clavicle). On the basis of a sufficient dataset, a multitask dense connection U-Net (MDU-Net) is proposed to address the challenge of bone segmentation from a chest radiograph. We first combine the U-Net multiscale feature fusion method, DenseNet dense connection, and multitasking mechanism to construct the proposed network referred to as MDU-Net. We then present a mask encoding mechanism that can force the network to learn the background features. Transfer learning is ultimately introduced to help the network extract sufficient features. We evaluate the proposed network by fourfold cross validation on 88 chest radiography images. The proposed method achieves the average DSC (Dice similarity coefficient) values of 93.78%, 80.95%, 89.06%, and 88.38% in clavicle segmentation, anterior rib segmentation, posterior rib segmentation, and segmentation of all bones, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

MDU-Net: A Convolutional Network for Clavicle and Rib Segmentation from a Chest Radiograph

Wang

Feng

et al. 2020

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…For each input CT volume, we firstly segmented the lung area using our previously developed multiscale lung segmentation method [13] , based on deep convolutional neural network (DCNN) trained by multiscale Dice (MD) loss. The purpose of this process was to limit the lesion detection in a subregion to reduce the computation time as well as avoid false positives (FPs).…”

Section: Methodsmentioning

confidence: 99%

2019 Novel Coronavirus-Infected Pneumonia on CT: A Feasibility Study of Few-Shot Learning for Computerized Diagnosis of Emergency Diseases

Lai

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

COVID-19 is an emerging disease with transmissibility and severity. So far, there are no effective therapeutic drugs or vaccines for COVID-19. The most serious complication of COVID-19 is a type of pneumonia called 2019 novel coronavirus-infected pneumonia (NCIP) with about 4.3% mortality rate. Comparing to chest Digital Radiography (DR), it is recently reported that chest Computed Tomography (CT) is more useful to serve as the early screening and diagnosis tool for NCIP. In this study, aimed to help physicians make the diagnostic decision, we develop a machine learning (ML) approach for automated diagnosis of NCIP on chest CT. Different from most ML approaches which often require training on thousands or millions of samples, we design a few-shot learning approach, in which we combine few-shot learning with weakly supervised model training, for computerized NCIP diagnosis. A total of 824 patients are retrospectively collected from two Hospitals with IRB approval. We first use 9 patients with clinically confirmed NCIP and 20 patients without known lung diseases for training a location detector which is a multitask deep convolutional neural network (DCNN) designed to output a probability of NCIP and the segmentation of targeted lesion area. An experienced radiologist manually localizes the potential locations of NCIPs on chest CTs of 9 COVID-19 patients and interactively segments the area of the NCIP lesions as the reference standard. Then, the multitask DCNN is furtherly fine-tuned by a weakly supervised learning scheme with 291 case-level labeled samples without lesion labels. A test set of 293 patients is independently collected for evaluation. With our NCIP-Net, the test AUC is 0.91. Our system has potential to serve as the NCIP screening and diagnosis tools for the fight of COVID-19's endemic and pandemic.

show abstract

“…Using residual convolution blocks in a deep neural network solves gradient exploding and vanishing problems, providing the shortcut connection between input and output. The authors selected the lung CT scans from LUNA16 and NLST (National Lung Screening Trial) Dataset [18], having the criterion of selecting those CT scans that have interstitial lung disease and lung nodules attached on the lung wall [17].…”

Section: Related Workmentioning

confidence: 99%

“…Lung segmentation prevents computer program to process irrelevant volumetric data that can produce false positives and leads to the erroneous diagnosis. Additionally, it can be considered as a necessary preprocessing for different lung disease analysis such as lung nodule detection or segmentation, pulmonary embolism (PE) diagnosis, Acute Respiratory Distress Syndrome (ARDS), and pneumothorax analysis [17] [19] [20].…”

Section: Introductionmentioning

confidence: 99%

R²U3D: Recurrent Residual 3D U-Net for Lung Segmentation

et al. 2021

View full text Add to dashboard Cite

This paragraph of the first footnote will contain support information, including sponsor and financial support acknowledgment.ABSTRACT 3D lung segmentation is essential since it processes the volumetric information of the lungs, removes the unnecessary areas of the scan, and segments the actual area of the lungs in a 3D volume. Recently, the deep learning model, such as U-Net outperforms other network architectures for biomedical image segmentation. In this paper, we propose a novel model, namely, Recurrent Residual 3D U-Net (R 2 U3D), for the 3D lung segmentation task. In particular, the proposed model integrates 3D convolution into the Recurrent Residual Neural Network based on U-Net. It helps learn spatial dependencies in 3D and increases the propagation of 3D volumetric information. The proposed R 2 U3D network is trained on the publicly available dataset LUNA16 and it achieves state-of-the-art performance on both LUNA16 (testing set) and VESSEL12 dataset. In addition, we show that training the R 2 U3D model with a smaller number of CT scans, i.e., 100 scans, without applying data augmentation achieves an outstanding result in terms of Soft Dice Similarity Coefficient (Soft-DSC) of 0.9920.

show abstract

Multi-Scale Prediction Network for Lung Segmentation

Cited by 11 publications

References 11 publications

MDU-Net: A Convolutional Network for Clavicle and Rib Segmentation from a Chest Radiograph

MDU-Net: A Convolutional Network for Clavicle and Rib Segmentation from a Chest Radiograph

2019 Novel Coronavirus-Infected Pneumonia on CT: A Feasibility Study of Few-Shot Learning for Computerized Diagnosis of Emergency Diseases

R²U3D: Recurrent Residual 3D U-Net for Lung Segmentation

Contact Info

Product

Resources

About

Multi-Scale Prediction Network for Lung Segmentation

Cited by 11 publications

References 11 publications

MDU-Net: A Convolutional Network for Clavicle and Rib Segmentation from a Chest Radiograph

MDU-Net: A Convolutional Network for Clavicle and Rib Segmentation from a Chest Radiograph

2019 Novel Coronavirus-Infected Pneumonia on CT: A Feasibility Study of Few-Shot Learning for Computerized Diagnosis of Emergency Diseases

R2U3D: Recurrent Residual 3D U-Net for Lung Segmentation

Contact Info

Product

Resources

About

R²U3D: Recurrent Residual 3D U-Net for Lung Segmentation