Comparison of Conventional and Deep Learning Based Methods for Pulmonary Nodule Segmentation in CT Images

Rocha, Joana; Cunha, António; Mendonça, Ana Maria

doi:10.1007/978-3-030-30241-2_31

Cited by 6 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 compares the proposed method with the iW‐Net method proposed in [35] and the gradient vector flow active contour (SEGvAC) method presented in [15]. Because the U‐Net method is widely used for biomedical image segmentation [39, 40] and particularly pulmonary nodule segmentation [41, 42], the performance of U‐Net and U‐Net++ methods are also reported in Table 2. The SEGvAC method reported in [15] outperforms the performance of preceding non‐deep learning‐based methods.…”

Section: Resultsmentioning

confidence: 99%

“…Scholars segment the nodule in the CT images based on the distribution of the intensity [23]. Examples of the segmentation approaches in the literature are region growing [24], thresholding [25–27], a user‐interactive framework using 3D region growing on the fuzzy connectivity map [28] and based on grey‐level similarity and shape [29], voxel‐level and object‐level classification [30], region growing on the Euclidean distance map [31], active contour [15], anatomy packing with hierarchical segmentation [32], multi‐features clustering with adaptive local region energy [33], a modified deconvolutional neural network [34], deep learning methods [35–44], and graph cut with a deep learned prior [45].…”

Section: Introductionmentioning

confidence: 99%

“…However, the average reported Dice Similarity Coefficient (DSC) of this method is low. Generally, the deep learning‐based approaches in the field [35–44] are proven to have good performance. However, since there are similar lesions to a nodule in the Region of Interest (ROI), such as vessel pieces, it is likely that these lesions are falsely labelled as nodules.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation of the pulmonary nodule and the attached vessels in the CT scan of the chest using morphological features and topological skeleton of the nodule

Tavakoli

Orooji²,

Teimouri

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of the pulmonary nodule and the attached vessels in the CT scan of the chest using morphological features and topological skeleton of the nodule

Tavakoli

Orooji²,

Teimouri

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

“…Despite extensive research, classical image processing techniques were unable to provide sufficiently robust and accurate volumetric nodule segmentation. On the other hand, recent advancements in deep learning (DL) have revolutionized image enhancement 20 and segmentation-related applications 2122 , including lung nodule segmentation tasks 23 . Especially the introduction of the U-Net architecture 24 , for segmentation in medical images, has remarkably enhanced the performance for these tasks.…”

Section: Related Workmentioning

confidence: 99%

Volumetric lung nodule segmentation using adaptive ROI with multi-view residual learning

Usman

Lee

Byon³

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Byung-il Lee 2 & Yeong-Gil Shin 1 Accurate quantification of pulmonary nodules can greatly assist the early diagnosis of lung cancer, enhancing patient survival possibilities. A number of nodule segmentation techniques, which either rely on a radiologist-provided 3-D volume of interest (VOI) or use the constant region of interests (ROIs) for all the slices, are proposed; however, these techniques can only investigate the presence of nodule voxels within the given VOI. Such approaches restrain the solutions to freely investigate the nodule presence outside the given VOI and also include the redundant structures (non-nodule) into VOI, which limits the segmentation accuracy. In this work, a novel semi-automated approach for 3-D segmentation of lung nodule in computerized tomography scans, has been proposed. The technique is segregated into two stages. In the first stage, a 2-D ROI containing the nodule is provided as an input to perform a patch-wise exploration along the axial axis using a novel adaptive ROI algorithm. This strategy enables the dynamic selection of the ROI in the surrounding slices to investigate the presence of nodules using a Deep Residual U-Net architecture. This stage provides the initial estimation of the nodule utilized to extract the VOI. In the second stage, the extracted VOI is further explored along the coronal and sagittal axes, in patchwise fashion, with Residual U-Nets. All the estimated masks are then fed into a consensus module to produce a final volumetric segmentation of the nodule. The algorithm is rigorously evaluated on LIDC-IDRI dataset, which is the largest publicly available dataset. The proposed approach achieved the average dice score of 87.5%, which is significantly higher than the existing state-of-the-art techniques. Lung cancer is one of the most severe and highly-prevalent cancers and is the leading cause of cancer deaths worldwide 1. It has been forecasted to be one of the greatest single cause of mortality among the European population in 2019 2. Early diagnosis of lung cancer is crucial to enable possible life-saving interventions 3 , which relies on accurate quantification of pulmonary nodule; albeit pulmonary nodules can be associated with several diseases, their recurrent diagnosis is lung cancer. The continuous monitoring of lung nodule volume is vital to estimate the malignancy and to better forecast, the probability of lung cancer 45. For calculation of volume, the nodule is first segmented, while the manual segmentation of nodule is a tedious and time-consuming task which also introduces the inter and intra-observer variabilities 6. Computer-aided diagnosis (CAD) systems have huge potential to overcome the challenges faced during manual segmentation of pulmonary nodules and can remarkably enhance the productivity of radiologists. Therefore, several automatic nodule segmentation techniques have been proposed to facilitate radiologists, including advanced deep learning and classical image processing based techniques 7. All existing techniques require a 3-D volum...

show abstract

“…Despite extensive research, classical image processing techniques are unable to provide sufficiently robust and accurate volumetric nodule segmentation. On the other hand, recent advancements in deep learning [19]- [24] have revolutionized image segmentation-related applications [25]- [27], including lung nodule segmentation tasks [28]. Especially the introduction of the U-Net architecture [29] for segmentation in medical images remarkably enhanced the performance for these tasks.…”

Section: Related Workmentioning

confidence: 99%

Volumetric Lung Nodule Segmentation using Adaptive ROI with Multi-View Residual Learning

Usman¹,

Lee

Byon³

et al. 2019

Preprint

View full text Add to dashboard Cite

Accurate quantification of pulmonary nodules can assist the early diagnosis of lung cancer, enhancing patient survival possibilities. A number of nodule segmentation techniques, which rely on a radiologist-provided 3-D volume of interest (VOI) input or the use of a constant region of interest (ROI), are proposed; however, these techniques can only investigate the presence of nodule voxels within the given VOI. Such approaches restrain the solutions to freely investigate the nodule presence outside the given VOI and also include the redundant structures (non-nodule) into VOI, which could lead to inaccurate nodule segmentation. In this work, a novel semi-automated approach for 3-D segmentation of nodule in volumetric computerized tomography (CT) lung scans has been proposed. The technique is segregated into two stages. In the first stage, a 2-D ROI containing the nodule is provided as an input to perform a patchwise exploration along the axial axis using a novel adaptive ROI algorithm. This strategy enables the dynamic selection of the ROI in the surrounding slices to investigate the presence of nodules using a Deep Residual U-Net architecture. This stage provides the initial estimation of the nodule utilized to extract the VOI. In the second stage, the extracted VOI is further explored along the coronal and sagittal axes with two networks . All the estimated masks are then fed into a consensus module to produce a final volumetric segmentation of the nodule. The proposed approach is rigorously evaluated on LIDC-IDRI dataset, which is the largest publicly available dataset. The results suggest that the proposed approach is more robust and accurate than the previous stateof-the-art techniques.

show abstract

Comparison of Conventional and Deep Learning Based Methods for Pulmonary Nodule Segmentation in CT Images

Cited by 6 publications

References 10 publications

Segmentation of the pulmonary nodule and the attached vessels in the CT scan of the chest using morphological features and topological skeleton of the nodule

Segmentation of the pulmonary nodule and the attached vessels in the CT scan of the chest using morphological features and topological skeleton of the nodule

Volumetric lung nodule segmentation using adaptive ROI with multi-view residual learning

Volumetric Lung Nodule Segmentation using Adaptive ROI with Multi-View Residual Learning

Contact Info

Product

Resources

About