Coarse-to-Fine Lung Nodule Segmentation in CT Images With Image Enhancement and Dual-Branch Network

Wu, Zhitong; Zhou, Quan; Wang, Feng

doi:10.1109/access.2021.3049379

Cited by 27 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The threshold and initial seed values were defined by the user based on the input image. These are limitations of the segmentation network proposed by Wu et al 28 . The reported DSC of this method was 83.16%, which is 12.54% lower than Lung_PAYNet.…”

Section: Experiment Results and Discussionmentioning

confidence: 98%

See 1 more Smart Citation

Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation

Bruntha

Pandian

Sagayam

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Accurate and reliable lung nodule segmentation in computed tomography (CT) images is required for early diagnosis of lung cancer. Some of the difficulties in detecting lung nodules include the various types and shapes of lung nodules, lung nodules near other lung structures, and similar visual aspects. This study proposes a new model named Lung_PAYNet, a pyramidal attention-based architecture, for improved lung nodule segmentation in low-dose CT images. In this architecture, the encoder and decoder are designed using an inverted residual block and swish activation function. It also employs a feature pyramid attention network between the encoder and decoder to extract exact dense features for pixel classification. The proposed architecture was compared to the existing UNet architecture, and the proposed methodology yielded significant results. The proposed model was comprehensively trained and validated using the LIDC-IDRI dataset available in the public domain. The experimental results revealed that the Lung_PAYNet delivered remarkable segmentation with a Dice similarity coefficient of 95.7%, mIOU of 91.75%, sensitivity of 92.57%, and precision of 96.75%.

show abstract

Section: Experiment Results and Discussionmentioning

confidence: 98%

“…Wu et al 28 developed a dual branch network based on UNet for segmenting the lung nodules. To improve the contrast between the nodules and the background, a technique called histogram equalization is applied.…”

Section: Related Workmentioning

confidence: 99%

Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation

Bruntha

Pandian

Sagayam

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…To effectively reduce the false positive, they utilize a dynamically scaled cross entropy loss. Similarly, in [31] Wu et. al., combined the image enhancement and a Dual-branch neural network for improving the visibility of lung nodules by suppressing the noises from background.…”

Section: Introductionmentioning

confidence: 83%

“…They also applied channel interaction unit prior to the detection head and the gradient harmonizing mechanism loss function was used combat the problem of imbalance of positive and negative samples problem. In [33] Luo et. al.…”

Section: Introductionmentioning

confidence: 99%

MEDS-Net: Self-Distilled Multi-Encoders Network with Bi-Direction Maximum Intensity projections for Lung Nodule Detection

Usman¹,

Rehman²,

Shahid³

et al. 2022

Preprint

View full text Add to dashboard Cite

Early detection of lung cancer is an effective way to improve the survival rate of patients. It is a critical step to have accurate detection of lung nodules in computed tomography (CT) images for the diagnosis of lung cancer. However, due to the heterogeneity of the lung nodules and the complexity of the surrounding environment, it is a challenge to develop a robust nodule detection method. Numerous efforts have been made to develop an efficient Computer-aided detection (CADe) systems, albeit none compliance with the routine workflow of radiologists which limits the adaptability of such CADe system. To overcome this deficiency, in this study we propose a lung nodule detection scheme which fully incorporates the clinic workflow of radiologists. Particularly, we exploit Bi-Directional Maximum intensity projection (MIP) images of various thicknesses (i.e., 3, 5 and 10mm) along with 3D patch of CT scan, consisting of 10 adjacent slices to feed into self distillation based Multi-Encoders Network (MEDS-Net). The propose architecture first condense 3D patch input to three channels by using dense block which consists of dense units which effectively examines the nodule presence from 2D axial slices. This condensed information, along with the forward and backward MIP images is fed to three different encoders to learn the most meaningful representation which is forwarded into decoded block at various levels. At decoder block, we employ self distillation mechanism by connecting the distillation block which contains five lung nodule detectors. It helps to expedite the convergence and improves the learning ability of proposed architecture. Finally, the propose scheme reduces the false positives by complementing the main detector with auxiliary detectors. The proposed scheme has been rigorously evaluated on 888 scans of LUNA16 dataset and obtained a CPM score of 93.6%. The results demonstrate that incorporating of bi-direction MIP images enables MEDS-Net to effectively distinguish nodules from surroundings which helps to achieve the sensitivity of . false positives per scans with the sensitivity of 91.5% and 92.8% with the false positive rate of 0.25 and 0.5 per scan, respectively.

show abstract

“…Deep learning (DL)-based studies for lung nodule segmentation can be broadly categorized into three groups: voxellevel classification (VLC) [18], [19], [20], 3D segmentation [21], [22], [23], and 2D patch-wise segmentation [24], [25], [26]. The VLC methodology involves classifying each voxel within the volume of interest (VOI) as either nodular or non-nodular.…”

Section: Introductionmentioning

confidence: 99%

DEHA-Net: A Dual-Encoder-Based Hard Attention Network with an Adaptive ROI Mechanism for Lung Nodule Segmentation

Usman

Shin

2023

Sensors

View full text Add to dashboard Cite

Measuring pulmonary nodules accurately can help the early diagnosis of lung cancer, which can increase the survival rate among patients. Numerous techniques for lung nodule segmentation have been developed; however, most of them either rely on the 3D volumetric region of interest (VOI) input by radiologists or use the 2D fixed region of interest (ROI) for all the slices of computed tomography (CT) scan. These methods only consider the presence of nodules within the given VOI, which limits the networks’ ability to detect nodules outside the VOI and can also encompass unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation that utilizes the 2D region of interest (ROI) inputted from a radiologist or computer-aided detection (CADe) system. Concretely, we developed a two-stage lung nodule segmentation technique. Firstly, we designed a dual-encoder-based hard attention network (DEHA-Net) in which the full axial slice of thoracic computed tomography (CT) scan, along with an ROI mask, were considered as input to segment the lung nodule in the given slice. The output of DEHA-Net, the segmentation mask of the lung nodule, was inputted to the adaptive region of interest (A-ROI) algorithm to automatically generate the ROI masks for the surrounding slices, which eliminated the need for any further inputs from radiologists. After extracting the segmentation along the axial axis, at the second stage, we further investigated the lung nodule along sagittal and coronal views by employing DEHA-Net. All the estimated masks were inputted into the consensus module to obtain the final volumetric segmentation of the nodule. The proposed scheme was rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset, and an extensive analysis of the results was performed. The quantitative analysis showed that the proposed method not only improved the existing state-of-the-art methods in terms of dice score but also showed significant robustness against different types, shapes, and dimensions of the lung nodules. The proposed framework achieved the average dice score, sensitivity, and positive predictive value of 87.91%, 90.84%, and 89.56%, respectively.

show abstract

Coarse-to-Fine Lung Nodule Segmentation in CT Images With Image Enhancement and Dual-Branch Network

Cited by 27 publications

References 28 publications

Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation

Lung_PAYNet: a pyramidal attention based deep learning network for lung nodule segmentation

MEDS-Net: Self-Distilled Multi-Encoders Network with Bi-Direction Maximum Intensity projections for Lung Nodule Detection

DEHA-Net: A Dual-Encoder-Based Hard Attention Network with an Adaptive ROI Mechanism for Lung Nodule Segmentation

Contact Info

Product

Resources

About