Table 1.
A list of algorithms that are related to the proposed method.
| Authors | Brief Description |
|---|---|
| Lung Nodule Segmentation | |
| Kostis et al. 2003 [10] | Applied iterative morphological filtering to remove vessels affixed to solid nodules |
| Kuhnigk et al. 2006 [11] | Employed morphological correction allowing to manage nodules regardless of size |
| Dehmeshki et al. 2008 [13] | Proposed a contrast based region growing method, that employs a fuzzy connectivity map |
| Chan and Vese 2001 [14] | Formulated segmentation as an energy minimization of an evolving contour seen as a level set |
| Farag et al. 2013 [15] | Used shape prior hypothesis along with level sets |
| Boykov and Kolmogorov et al. 2004 [16] | Framed the problem within a maximum flow optimization framework and used a graph cut method |
| Miao et al. 2016 [17] | GGO lung nodule segmentation with expectation–maximization algorithm |
| Miao et al. 2017 [18] | GGO lung nodule segmentation with ACM, solid and non-solid parts treated separately and combined |
| Li et al. 2020 [19] | Nodule segmentation with fuzzy C-means clustering and Gaussian mixture models |
| Wang et al. 2021 [21] | Enhanced total-variance pyramid and grab cut, boundary extraction with Gibbs energy functional |
| Lu et al. 2011 [22] | Proposed a stratified learning framework including supervised image segmentation |
| Hu et al. 2016 [23] | Utilized a Hessian-based vascular feature extraction procedure and classified nodules with a neural network |
| Gonçalves et al. 2016 [24] | Hessian-based strategies with a multiscale process that uses the central medialness adaptive principle |
| Jung et al. 2017 [25] | Separate solid and non-solid in GGO nodules using an asymmetric multi-phase deformable mode |
| Wang et al. 2017 [26] | MVCNN for nodule segmentation, which extracts features from axial, coronal and sagittal views |
| Ronneberger et al. 2015 [27] | U-Net architecture specialized for biomedical imaging |
| Wang et al. 2017 [28] | Central focused convolutional neural network for lung nodule segmentation |
| Cao et al. 2020 [29] | Dual-branch residual network for lung nodule segmentation |
| Qi et al. 2020 [30] | GGO nodules segmentation using CAD system based on CCN, analyzing growth and risk factors. |
| Funke et al. 2020 [31] | Trained a 3D-UNet model using using the STAPLE algorithm |
| Xiao et al. 2020 [32] | Combined the 3D-UNet and Res2Net architectures to create a new model |
| Hu et al. 2021 [33] | Hybrid attention mechanism and densely connected convolutional networks |
| Lung Segmentation | |
| Kavitha et al. 2019 [36] | Novel strip and marker-watershed based on PSO and fuzzy c-means clustering for lung segmentation |
| Kim et al. 2021 [37] | U-Net with self-attention for lung segmentation in chest X-rays. |
| Lung Nodule Detection and Segmentation | |
| Mekali et al. 2021 [20] | Lung boundary pixels and concave points extraction, separation of attached pleural from nodule |
| Huang et al. 2019 [38] | Detection with regional-CNN and segmentation with a FCN. |
| Other Pulmonary Disease Detection | |
| Polap et al. 2018 [39] | Diseased tissue detection via lung segmentation and bio-inspired algorithm |
| Ke et al. 2019 [40] | Detection of pulmonary disease with neuro-heuristic method |
| Santoso et al. 2020 [41] | ANFIS for detection of pneumonia and pulmonary tuberculosis |
| Ukaoha et al. 2020 [42] | ANFIS for diagnosis of COVID-19 |
| Akram et al. 2021 [43] | COVID-19 diagnosis in X-rays via optimized genetic algorithm selector and naive Bayes classifier |
| Wang et al. 2020 [44] | Deep convolutional network for COVID-19 detection in X-rays |