Table 5.
Overview of published works regarding learning-based methodologies for the segmentation of lung CT images (2019–2021).
| Authors | Year | Dataset | Methods | Performance Results (%) |
|---|---|---|---|---|
| Dong et al. [155] | 2019 | LCTSC | U-net generator with a FCN discriminator | DSC = 97.0 |
| Feng et al. [156] | 2019 | LCTSC | Two-stage segmentation process with 3D U-net | DSC = 97.2 (RL), 97.9 (LL) |
| Park et al. [157] | 2019 | LCTSC Private (30 patients) | U-net | DSC = 98.8 JSC = 97.7 MSD = 0.270 mm HSD = 25.5 mm |
| Hofmanninger et al. [158] | 2020 | LCTSC, LTRC, VISCERAL, VESSEL12 Private (5300 patients) | U-net, ResUNet, Dilated residual network-D-22, DeepLab v3+ | (merged dataset) DSC = 98.0 HD95 = 3.14 mm MSD = 0.620 mm |
| Yoo et al. [159] | 2020 | HUG-ILD Private (203 patients) | 2D and 3D U-net | (Private - 2D; 3D) DSC = 99.6; 99.4 TPR = 99.5; 99.1 PPV = 99.6; 99.7 HD = 17.7 px; 18.7 px (HUG-ILD - 2D; 3D) DSC = 98.4; 95.3 TPR = 98.7; 98.0 PPV = 98.1; 92.8 HD = 7.66 px; 15.6 px |
| Khanna et al. [167] | 2020 | LUNA16 VESSEL12 2HUG-ILD | ResUNet + false positive removal algorithm | (LUNA16) DSC = 96.6 JI = 93.4 TPR = 97.5 (VESSEL12) DSC = 98.3 JI = 97.9 TPR = 98.8 (HUG-ILD) DSC = 98.1 JI = 96.3 TPR = 98.3 |
| Shi et al. [160] | 2020 | StructSeg 2019 | TA-Net | DSC = 96.8 (LL), 97.1 (RL) HD = 0.188 mm (LL), 0.171 mm (RL) |
| Nemoto et al. [161] | 2020 | NSCLC-Radiomics | 2D and 3D U-net | DSC = 99.0 (2D/3D U-net) |
| Zhang et al. [162] | 2020 | Lung dataset (Kaggle “Finding and Measuring Lungs in CT Data” competition) | Dense-Inception U-net (DIU-net) | DSC = 98.6 JI = 98.7 ACC = 99.4 TPR = 98.5 TNR = 99.8 F-score = 98.5 AUC = 99.0 |
| Vu et al. [163] | 2020 | Private (168 patients) | U-net with pre-trained VGG16 | DSC = 97.0 (RL and LL) HD-95 = 5.10 mm (RL), 4.09 mm (LL) |
| Liu et al. [171] | 2020 | HUG-ILD | Random forest fusion classification of deep, texture and intensity features | DSC = 96.4 JI = 91.1 OR = 5.04 UR = 4.76 |
| Hu et al. [172] | 2020 | Private (39 patients) | Mask R-CNN + supervised and unsupervised classifiers | DSC = 97.3 ACC = 97.7 TPR = 96.6 TNR = 97.1 |
| Han et al. [173] | 2020 | Private | Xception + VGG with SVM-RBF Detectron2 + contour fine-tuning | DSC = 97.0 ACC = 99.0 TPR = 96.5 TNR = 99.4 |
| Xu et al. [170] | 2021 | Private (217 patients) COVID-19-CT-Seg HUG-ILD VESSEL12 | Boundary-Guided Network (BG-Net) | DSC = 98.6 (Private), 96.5 (StructSeg), 98.9 (HUG-ILD), 99.5 (VESSEL12) HD = 2.77 mm (Private), 1.39 mm (StructSeg), 0.665 mm (HUD-ILD), 1.40 mm (VESSEL12) |
| Jalali et al. [166] | 2021 | LIDC-IDRI | ResBCDU-Net | DSC = 97.1 |
| Wang et al. [164] | 2021 | Lung dataset (Kaggle “Finding and Measuring Lungs in CT Data” competition) | HDA-ResUNet | DSC = 97.9 JI = 96.0 ACC = 99.3 |
| Tan et al. [168] | 2021 | LIDC-IDRI QIN lung CT dataset | LGAN | (LIDC-IDRI) IOU = 92.3 HD = 3.38 mm (QIN) IOU = 93.8 HD = 2.68 mm |
| Pawar and Talbar [169] | 2021 | HUG-ILD | LungSeg-Net | DSC = 96.3 (Fibrosis), 96.5 (Ground glass), 91.4 (Reticulation), 97.6 (Consolidation), 97.8 (Emphysema), 99.0 (Nodules) JI = 93.7 (Fibrosis), 93.9 (Ground glass), 86.9 (Reticulation), 95.3 (Consolidation), 96.2 (Emphysema), 98.0 (Nodules) |
| Cao et al. [165] | 2021 | StructSeg 2019 | C-SE-ResUNet | DCS = 97.0 (LL) 96.6 (RL) |
ACC: accuracy; AUC: area under the ROC curve; DSC: Sørensen–Dice coefficient; HD: Hausdorff distance; IOU: intersection over union; JI: Jaccard index; LL: left lung; OR: over-segmentation rate; PPV: positive predictive vale; RL: right lung; TNR: true negative rate; TPR: true positive rate; UR: under-segmentation rate.