Table 2.
Literature overview on colorectal whole slide image diagnosis.
| Author | Year | Task | Dataset | Description | Results |
|---|---|---|---|---|---|
| Kalkan et al.37 | 2012 | CRC detection (normal vs cancer) | 120 H&E slides (tile annotations) | 1024 × 1024 px tiles; k-NN classifier + Logistic-linear classifier | Acc.: 87.69%; AUC: 0.90 |
| Korbar et al.40 | 2017 | Polyp classification (6-class): normal, hyperplastic, sessile serrated, traditional serrated, tubular and tubulovillous/villous | 697 H&E slides (annotated) | 811 × 984 px ROIs (mean size); ResNet-152 + argmax of tile class frequency | Acc.: 93%; Precision: 89.7%; Recall: 88.3%; F1-score: 88.8% |
| Yoshida et al.38 | 2017 | CRC classification (4-class): unclassifiable, non-neoplastic, adenoma and CA | 1068 H&E slides (w/ labelled tissue sections) | Tissue sections crop + cytological atypia analysis + structural atypia analysis + overall classification | FNR (CA): 9.3%; FNR (adenoma): 0%; FPR: 27.1% |
| Iizuka et al.43 | 2020 | CRC classification (3-class): non-neoplastic, AD and ADC | 4536 H&E slides (annotated) + 547 H&E slides from TCGA-COAD collection | 512 × 512 px tiles at 20×; Inception-v3 + RNN | AUC: 0.962 (ADC), 0.993 (AD); AUC (TCGA-COAD subset): 0.982 (ADC) |
| Song et al.46 | 2020 | Colorectal adenoma detection (normal vs adenoma) | 411 H&E slides (annotated) + external set: 168 H&E slides | 640 × 640 px tiles at 10×; Modified DeepLab-v2 + 15th largest pixel probability | AUC: 0.92; Acc. (external set): >90% |
| Wei et al.45 | 2020 | Polyp classification (5-class): Normal, hyperplastic, tubular, tubulovillous/villous, sessile serrated | 508 H&E slides (annotated) + external set: 238 H&E slides | 224 × 224 px tiles at 40×; ResNet models ensemble + hierarchical classification | Acc.: 93.5%; Acc. (external set): 87% |
| Xu et al.47 | 2020 | CRC detection (normal vs cancer) | 307 H&E slides (annotated) + 50 H&E slides (external set) | 768 × 768 px tiles; Inception-v3 + tiles tumour probability thresholding | Acc.: >93%; Acc. (external set): >87% |
CRC: Colorectal Cancer; AD: Adenoma; CA: Carcinoma; ADC: Adenocarcinoma; H&E: Haemotoxylin & Eosin; px: pixels; k-NN: k Nearest Neighbours; ROI: Region of Interest CNN: Convolutional Neu- ral Network; SVM: Support Vector Machine; MLP: Multi-Layer Perceptron; MIL: Multiple Instance Learning; Acc.: Accuracy; AUC: Area Under the ROC Curve; FNR/FPR: False Negative/Positive Rate