Artificial intelligence in rectal cancer

Table 1 Target volume and organs at risk contouring with artificial intelligence

Ref.	Number of patients	Imaging method	Contouring	Artificial intelligence method	Results
Wang et al[54], 2018	93	MR (3 Tesla, T2 -weighted)	GTV, CTV	CNN	Between deep learning-based autosegmentation and manual contouring DSC (P = 0.42), JSC (P = 0.35), HD (P = 0.079), and ASD (P = 0.16); Before postprocess process only in HD (P = 0.0027).
Trebeschi et al[55], 2017	140	Multiparametric MRI (1.5 Tesla, T2- weighted)	GTV	CNN	According to CNN and both radiologists in independent validation data set DSC: 0.68 and 0.70; For both radiologists AUC: 0.99.
Song et al[56], 2020	199	CT (3 mm section thickness)	CTV and OAR	CNNs (DeepLabv3+ and ResUNet)	CTV segmentation better with DeepLabv3+ than ResUNet (volumetric DSC, 0.88 vs 0.87, P = 0.0005; surface DSC, 0.79 vs 0.78, P = 0.008); DeepLabv3+ model segmentation was better in the small intestine, with the ResUNet model, bladder and femoral heads segmentation results were better. In both models, the OAR manual correction time was 4 min.
Men et al[60], 2017	278	CT (5 mm section thickness)	CTV and OAR	CNN (DDCNN)	DSC values; CTV: 87.7%, bladder: 93.4%, left femoral head: 92.1%, right femoral head: 92.3%, small intestine: 65.3%, colon 61.8%.
Men et al[61], 2018	100	CT (3 mm section thickness)	CTV and OAR	CNN	CTV and bladder contouring were better in the model trained in the same position than the model trained in a different position (P < 0.05). No statistically significant difference between femoral heads (P > 0.05). No statistical difference between accuracy rates in CTV, bladder, and femoral heads segmentation in the model trained in both positions (P > 0.05).

AUC: Area under the curve; ASD: Average surface distance; CNN: Convolutional neural network; CT: Computed tomography; CTV: Clinical target volume; DDCNN: Deep dilated convolutional neural network; DSC: Dice similarity coefficient; GTV: Gross tumor volume; HD: Hausdorff distance; JSC: Jaccard index; MRI: Magnetic resonance imaging; OAR: Organs at risk.

Table 2 Studies of chemoradiotherapy response prediction with artificial intelligence

Ref.	Number of patients	Parameters evaluated	Imaging method	Technique used	Results
Shi et al[71], 2019	51 (90% cases for training and the remaining 10% for testing)	Tumor volume, mean ADC, radiomic	MRI (Pre-CRT and mid-CRT) (T2-DWI, DCE)	CNN	(1) pCR response prediction: (a) Pre-CRT with MR AUC: 0.80; (b) Mid-CRT with MR AUC: 0.82; and (c) Pre- and mid-CRT MR together AUC: 0.86; and (2) Good response to CRT: predicting yes/no: (a) Pre-CRT with MR AUC: 0.91; (b) Mid-CRT with MR AUC: 0.92; and (c) Pre-- and mid-CRT MR together AUC: 0.93.
Fu et al[73], 2020	43	Radiomic	MRI (Pre-CRT, DWI)	Handcrafted traditional computer-aided diagnostic method vs deep learning	Deep learning model with handcrafted model CRT response prediction AUC values: 0.64 vs 0.73 (P < 0.05)
Shayesteh et al[74], 2019	98 (53 training and 45 validation set)	Radiomic	MRI (1 wk before CRT) (3 Tesla, T2W-weighted)	Machine learning (SVM, BN, NN, KNN)	AUC for the BN algorithm: 74%, accuracy: 79%; When four algorithms were used together, AUC: 97.8% and accuracy rate 92.8%.
Yang et al[75], 2019	89 (66 training and 23 testing)	Radiomic and clinical features	MRI (Pre-CRT) (3 Tesla, T2W, 3 mm section thickness)	RFC	Predicting the accuracy of tumor resistance with RFC 91.3%, AUC: 0.83.
Ferrari et al[76], 2019	55 (28 training, 27 validation)	Radiomic	MR (Pre, Mid, Post RT) (3 Tesla, T2W, 2 mm section thickness)	RFC	(1) Prediction of cases with pCR by RFC; AUC: 0.86; and (2) Prediction of unresponsive cases with RFC; AUC 0.83.
Bibault et al[77], 2018	95	Radiomic, clinical variables	CT	DNN, SVM, LR	CRT response prediction accuracy rates; DNN: 80%; SVM: 71.5% LR: 69.5%.
Huang et al[78], 2020	270 (236 training, 34 validation)	Clinical variables	-	ANN, KNN, SVM, NBC, MLR	pCR prediction accuracy rates and AUC values; ANN: 88%, 0.84 KNN: 80%, 0.74 SVM: 71%, 0.76 NBC: 80%, 0.63 MLR: 83%, 0.77.

ADC: Apparent diffusion coefficient; ANN: Artificial neural network; AUC: Area under the curve; BN: Bayesian network; CNN: Convolutional neural network; CRT: Chemoradiotherapy; CT: Computed tomography; DCE: Dynamic contrast-enhanced; DNN: Deep neural network; DWI: Diffusion-weighted imaging; KNN: K-nearest neighbors; LR: Linear regression; MLR: Multiple logistic regression; MRI: Magnetic resonance imaging; NBC: Naïve bayes classifier; NN: Neural network; pCR: Pathological complete response; RFC: Random forest classifier; SVM: Support vector machine.