Deep Learning for Predicting Distant Metastasis in Patients with Nasopharyngeal Carcinoma Based on Pre-Radiotherapy Magnetic Resonance Imaging

Abstract

Importance: Accurate pre-treatment prediction of distant metastasis in patients with Nasopharyngeal Carcinoma (NPC) enables the implementation of appropriate treatment strategies for high-risk individuals. Purpose: To develop and assess a Convolutional Neural Network (CNN) model using pre-therapy Magnetic Resonance (MR) imaging to predict distant metastasis in NPC patients. Methods: We retrospectively reviewed data of 441 pathologically diagnosed NPC patients who underwent complete radiotherapy and chemotherapy at Renmin Hospital of Wuhan University (Hubei, China) between February 2012 and March 2018. Using Adobe Photoshop, an experienced radiologist segmented MR images with rectangular regions of interest. To develop an accurate model according to the primary tumour, Cervical Metastatic Lymph Node (CMLN), the largest area of invasion of the primary tumour, and image segmentation methods, we constructed intratumoural and intra-peritumoural datasets that were used for training and test of the transfer learning models. Each model’s precision was assessed according to its receiver operating characteristic curve and accuracy. Generated high-risk-related Grad-Cams demonstrated how the model captured the image features and further verified its reliability. Results: Among the four models, all intra-peritumoural datasets performed better than the corresponding intratumoural datasets, with the CMLN intra-peritumoural dataset exhibiting the best performance (average area under the curves (AUCs) = 0.88). There was no significant difference between average AUCs of the Max and NPC tumour datasets. AUCs of the eight datasets for the four models were higher than those of the Tumour-Node-Metastasis staging system (AUC=0.67). In most datasets, the xception model had higher AUCs than other models. The efficientnet-b0 and xception models efficiently extracted high-risk features. Conclusion: The CNN model predicted distant metastasis in NPC patients with high accuracy. Compared to the primary tumour, the CMLN better predicted distant metastasis. In addition to intratumoural data, peritumoural information can facilitate the prediction of distant metastasis. With a larger sample size, datasets of the largest areas of tumour invasion may achieve meaningful accuracy. Among the models, xception had the best overall performance.

Deep Learning Techniques and Imaging in Otorhinolaryngology—A State-of-the-Art Review

“…From MRI-based applications focusing on the differ-ential diagnosis between benign and malignant nasopharyngeal diseases [26,27] to the automatic detection of pathological lymph nodes and assessment of the peritumoral area in nasopharyngeal carcinoma, DL algorithms can significantly assist in disease prognosis and treatment planning [28]. Interestingly, peritumoral information, especially the largest areas of tumor invasion, has been shown to provide valuable insights for distant metastasis prediction in individuals with nasopharyngeal carcinoma [29].…”

“…CNN assessing pre-treatment MRI scans to predict the possibility of distant metastases in individuals with nasopharyngeal carcinoma can also be useful, since the occurrence of a metastasis is the main reason for radiotherapy failure in this patient group. Predicting the high risk for distant metastasis in a patient can lead to a more aggressive treatment approach [29]. Moreover, pre-therapy MRI scans have been used in patients with advanced (T3N1M0) nasopharyngeal carcinoma to guide the clinicians in deciding between induction chemotherapy plus concurrent chemoradiotherapy or concurrent chemoradiotherapy alone [43].…”

Deep learning in MRI‐guided radiation therapy: A systematic review

“…achieves better results in predicting adverse effects by combining hand‐crafted radiomics and deep learning features. 15 Other notable papers include Huisman et al., which uses an FCN suggesting that radiation therapy accelerates brain aging by 2.78 times, 143 Hua et al., which predicts distant metastases with an AUC of 0.88, 144 and Jalalifar et al., which achieves excellent results by feeding in clinical and deep learning features into an LSTM model 145 An additional study by Jalalifar et al. finds the best performance for local treatment response prediction using a hybrid CNN‐transformer architecture when compared to other methods.…”

“…Hua et al, which predicts distant metastases with an AUC of 0.88,144 and Jalalifar et al, which achieves excellent results by feeding in clinical and deep learning features into an LSTM model145 An additional study by Jalalifar et al finds the best performance for local treatment response prediction using a hybrid CNN-transformer architecture when compared to other methods. Residual connections and algorithmic hyperparameter selection further improve results 146.…”