Automatic tumor segmentation and metachronous single-organ metastasis prediction of nasopharyngeal carcinoma patients based on multi-sequence magnetic resonance imaging

Abstract

Background: Distant metastases is the main failure mode of nasopharyngeal carcinoma. However, early prediction of distant metastases in NPC is extremely challenging. Deep learning has made great progress in recent years. Relying on the rich data features of radiomics and the advantages of deep learning in image representation and intelligent learning, this study intends to explore and construct the metachronous single-organ metastases (MSOM) based on multimodal magnetic resonance imaging.

Patients and methods: The magnetic resonance imaging data of 186 patients with nasopharyngeal carcinoma before treatment were collected, and the gross tumor volume (GTV) and metastatic lymph nodes (GTVln) prior to treatment were defined on T1WI, T2WI, and CE-T1WI. After image normalization, the deep learning platform Python (version 3.9.12) was used in Ubuntu 20.04.1 LTS to construct automatic tumor detection and the MSOM prediction model.

Results: There were 85 of 186 patients who had MSOM (including 32 liver metastases, 25 lung metastases, and 28 bone metastases). The median time to MSOM was 13 months after treatment (7-36 months). The patients were randomly assigned to the training set (N = 140) and validation set (N = 46). By comparison, we found that the overall performance of the automatic tumor detection model based on CE-T1WI was the best (6). The performance of automatic detection for primary tumor (GTV) and lymph node gross tumor volume (GTVln) based on the CE-T1WI model was better than that of models based on T1WI and T2WI (AP@0.5 is 59.6 and 55.6). The prediction model based on CE-T1WI for MSOM prediction achieved the best overall performance, and it obtained the largest AUC value (AUC = 0.733) in the validation set. The precision, recall, precision, and AUC of the prediction model based on CE-T1WI are 0.727, 0.533, 0.730, and 0.733 (95% CI 0.557-0.909), respectively. When clinical data were added to the deep learning prediction model, a better performance of the model could be obtained; the AUC of the integrated model based on T2WI, T1WI, and CE-T1WI were 0.719, 0.738, and 0.775, respectively. By comparing the 3-year survival of high-risk and low-risk patients based on the fusion model, we found that the 3-year DMFS of low and high MSOM risk patients were 95% and 11.4%, respectively (p < 0.001).

Conclusion: The intelligent prediction model based on magnetic resonance imaging alone or combined with clinical data achieves excellent performance in automatic tumor detection and MSOM prediction for NPC patients and is worthy of clinical application.

Keywords: automatic learning; intelligent prediction; metachronous single-organ metastases prediction; multimodal magnetic resonance imaging; nasopharyngeal carcinoma.

Figure 1

Workflow of deep learning and model building.

Figure 2

The visualization of detection model for one example slice in three channels. (A). Manually labeled GTV and GTVln on T2WI; (B) Automatically detected GTV and GTVln on T2WI; (C) Automatically detected GTV and GTVln on T1WI; (D) Automatically detected GTV and GTVln on CE-T1WI).

Figure 3

AUC of the prediction model based on multi-sequence MRI alone or integrated with clinical data. (A–C), AUC of the prediction model based on multisequence MRI. (A) AUC of the prediction model based on TIWI, (B) AUC of the prediction model based on T2WI, (C) AUC of the prediction model based on CE-T1WI. (D–F), AUC of the prediction model based on multi-sequence MRI and clinical data. (D) AUC of the prediction model based on TIWI and clinical data. (E) AUC of the prediction model based on T2WI and clinical data. (F) AUC of the prediction model based on CE-T1WI and clinical data).

Figure 4

Survival curve of patients with high and low MSOM risk. (A) Distant metastasis-free survival (DMFS) of patients in different risk groups according to the CE-T1WI-based model. (B) Overall survival (OS) of patients in different risk groups according to the CE-T1WI-based model. (C) Distant metastasis-free survival (DMFS) of patients in different risk groups according to integrated model. (D) Overall survival (OS) of patients in different risk groups according to the integrated model).