Search

Nasopharyngeal carcinoma (NPC) is prevalent in certain areas, such as South China, Southeast Asia, and the Middle East. Radiation therapy is the most efficient means to treat this malignant tumor. Positron emission tomography–computed tomography (PET-CT) is a suitable imaging technique to assess this disease. However, the large amount of data produced by numerous patients causes traditional manual delineation of tumor contour, a basic step for radiotherapy, to become time-consuming and labor-intensive. Thus, the demand for automatic and credible segmentation methods to alleviate the workload of radiologists is increasing. This paper presents a method that uses fully convolutional networks with auxiliary paths to achieve automatic segmentation of NPC on PET-CT images. This work is the first to segment NPC using dual-modality PET-CT images. This technique is identical to what is used in clinical practice and offers considerable convenience for subsequent radiotherapy. The deep supervision introduced by auxiliary paths can explicitly guide the training of lower layers, thus enabling these layers to learn more representative features and improve the discriminative capability of the model. Results of threefold cross-validation with a mean dice score of 87.47% demonstrate the efficiency and robustness of the proposed method. The method remarkably outperforms state-of-the-art methods in NPC segmentation. We also validated by experiments that the registration process among different subjects and the auxiliary paths strategy are considerably useful techniques for learning discriminative features and improving segmentation performance. [ABSTRACT FROM AUTHOR]

Background: Lymph node metastasis of rectal neuroendocrine tumors (RNETs) predicts poor prognosis. However, the assessment of lymph node metastasis remains a challenge. It has been reported that 68Ga-DOTANOC and 18F-FDG PET-CT scans could be employed in the work-up of rectal neuroendocrine tumors (RNETs). This study aimed to assess both tracers' ability to identify primary tumors and lymph node (LN) metastasis in RNETs., Methods: A total of 537 patients with RNETs were enrolled from January 2014 to January 2021. Both 68Ga-DOTANOC and 18F-FDG PET-CT scans were used to evaluate primary tumors and LN group metastasis. PET images were evaluated through visual and semiquantitative assessment. Receiver Operating Characteristics (ROC) curve analysis was used to investigate the performance of SUVmax of 68Ga-DOTANOC and 18F-FDG PET in predicting LN group metastasis., Results: Fifty-two patients with preoperative 68Ga-DOTANOC with 18F-FDG PET-CT scans underwent endoscopic biopsy or dissection of the primary tumor, while 11 patients underwent rectal surgery together with regional LN dissection. For primary tumors, 68Ga-DOTANOC had a sensitivity of 89.58% and a positive predictive value (PPV) of 95.56% through visual assessment, while 18F-FDG PET-CT showed 77.08% sensitivity and 97.37% PPV. For the prediction of LN group metastasis, 68Ga-DOTANOC PET-CT had 77.78% sensitivity and 91.67% specificity, while 18F-FDG PET-CT had 38.89% sensitivity and 100% specificity according to visual assessment. The area under the ROC curves (AUC) for 68Ga-DOTANOC PET/CT was 0.852 (95%CI:0.723-0.981) with an optimal SUVmax cut-off value of 2.25, while the AUC for 18F-FDG PET were 0.664 (95%CI:0.415-0.799) with an optimal SUVmax cut-off value of 1.05., Conclusions: This study showed that 68Ga-DOTANOC PET-CT was a promising tool for detecting LN metastasis in RNETs with high sensitivity and specificity in visual assessment and semiquantitative assessment, which was better than 18F-FDG PET-CT., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Zhou, Wang, Zhang, Wu, Li and Wang.)