End-to-End Deep-Learning-Based Diagnosis of Benign and Malignant Orbital Tumors on Computed Tomography Images.

Determining the nature of orbital tumors is challenging for current imaging interpretation methods, which hinders timely treatment. This study aimed to propose an end-to-end deep learning system to automatically diagnose orbital tumors. A multi-center dataset of 602 non-contrast-enhanced computed tomography (CT) images were prepared. After image annotation and preprocessing, the CT images were used to train and test the deep learning (DL) model for the following two stages: orbital tumor segmentation and classification. The performance on the testing set was compared with the assessment of three ophthalmologists. For tumor segmentation, the model achieved a satisfactory performance, with an average dice similarity coefficient of 0.89. The classification model had an accuracy of 86.96%, a sensitivity of 80.00%, and a specificity of 94.12%. The area under the receiver operating characteristics curve (AUC) of the 10-fold cross-validation ranged from 0.8439 to 0.9546. There was no significant difference on diagnostic performance of the DL-based system and three ophthalmologists (p > 0.05). The proposed end-to-end deep learning system could deliver accurate segmentation and diagnosis of orbital tumors based on noninvasive CT images. Its effectiveness and independence from human interaction allow the potential for tumor screening in the orbit and other parts of the body.

[The clinical analysis of cervical lymph node metastases from squamous cell carcinoma of the larynx and hypopharynx treated with total laryngectomy].

OBJECTIVE: To detect the distribution and characteristics of lymph nodes metastasis in patients of laryngeal and hypopharyngeal cancer. METHOD: A retrospective review of 129 patients who had radical neck dissection, including first recurrence in cervical lymph nodes after laryngectomy, was performed to analyze the cervical lymph node metastases of different types of laryngeal and hypopharyngeal cancer treated by total laryngectomy. RESULT: The patients of the hypopharyngeal and supraglottic cancer had a tendency of cervical lymph nodes metastasis in their early stage. The rate of the fusional lymph nodes was high in hypopharyngeal cancer, and so as to the rate of the positive lymph nodes in their level IV. In our study the percentage of the poor-differentiated squamous cell carcinoma was relatively high in hypopharyngeal and supraglottic cancer than in glottic cancer. And there was no statistical difference in stages of the primary tumour between groups of neck dissection with laryngectomy simultaneously and of first recurrence in lymph nodes after laryngectomy. CONCLUSION: The latent lymph nodes metastasis and preventive neck dissection should be considered in patients of hypopharyngeal and supraglottic cancer in or above stages of T2, especially in patients with poor-differentiated squamous cell carcinoma, though the sign of positive lymph nodes was not evident.