Predicting Tertiary Lymphoid Structures in Head and Neck Contrast-Enhanced CT Images using a 3D CNN

Squamous cell carcinoma of the head and neck is currently the eighth most common cancer worldwide. In recent years, medical researchers have proposed a promising immune checkpoint blockade treatment to treat the disease, however, only a small number of patients with advanced head and neck squamous cell carcinoma (about 13%) can benefit from immune checkpoint blockade therapy. Therefore, assessing the patient’s response to immune checkpoint blockade before treatment can help develop a treatment strategy. Tertiary lymphoid structures (TLSs) are complex structures that often appear around tumors, and their presence suggests strong immunoactivity and sensitivity to immunotherapy. Therefore, the presence or absence of TLSs is a valid indicator of the patient’s response to immune checkpoint blockade before surgery. At present, the detection methods for TLSs are all postoperative pathological examinations, but their speed is slow and aggressive. However, few studies have employed non-invasive methods to detect and assess the TLS status of cancer before surgery. In this paper, we propose a 3D convolutional neural network UDNet based on the original U-Net and Dense-Net, which can determine the presence of TLSs by using the patient’s contrast-enhanced CT image. At last, we verify the ability of the model to predict TLSs by comparing the predicting results of the model and the predicting results of three experienced clinicians. The results show that the accuracy of UDNet (72.7%) is much higher than the average accuracy (42.4%) predicted by the three experienced clinicians.