A multi-perspective information aggregation network for automated T-staging detection of nasopharyngeal carcinoma

Abstract

Accurate T-staging is important when planning personalized radiotherapy. However, T-staging via manual slice-by-slice inspection is time-consuming while tumor sizes and shapes are heterogeneous, and junior physicians find such inspection challenging. With inspiration from oncological diagnostics, we developed a multi-perspective aggregation network that incorporated various diagnosis-oriented knowledge which allowed automated nasopharyngeal carcinoma T-staging detection (TSD Net). Specifically, our TSD Net was designed in multi-branch architecture, which can capture tumor size and shape information (basic knowledge), strongly correlated contextual features, and associations between the tumor and surrounding tissues. We defined the association between the tumor and surrounding tissues by a signed distance map (SDM) which can embed points and tumor contours in higher-dimensional spaces, yielding valuable information regarding the locations of tissue associations. TSD Net finally outputs a T1-T4 stage prediction by aggregating data from the three branches. We evaluated TSD Net by using the T1-weighted contrast-enhanced (T1CE) magnetic resonance imaging database of 320 patients in three-fold cross-validations manner. The results show that the proposed method achieves a mean area under the curve (AUC) as high as 87.95%. We also compared our method to traditional classifiers and a deep learning-based method. Our TSD Net is efficient and accurate and outperforms other methods.

A transformer-based multi-task deep learning model for simultaneous T-stage identification and segmentation of nasopharyngeal carcinoma

“…We hypothesize that integrating data from multiple sequences in future iterations of our multi-task model could further enhance its GTV contouring performance. In previous study focusing on T-stage prediction, a multi-perspective information aggregation framework demonstrated a slightly higher AUC (0.88 vs 0.85) for automatic T-staging in NPC than our multi-task model (34). However, it is important to note that this framework employed a multi-branch architecture with outputs from three parallel branches integrated through major voting, which may have contributed to its enhanced performance.…”

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

“…Tumor sizes and forms vary, making individual slice-by-slice screening for T-staging time intensive. Consequently, a multi-perspective aggregation network (TSD Net) has been created with ideas from oncological diagnostics that included different diagnosis-oriented knowledge and enabled automatic nasopharyngeal carcinoma T-staging identification [104].…”