Head and Neck Tumor Segmentation of MRI from Pre- and Mid-radiotherapy with Pre-training, Data Augmentation and Dual Flow UNet

TL;DR

This paper presents a comprehensive study on head and neck tumor segmentation in MRI images before and during radiotherapy, employing pre-training, data augmentation, and a novel dual-encoder UNet architecture to improve accuracy.

Contribution

The study introduces a new dual-encoder UNet architecture for mid-RT images and evaluates the effects of pre-training and data augmentation on segmentation performance.

Findings

Achieved 82.38% DSC for pre-RT segmentation

Achieved 72.53% DSC for mid-RT segmentation

Demonstrated the effectiveness of pre-training and data augmentation

Abstract

Head and neck tumors and metastatic lymph nodes are crucial for treatment planning and prognostic analysis. Accurate segmentation and quantitative analysis of these structures require pixel-level annotation, making automated segmentation techniques essential for the diagnosis and treatment of head and neck cancer. In this study, we investigated the effects of multiple strategies on the segmentation of pre-radiotherapy (pre-RT) and mid-radiotherapy (mid-RT) images. For the segmentation of pre-RT images, we utilized: 1) a fully supervised learning approach, and 2) the same approach enhanced with pre-trained weights and the MixUp data augmentation technique. For mid-RT images, we introduced a novel computational-friendly network architecture that features separate encoders for mid-RT images and registered pre-RT images with their labels. The mid-RT encoder branch integrates information from pre-RT images and labels progressively during the forward propagation. We selected the highest-performing model from each fold and used their predictions to create an ensemble average for inference. In the final test, our models achieved a segmentation performance of 82.38% for pre-RT and 72.53% for mid-RT on aggregated Dice Similarity Coefficient (DSC) as HiLab. Our code is available at https://github.com/WltyBY/HNTS-MRG2024_train_code.