ESTRO 2022 - Abstract Book

S1399

Abstract book

ESTRO 2022

Conclusion In order to generate sCT from prostate MRI, the 2D+ Pix2Pix model allows to generate sCT with less image uncertainties than the 2D Pix2Pix model. The next step will be a dosimetric evaluation of sCTs generated by the 2D+ Pix2Pix model.

PO-1612 CNN-based multi-task learning for tumor segmentation and T-Stage classification in NPC MRI

J. peng 1

1 Fudan University Shanghai Cancer Center, Department of Radiation Oncology, Shanghai, China

Purpose or Objective Automatic tumor delineation has been one of the most popular topics in deep learning. T-Stage is determined by tumor size and tumor location, classification of which can help physicians to make treatment decision and predict patients’ prognosis. In recent years, multi-task deep learning has been widely used in many fields. It may get better results by integrating different types but related information. As far as we know, no attempt has been made to combine tumor segmentation and T-Stage classification. In this study, we aimed to find a CNN-based multi-task architecture to obtain results for both tumor segmentation and T-Stage classification. Materials and Methods Six-hundred-forty-four patients were enrolled in this study, each of which had 3 MR images with T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequence. The T-Stage (T0:181, T1:76, T2:140, T3:115, T4:132) was extracted from EMR system and reviewed by physician. Tumors were manually contoured on MR images. MR images were input into a supervised CNN to output both T-Stage classification and tumor segmentation. We analyzed three types of CNN architectures: DeepLab (figure 1(a)), Trival Unet (figure 1(b)) and Modified Unet (figure 1(c)). The first one was based on DeepLab V3 and the last two were based on the Unet. The difference between Trival Unet and Modified Unet was that in order to strengthen the connection between T-Stage classification and tumor segmenation, we feedback the prediction results of T-Stage classification to tumor segmenation in Modified Unet. Performance of CNN architecture was assessed by Dice coefficient (DSC) for segmentation task and accuracy for T-Stage classification.