Key points:
- Accurate preoperative prediction of the CRS type is necessary for
predicting postoperative outcomes and administering personalized
treatment
- We combined semantic segmentation with classification network for
sinus region segmentation and differentiating between ECRS and NECRS
on preoperative CT
- The segmentation model could accurately segment the sinus region in CT
images
- The classification model could effectively distinguish between
patients with ECRS and NECRS based on preoperative sinus CT images
- Labeling each patient to build a dataset for classification may be
more reliable than labeling each medical image.