3D reconstruction of the uterus and automatic segmentation of the uterine cavity on 3D magnetic resonance imaging: A preliminary study

Abstract

Purpose: To determine the differences in 3D shape features between septate uterus (SU) and normal uterus and to train a network to automatically delineate uterine cavity on 3D magnetic resonance imaging (MRI). Methods: A total of 43 patients (22 cases of partial septate uterus and 21 cases of complete septate uterus) were included in the experimental group. Nine volunteers were recruited as a control group. The uterine cavity (UC), myometrium (UM), and cervical canal of the uterus were segmented manually using ITK-SNAP software. The three-dimensional shape features of the UC and UM were extracted by using PyRadiomics. The recurrent saliency transformation network (RSTN) method was used to segment the UC. Results: The values of four 3D shape features were significantly lower in the control group than in the partial septate group and the complete septate group, while the values of two features were significantly higher (p < 0.05). The UCs of the three groups were significantly different in terms of flatness and sphericity. The values of six features were significantly lower in the UMs of the control group than in those of the partial septate group and the complete septate group (p < 0.05). After the deep learning networks were trained, the Dice similarity coefficient (DSC) scores of the four folds for different thresholds were all over 80 %. The average volume ratio between predictions and manual segmentation was 101.2 %. Conclusions: Based on 3D reconstruction, 3D shape features can be used to comprehensively evaluate septate uterus and provide a reference for subsequent research. The UC can be automatically segmented on 3D MRI using the RSTN method.

Keywords

• Deep learning
• Magnetic resonance imaging
• Septate uterus
• 3D reconstruction
• Automatic segmentation