Multi‐scale consistent self‐training network for semi‐supervised orbital tumor segmentation

Abstract

PurposeSegmentation of orbital tumors in CT images is of great significance for orbital tumor diagnosis, which is one of the most prevalent diseases of the eye. However, the large variety of tumor sizes and shapes makes the segmentation task very challenging, especially when the available annotation data is limited.MethodsTo this end, in this paper, we propose a multi‐scale consistent self‐training network (MSCINet) for semi‐supervised orbital tumor segmentation. Specifically, we exploit the semantic‐invariance features by enforcing the consistency between the predictions of different scales of the same image to make the model more robust to size variation. Moreover, we incorporate a new self‐training strategy, which adopts iterative training with an uncertainty filtering mechanism to filter the pseudo‐labels generated by the model, to eliminate the accumulation of pseudo‐label error predictions and increase the generalization of the model.ResultsFor evaluation, we have built two datasets, the orbital tumor binary segmentation dataset (Orbtum‐B) and the orbital multi‐organ segmentation dataset (Orbtum‐M). Experimental results on these two datasets show that our proposed method can both achieve state‐of‐the‐art performance. In our datasets, there are a total of 55 patients containing 602 2D images.ConclusionIn this paper, we develop a new semi‐supervised segmentation method for orbital tumors, which is designed for the characteristics of orbital tumors and exhibits excellent performance compared to previous semi‐supervised algorithms.