Deep learning segmentation of Primary Sjögren's syndrome affected salivary glands from ultrasonography images

Abstract

Salivary gland ultrasonography (SGUS) has proven to be a promising tool for diagnosing various diseases manifesting with abnormalities in salivary glands (SGs), including primary Sjögren's syndrome (pSS). At present, the major obstacle for establishing SUGS as a standardized tool for pSS diagnosis is its low inter/intra observer reliability. The aim of this study was to address this problem by proposing a robust deep learning-based solution for the automated segmentation of SGUS images. For these purposes, four architectures were considered: a fully convolutional neural network, fully convolutional "DenseNets" (FCN-DenseNet) network, U-Net, and LinkNet. During the course of the study, the growing HarmonicSS cohort included 1184 annotated SGUS images. Accordingly, the algorithms were trained using a transfer learning approach. With regard to the intersection-over-union (IoU), the top-performing FCN-DenseNet (IoU = 0.85) network showed a considerable margin above the inter-observer agreement (IoU = 0.76) and slightly above the intra-observer agreement (IoU = 0.84) between clinical experts. Considering its accuracy and speed (24.5 frames per second), it was concluded that the FCN-DenseNet could have wider applications in clinical practice. Further work on the topic will consider the integration of methods for pSS scoring, with the end goal of establishing SGUS as an effective noninvasive pSS diagnostic tool. To aid this progress, we created inference (frozen models) files for the developed models, and made them publicly available.

Keywords: Deep learning; HarmonicSS project; Salivary glands; Segmentation; Sjögren's syndrome.