Deep learning based medical image segmentation models usually require large datasets with high-quality dense segmentations to train, which are very time-consuming and expensive to prepare. One way to tackle this challenge is using the mixed-supervised learning framework, in which only a part of data is densely annotated with segmentation label and the rest is weakly labeled with bounding boxes. The model is trained jointly in a multi-task learning setting. In this paper, we propose Mixed-Supervised Dual-Network (MSDN), a novel architecture which consists of two separate networks for the detection and segmentation tasks respectively, and a series of connection modules between the layers of the two networks. These connection modules are used to transfer useful information from the auxiliary detection task to help the segmentation task. We propose to use a recent technique called Squeeze and Excitation in the connection module to boost the transfer. We conduct experiments on two medical image segmentation datasets. The proposed MSDN model outperforms multiple baselines.
BACKGROUND AND PURPOSE: MR imaging is not routinely used to image the extracranial facial nerve. The purpose of this study was to determine the extent to which this nerve can be visualized with a CISS sequence and to determine the feasibility of using that sequence for locating the nerve relative to tumor.
MATERIALS AND METHODS:Thirty-two facial nerves in 16 healthy subjects and 4 facial nerves in 4 subjects with parotid gland tumors were imaged with an axial CISS sequence protocol that included 0.8-mm isotropic voxels on a 3T MR imaging system with a 64-channel head/neck coil. Four observers independently segmented the 32 healthy subject nerves. Segmentations were compared by calculating average Hausdorff distance values and Dice similarity coefficients.
RESULTS:The primary bifurcation of the extracranial facial nerve into the superior temporofacial and inferior cervicofacial trunks was visible on all 128 segmentations. The mean of the average Hausdorff distances was 1.2 mm (range, 0.3-4.6 mm). Dice coefficients ranged from 0.40 to 0.82. The relative position of the facial nerve to the tumor could be inferred in all 4 tumor cases.
CONCLUSIONS:The facial nerve can be seen on CISS images from the stylomastoid foramen to the temporofacial and cervicofacial trunks, proximal to the parotid plexus. Use of a CISS protocol is feasible in the clinical setting to determine the location of the facial nerve relative to tumor.
The foreign body response to implanted materials often complicates the functionality of sensitive biomedical devices. For cochlear implants, this response can reduce device performance, battery life and preservation of residual acoustic hearing. As a permanent and passive solution to the foreign body response, this work investigates ultra-low-fouling poly(carboxybetaine methacrylate) (pCBMA) thin film hydrogels that are simultaneously photo-grafted and photo-polymerized onto polydimethylsiloxane (PDMS). The cellular anti-fouling properties of these coatings are robustly maintained even after six-months subcutaneous incubation and over a broad range of cross-linker compositions. On pCBMA-coated PDMS sheets implanted subcutaneously, capsule thickness and inflammation are reduced significantly in comparison to uncoated PDMS or coatings of polymerized poly(ethylene glycol dimethacrylate) (pPEGDMA) or poly(hydroxyethyl methacrylate) (pHEMA). Further, capsule thickness is reduced over a wide range of pCBMA cross-linker compositions. On cochlear implant electrode arrays implanted subcutaneously for one year, the coating bridges over the exposed platinum electrodes and dramatically reduces the capsule thickness over the entire implant. Coated cochlear implant electrode arrays could therefore lead to persistent improved performance and reduced risk of residual hearing loss. More generally, the in vivo anti-fibrotic properties of pCBMA coatings also demonstrate potential to mitigate the fibrotic response on a variety of sensing/stimulating implants.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.