Browsing by Author "Jagersand, Martin"
Now showing 1 - 3 of 3
Results Per Page
- ItemA deep level set method for image segmentation(2017) Tang, Min; Valipour, Sepehr; Zhang, Zichen; Cobzas, Dana; Jagersand, MartinThis paper proposes a novel image segmentation approach that integrates fully convolutional networks (FCNs) with a level set model. Compared with a FCN, the integrated method can incorporate smoothing and prior information to achieve an accurate segmentation. Furthermore, different than using the level set model as a post-processing tool, we integrate it into the training phase to fine-tune the FCN. This allows the use of unlabeled data during training in a semi-supervised setting. Using two types of medical imaging data (liver CT and left ventricle MRI data), we show that the integrated method achieves good performance even when little training data is available, outperforming the FCN or the level set model alone.
- ItemEnd-to-end detection-segmentation network with ROI convolution(2018) Zhang, Zichen; Tang, Min; Cobzas, Dana; Zonoobi, Dornoosh; Jagersand, Martin; Jaremko, Jacob L.We propose an end-to-end neural network that improves the segmentation accuracy of fully convolutional networks by incorporating a localization unit. This network performs object localization first, which is then used as a cue to guide the training of the segmentation network. We test the proposed method on a segmentation task of small objects on a clinical dataset of ultrasound images. We show that by jointly learning for detection and segmentation, the proposed network is able to improve the segmentation accuracy compared to only learning for segmentation.
- ItemSegmentation-by-detection: a cascade network for volumetric medical image segmentation(2018) Tang, Min; Zhang, Zichen; Cobzas, Dana; Jagersand, Martin; Jaremko, Jacob L.We propose an attention mechanism for 3D medical image segmentation. The method, named segmentation-by-detection, is a cascade of a detection module followed by a segmentation module. The detection module enables a region of interest to come to attention and produces a set of object region candidates which are further used as an attention model. Rather than dealing with the entire volume, the segmentation module distills the information from the potential region. This scheme is an efficient solution for volumetric data as it reduces the influence of the surrounding noise. This is especially important for medical data with low signal-to-noise ratio. Experimental results on 3D ultrasound data of the femoral head shows superiority of the proposed method when compared with a standard fully convolutional network like the U-Net.