Accurate and automatic segmentation of medical images is a crucial step for clinical diagnosis and analysis. The convolutional neural network (CNN) approaches based on the U-shape structure have achieved remarkable performances in many different medical image segmentation tasks. However, the context information extraction capability of single stage is insufficient in this structure, due to the problems such as imbalanced class and blurred boundary. In this paper, we propose a novel Context Pyramid Fusion Network (named CPFNet) by combining two pyramidal modules to fuse global/multi-scale context information. Based on the U-shape structure, we first design multiple global pyramid guidance (GPG) modules between the encoder and the decoder, aiming at providing different levels of global context information for the decoder by reconstructing skip-connection. We further design a scale-aware pyramid fusion (SAPF) module to dynamically fuse multi-scale context information in high-level features. These two pyramidal modules can exploit and fuse rich context information progressively. Experimental results show that our proposed method is very competitive with other state-of-the-art methods on four different challenging tasks, including skin lesion segmentation, retinal linear lesion segmentation, multi-class segmentation of thoracic organs at risk and multi-class segmentation of retinal edema lesions.

Speckle noise in optical coherence tomography (OCT) impairs both the visual quality and the performance of automatic analysis. Edge preservation is an important issue for speckle reduction. In this paper, we propose an end-to-end framework for simultaneous speckle reduction and contrast enhancement for retinal OCT images based on the conditional generative adversarial network (cGAN). The edge loss function is added to the final objective so that the model is sensitive to the edge-related details. We also propose a novel method for obtaining clean images for training from outputs of commercial OCT scanners. The results show that the overall denoising performance of the proposed method is better than other traditional methods and deep learning methods. The proposed model also has good generalization ability and is capable of despeckling different types of retinal OCT images.

Liver segmentation is still a challenging task in medical image processing area due to the complexity of the liver's anatomy, low contrast with adjacent organs, and presence of pathologies. This investigation was used to develop and validate an automated method to segment livers in CT images. The proposed framework consists of three steps: 1) preprocessing; 2) initialization; and 3) segmentation. In the first step, a statistical shape model is constructed based on the principal component analysis and the input image is smoothed using curvature anisotropic diffusion filtering. In the second step, the mean shape model is moved using thresholding and Euclidean distance transformation to obtain a coarse position in a test image, and then the initial mesh is locally and iteratively deformed to the coarse boundary, which is constrained to stay close to a subspace of shapes describing the anatomical variability. Finally, in order to accurately detect the liver surface, deformable graph cut was proposed, which effectively integrates the properties and inter-relationship of the input images and initialized surface. The proposed method was evaluated on 50 CT scan images, which are publicly available in two databases Sliver07 and 3Dircadb. The experimental results showed that the proposed method was effective and accurate for detection of the liver surface.

Automated retinal layer segmentation of optical coherence tomography (OCT) images has been successful for normal eyes but becomes challenging for eyes with retinal diseases if the retinal morphology experiences critical changes. We propose a method to automatically segment the retinal layers in 3-D OCT data with serous retinal pigment epithelial detachments (PED), which is a prominent feature of many chorioretinal disease processes. The proposed framework consists of the following steps: fast denoising and B-scan alignment, multi-resolution graph search based surface detection, PED region detection and surface correction above the PED region. The proposed technique was evaluated on a dataset with OCT images from 20 subjects diagnosed with PED. The experimental results showed the following. 1) The overall mean unsigned border positioning error for layer segmentation is 7.87±3.36 μm, and is comparable to the mean inter-observer variability ( 7.81±2.56 μm). 2) The true positive volume fraction (TPVF), false positive volume fraction (FPVF) and positive predicative value (PPV) for PED volume segmentation are 87.1%, 0.37%, and 81.2%, respectively. 3) The average running time is 220 s for OCT data of 512 × 64 × 480 voxels.

Optical Coherence Tomography (OCT) is becoming one of the most important modalities for the noninvasive assessment of retinal eye diseases. As the number of acquired OCT volumes increases, automating the OCT image analysis is becoming increasingly relevant. In this paper, we propose a surrogate-assisted classification method to classify retinal OCT images automatically based on convolutional neural networks (CNNs). Image denoising is first performed to reduce the noise. Thresholding and morphological dilation are applied to extract the masks. The denoised images and the masks are then employed to generate a lot of surrogate images, which are used to train the CNN model. Finally, The prediction for a test image is determined by the average of the outputs from the trained CNN model on the surrogate images. The proposed method has been evaluated on different databases. The results (AUC of 0.9783 in the local database and AUC of 0.9856 in the Duke database) show that the proposed method is a very promising tool for classifying the retinal OCT images automatically.

Learning how to capture long-range dependencies and restore spatial information of down-sampled feature maps are the basis of the encoder-decoder structure networks in medical image segmentation. U-Net based methods use feature fusion to alleviate these two problems, but the global feature extraction ability and spatial information recovery ability of U-Net are still insufficient. In this paper, we propose a Global Feature Reconstruction (GFR) module to efficiently capture global context features and a Local Feature Reconstruction (LFR) module to dynamically up-sample features, respectively. For the GFR module, we first extract the global features with category representation from the feature map, then use the different level global features to reconstruct features at each location. The GFR module establishes a connection for each pair of feature elements in the entire space from a global perspective and transfers semantic information from the deep layers to the shallow layers. For the LFR module, we use low-level feature maps to guide the up-sampling process of high-level feature maps. Specifically, we use local neighborhoods to reconstruct features to achieve the transfer of spatial information. Based on the encoder-decoder architecture, we propose a Global and Local Feature Reconstruction Network (GLFRNet), in which the GFR modules are applied as skip connections and the LFR modules constitute the decoder path. The proposed GLFRNet is applied to four different medical image segmentation tasks and achieves state-of-the-art performance.