Globally optimal OCT surface segmentation using a constrained IPM optimization.

Segmentation of multiple surfaces in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak boundaries, varying layer thicknesses, and mutual influence between adjacent surfaces. The traditional graph-based optimal surface segmentation method has proven its effectiveness with its ability to capture various surface priors in a uniform graph model. However, its efficacy heavily relies on handcrafted features that are used to define the surface cost for the "goodness" of a surface. Recently, deep learning (DL) is emerging as a powerful tool for medical image segmentation thanks to its superior feature learning capability. Unfortunately, due to the scarcity of training data in medical imaging, it is nontrivial for DL networks to implicitly learn the global structure of the target surfaces, including surface interactions. This study proposes to parameterize the surface cost functions in the graph model and leverage DL to learn those parameters. The multiple optimal surfaces are then simultaneously detected by minimizing the total surface cost while explicitly enforcing the mutual surface interaction constraints. The optimization problem is solved by the primal-dual interior-point method (IPM), which can be implemented by a layer of neural networks, enabling efficient end-to-end training of the whole network. Experiments on spectral-domain optical coherence tomography (SD-OCT) retinal layer segmentation demonstrated promising segmentation results with sub-pixel accuracy.

Simultaneous cosegmentation of tumors in PET-CT images using deep fully convolutional networks.

PURPOSE: To investigate the use and efficiency of 3-D deep learning, fully convolutional networks (DFCN) for simultaneous tumor cosegmentation on dual-modality nonsmall cell lung cancer (NSCLC) and positron emission tomography (PET)-computed tomography (CT) images. METHODS: We used DFCN cosegmentation for NSCLC tumors in PET-CT images, considering both the CT and PET information. The proposed DFCN-based cosegmentation method consists of two coupled three-dimensional (3D)-UNets with an encoder-decoder architecture, which can communicate with the other in order to share complementary information between PET and CT. The weighted average sensitivity and positive predictive values denoted as Scores, dice similarity coefficients (DSCs), and the average symmetric surface distances were used to assess the performance of the proposed approach on 60 pairs of PET/CTs. A Simultaneous Truth and Performance Level Estimation Algorithm (STAPLE) of 3 expert physicians' delineations were used as a reference. The proposed DFCN framework was compared to 3 graph-based cosegmentation methods. RESULTS: Strong agreement was observed when using the STAPLE references for the proposed DFCN cosegmentation on the PET-CT images. The average DSCs on CT and PET are 0.861 ± 0.037 and 0.828 ± 0.087, respectively, using DFCN, compared to 0.638 ± 0.165 and 0.643 ± 0.141, respectively, when using the graph-based cosegmentation method. The proposed DFCN cosegmentation using both PET and CT also outperforms the deep learning method using either PET or CT alone. CONCLUSIONS: The proposed DFCN cosegmentation is able to outperform existing graph-based segmentation methods. The proposed DFCN cosegmentation shows promise for further integration with quantitative multimodality imaging tools in clinical trials.

Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images.

Automated segmentation of object boundaries or surfaces is crucial for quantitative image analysis in numerous biomedical applications. For example, retinal surfaces in optical coherence tomography (OCT) images play a vital role in the diagnosis and management of retinal diseases. Recently, graph based surface segmentation and contour modeling have been developed and optimized for various surface segmentation tasks. These methods require expertly designed, application specific transforms, including cost functions, constraints and model parameters. However, deep learning based methods are able to directly learn the model and features from training data. In this paper, we propose a convolutional neural network (CNN) based framework to segment multiple surfaces simultaneously. We demonstrate the application of the proposed method by training a single CNN to segment three retinal surfaces in two types of OCT images - normal retinas and retinas affected by intermediate age-related macular degeneration (AMD). The trained network directly infers the segmentations for each B-scan in one pass. The proposed method was validated on 50 retinal OCT volumes (3000 B-scans) including 25 normal and 25 intermediate AMD subjects. Our experiment demonstrated statistically significant improvement of segmentation accuracy compared to the optimal surface segmentation method with convex priors (OSCS) and two deep learning based UNET methods for both types of data. The average computation time for segmenting an entire OCT volume (consisting of 60 B-scans each) for the proposed method was 12.3 seconds, demonstrating low computation costs and higher performance compared to the graph based optimal surface segmentation and UNET based methods.

IMPROVING TUMOR CO-SEGMENTATION ON PET-CT IMAGES WITH 3D CO-MATTING.

Positron emission tomography and computed tomography (PET-CT) plays a critically important role in modern cancer therapy. In this paper, we focus on automated tumor delineation on PET-CT image pairs. Inspired by co-segmentation model, we develop a novel 3D image co-matting technique making use of the inner-modality information of PET and CT for matting. The obtained co-matting results are then incorporated in the graph-cut based PET-CT co-segmentation framework. Our comparative experiments on 32 PET-CT scan pairs of lung cancer patients demonstrate that the proposed 3D image co-matting technique can significantly improve the quality of cost images for the co-segmentation, resulting in highly accurate tumor segmentation on both PET and CT scan pairs.

3D FULLY CONVOLUTIONAL NETWORKS FOR CO-SEGMENTATION OF TUMORS ON PET-CT IMAGES.

Positron emission tomography and computed tomography (PET-CT) dual-modality imaging provides critical diagnostic information in modern cancer diagnosis and therapy. Automated accurate tumor delineation is essentially important in computer-assisted tumor reading and interpretation based on PET-CT. In this paper, we propose a novel approach for the segmentation of lung tumors that combines the powerful fully convolutional networks (FCN) based semantic segmentation framework (3D-UNet) and the graph cut based co-segmentation model. First, two separate deep UNets are trained on PET and CT, separately, to learn high level discriminative features to generate tumor/non-tumor masks and probability maps for PET and CT images. Then, the two probability maps on PET and CT are further simultaneously employed in a graph cut based co-segmentation model to produce the final tumor segmentation results. Comparative experiments on 32 PET-CT scans of lung cancer patients demonstrate the effectiveness of our method.