skip to main content

Title: 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.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Optics Express
Page Range / eLocation ID:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Multiple-surface segmentation in optical coherence tomography (OCT) images is a challenging problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning-based methods have been developed for this task and yield remarkable performance. Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for deep learning networks to learn the global structure of the target surfaces, including surface smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net for feature learning with a constrained differentiable dynamic programming module to achieve end-to-end learning for retina OCT surface segmentation to explicitly enforce surface smoothness. It effectively utilizes the feedback from the downstream model optimization module to guide feature learning, yielding better enforcement of global structures of the target surfaces. Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple sclerosis) OCT data sets for retinal layer segmentation demonstrated that the proposed method was able to achieve subvoxel accuracy on both datasets, with the mean absolute surface distance (MASD) errors of 1.88 ± 1.96μmand 2.75 ± 0.94μm, respectively, over all the segmented surfaces.

    more » « less
  2. null (Ed.)
    Abstract One of the core challenges in applying machine learning and artificial intelligence to medicine is the limited availability of annotated medical data. Unlike in other applications of machine learning, where an abundance of labeled data is available, the labeling and annotation of medical data and images require a major effort of manual work by expert clinicians who do not have the time to annotate manually. In this work, we propose a new deep learning technique (SLIVER-net), to predict clinical features from 3-dimensional volumes using a limited number of manually annotated examples. SLIVER-net is based on transfer learning, where we borrow information about the structure and parameters of the network from publicly available large datasets. Since public volume data are scarce, we use 2D images and account for the 3-dimensional structure using a novel deep learning method which tiles the volume scans, and then adds layers that leverage the 3D structure. In order to illustrate its utility, we apply SLIVER-net to predict risk factors for progression of age-related macular degeneration (AMD), a leading cause of blindness, from optical coherence tomography (OCT) volumes acquired from multiple sites. SLIVER-net successfully predicts these factors despite being trained with a relatively small number of annotated volumes (hundreds) and only dozens of positive training examples. Our empirical evaluation demonstrates that SLIVER-net significantly outperforms standard state-of-the-art deep learning techniques used for medical volumes, and its performance is generalizable as it was validated on an external testing set. In a direct comparison with a clinician panel, we find that SLIVER-net also outperforms junior specialists, and identifies AMD progression risk factors similarly to expert retina specialists. 
    more » « less
  3. Abstract Background

    Lung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin‐sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities.


    The standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error‐prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection.


    A robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI) dataset are used for training, validation, and testing.


    Using only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre‐defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions.


    A pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients.

    more » « less
  4. Abstract

    Optical coherence tomography (OCT) is widely used for biomedical imaging and clinical diagnosis. However, speckle noise is a key factor affecting OCT image quality. Here, we developed a custom generative adversarial network (GAN) to denoise OCT images. A speckle‐modulating OCT (SM‐OCT) was built to generate low speckle images to be used as the ground truth. In total, 210 000 SM‐OCT images were used for training and validating the neural network model, which we call SM‐GAN. The performance of the SM‐GAN method was further demonstrated using online benchmark retinal images, 3D OCT images acquired from human fingers and OCT videos of a beating fruit fly heart. The denoise performance of the SM‐GAN model was compared to traditional OCT denoising methods and other state‐of‐the‐art deep learning based denoise networks. We conclude that the SM‐GAN model presented here can effectively reduce speckle noise in OCT images and videos while maintaining spatial and temporal resolutions.

    more » « less
  5. Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance. 
    more » « less