Fully Convolutional Boundary Regression for Retina OCT Segmentation

He, Yufan; Carass, Aaron; Liu, Yihao; Jedynak, Bruno; Solomon, Sharon D.; Saidha, Shiv; Calabresi, Peter A.; Prince, Jerry L.

doi:10.1007/978-3-030-32239-7_14

Cited by 59 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OCT is used for the diagnosis of different ocular diseases, such as age-related macular degeneration (AMD), retinal vein occlusion, and diabetic macular edema [338]. U-net has been used on OCT for segmentation of retinal layers [339]- [341], blood vessels [342], fluid regions [343], [344], and Drusen [345]. Other uncommon applications are segmentation of blood vessels in digital subtraction angiography (DSA) [68], [346], [347], white matter tract segmentation in diffusion tensor imaging (DTI) [30], iris segmentation in iris imaging [37], tumor detection in mammograms [56], and capillary segmentation in nailfold capillaroscopy [348].…”

Section: H Other Modalitiesmentioning

confidence: 99%

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

U-net is an image segmentation technique developed primarily for image segmentation tasks. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities, from CT scans and MRI to Xrays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net's potential is still increasing, this narrative literature review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.

show abstract

Section: H Other Modalitiesmentioning

confidence: 99%

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Ronneberger et al [22] proposed the U-Net for the segmentation task in medical images. Due to the fast and effective training advantages, the U-Net and its variants, such as V-Net [23] for volume medical image segmentation, ReLayNet [24], He et al [25] and Kepp et al [26] for retinal layers and fluid segmentation, are the most commonly used networks in this filed. The network presented in this paper is inspired by ReLayNet [24].…”

Section: During the Diagnosis Andmentioning

confidence: 99%

The Segmentation of Retinal Layer and Fluid in SD-OCT Images Using Mutex Dice Loss Based Fully Convolutional Networks

Wei

Peng

2020

IEEE Access

View full text Add to dashboard Cite

Spectral domain optical coherence tomography (SD-OCT) is a non-invasive imaging modality for assessing retinal diseases, such as diabetic retinopathy (DR), which is one of the most prevalent diseases responsible for visual impairment and blindness in the world. The main manifestations of DR are retinal deformation and fluid masses, termed diabetic macular edema (DME), which is the primary biomarker for assessing and diagnosing diseases. In the clinic, ophthalmologists can manually segment retinal layers and fluids to get quantitative and diagnostic information, which is the basement of the final diagnosis. However, this manual segmentation is time-consuming and labor-intensive. To facilitate and promote it, researchers have proposed many automated methods, where most of them usually ignore the priorities in ophthalmology and just regard this task as a standard semantic segmentation task. In this study, we consider the priority of the mutex relationship among different layers and introduce it into the dice loss function to build a novel one, named mutex dice loss (MDL). Besides, we propose a novel fully convolutional network based on our proposed depth max pooling (DMP) to segment retinal layers and fluids in SD-OCT images. Experimental results of the proposed method on two public datasets demonstrate promising performance, which also shows the potential to help ophthalmologists in the diagnostic process of DR or other related diseases. INDEX TERMS Diabetic macular edema (DME), retinal layer segmentation, fully convolutional network, mutex dice loss.

show abstract

“…Common approaches to localization can be divided into two categories: regression-based and detection-based. Detection-based methods show superiority over regression-based methods and demonstrate impressive performance on a wide variety of tasks [51,43,49,16,24,18,26,21,41,27,40]. Probability maps (also referred to as heat maps) are predicted in detection-based methods to indicate the likelihood of the target position.…”

Section: Introductionmentioning

confidence: 99%

Localization with Sampling-Argmax

Li¹,

Chen²,

Shi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Soft-argmax operation is commonly adopted in detection-based methods to localize the target position in a differentiable manner. However, training the neural network with soft-argmax makes the shape of the probability map unconstrained. Consequently, the model lacks pixel-wise supervision through the map during training, leading to performance degradation. In this work, we propose sampling-argmax, a differentiable training method that imposes implicit constraints to the shape of the probability map by minimizing the expectation of the localization error. To approximate the expectation, we introduce a continuous formulation of the output distribution and develop a differentiable sampling process. The expectation can be approximated by calculating the average error of all samples drawn from the output distribution. We show that sampling-argmax can seamlessly replace the conventional soft-argmax operation on various localization tasks. Comprehensive experiments demonstrate the effectiveness and flexibility of the proposed method.Code is available at https://github.com/Jeff-sjtu/sampling-argmax.Prior work [37] attempts to shape the probability map by introducing hand-crafted regularizations. The variance regularization encourages the variance of the probability map to get close to the predefined variance. The Gaussian regularization forces the probability map to resemble a Gaussian distribution. We argue that these variants are overconstrained. The hand-crafted constraints are not 35th Conference on Neural Information Processing Systems (NeurIPS 2021),

show abstract

Fully Convolutional Boundary Regression for Retina OCT Segmentation

Cited by 59 publications

References 17 publications

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

The Segmentation of Retinal Layer and Fluid in SD-OCT Images Using Mutex Dice Loss Based Fully Convolutional Networks

Localization with Sampling-Argmax

Contact Info

Product

Resources

About