Depthwise Separable Convolutional Neural Network Model for Intra-Retinal Cyst Segmentation

Girish, G. N.; Saikumar, Banoth; Roychowdhury, Sohini; Kothari, Abhishek; Rajan, Jeny

doi:10.1109/embc.2019.8857333

Cited by 18 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Venhuizen et al scored a 0.64 to segment the IRF fluids. Besides, Girish et al [20] used a modified U -net model with the use of depthwise separable convolution operations in the OPTIMA dataset, and the average DSC score is 0.74. The best DSC score of all networks belongs to the Deeplabv3+ Pa model, which scores 0.78 on the Topcon dataset.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Retinal Fluid Segmentation Using Ensembled 2-Dimensionally and 2.5-Dimensionally Deep Learning Networks

et al. 2020

View full text Add to dashboard Cite

Morphological changes related to different diseases that occur in the retina are currently extensively researched. Manual segmentation of retinal fluids is time-consuming and subject to variability, giving prominence to the demand for robust automatic segmentation methods. The standard in assessing the existence and mass of retinal fluids at present is through the optical coherence tomography (OCT) modality. In this study, semantic segmentation deep learning networks were examined in 2.5D and ensembled with 2D networks. This analysis aims to show how these networks can perform in-depth than using only a single B-scan and the effects of 2.5 patches when fitted to the deep networks. All experiments were evaluated using public data from the RETOUCH challenge as well as the OPTIMA challenge dataset and Duke dataset. The networks trained in 2.5D performed slightly better than 2D networks in all datasets. The average performance of the best network was 0.867, using the dice similarity coefficient score (DSC) metric on the RETOUCH dataset. On the DUKE dataset, Deeplabv3+ Pa outperformed other networks in this study with a dice score of 0.80. Experiments showed a more robust performance when networks were ensembled. Intraretinal fluid (IRF) was recognized better than other fluids with a DSC of 0.924. Deeplabv3+ Pa model outperformed all other networks with a p-value average of 0.03 on the RETOUCH challenge dataset. Methods used in this study to distinguish retinal disorders outperform human performance as well as showed competitive results to the teams who joined both challenges. Three consecutive B-scans, including partial depth information in training neural networks, were stacked as a single image built for more robust networks compared to providing only 2D information.INDEX TERMS 2.5D networks, deep learning, ensembled networks, retinal diseases, SD-OCT segmentation.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The ReLayNet model [19] scored the dice value of 0.81 using the DUKE dataset. Girish et al [20] used a modified U -net model with the use of depthwise separable convolution operations. Additionally, Gopinath and Sivaswamy [21] validated the proposed CNN model using three datasets, including the OPTIMA dataset.…”

Section: Related Workmentioning

confidence: 99%

Retinal Fluid Segmentation Using Ensembled 2-Dimensionally and 2.5-Dimensionally Deep Learning Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The variance over mean for the RPs (Φ Π ) captures the relative dis-agreeability between each other in (7). The mean IOU between the RPs and the jth target label can then be evaluated as µ I (Π,T j ) using (10), such that a higher value implies a good target label T j .…”

Section: Mathematical Frameworkmentioning

confidence: 99%

“…The OPTIMA cyst segmentation challenge (OCSC) [6] data set analyzed in this work contains OCT image stacks acquired by a variety of imaging vendors, where, each image is manually annotated by two manual graders/annotators, such that the dice coefficient (DC) between the graders ranges from 0.68 − 0.88 [5]. Although "aggregated" DCs reported across vendors in [7] [8] and [5] are shown to have minimal variations across manual graders, the analysis per vendor image stack illustrates high variabilities across manual graders. For instance, the multi-scale CNN based model in [5] reports aggregated DCs of 0.56, 0.55, 0.54 across all vendor stacks for target labels (TLs)/graders .…”

Section: Introductionmentioning

confidence: 99%

Few Shot Learning Framework to Reduce Inter-observer Variability in Medical Images

Roychowdhury¹

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Most computer aided pathology detection systems rely on large volumes of quality annotated data to aid diagnostics and follow up procedures. However, quality assuring large volumes of annotated medical image data can be subjective and expensive. In this work we present a novel standardization framework that implements three few-shot learning (FSL) models that can be iteratively trained by atmost 5 images per 3D stack to generate multiple regional proposals (RPs) per test image. These FSL models include a novel parallel echo state network (ParESN) framework and an augmented U-net model. Additionally, we propose a novel target label selection algorithm (TLSA) that measures relative agreeability between RPs and the manually annotated target labels to detect the "best" quality annotation per image. Using the FSL models, our system achieves 0.28-0.64 Dice coefficient across vendor image stacks for intraretinal cyst segmentation. Additionally, the TLSA is capable of automatically classifying high quality target labels from their noisy counterparts for 60-97% of the images while ensuring manual supervision on remaining images. Also, the proposed framework with ParESN model minimizes manual annotation checking to 12-28% of the total number of images. The TLSA metrics further provide confidence scores for the automated annotation quality assurance. Thus, the proposed framework is flexible to extensions for quality image annotation curation of other image stacks as well.

show abstract

“…Thus, playing a vital role in the treatment of retinal diseases. Several deep learning methods were employed to automate this process and tackle various image analysis tasks like detection and segmentation in OCT imaging [4,5,6,7]. However, to achieve these tasks, a large dataset is usually required.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Image to Image Translation for Multiple Retinal Pathology Synthesis in Optical Coherence Tomography Scans

Hemanth¹,

Girish²

2021

Preprint

View full text Add to dashboard Cite

Image to Image Translation (I2I) is a challenging computer vision problem used in numerous domains for multiple tasks. Recently, ophthalmology became one of the major fields where the application of I2I is increasing rapidly. One such application is the generation of synthetic retinal optical coherence tomographic (OCT) scans. Existing I2I methods require training of multiple models to translate images from normal scans to a specific pathology: limiting the use of these models due to their complexity. To address this issue, we propose an unsupervised multi-domain I2I network with pre-trained style encoder that translates retinal OCT images in one domain to multiple domains. We assume that the image splits into domain-invariant content and domain-specific style codes, and pre-train these style codes. The performed experiments show that the proposed model outperforms state-of-the-art models like MUNIT and CycleGAN synthesizing diverse pathological scans.

show abstract

Depthwise Separable Convolutional Neural Network Model for Intra-Retinal Cyst Segmentation

Cited by 18 publications

References 13 publications

Retinal Fluid Segmentation Using Ensembled 2-Dimensionally and 2.5-Dimensionally Deep Learning Networks

Retinal Fluid Segmentation Using Ensembled 2-Dimensionally and 2.5-Dimensionally Deep Learning Networks

Few Shot Learning Framework to Reduce Inter-observer Variability in Medical Images

Unsupervised Image to Image Translation for Multiple Retinal Pathology Synthesis in Optical Coherence Tomography Scans

Contact Info

Product

Resources

About