Deep learning architectures analysis for age-related macular degeneration segmentation on optical coherence tomography scans

RetiFluidNet: A Self-Adaptive and Multi-Attention Deep Convolutional Network for Retinal OCT Fluid Segmentation

Optical coherence tomography (OCT) helps ophthalmologists assess macular edema, accumulation of fluids, and lesions at microscopic resolution. Quantification of retinal fluids is necessary for OCT-guided treatment management, which relies on a precise image segmentation step. As manual analysis of retinal fluids is a time-consuming, subjective, and error-prone task, there is increasing demand for fast and robust automatic solutions. In this study, a new convolutional neural architecture named RetiFluidNet is proposed for multi-class retinal fluid segmentation. The model benefits from hierarchical representation learning of textural, contextual, and edge features using a new self-adaptive dual-attention (SDA) module, multiple self-adaptive attention-based skip connections (SASC), and a novel multi-scale deep self-supervision learning (DSL) scheme. The attention mechanism in the proposed SDA module enables the model to automatically extract deformation-aware representations at different levels, and the introduced SASC paths further consider spatial-channel interdependencies for concatenation of counterpart encoder and decoder units, which improve representational capability. RetiFluidNet is also optimized using a joint loss function comprising a weighted version of dice overlap and edge-preserved connectivity-based losses, where several hierarchical stages of multi-scale local losses are integrated into the optimization process. The model is validated based on three publicly available datasets: RETOUCH, OPTIMA, and DUKE, with comparisons against several baselines. Experimental results on the datasets prove the effectiveness of the proposed model in retinal OCT fluid segmentation and reveal that the suggested method is more effective than existing state-of-the-art fluid segmentation algorithms in adapting to retinal OCT scans recorded by various image scanning instruments.

A multi-modal fundus image based auxiliary location method of lesion boundary for guiding the layout of laser spot in central serous chorioretinopathy therapy

The lesion boundary of central serous chorioretinopathy (CSCR) is the guarantee to guide the ophthalmologist to accurately arrange the laser spots, so as to enable this ophthalmopathy to be treated precisely. Currently, the accuracy and rapidity of manually locating CSCR lesion boundary in clinic based on single-modal fundus image are limited by imaging quality and ophthalmologist experience, which is also accompanied by poor repeatability, weak reliability and low efficiency. Consequently, a multi-modal fundus image-based lesion boundary auxiliary location method is developed. Firstly, the initial location module (ILM) is employed to achieve the preliminary location of key boundary points of CSCR lesion area on the optical coherence tomography (OCT) B-scan image, then followed by the joint location module (JLM) created based on reinforcement learning for further enhancing the location accuracy. Secondly, the scanning line detection module (SLDM) is constructed to realize the location of lesion scanning line on the scanning laser ophthalmoscope (SLO) image, so as to facilitate the cross-modal mapping of key boundary points. Finally, a simple yet effective lesion boundary location module (LBLM) is designed to assist the automatic cross-modal mapping of key boundary points and enable the final location of lesion boundary. Extensive experiments show that each module can perform well on its corresponding sub task, such as JLM, which makes the correction rate (CR) of ILM increase to 92.11%, comprehensively indicating the effectiveness and feasibility of this method in providing effective lesion boundary guidance for assisting ophthalmologists to precisely arrange the laser spots, and also opening a new research idea for the automatic location of lesion boundary of other fundus diseases.

An Automatic Image Processing Method Based on Artificial Intelligence for Locating the Key Boundary Points in the Central Serous Chorioretinopathy Lesion Area

Accurately and rapidly measuring the diameter of central serous chorioretinopathy (CSCR) lesion area is the key to judge the severity of CSCR and evaluate the efficacy of the corresponding treatments. Currently, the manual measurement scheme based on a single or a small number of optical coherence tomography (OCT) B-scan images encounters the dilemma of incredibility. Although manually measuring the diameters of all OCT B-scan images of a single patient can alleviate the previous issue, the situation of inefficiency will thus arise. Additionally, manual operation is subject to subjective factors of ophthalmologists, resulting in unrepeatable measurement results. Therefore, an automatic image processing method (i.e., a joint framework) based on artificial intelligence (AI) is innovatively proposed for locating the key boundary points of CSCR lesion area to assist the diameter measurement. Firstly, the initial location module (ILM) benefiting from multitask learning is properly adjusted and tentatively achieves the preliminary location of key boundary points. Secondly, the location task is formulated as a Markov decision process, aiming at further improving the location accuracy by utilizing the single agent reinforcement learning module (SARLM). Finally, the joint framework based on the ILM and SARLM is skillfully established, in which ILM provides an initial starting point for SARLM to narrow the active region of agent, and SARLM makes up for the defect of low generalization of ILM by virtue of the independent exploration ability of agent. Experiments reveal the AI-based method which joins the multitask learning, and single agent reinforcement learning paradigms enable agents to work in local region, alleviating the time-consuming problem of SARLM, performing location task in a global scope, and improving the location accuracy of ILM, thus reflecting its effectiveness and clinical application value in the task of rapidly and accurately measuring the diameter of CSCR lesions.

Artificial intelligence based detection of age-related macular degeneration using optical coherence tomography with unique image preprocessing

PURPOSE

The aim of the study is to improve the accuracy of age related macular degeneration (AMD) disease in its earlier phases with proposed Capsule Network (CapsNet) architecture trained on speckle noise reduced spectral domain optical coherence tomography (SD-OCT) images based on an optimized Bayesian non-local mean (OBNLM) filter augmentation techniques.

METHODS

A total of 726 local SD-OCT images were collected and labelled as 159 drusen, 145 dry AMD, 156 wet AMD and 266 normal. Region of interest (ROI) was identified. Speckle noise in SD-OCT images were reduced based on OBNLM filter. The processed images were fed to proposed CapsNet architecture to clasify SD-OCT images. Accuracy rates were calculated in both public and local dataset.

RESULTS

Accuracy rate of local SD-OCT image dataset classification was achieved to a value of 96.39% after performing data augmentation and speckle noise reduction with OBNLM. The performance of proposed CapsNet was also evaluated on the public Kaggle dataset under the same processing procedures and the accuracy rate was calculated as 98.07%. The sensitivity and specificity rates were 96.72% and 99.98%, respectively.

CONCLUSIONS

The classification success of proposed CapsNet may be improved with robust pre-processing steps like; determination of ROI and denoised SD-OCT images based on OBNLM. These impactful image preprocessing steps yielded higher accuracy rates for determining different types of AMD including its precursor lesion on the both local and public dataset with proposed CapsNet architecture.

Algorithm of segmentation of OCT macular images to analyze the results in patients with age-related macular degeneration

Age-related macular degeneration (AMD) is one of the main causes of loss of sight and hypovision in people over working age. Results of optical coherence tomography (OCT) are essential for diagnostics of the disease. Developing the recommendation system to analyze OCT images will reduce the time to process visual data and decrease the probability of errors while working as a doctor. The purpose of the study was to develop an algorithm of segmentation to analyze the results of macular OCT in patients with AMD. It allows to provide a correct prediction of an AMD stage based on the form of discovered pathologies. A program has been developed in the Python programming language using the Pytorch and TensorFlow libraries. Its quality was estimated using OCT macular images of 51 patients with early, intermediate, late AMD. A segmentation algorithm of OCT images was developed based on convolutional neural network. UNet network was selected as architecture of high-accuracy neural net. The neural net is trained on macular OCT images of 125 patients (197 eyes). The author algorithm displayed 98.1% of properly segmented areas on OCT images, which are the most essential for diagnostics and determination of an AMD stage. Weighted sensitivity and specificity of AMD stage classifier amounted to 83.8% and 84.9% respectively. The developed algorithm is promising as a recommendation system that implements the AMD classification based on data that promote taking decisions regarding the treatment strategy.

A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation

Deep learning methods have enabled a fast, accurate and automated approach for retinal layer segmentation in posterior segment OCT images. Due to the success of semantic segmentation methods adopting the U-Net, a wide range of variants and improvements have been developed and applied to OCT segmentation. Unfortunately, the relative performance of these methods is difficult to ascertain for OCT retinal layer segmentation due to a lack of comprehensive comparative studies, and a lack of proper matching between networks in previous comparisons, as well as the use of different OCT datasets between studies. In this paper, a detailed and unbiased comparison is performed between eight U-Net architecture variants across four different OCT datasets from a range of different populations, ocular pathologies, acquisition parameters, instruments and segmentation tasks. The U-Net architecture variants evaluated include some which have not been previously explored for OCT segmentation. Using the Dice coefficient to evaluate segmentation performance, minimal differences were noted between most of the tested architectures across the four datasets. Using an extra convolutional layer per pooling block gave a small improvement in segmentation performance for all architectures across all four datasets. This finding highlights the importance of careful architecture comparison (e.g. ensuring networks are matched using an equivalent number of layers) to obtain a true and unbiased performance assessment of fully semantic models. Overall, this study demonstrates that the vanilla U-Net is sufficient for OCT retinal layer segmentation and that state-of-the-art methods and other architectural changes are potentially unnecessary for this particular task, especially given the associated increased complexity and slower speed for the marginal performance gains observed. Given the U-Net model and its variants represent one of the most commonly applied image segmentation methods, the consistent findings across several datasets here are likely to translate to many other OCT datasets and studies. This will provide significant value by saving time and cost in experimentation and model development as well as reduced inference time in practice by selecting simpler models.

Multi-Scale Pathological Fluid Segmentation in OCT With a Novel Curvature Loss in Convolutional Neural Network

The segmentation of pathological fluid lesions in optical coherence tomography (OCT), including intraretinal fluid, subretinal fluid, and pigment epithelial detachment, is of great importance for the diagnosis and treatment of various eye diseases such as neovascular age-related macular degeneration and diabetic macular edema. Although significant progress has been achieved with the rapid development of fully convolutional neural networks (FCN) in recent years, some important issues remain unsolved. First, pathological fluid lesions in OCT show large variations in location, size, and shape, imposing challenges on the design of FCN architecture. Second, fluid lesions should be continuous regions without holes inside. But the current architectures lack the capability to preserve the shape prior information. In this study, we introduce an FCN architecture for the simultaneous segmentation of three types of pathological fluid lesions in OCT. First, attention gate and spatial pyramid pooling modules are employed to improve the ability of the network to extract multi-scale objects. Then, we introduce a novel curvature regularization term in the loss function to incorporate shape prior information. The proposed method was extensively evaluated on public and clinical datasets with significantly improved performance compared with the state-of-the-art methods.

Real-time OCT image denoising using a self-fusion neural network

Optical coherence tomography (OCT) has become the gold standard for ophthalmic diagnostic imaging. However, clinical OCT image-quality is highly variable and limited visualization can introduce errors in the quantitative analysis of anatomic and pathologic features-of-interest. Frame-averaging is a standard method for improving image-quality, however, frame-averaging in the presence of bulk-motion can degrade lateral resolution and prolongs total acquisition time. We recently introduced a method called self-fusion, which reduces speckle noise and enhances OCT signal-to-noise ratio (SNR) by using similarity between from adjacent frames and is more robust to motion-artifacts than frame-averaging. However, since self-fusion is based on deformable registration, it is computationally expensive. In this study a convolutional neural network was implemented to offset the computational overhead of self-fusion and perform OCT denoising in real-time. The self-fusion network was pretrained to fuse 3 frames to achieve near video-rate frame-rates. Our results showed a clear gain in peak SNR in the self-fused images over both the raw and frame-averaged OCT B-scans. This approach delivers a fast and robust OCT denoising alternative to frame-averaging without the need for repeated image acquisition. Real-time self-fusion image enhancement will enable improved localization of OCT field-of-view relative to features-of-interest and improved sensitivity for anatomic features of disease.

Prediction of postoperative visual acuity after vitrectomy for macular hole using deep learning-based artificial intelligence

PURPOSE

To create a model for prediction of postoperative visual acuity (VA) after vitrectomy for macular hole (MH) treatment using preoperative optical coherence tomography (OCT) images, using deep learning (DL)-based artificial intelligence.

METHODS

This was a retrospective single-center study. We evaluated 259 eyes that underwent vitrectomy for MHs. We divided the eyes into four groups, based on their 6-month postoperative Snellen VA values: (A) ≥ 20/20; (B) 20/25-20/32; (C) 20/32-20/63; and (D) ≤ 20/100. Training data were randomly selected, comprising 20 eyes in each group. Test data were also randomly selected, comprising 52 total eyes in the same proportions as those of each group in the total database. Preoperative OCT images with corresponding postoperative VA values were used to train the original DL network. The final prediction of postoperative VA was subjected to regression analysis based on inferences made with DL network output. We created a model for predicting postoperative VA from preoperative VA, MH size, and age using multivariate linear regression. Precision values were determined, and correlation coefficients between predicted and actual postoperative VA values were calculated in two models.

RESULTS

The DL and multivariate models had precision values of 46% and 40%, respectively. The predicted postoperative VA values on the basis of DL and on preoperative VA and MH size were correlated with actual postoperative VA at 6 months postoperatively (P < .0001 and P < .0001, r = .62 and r = .55, respectively).

CONCLUSION

Postoperative VA after MH treatment could be predicted via DL using preoperative OCT images with greater accuracy than multivariate linear regression using preoperative VA, MH size, and age.

Deep neural network for automated simultaneous intervertebral disc (IVDs) identification and segmentation of multi-modal MR images

BACKGROUND AND OBJECTIVE

Lower back pain in humans has become a major risk. Classical approaches follow a non-invasive imaging technique for the assessment of spinal intervertebral disc (IVDs) abnormalities, where identification and segmentation of discs are done separately, making it a time-consuming phenomenon. This necessitates designing a robust automated and simultaneous IVDs identification and segmentation of multi-modality MRI images.

METHODS

We introduced a novel deep neural network architecture coined as 'RIMNet', a Region-to-Image Matching Network model, capable of performing an automated and simultaneous IVDs identification and segmentation of MRI images. The multi-modal input data is being fed to the network with a dropout strategy, by randomly disabling modalities in mini-batches. The performance accuracy as a function of the testing dataset was determined. The execution of the deep neural network model was evaluated by computing the IVDs Identification Accuracy, Dice coefficient, MDOC, Average Symmetric Surface Distance, Jaccard Coefficient, Hausdorff Distance and F1 Score.

RESULTS

Proposed model has attained 94% identification accuracy, dice coefficient value of 91.7±1% in segmentation and MDOC 90.2±1%. Our model also achieved 0.87±0.02 for Jaccard Coefficient, 0.54±0.04 for ASD and 0.62±0.02 mm Hausdorff Distance. The results have been validated and compared with other methodologies on dataset of MICCAI IVD 2018 challenge.

CONCLUSIONS

Our proposed deep-learning methodology is capable of performing simultaneous identification and segmentation on IVDs MRI images of the human spine with high accuracy.

Automated Quantitative Assessment of Retinal Fluid Volumes as Important Biomarkers in Neovascular Age-Related Macular Degeneration

PURPOSE

To evaluate retinal fluid volume data extracted from optical coherence tomography (OCT) scans by artificial intelligence algorithms in the treatment of neovascular age-related macular degeneration (NV-AMD).

DESIGN

Perspective.

METHODS

A review was performed of retinal image repository datasets from diverse clinical settings.

SETTINGS

Clinical trial (HARBOR) and trial follow-on (Age-Related Eye Disease Study 2 10-year Follow-On); real-world (Belfast and Tel-Aviv tertiary centers).

PATIENTS

24,362 scans of 1,095 eyes (HARBOR); 4,673 of 880 (Belfast); 1,470 of 132 (Tel-Aviv); 511 of 511 (Age-Related Eye Disease Study 2 10-year Follow-On). ObservationProcedures: Vienna Fluid Monitor or Notal OCT Analyzer applied to macular cube scans. OutcomeMeasures: Intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED) volumes.

RESULTS

The fluid volumes measured in neovascular AMD were expressed efficiently in nanoliters. Large ranges that differed by population were observed at the treatment-naïve stage: 0-3,435 nL (IRF), 0-5,018 nL (SRF), and 0-10,022 nL (PED). Mean volumes decreased rapidly and consistently with anti-vascular endothelial growth factor therapy. During maintenance therapy, mean IRF volumes were highest in Tel-Aviv (100 nL), lower in Belfast and HARBOR-Pro Re Nata, and lowest in HARBOR-monthly (21 nL). Mean SRF volumes were low in all: 30 nL (HARBOR-monthly) and 48-49 nL (others).

CONCLUSIONS

Quantitative measures of IRF, SRF, and PED are important biomarkers in NV-AMD. Accurate volumes can be extracted efficiently from OCT scans by artificial intelligence algorithms to guide the treatment of exudative macular diseases. Automated fluid monitoring identifies fluid characteristics in different NV-AMD populations at baseline and during follow-up. For consistency between studies, we propose the nanoliter as a convenient unit. We explore the advantages of using these quantitative metrics in clinical practice and research.