Benchmarking automated detection of the retinal external limiting membrane in a 3D spectral domain optical coherence tomography image dataset of full thickness macular holes
“…These DL-based image informatics approaches have limitations related to (1) image and label data preparation, (2) data volume, (3) data quality, and ( 4) low-level model robustness and generalisation when using a wide range of OCT machines at different hospitals. To address some of these limitations, we recently presented a more comprehensive image informatics framework utilising robust data preparation and anomaly detection approaches combined with state-of-art DL models on a closely allied OCT analysis problem of external limiting membrane detection [11].…”
Section: ) Deep Learning Based Methodsmentioning
confidence: 99%
“…This led to an improvement in our proposed model's results. According to [11], [58], although several anomaly detection methods have been developed, unsupervised anomaly detection methods are preferred. This is because they have the most flexible setup and do not require any labels or prior knowledge about the dataset [59].…”
Section: ) Anomaly Detectionmentioning
confidence: 99%
“…Three-dimensional automated image reconstruction has improved this ability [8], [9], but there are no current standards for shape, size, and resolution of OCT imaging data captured by different OCT devices for this task [10]. There are also many qualitative features and subtle alterations in retinal anatomy, for example, associated with chronicity, which may be predictive of acuity outcomes and that are difficult to measure [11], [12]. Additionally, image artefacts related to a patient's eye movement and media opacity pose a further challenge in developing image informatics methods [13].…”
This study presents a fully automated image informatics framework. The framework is combined with a deep learning (DL) approach to automatically predict visual acuity outcomes for people undergoing surgery for idiopathic full-thickness macular holes using 3D spectral-domain optical coherence tomography (SD-OCT) images. To overcome the impact of high variation in real-world image quality on the robustness of DL models, comprehensive imaging data pre-processing, quality assurance, and anomaly detection procedures were utilised. We then implemented, trained, and tested nine state-of-the-art DL predictive models through our designed loss function with multiple 2D input channels on the imaging dataset. Finally, we quantitatively compared the models using four evaluation metrics. Overall, the predictive model achieved a MAE of 6.47 ETDRS letters score, demonstrating high predictability. This confirms that our fully automated approach with input from seven central SD-OCT images from each patient can robustly predict visual acuity measurements. Further research will focus on adapting 3D DL-based predictive models and the uncertainty of 2D and 3D DL-based predictive models.INDEX TERMS Image analysis, machine learning, optical coherence tomography, visual acuity measurement.
“…These DL-based image informatics approaches have limitations related to (1) image and label data preparation, (2) data volume, (3) data quality, and ( 4) low-level model robustness and generalisation when using a wide range of OCT machines at different hospitals. To address some of these limitations, we recently presented a more comprehensive image informatics framework utilising robust data preparation and anomaly detection approaches combined with state-of-art DL models on a closely allied OCT analysis problem of external limiting membrane detection [11].…”
Section: ) Deep Learning Based Methodsmentioning
confidence: 99%
“…This led to an improvement in our proposed model's results. According to [11], [58], although several anomaly detection methods have been developed, unsupervised anomaly detection methods are preferred. This is because they have the most flexible setup and do not require any labels or prior knowledge about the dataset [59].…”
Section: ) Anomaly Detectionmentioning
confidence: 99%
“…Three-dimensional automated image reconstruction has improved this ability [8], [9], but there are no current standards for shape, size, and resolution of OCT imaging data captured by different OCT devices for this task [10]. There are also many qualitative features and subtle alterations in retinal anatomy, for example, associated with chronicity, which may be predictive of acuity outcomes and that are difficult to measure [11], [12]. Additionally, image artefacts related to a patient's eye movement and media opacity pose a further challenge in developing image informatics methods [13].…”
This study presents a fully automated image informatics framework. The framework is combined with a deep learning (DL) approach to automatically predict visual acuity outcomes for people undergoing surgery for idiopathic full-thickness macular holes using 3D spectral-domain optical coherence tomography (SD-OCT) images. To overcome the impact of high variation in real-world image quality on the robustness of DL models, comprehensive imaging data pre-processing, quality assurance, and anomaly detection procedures were utilised. We then implemented, trained, and tested nine state-of-the-art DL predictive models through our designed loss function with multiple 2D input channels on the imaging dataset. Finally, we quantitatively compared the models using four evaluation metrics. Overall, the predictive model achieved a MAE of 6.47 ETDRS letters score, demonstrating high predictability. This confirms that our fully automated approach with input from seven central SD-OCT images from each patient can robustly predict visual acuity measurements. Further research will focus on adapting 3D DL-based predictive models and the uncertainty of 2D and 3D DL-based predictive models.INDEX TERMS Image analysis, machine learning, optical coherence tomography, visual acuity measurement.
“…An element in W has a value of 1 if the quality of the BUS frame exceeds the thresholds of the brightness and blurriness scores, and N q is the number of the frames in the BUS sequence exceeding the thresholds of the brightness and blurriness scores. Blurriness score: To estimate the blurriness a variance of the BUS image I BUS (p, q) intensity smoothed by a Gaussian filter G f (p, q) [27,28] was employed. The Gaussian filter can be expressed as follows:…”
Breast cancer needs to be detected early to reduce mortality rate. Ultrasound imaging (US) could significantly enhance diagnosing cases with dense breasts. Most of the existing computer-aided diagnosis (CAD) systems employ a single ultrasound image for the breast tumor to extract features to classify it as benign or malignant. However, the accuracy of such CAD system is limited due to the large tumor size and shape variation, irregular and ambiguous tumor boundaries, and low signal-to-noise ratio in ultrasound images due to their noisy nature and the significant similarity between normal and abnormal tissues. To handle these issues, we propose a deep-learning-based radiomics method based on breast US sequences in this paper. The proposed approach involves three main components: radiomic features extraction based on a deep learning network, so-called ConvNeXt, a malignancy score pooling mechanism, and visual interpretations. Specifically, we employ the ConvNeXt network, a deep convolutional neural network (CNN) trained using the vision transformer style. We also propose an efficient pooling mechanism to fuse the malignancy scores of each breast US sequence frame based on image-quality statistics. The ablation study and experimental results demonstrate that our method achieves competitive results compared to other CNN-based methods.
“…The last several years have seen an explosion of deep learning models applied to ophthalmic clinical technologies including OCT and fundus imaging. These applications may be divided into the broad areas of classification/diagnosis [8][9][10][11][12][13][14][15][16][17][18], segmentation [19][20][21][22][23][24][25][26], image quality [27], and demographics prediction [28]. The current ophthalmic deep learning models focus primarily on diabetic retinopathy, age-related macular degeneration, retinopathy of prematurity, and glaucoma [29][30][31].…”
There is a growing interest in using computer-assisted models for the detection of macular conditions using optical coherence tomography (OCT) data. As the quantity of clinical scan data of specific conditions is limited, these models are typically developed by fine-tuning a generalized network to classify specific macular conditions of interest. Full thickness macular holes (FTMH) present a condition requiring timely surgical intervention to prevent permanent vision loss. Other works on automated FTMH classification have tended to use supervised ImageNet pre-trained networks with good results but leave room for improvement. In this paper, we develop a model for FTMH classification using OCT slices around the central foveal region to pre-train a naïve network using contrastive self-supervised learning. We found that self-supervised pre-trained networks outperform ImageNet pre-trained networks despite a small training set size (284 eyes total, 51 FTMH+ eyes, 3 slices from each eye). 3D spatial contrast pre-training yields a model with an F1-score of 1.0 on holdout data (50 eyes total, 10 FTMH+), compared ImageNet pre-trained models, respectively. These results demonstrate that even limited data may be applied toward self-supervised pre-training to substantially improve performance for FTMH classification, indicating applicability toward other OCT-based problems.Author SummaryFull thickness macular holes (FTMH) are a sight-threatening condition that involves the fovea, the area of the eye involved in central vision. Timely diagnosis is paramount because of the risk of permanent vision loss. In clinical practice, full thickness macular holes are commonly diagnosed with the aid of optical coherence tomography (OCT) images of the fovea. However, certain conditions such as pseudoholes and epiretinal membranes may complicate the diagnosis of full thickness macular holes on imaging. Here, we employ the use of artificial intelligence and present a machine-learning model for full thickness macular hole classification and distinction from conditions that may present similarly upon image review. Despite training our model with a smaller data set, it outperformed traditional models previously seen in other works. We provide a strong framework for a self-supervised pre-trained model that can accurately distinguish full thickness macular holes from epiretinal membranes and pseudoholes. Overall, our study provides evidence of the benefit and efficacy with the introduction of artificial intelligence for image classification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.