scholarly journals A hierarchical deep learning approach with transparency and interpretability based on small samples for glaucoma diagnosis

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Yongli Xu ◽  
Man Hu ◽  
Hanruo Liu ◽  
Hao Yang ◽  
Huaizhou Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithms ◽  
High Sensitivity ◽  
Learning System ◽  
Small Samples ◽  
Fundus Images ◽  
Fiber Layer ◽  
Glaucoma Diagnosis ◽  
Diagnostic Thinking

AbstractThe application of deep learning algorithms for medical diagnosis in the real world faces challenges with transparency and interpretability. The labeling of large-scale samples leads to costly investment in developing deep learning algorithms. The application of human prior knowledge is an effective way to solve these problems. Previously, we developed a deep learning system for glaucoma diagnosis based on a large number of samples that had high sensitivity and specificity. However, it is a black box and the specific analytic methods cannot be elucidated. Here, we establish a hierarchical deep learning system based on a small number of samples that comprehensively simulates the diagnostic thinking of human experts. This system can extract the anatomical characteristics of the fundus images, including the optic disc, optic cup, and appearance of the retinal nerve fiber layer to realize automatic diagnosis of glaucoma. In addition, this system is transparent and interpretable, and the intermediate process of prediction can be visualized. Applying this system to three validation datasets of fundus images, we demonstrate performance comparable to that of human experts in diagnosing glaucoma. Moreover, it markedly improves the diagnostic accuracy of ophthalmologists. This system may expedite the screening and diagnosis of glaucoma, resulting in improved clinical outcomes.

scholarly journals Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Zhongwen Li ◽  
Chong Guo ◽  
Danyao Nie ◽  
Duoru Lin ◽  
Yi Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Retinal Detachment ◽  
Large Scale ◽  
Global Scale ◽  
Clinical Applications ◽  
Learning System ◽  
Vision Impairment ◽  
Fundus Images ◽  
Severe Visual Loss ◽  
Visual Results

AbstractRetinal detachment can lead to severe visual loss if not treated timely. The early diagnosis of retinal detachment can improve the rate of successful reattachment and the visual results, especially before macular involvement. Manual retinal detachment screening is time-consuming and labour-intensive, which is difficult for large-scale clinical applications. In this study, we developed a cascaded deep learning system based on the ultra-widefield fundus images for automated retinal detachment detection and macula-on/off retinal detachment discerning. The performance of this system is reliable and comparable to an experienced ophthalmologist. In addition, this system can automatically provide guidance to patients regarding appropriate preoperative posturing to reduce retinal detachment progression and the urgency of retinal detachment repair. The implementation of this system on a global scale may drastically reduce the extent of vision impairment resulting from retinal detachment by providing timely identification and referral.

scholarly journals Development and validation of a deep learning system to screen vision-threatening conditions in high myopia using optical coherence tomography images

2020 ◽  
pp. bjophthalmol-2020-317825
Author(s):  
Yonghao Li ◽  
Weibo Feng ◽  
Xiujuan Zhao ◽  
Bingqian Liu ◽  
Yan Zhang ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
High Myopia ◽  
Large Scale ◽  
Learning System ◽  
Youden Index ◽  
Optical Coherence ◽  
Test Dataset ◽  
Independent Test ◽  
Independent Test Dataset

Background/aimsTo apply deep learning technology to develop an artificial intelligence (AI) system that can identify vision-threatening conditions in high myopia patients based on optical coherence tomography (OCT) macular images.MethodsIn this cross-sectional, prospective study, a total of 5505 qualified OCT macular images obtained from 1048 high myopia patients admitted to Zhongshan Ophthalmic Centre (ZOC) from 2012 to 2017 were selected for the development of the AI system. The independent test dataset included 412 images obtained from 91 high myopia patients recruited at ZOC from January 2019 to May 2019. We adopted the InceptionResnetV2 architecture to train four independent convolutional neural network (CNN) models to identify the following four vision-threatening conditions in high myopia: retinoschisis, macular hole, retinal detachment and pathological myopic choroidal neovascularisation. Focal Loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index.ResultsIn the independent test dataset, the areas under the receiver operating characteristic curves were high for all conditions (0.961 to 0.999). Our AI system achieved sensitivities equal to or even better than those of retina specialists as well as high specificities (greater than 90%). Moreover, our AI system provided a transparent and interpretable diagnosis with heatmaps.ConclusionsWe used OCT macular images for the development of CNN models to identify vision-threatening conditions in high myopia patients. Our models achieved reliable sensitivities and high specificities, comparable to those of retina specialists and may be applied for large-scale high myopia screening and patient follow-up.

scholarly journals Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

2021 ◽  
Vol 13 (11) ◽  
pp. 2220
Author(s):  
Yanbing Bai ◽  
Wenqi Wu ◽  
Zhengxin Yang ◽  
Jinze Yu ◽  
Bo Zhao ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithms ◽  
Flood Events ◽  
Test Set ◽  
Source Data ◽  
Flood Disasters ◽  
Temporary Water ◽  
Sentinel 2

Identifying permanent water and temporary water in flood disasters efficiently has mainly relied on change detection method from multi-temporal remote sensing imageries, but estimating the water type in flood disaster events from only post-flood remote sensing imageries still remains challenging. Research progress in recent years has demonstrated the excellent potential of multi-source data fusion and deep learning algorithms in improving flood detection, while this field has only been studied initially due to the lack of large-scale labelled remote sensing images of flood events. Here, we present new deep learning algorithms and a multi-source data fusion driven flood inundation mapping approach by leveraging a large-scale publicly available Sen1Flood11 dataset consisting of roughly 4831 labelled Sentinel-1 SAR and Sentinel-2 optical imagery gathered from flood events worldwide in recent years. Specifically, we proposed an automatic segmentation method for surface water, permanent water, and temporary water identification, and all tasks share the same convolutional neural network architecture. We utilize focal loss to deal with the class (water/non-water) imbalance problem. Thorough ablation experiments and analysis confirmed the effectiveness of various proposed designs. In comparison experiments, the method proposed in this paper is superior to other classical models. Our model achieves a mean Intersection over Union (mIoU) of 52.99%, Intersection over Union (IoU) of 52.30%, and Overall Accuracy (OA) of 92.81% on the Sen1Flood11 test set. On the Sen1Flood11 Bolivia test set, our model also achieves very high mIoU (47.88%), IoU (76.74%), and OA (95.59%) and shows good generalization ability.

scholarly journals Towards Neuromorphic Learning Machines Using Emerging Memory Devices with Brain-Like Energy Efficiency

2018 ◽  
Vol 8 (4) ◽  
pp. 34 ◽  
Author(s):  
Vishal Saxena ◽  
Xinyu Wu ◽  
Ira Srivastava ◽  
Kehan Zhu
Keyword(s):  
Machine Learning ◽  
Energy Efficiency ◽  
Deep Learning ◽  
Large Scale ◽  
Learning Algorithms ◽  
Memory Devices ◽  
Cognitive Computing ◽  
Mixed Signal ◽  
Von Neumann ◽  
Emerging Memory

The ongoing revolution in Deep Learning is redefining the nature of computing that is driven by the increasing amount of pattern classification and cognitive tasks. Specialized digital hardware for deep learning still holds its predominance due to the flexibility offered by the software implementation and maturity of algorithms. However, it is being increasingly desired that cognitive computing occurs at the edge, i.e., on hand-held devices that are energy constrained, which is energy prohibitive when employing digital von Neumann architectures. Recent explorations in digital neuromorphic hardware have shown promise, but offer low neurosynaptic density needed for scaling to applications such as intelligent cognitive assistants (ICA). Large-scale integration of nanoscale emerging memory devices with Complementary Metal Oxide Semiconductor (CMOS) mixed-signal integrated circuits can herald a new generation of Neuromorphic computers that will transcend the von Neumann bottleneck for cognitive computing tasks. Such hybrid Neuromorphic System-on-a-chip (NeuSoC) architectures promise machine learning capability at chip-scale form factor, and several orders of magnitude improvement in energy efficiency. Practical demonstration of such architectures has been limited as performance of emerging memory devices falls short of the expected behavior from the idealized memristor-based analog synapses, or weights, and novel machine learning algorithms are needed to take advantage of the device behavior. In this article, we review the challenges involved and present a pathway to realize large-scale mixed-signal NeuSoCs, from device arrays and circuits to spike-based deep learning algorithms with ‘brain-like’ energy-efficiency.

scholarly journals A64 Viral sequence classification using deep learning algorithms

2019 ◽  
Vol 5 (Supplement_1) ◽  
Author(s):  
David Nieuwenhuijse ◽  
Bas Oude Munnink ◽  
My Phan ◽  
Marion Koopmans
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
High Sensitivity ◽  
Current Approach ◽  
Metagenomic Sequencing ◽  
Public Health Importance ◽  
Short Reads ◽  
Deep Learning Algorithm ◽  
High Threat

Abstract Sewage samples have a high potential benefit for surveillance of circulating pathogens because they are easy to obtain and reflect population-wide circulation of pathogens. These type of samples typically contain a great diversity of viruses. Therefore, one of the main challenges of metagenomic sequencing of sewage for surveillance is sequence annotation and interpretation. Especially for high-threat viruses, false positive signals can trigger unnecessary alerts, but true positives should not be missed. Annotation thus requires high sensitivity and specificity. To better interpret annotated reads for high-threat viruses, we attempt to determine how classifiable they are in a background of reads of closely related low-threat viruses. As an example, we attempted to distinguish poliovirus reads, a virus of high public health importance, from other enterovirus reads. A sequence-based deep learning algorithm was used to classify reads as either polio or non-polio enterovirus. Short reads were generated from 500 polio and 2,000 non-polio enterovirus genomes as a training set. By training the algorithm on this dataset we try to determine, on a single read level, which short reads can reliably be labeled as poliovirus and which cannot. After training the deep learning algorithm on the generated reads we were able to calculate the probability with which a read can be assigned to a poliovirus genome or a non-poliovirus genome. We show that the algorithm succeeds in classifying the reads with high accuracy. The probability of assigning the read to the correct class was related to the location in the genome to which the read mapped, which conformed with our expectations since some regions of the genome are more conserved than others. Classifying short reads of high-threat viral pathogens seems to be a promising application of sequence-based deep learning algorithms. Also, recent developments in software and hardware have facilitated the development and training of deep learning algorithms. Further plans of this work are to characterize the hard-to-classify regions of the poliovirus genome, build larger training databases, and expand on the current approach to other viruses.

scholarly journals A deep learning system for identifying lattice degeneration and retinal breaks using ultra-widefield fundus images

2019 ◽  
Vol 7 (22) ◽  
pp. 618-618 ◽  
Author(s):  
Zhongwen Li ◽  
Chong Guo ◽  
Danyao Nie ◽  
Duoru Lin ◽  
Yi Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning System ◽  
Fundus Images ◽  
Retinal Breaks ◽  
Lattice Degeneration

scholarly journals A Hybrid Deep Learning System for Real-World Mobile User Authentication Using Motion Sensors

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 3876 ◽  
Author(s):  
Tiantian Zhu ◽  
Zhengqiu Weng ◽  
Guolang Chen ◽  
Lei Fu
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Mobile Devices ◽  
Real World ◽  
Large Scale ◽  
User Authentication ◽  
Mobile User ◽  
Learning System ◽  
Support Vector ◽  
Motion Sensors

With the popularity of smartphones and the development of hardware, mobile devices are widely used by people. To ensure availability and security, how to protect private data in mobile devices without disturbing users has become a key issue. Mobile user authentication methods based on motion sensors have been proposed by many works, but the existing methods have a series of problems such as poor de-noising ability, insufficient availability, and low coverage of feature extraction. Based on the shortcomings of existing methods, this paper proposes a hybrid deep learning system for complex real-world mobile authentication. The system includes: (1) a variational mode decomposition (VMD) based de-noising method to enhance the singular value of sensors, such as discontinuities and mutations, and increase the extraction range of the feature; (2) semi-supervised collaborative training (Tri-Training) methods to effectively deal with mislabeling problems in complex real-world situations; and (3) a combined convolutional neural network (CNN) and support vector machine (SVM) model for effective hybrid feature extraction and training. The training results under large-scale, real-world data show that the proposed system can achieve 95.01% authentication accuracy, and the effect is better than the existing frontier methods.

Sign in / Sign up

Export Citation Format

Share Document