Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning

  title={Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning},
  author={Daniel S. Kermany and Michael H. Goldbaum and Wenjia Cai and Carolina Carvalho Soares Valentim and Huiying Liang and Sally L. Baxter and Alex McKeown and Ge Yang and Xiaokang Wu and Fangbing Yan and Justin Dong and Made K. Prasadha and Jacqueline Pei and Magdalene Yin Lin Ting and Jie Zhu and Christina M. Li and Sierra Hewett and Jason Dong and Ian Ziyar and Alexander Shi and Runze Zhang and Lianghong Zheng and Rui Hou and William Shi and Xin Fu and Yaou Duan and Viet Anh Nguyen Huu and Cindy Wen and Edward D. Zhang and Charlotte L. Zhang and Oulan Li and Xiaobo Wang and Michael A. Singer and Xiaodong Sun and Jie Xu and Ali R. Tafreshi and M. Anthony Lewis and Huimin Xia and Kang Zhang},

Figures from this paper

Interpretation of deep learning using attributions: application to ophthalmic diagnosis

A framework for interpreting the decision making of a deep learning network for retinal OCT image classification is proposed and results showed a successful attribution of the specific pathological regions of the OCT that are responsible for a given condition in the absence of any pixel-level annotations.

Deep CNN framework for retinal disease diagnosis using optical coherence tomography images

A deep convolutional neural network framework for the diagnosis and classification into Normal, DMD and DME effectively is proposed effectively and an authoritative study is performed between the pre-trained models and proposed framework using the acquired performance metrics to demonstrate the efficacy of the model.

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

A hierarchical deep learning system based on a small number of samples that comprehensively simulates the diagnostic thinking of human experts in diagnosing glaucoma is established and markedly improves the diagnostic accuracy of ophthalmologists.

A Data-Efficient Approach for Automated Classification of OCT Images Using Generative Adversarial Network

A data-efficient semisupervised generative adversarial network based classifier for automated diagnosis with limited labeled data and shows an overall improvement of more than 10% in accuracy, compared to the state-of-the-art methods.

Evaluation of Explainable Deep Learning Methods for Ophthalmic Diagnosis

A comparative analysis was performed to determine the method with the best explanations for retinal OCT diagnosis, and an attribution method based on Taylor series expansion was rated the highest by clinicians.

Deep Learning Methodologies for Diagnosis of Respiratory Disorders from Chest X-ray Images: A Comparative Study †

This paper surveys the DL methods for lung disease detection from chest X-ray images and finds that the presented methods may prove extremely useful for people to ideate their research contributions in this area.

Artificial intelligence-based decision-making for age-related macular degeneration

An AI- and cloud-based telemedicine interaction tool for diagnosis and proposed treatment of AMD is presented and a website for realistic cloud computing based on this AI platform, available at

Computer-Aided Diagnosis of Ophthalmic Diseases Using OCT Based on Deep Learning: A Review

The computer-aided diagnosis system of multiple ophthalmic diseases using OCT in recent years is introduced, including age-related macular degeneration, glaucoma, diabetic macular edema and so on, and an overview of the main challenges faced by deep learning in OCT imaging is introduced.



Deep learning is effective for the classification of OCT images of normal versus Age-related Macular Degeneration

Deep learning techniques achieve high accuracy and is effective as a new image classification technique in Optical coherence tomography and have important implications in utilizing OCT in automated screening and the development of computer aided diagnosis tools in the future.

Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

An algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy and diabetic macular edema in retinal fundus photographs from adults with diabetes.

Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images

An effort at image understanding in fundus images anticipates the future use of medical images by ophthalmologists and physicians in other fields that rely in images.

Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response

An automated method to locate and outline blood vessels in images of the ocular fundus that uses local and global vessel features cooperatively to segment the vessel network is described.

Visualizing and Understanding Convolutional Networks

A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.

How transferable are features in deep neural networks?

This paper quantifies the generality versus specificity of neurons in each layer of a deep convolutional neural network and reports a few surprising results, including that initializing a network with transferred features from almost any number of layers can produce a boost to generalization that lingers even after fine-tuning to the target dataset.

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.

The ecosystem that powered the translation of OCT from fundamental research to clinical and commercial impact [Invited].

The translation of OCT from fundamental research to clinical practice and commercial impact is discussed, as well as the ecosystem that helped power OCT to where it is today and will continue to drive future advances is described.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Rethinking the Inception Architecture for Computer Vision

This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.