medical-9

Retinal OCT Disease Classification

3260 papers • 126 benchmarks • 313 datasets

Classifying different Retinal degeneration from Optical Coherence Tomography Images (OCT).

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in retinal-oct-disease-classification-18

Trend

Dataset

Best Model

Actions

OCT2017

Srinivasan2014

Libraries

i

Use these libraries to find retinal-oct-disease-classification-18 models and implementations

pytorch/vision

3 papers 15,170

Datasets

OCTID

RETOUCH

Subtasks

No subtasks available.

Most implemented papers

Deep Residual Learning for Image Recognition

Kaiming He, X. Zhang, Shaoqing Ren•Wed Dec 09 2015

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

214235

Content

open-mmlab/mmclassification

3 papers 3,027

osmr/imgclsmob

3 papers 2,898

rwightman/pytorch-image-models

2 papers 28,902

PaddlePaddle/PaddleDetection

2 papers 11,841

open-mmlab/mmpose

2 papers 4,761

Deci-AI/super-gradients

2 papers 4,221

DeepMark/deepmark

2 papers 351

peteryuX/arcface-tf2

2 papers 252

canturan10/satellighte

2 papers 73

0

Paper Graph

Rethinking the Inception Architecture for Computer Vision

Z. Wojna, Sergey Ioffe, Christian Szegedy, Vincent Vanhoucke, Jonathon Shlens•Tue Dec 01 2015

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.

29572 0

Paper Graph

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Liang-Chieh Chen, Andrew G. Howard, Menglong Zhu, M. Sandler, A. Zhmoginov•Fri Jan 12 2018

A new mobile architecture, MobileNetV2, is described that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes and allows decoupling of the input/output domains from the expressiveness of the transformation.

23065 0

Paper Graph

Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images

A. Tavakkoli, Sharif Amit Kamran, Sourajit Saha, A. Sabbir•Sat Oct 12 2019

A novel convolution neural network architecture is proposed to successfully distinguish between different degeneration of retinal layers and their underlying causes and predicts retinal diseases in real time while outperforming human diagnosticians.

56 0

Paper Graph

Improving Robustness Using Joint Attention Network for Detecting Retinal Degeneration From Optical Coherence Tomography Images

A. Tavakkoli, Sharif Amit Kamran, S. Zuckerbrod•Fri May 15 2020

The use of disease-specific feature representation as a novel architecture comprised of two joint networks - one for supervised encoding of disease model and the other for producing attention maps in an unsupervised manner to retain disease specific spatial information is proposed.

29 0

Paper Graph

Retinal OCT disease classification with variational autoencoder regularization

M. Laves, L. Kahrs, T. Ortmaier, Sontje Ihler•Fri Mar 22 2019

This paper describes a method based on variational autoencoder regularization that improves classification performance when using a limited amount of labeled data and shows superior classification performance compared to a pre-trained and fully fine-tuned baseline ResNet-34.

3 0

Paper Graph

TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT Volumes

Hrvoje Bogunovi'c, T. Emre, A. Chakravarty, Antoine Rivail, Sophie Riedl, U. Schmidt-Erfurth•Wed Jun 29 2022

This model outperforms existing models in predicting the risk of conversion within a time frame from intermediate age-related macular degeneration to the late wet-AMD stage and can avoid heavy augmentations and implicitly incorporates the temporal information in the pairs.

15 0

Paper Graph

Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels

Valentyn Melnychuk, Evgeniy Faerman, I. Manakov, T. Seidl•Thu Oct 22 2020

It is found that both MixMatch and FixMatch algorithms outperform the transfer learning baseline on all fractions of labelled data and that exponential moving average of model parameters is not needed for the classification problem, as disabling it leaves the outcome unchanged.

1 0

Paper Graph

Adding a benchmark result helps the community track progress.