☆ 4.7 Article

Segmentation-guided domain adaptation and data harmonization of multi-device retinal optical coherence tomography using cycle-consistent generative adversarial networks

COMPUTERS IN BIOLOGY AND MEDICINE (2023)

Related references

Note: Only part of the references are listed.

Article Biology

Clinical explainable differential diagnosis of polypoidal choroidal vasculopathy and age-related macular degeneration using deep learning

Da Ma et al.

Summary: This study achieved automatic differential diagnosis between two types of retinal pathologies (PCV and wet AMD) with similar pathological features using an explainable deep-learning-based framework. Clinically-relevant pathological features were identified and clinical interpretability was achieved through automatically detected disease-related pathologies.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence

Andreas Holzinger et al.

Summary: Medical artificial intelligence systems have achieved significant success and are crucial for improving human health. In order to enhance performance, addressing uncertainty and errors while explaining the result process is essential. Information fusion can help develop more robust and explainable machine learning models.

INFORMATION FUSION (2022)

Add to Collection

Article Neurosciences

A deep learning-based multisite neuroimage harmonization framework established with a traveling-subject dataset

Dezheng Tian et al.

Summary: The accumulation of large-sample MRI datasets from multiple sites has provided critical resources for understanding brain function and disorders. However, significant site effects hinder consistent findings across studies. In this study, a deep learning-based framework was proposed to harmonize imaging data by eliminating site effects while preserving biological characteristics. The framework performed well in removing site effects and improving data similarity, offering a powerful solution for reliable and reproducible multisite studies.

NEUROIMAGE (2022)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

3C-GAN: class-consistent CycleGAN for malaria domain adaptation model

Aimon Rahman et al.

Summary: Unpaired domain translation models like CycleGAN are popular in shifting medical image domains, but they can lead to misdiagnosis due to unwanted feature hallucination. This paper proposes a modified distribution matching loss for CycleGAN on malaria dataset to eliminate feature hallucination and preserve original class labels. Experimental results show significant reduction in feature hallucination compared to classic CycleGAN, making it safer for clinical use.

BIOMEDICAL PHYSICS & ENGINEERING EXPRESS (2021)

Add to Collection

Article Engineering, Biomedical

LF-UNet-A novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images

Da Ma et al.

Summary: A novel framework for simultaneous retinal layers and fluid segmentation was proposed, showing superior performance compared to state-of-the-art methods. Incorporating relative positional map structural prior information further improved performance.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2021)

Add to Collection

Article Neurosciences

Deep learning-based unlearning of dataset bias for MRI harmonisation and confound removal

Nicola K. Dinsdale et al.

Summary: The study proposed a deep learning based training scheme to create scanner-invariant features, reducing the influence of scanner on network predictions. The framework can harmonize multi-site datasets and adapt to various data scenarios, including biased datasets and limited training labels.

NEUROIMAGE (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Generative Adversarial Networks

Ian Goodfellow et al.

COMMUNICATIONS OF THE ACM (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Measuring the Quality of Explanations: The System Causability Scale (SCS) Comparing Human and Machine Explanations

Andreas Holzinger et al.

KUNSTLICHE INTELLIGENZ (2020)

Add to Collection

Review Engineering, Multidisciplinary

Unsupervised Domain Adaptation in Semantic Segmentation: A Review

Marco Toldo et al.

TECHNOLOGIES (2020)

Add to Collection

Review Computer Science, Artificial Intelligence

Causability and explainability of artificial intelligence in medicine

Andreas Holzinger et al.

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY (2019)

Add to Collection

Article Biology

Deep learning based retinal OCT segmentation

M. Pekala et al.

COMPUTERS IN BIOLOGY AND MEDICINE (2019)

Add to Collection

Article Biochemical Research Methods

ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks

Abhijit Guha Roy et al.

BIOMEDICAL OPTICS EXPRESS (2017)

Add to Collection

Article Optics

Retina layer segmentation using kernel graph cuts and continuous max-flow

D. Kaba et al.

OPTICS EXPRESS (2015)

Add to Collection

Editorial Material Medicine, General & Internal

UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age

Cathie Sudlow et al.

PLOS MEDICINE (2015)

Add to Collection

Article Biochemical Research Methods

Integrating structured biological data by Kernel Maximum Mean Discrepancy

Karsten M. Borgwardt et al.

BIOINFORMATICS (2006)

Add to Collection

Article Computer Science, Artificial Intelligence

Image quality assessment: From error visibility to structural similarity

Z Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2004)

Add to Collection

Article Optics

Statistics and reduction of speckle in optical coherence tomography

M Bashkansky et al.

OPTICS LETTERS (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.