MRI Knee Domain Translation for Unsupervised Segmentation By CycleGAN (data from Osteoarthritis initiative (OAI))

Felfeliyan, Banafshe; Hareendranathan, Abhilash Rakkunedeth; Kuntze, Gregor; Jaremko, Jacob L.; Ronsky, Janet L.

doi:10.1109/embc46164.2021.9629705

Cited by 8 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1), and ranges from 0 to ∞. The cosine similarity loss or distance [67] computed for a pair of vectorized slice stacks (X, Y ) as shown in Eqn. (2).…”

Section: E Performance Evaluationmentioning

confidence: 99%

Outlier-Based Autism Detection Using Longitudinal Structural MRI

et al. 2022

View full text Add to dashboard Cite

Diagnosis of Autism Spectrum Disorder (ASD) using clinical evaluation (cognitive tests) is challenging due to wide variations amongst individuals. Since no effective treatment exists, prompt and reliable ASD diagnosis can enable the effective preparation of treatment regimens. This paper proposes structural Magnetic Resonance Imaging (sMRI)-based ASD diagnosis via an outlier detection approach. To learn spatio-temporal patterns in structural brain connectivity, a Generative Adversarial Network (GAN) is trained exclusively with sMRI scans of healthy subjects. Given a stack of three adjacent slices as input, the GAN generator reconstructs the next three adjacent slices; the GAN discriminator then identifies ASD sMRI scan reconstructions as outliers. This model is compared against two other baselines-a simpler UNet and a sophisticated Self-Attention GAN. Axial, Coronal and Sagittal sMRI slices from the multi-site ABIDE II dataset are used for evaluation. Extensive experiments reveal that our ASD detection framework performs comparably with the state-of-the-art with far fewer training data. Furthermore, longitudinal data (two scans per subject over time) achieve 17-28% higher accuracy than cross-sectional data (one scan per subject). Among other findings, metrics employed for model training as well as reconstruction loss computation impact detection performance, and the coronal modality is found to best encode structural information for ASD detection.

show abstract

“…(1), and ranges from 0 to ∞. The cosine similarity loss or distance [67] computed for a pair of vectorized slice stacks (X, Y ) as shown in Eqn. (2).…”

Section: E Performance Evaluationmentioning

confidence: 99%

Outlier-Based Autism Detection Using Longitudinal Structural MRI

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For source-involved UDA approaches, we compared the proposed method with the classic pixel-level UDA framework CycleGAN [29] and the feature-level UDA method presented by Panfilov [18], which is called UDA-mixup. Both have been demonstrated for use in knee tissue segmentation [18,28]. For source-free UDA methods, we compared the proposed framework against DPL [22], TT-SFUDA [23], and SFUDA [24].…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

“…This strategy has been explored for the segmentation of cardiac structures [26] and abdominal organs [27] with domain adaptation between MRI and computed tomography (CT). Felfeliyan et al [28] combined CycleGAN [29] with UNet and trained the network using unpaired source and target domain data to segment the knee structure.…”

Section: A Unsupervised Domain Adaptationmentioning

confidence: 99%

Source-free unsupervised adaptive segmentation for knee joint MRI

Li,

Zhao,

Zhang

et al. 2024

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…It establishes neural networks that can simulate the human brain for analytical learning. It stimulates the mechanism of human brain to interpret data, such as images, texts, and sounds, and is also widely used in the field of clinical medical images [16].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Multimodal 3 T MRI for the Diagnosis of Knee Osteoarthritis

Tang

Zhao

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

The objective of this study was to investigate the application effect of deep learning model combined with different magnetic resonance imaging (MRI) sequences in the evaluation of cartilage injury of knee osteoarthritis (KOA). Specifically, an image superresolution algorithm based on an improved multiscale wide residual network model was proposed and compared with the single-shot multibox detector (SSD) algorithm, superresolution convolutional neural network (SRCNN) algorithm, and enhanced deep superresolution (EDSR) algorithm. Meanwhile, 104 patients with KOA diagnosed with cartilage injury were selected as the research subjects and underwent MRI scans, and the diagnostic performance of different MRI sequences was analyzed using arthroscopic results as the gold standard. It was found that the image reconstructed by the model in this study was clear enough, with minimum noise and artifacts, and the overall quality was better than that processed by other algorithms. Arthroscopic analysis found that grade I and grade II lesions concentrated on patella (26) and femoral trochlear (15). In addition to involving the patella and femoral trochlea, grade III and grade IV lesions gradually developed into the medial and lateral articular cartilage. The 3D-DS-WE sequence was found to be the best sequence for diagnosing KOA injury, with high diagnostic accuracy of over 95% in grade IV lesions. The consistency test showed that the 3D-DESS-WE sequence and T2 ∗ mapping sequence had a strong consistency with the results of arthroscopy, and the Kappa consistency test values were 0.748 and 0.682, respectively. In conclusion, MRI based on deep learning could clearly show the cartilage lesions of KOA. Of different MRI sequences, 3D-DS-WE sequence and T2 ∗ mapping sequence showed the best diagnosis results for different degrees of KOA injury.

show abstract

MRI Knee Domain Translation for Unsupervised Segmentation By CycleGAN (data from Osteoarthritis initiative (OAI))

Cited by 8 publications

References 20 publications

Outlier-Based Autism Detection Using Longitudinal Structural MRI

Outlier-Based Autism Detection Using Longitudinal Structural MRI

Source-free unsupervised adaptive segmentation for knee joint MRI

Deep Learning-Based Multimodal 3 T MRI for the Diagnosis of Knee Osteoarthritis

Contact Info

Product

Resources

About