Deep learning solution for medical image localization and orientation detection

Zhao, Yu; Zeng, Ke; Zhao, Yiyuan; Bhatia, Parmeet; Ranganath, Mahesh; Kozhikkavil, Muhammed Labeeb; Li, Chen; Hermosillo, Gerardo

doi:10.1016/j.media.2022.102529

Cited by 13 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The limitations of our study include the focus on COVID-19 alone. For future work, we plan to extend our work in two directions: first, we will extend the MAE model to handle 3D medical images, such as 3D brain imaging for Alzheimer’s Disease [ 43 , 44 , 45 ]; second, we will explore the potential of the MAE for other tasks, such as image segmentation and localization [ 6 , 46 ], beyond image classification.…”

Section: Discussionmentioning

confidence: 99%

Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder

Xing,

Liang,

Wang

et al. 2023

Bioengineering

View full text Add to dashboard Cite

The COVID-19 pandemic has underscored the urgent need for rapid and accurate diagnosis facilitated by artificial intelligence (AI), particularly in computer-aided diagnosis using medical imaging. However, this context presents two notable challenges: high diagnostic accuracy demand and limited availability of medical data for training AI models. To address these issues, we proposed the implementation of a Masked AutoEncoder (MAE), an innovative self-supervised learning approach, for classifying 2D Chest X-ray images. Our approach involved performing imaging reconstruction using a Vision Transformer (ViT) model as the feature encoder, paired with a custom-defined decoder. Additionally, we fine-tuned the pretrained ViT encoder using a labeled medical dataset, serving as the backbone. To evaluate our approach, we conducted a comparative analysis of three distinct training methods: training from scratch, transfer learning, and MAE-based training, all employing COVID-19 chest X-ray images. The results demonstrate that MAE-based training produces superior performance, achieving an accuracy of 0.985 and an AUC of 0.9957. We explored the mask ratio influence on MAE and found ratio = 0.4 shows the best performance. Furthermore, we illustrate that MAE exhibits remarkable efficiency when applied to labeled data, delivering comparable performance to utilizing only 30% of the original training dataset. Overall, our findings highlight the significant performance enhancement achieved by using MAE, particularly when working with limited datasets. This approach holds profound implications for future disease diagnosis, especially in scenarios where imaging information is scarce.

show abstract

Section: Discussionmentioning

confidence: 99%

Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder

Xing,

Liang,

Wang

et al. 2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…Zhao et al [ 161 ] proposed a scientific studies and healthcare diagnostics both heavily rely on Magnetic Resonance (MR) scanning. The location of the layer cluster has a significant impact on the utility of the recovery since MR scanning has a strong in-slice accuracy and a poor through-slice resolution.…”

Section: Deep Learning For Medical Image Analysis and Cadmentioning

confidence: 99%

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Iqbal

Qureshi

et al. 2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

show abstract

“…More recently, deep learning methods were applied to address the challenge of detecting image orientations in various critical sectors [1,2,4].…”

Section: Related Workmentioning

confidence: 99%

“…Because there are four possible probabilities for image orientation detection instead of two, we aim to build a multiclass logistic regression model [34]. We use the Limitedmemory Broyden Fletcher Goldfarb Shanno(L-BFGH) algorithm to solve the optimization problem (1), which is an algorithm from the family of quasi-Newton methods. We applied the one-vs-rest (OVR) approach: and constructed a binary problem for each class to differentiate instances of that class from all other classes.…”

Section: Trainingmentioning

confidence: 99%

“…Detecting image orientation is crucial in many compulsory domains, such as medical diagnosis, robotassisted automatic intervention systems (RAIS), authentication systems, and face detection. For instance, in magnetic resonance imaging (MRI), the position and orientation of slice groups are critical for achieving high image diagnostic quality and meeting various clinical workflows [1]. Many bronchial branches with standard orientations are found in automatic robot-assisted intervention systems (RAIS), such as bronchoscopy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning for Automatic Image Orientation Detection Using Deep Learning and Logistic Regression

Amjoud

Amrouch

2022

IEEE Access

View full text Add to dashboard Cite

The number of images produced each day increased significantly. The ability to detect and correct an image's orientation can provide several advantages in computer vision. This paper presents a new framework based on a transfer learning technique for automatically detecting image orientation. To implement the power of deep neural networks, we applied a convolutional neural network model pretrained on the ImageNet database for feature extraction. Then, we built a multi-class logistic regression classifier to detect the four image orientation probabilities corresponding to the following orientations (0 for no orientation, 90, 180, and 270). We tested our model on the SUN-397 dataset, one of the most extensive data sets currently used for image-orientation detection tasks. We conducted a cross-dataset evaluation for in-depth testing and analysis. We also examined our model using different old and recent state-of-the-art convolutional neural network (CNN) baselines. We demonstrate that our model yields promising results based on transfer learning for feature extraction combined with a one-vs-rest logistic regression classifier. Our proposed model surpassed the state-of-the-art results in terms of accuracy and performance.

show abstract

Deep learning solution for medical image localization and orientation detection

Cited by 13 publications

References 11 publications

Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder

Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Transfer Learning for Automatic Image Orientation Detection Using Deep Learning and Logistic Regression

Contact Info

Product

Resources

About