scholarly journals Fproi-GAN with Fused Regional Features for the Synthesis of High-Quality Paired Medical Images

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jiale Dong ◽  
Caiwei Liu ◽  
Panpan Man ◽  
Guohua Zhao ◽  
Yaping Wu ◽  
...  
Keyword(s):  
Prediction Models ◽  
Medical Images ◽  
A Priori ◽  
Region Of Interest ◽  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
High Quality ◽  
Regional Feature ◽  
Tissue Contrast ◽  
Structural Consistency

The use of medical image synthesis with generative adversarial networks (GAN) is effective for expanding medical samples. The structural consistency between the synthesized and actual image is a key indicator of the quality of the synthesized image, and the region of interest (ROI) of the synthesized image is related to its usability, and these parameters are the two key issues in image synthesis. In this paper, the fusion-ROI patch GAN (Fproi-GAN) model was constructed by incorporating a priori regional feature based on the two-stage cycle consistency mechanism of cycleGAN. This model has improved the tissue contrast of ROI and achieved the pairwise synthesis of high-quality medical images and their corresponding ROIs. The quantitative evaluation results in two publicly available datasets, INbreast and BRATS 2017, show that the synthesized ROI images have a DICE coefficient of 0.981 ± 0.11 and a Hausdorff distance of 4.21 ± 2.84 relative to the original images. The classification experimental results show that the synthesized images can effectively assist in the training of machine learning models, improve the generalization performance of prediction models, and improve the classification accuracy by 4% and sensitivity by 5.3% compared with the cycleGAN method. Hence, the paired medical images synthesized using Fproi-GAN have high quality and structural consistency with real medical images.

scholarly journals An Intelligent cluster-based segmentation using Wavelet Features:Application to Medical Images

2010 ◽  
Author(s):  
Thavavel V ◽  
JafferBasha J
Keyword(s):  
Medical Images ◽  
Automatic Segmentation ◽  
A Priori ◽  
User Interaction ◽  
Region Of Interest ◽  
Feature Space ◽  
Discrete Wavelet ◽  
Wavelet Frames ◽  
Translation Invariant ◽  
Spherical Coordinate

Segmentation forms the onset for image analysis especially for medical images, making any abnormalities in tissues distinctly visible. Possible application includes the detection of tumor boundary in SPECT, MRI or electron MRI (EMRI). Nevertheless, tumors being heterogeneous pose a great problem when automatic segmentation is attempted to accurately detect the region of interest (ROI). Consequently, it is a challenging task to design an automatic segmentation algorithm without the incorporation of ‘a priori’ knowledge of an organ being imaged. To meet this challenge, here we propose an intelligence-based approach integrating evolutionary k-means algorithm within multi-resolution framework for feature segmentation with higher accuracy and lower user interaction cost. The approach provides several advantages. First, spherical coordinate transform (SCT) is applied on original RGB data for the identification of variegated coloring as well as for significant computational overhead reduction. Second the translation invariant property of the discrete wavelet frames (DWF) is exploited to define the features, color and texture using chromaticity of LL band and luminance of LH and HL band respectively. Finally, the genetic algorithm based K-means (GKA), which has the ability to learn intelligently the distribution of different tissue types without any prior knowledge, is adopted to cluster the feature space with optimized cluster centers. Experimental results of proposed algorithm using multi-modality images such as MRI, SPECT, and EMRI are presented and analyzed in terms of error measures to verify its effectiveness and feasibility for medical applications.

scholarly journals Medical Image Watermarking Technique for Accurate Tamper Detection in ROI and Exact Recovery of ROI

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
R. Eswaraiah ◽  
E. Sreenivasa Reddy
Keyword(s):  
Medical Image ◽  
Medical Images ◽  
Image Watermarking ◽  
Region Of Interest ◽  
Tamper Detection ◽  
High Quality ◽  
Medical Image Watermarking ◽  
Block Based ◽  
Embedding Distortion

In telemedicine while transferring medical images tampers may be introduced. Before making any diagnostic decisions, the integrity of region of interest (ROI) of the received medical image must be verified to avoid misdiagnosis. In this paper, we propose a novel fragile block based medical image watermarking technique to avoid embedding distortion inside ROI, verify integrity of ROI, detect accurately the tampered blocks inside ROI, and recover the original ROI with zero loss. In this proposed method, the medical image is segmented into three sets of pixels: ROI pixels, region of noninterest (RONI) pixels, and border pixels. Then, authentication data and information of ROI are embedded in border pixels. Recovery data of ROI is embedded into RONI. Results of experiments conducted on a number of medical images reveal that the proposed method produces high quality watermarked medical images, identifies the presence of tampers inside ROI with 100% accuracy, and recovers the original ROI without any loss.

Squint Pixel Steganography

2016 ◽  
Vol 8 (4) ◽  
pp. 37-47
Author(s):  
Rupa Ch.
Keyword(s):  
Information Security ◽  
Rapid Growth ◽  
Medical Image ◽  
Medical Images ◽  
Region Of Interest ◽  
High Accuracy ◽  
High Quality ◽  
Carrier Image ◽  
Authentic Data ◽  
Least Significant Bits

Technology is playing a major role in the rapid growth of Techno media in relation to information security. Tampers are a major handicap while transferring medical images. In order to circumvent these issues used Steganography to hide the information inside a cover medium with different carrier formats. In this paper, the author proposes a novel squint pixel based medical image steganography technique to avoid distortion by an attacker. In this method, Original medical image itself acts as a carrier image. A Medical image segmented into two sets of pixels, Region of interest (ROI) and squint pixels of region of non-interest (RONI). The authentic data and information of ROI of a medical image embedded in penultimate and least significant bits (PLSB) of squint pixels of RONI. Results of experiments on various medical images show that the proposed method produces high quality stego medical images with high accuracy and recovery of ROI data without loss.

scholarly journals Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks

2021 ◽  
Vol 7 (8) ◽  
pp. 133
Author(s):  
Jonas Denck ◽  
Jens Guehring ◽  
Andreas Maier ◽  
Eva Rothgang
Keyword(s):  
Magnetic Resonance ◽  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Data Generation ◽  
Mr Images ◽  
Generative Adversarial Network ◽  
Radiology Training ◽  
Repetition Time ◽  
Echo Time ◽  
Image Orientation

A magnetic resonance imaging (MRI) exam typically consists of the acquisition of multiple MR pulse sequences, which are required for a reliable diagnosis. With the rise of generative deep learning models, approaches for the synthesis of MR images are developed to either synthesize additional MR contrasts, generate synthetic data, or augment existing data for AI training. While current generative approaches allow only the synthesis of specific sets of MR contrasts, we developed a method to generate synthetic MR images with adjustable image contrast. Therefore, we trained a generative adversarial network (GAN) with a separate auxiliary classifier (AC) network to generate synthetic MR knee images conditioned on various acquisition parameters (repetition time, echo time, and image orientation). The AC determined the repetition time with a mean absolute error (MAE) of 239.6 ms, the echo time with an MAE of 1.6 ms, and the image orientation with an accuracy of 100%. Therefore, it can properly condition the generator network during training. Moreover, in a visual Turing test, two experts mislabeled 40.5% of real and synthetic MR images, demonstrating that the image quality of the generated synthetic and real MR images is comparable. This work can support radiologists and technologists during the parameterization of MR sequences by previewing the yielded MR contrast, can serve as a valuable tool for radiology training, and can be used for customized data generation to support AI training.

scholarly journals mustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis

2021 ◽  
pp. 101944
Author(s):  
Mahmut Yurt ◽  
Salman U.H. Dar ◽  
Aykut Erdem ◽  
Erkut Erdem ◽  
Kader K Oguz ◽  
...  
Keyword(s):  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Mr Image ◽  
Adversarial Networks

scholarly journals CDL-GAN: Contrastive Distance Learning Generative Adversarial Network for Image Generation

2021 ◽  
Vol 11 (4) ◽  
pp. 1380
Author(s):  
Yingbo Zhou ◽  
Pengcheng Zhao ◽  
Weiqin Tong ◽  
Yongxin Zhu
Keyword(s):  
Distance Learning ◽  
Feature Learning ◽  
Image Synthesis ◽  
Image Feature ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Feature Representations ◽  
Adversarial Network ◽  
Public Datasets

While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.

57 Precision neoantigen discovery using novel algorithms and expanded HLA-ligandome datasets

2020 ◽  
Vol 8 (Suppl 3) ◽  
pp. A62-A62
Author(s):  
Dattatreya Mellacheruvu ◽  
Rachel Pyke ◽  
Charles Abbott ◽  
Nick Phillips ◽  
Sejal Desai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cell Lines ◽  
Antigen Processing ◽  
Large Scale ◽  
Prediction Models ◽  
K562 Cells ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
High Quality ◽  
Tissue Samples

BackgroundAccurately identified neoantigens can be effective therapeutic agents in both adjuvant and neoadjuvant settings. A key challenge for neoantigen discovery has been the availability of accurate prediction models for MHC peptide presentation. We have shown previously that our proprietary model based on (i) large-scale, in-house mono-allelic data, (ii) custom features that model antigen processing, and (iii) advanced machine learning algorithms has strong performance. We have extended upon our work by systematically integrating large quantities of high-quality, publicly available data, implementing new modelling algorithms, and rigorously testing our models. These extensions lead to substantial improvements in performance and generalizability. Our algorithm, named Systematic HLA Epitope Ranking Pan Algorithm (SHERPA™), is integrated into the ImmunoID NeXT Platform®, our immuno-genomics and transcriptomics platform specifically designed to enable the development of immunotherapies.MethodsIn-house immunopeptidomic data was generated using stably transfected HLA-null K562 cells lines that express a single HLA allele of interest, followed by immunoprecipitation using W6/32 antibody and LC-MS/MS. Public immunopeptidomics data was downloaded from repositories such as MassIVE and processed uniformly using in-house pipelines to generate peptide lists filtered at 1% false discovery rate. Other metrics (features) were either extracted from source data or generated internally by re-processing samples utilizing the ImmunoID NeXT Platform.ResultsWe have generated large-scale and high-quality immunopeptidomics data by using approximately 60 mono-allelic cell lines that unambiguously assign peptides to their presenting alleles to create our primary models. Briefly, our primary ‘binding’ algorithm models MHC-peptide binding using peptide and binding pockets while our primary ‘presentation’ model uses additional features to model antigen processing and presentation. Both primary models have significantly higher precision across all recall values in multiple test data sets, including mono-allelic cell lines and multi-allelic tissue samples. To further improve the performance of our model, we expanded the diversity of our training set using high-quality, publicly available mono-allelic immunopeptidomics data. Furthermore, multi-allelic data was integrated by resolving peptide-to-allele mappings using our primary models. We then trained a new model using the expanded training data and a new composite machine learning architecture. The resulting secondary model further improves performance and generalizability across several tissue samples.ConclusionsImproving technologies for neoantigen discovery is critical for many therapeutic applications, including personalized neoantigen vaccines, and neoantigen-based biomarkers for immunotherapies. Our new and improved algorithm (SHERPA) has significantly higher performance compared to a state-of-the-art public algorithm and furthers this objective.

Sign in / Sign up

Export Citation Format

Share Document