Generative Adversarial Network for Medical Images (MI-GAN)

Iqbal, Talha; Ali, Hazrat

doi:10.1007/s10916-018-1072-9

Cited by 200 publications

(107 citation statements)

References 34 publications

Supporting

Mentioning

104

Contrasting

Unclassified

Order By: Relevance

“…Most works on the GANs have reported the use of an encoder-decoder style structure for generator network. So, a similar architecture for the generator is retained [37] [43]. This allows us to use noise code in a natural manner.…”

Section: B Generator Architecturementioning

confidence: 99%

“…They achieved competitive dice score on DRIVE and STARE datasets of retinal fundoscopic images [36]. In MI-GAN [37], the authors proposed a framework for the generation of synthetic medical images as well as their segmented masks. The synthetic images and their masks are further used for training of segmentation network, and the authors reported state-ofthe-art dice score on DRIVE and STARE datasets [37].…”

Section: Introductionmentioning

confidence: 99%

“…In this work, GAN based model for segmentation of lungs from Chest X-ray images is presented. Our model includes a generator similar to U-net architecture, [37] and multiple discriminators which are binary classifiers, which has not been reported to the best of our knowledge. Our main contributions are:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Chest X-ray (CXR) is a low-cost medical imaging technique. It is a common procedure for the identification of many respiratory diseases compared to MRI, CT, and PET scans. This paper presents the use of generative adversarial networks (GAN) to perform the task of lung segmentation on a given CXR. GANs are popular to generate realistic data by learning the mapping from one domain to another. In our work, the generator of the GAN is trained to generate a segmented mask of a given input CXR. The discriminator distinguishes between a ground truth and the generated mask, and updates the generator through the adversarial loss measure. The objective is to generate masks for the input CXR, which are as realistic as possible compared to the ground truth masks. The model is trained and evaluated using four different discriminators referred to as D1, D2, D3 and D4 respectively. Experimental results on three different CXR datasets reveal that the proposed model is able to achieve a dice-score of 0.9740, and IOU score of 0.943, which are better than other reported state-of-the art results. INDEX TERMS Deep learning, generative adversarial networks, lung segmentation, medical imaging.

show abstract

Section: B Generator Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning [13]- [15] has greatly revolutionized many different domains involving analysis of a large image, audio, text, video, or tabular data. Of particular relevance to the work reported in this paper are the advancement made in image and video processing using deep learning methods for segmentation, identification, recognition [16], deep learning for time-series data (e.g., speech) [17], and deep learning in medical imaging [12], [18]. Hence, we present the relevant details on deep learning for segmentation and signal detection in the subsequent text.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Pipeline for Identification of Motor Units in Musculoskeletal Ultrasound

et al. 2020

Self Cite

View full text Add to dashboard Cite

Skeletal muscles are functionally regulated by populations of so-called motor units (MUs). An MU comprises a bundle of muscle fibers controlled by a neuron from the spinal cord. Current methods to diagnose neuromuscular diseases and monitor rehabilitation, and study sports sciences rely on recording and analyzing the bio-electric activity of the MUs. However, these methods provide information from a limited part of a muscle. Ultrasound imaging provides information from a large part of the muscle. It has recently been shown that ultrafast ultrasound imaging can be used to record and analyze the mechanical response of individual MUs using blind source separation. In this work, we present an alternative method-a deep learning pipeline-to identify active MUs in ultrasound image sequences, including segmentation of their territories and signal estimation of their mechanical responses (twitch train). We train and evaluate the model using simulated data mimicking the complex activation pattern of tens of activated MUs with overlapping territories and partially synchronized activation patterns. Using a slow fusion approach (based on 3D CNNs), we transform the spatiotemporal image sequence data to 2D representations and apply a deep neural network architecture for segmentation. Next, we employ a second deep neural network architecture for signal estimation. The results show that the proposed pipeline can effectively identify individual MUs, estimate their territories, and estimate their twitch train signal at low contraction forces. The framework can retain spatio-temporal consistencies and information of the mechanical response of MU activity even when the ultrasound image sequences are transformed into a 2D representation for compatibility with more traditional computer vision and image processing techniques. The proposed pipeline is potentially useful to identify simultaneously active MUs in whole muscles in ultrasound image sequences of voluntary skeletal muscle contractions at low force levels. INDEX TERMS motor unit, decomposition, ultrafast ultrasound, medical imaging, deep learning, mechanical response, neural networks, recurrent neural networks.

show abstract

“…Deep learning (a sub branch of machine learning) algorithms have been popular for automatic recognition of digits and characters of different languages. Deep networks can be trained in supervised fashion requiring labels, or in an unsupervised way without requirements of labels [3], [4], [5]. In this work, we use an autoencoder network and a convolutional neural network (CNN) trained with 85% portion of the dataset and tested with the remaining 15% of the data.…”

Section: Introductionmentioning

confidence: 99%

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

et al. 2020

Self Cite

View full text Add to dashboard Cite

Automatic recognition of Urdu handwritten digits and characters, is a challenging task. It has applications in postal address reading, bank's cheque processing, and digitization and preservation of handwritten manuscripts from old ages. While there exists a significant work for automatic recognition of handwritten English characters and other major languages of the world, the work done for Urdu language is extremely insufficient. This paper has two goals. Firstly, we introduce a pioneer dataset for handwritten digits and characters of Urdu, containing samples from more than 900 individuals. Secondly, we report results for automatic recognition of handwritten digits and characters as achieved by using deep auto-encoder network and convolutional neural network. More specifically, we use a two-layer and a three-layer deep autoencoder network and convolutional neural network and evaluate the two frameworks in terms of recognition accuracy. The proposed framework of deep autoencoder can successfully recognize digits and characters with an accuracy of 97% for digits only, 81% for characters only and 82% for both digits and characters simultaneously. In comparison, the framework of convolutional neural network has accuracy of 96.7% for digits only, 86.5% for characters only and 82.7% for both digits and characters simultaneously. These frameworks can serve as baselines for future research on Urdu handwritten text.

show abstract

Generative Adversarial Network for Medical Images (MI-GAN)

Cited by 200 publications

References 34 publications

Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks

Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks

A Deep Learning Pipeline for Identification of Motor Units in Musculoskeletal Ultrasound

Pioneer dataset and automatic recognition of Urdu handwritten characters using a deep autoencoder and convolutional neural network

Contact Info

Product

Resources

About