End-to-End Adversarial Retinal Image Synthesis

Supervised Segmentation of Un-Annotated Retinal Fundus Images by Synthesis

We focus on the practical challenge of segmenting new retinal fundus images that are dissimilar to existing well-annotated data sets. It is addressed in this paper by a supervised learning pipeline, with its core being the construction of a synthetic fundus image data set using the proposed R-sGAN technique. The resulting synthetic images are realistic-looking in terms of the query images while maintaining the annotated vessel structures from the existing data set. This helps to bridge the mismatch between the query images and the existing well-annotated data set. As a consequence, any known supervised fundus segmentation technique can be directly utilized on the query images, after training on this synthetic data set. Extensive experiments on different fundus image data sets demonstrate the competitiveness of the proposed approach in dealing with a diverse range of mismatch settings.

Deep learning in medical imaging and radiation therapy

The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

Towards cross-modal organ translation and segmentation: A cycle- and shape-consistent generative adversarial network

Synthesized medical images have several important applications. For instance, they can be used as an intermedium in cross-modality image registration or used as augmented training samples to boost the generalization capability of a classifier. In this work, we propose a generic cross-modality synthesis approach with the following targets: 1) synthesizing realistic looking 2D/3D images without needing paired training data, 2) ensuring consistent anatomical structures, which could be changed by geometric distortion in cross-modality synthesis and 3) more importantly, improving volume segmentation by using synthetic data for modalities with limited training samples. We show that these goals can be achieved with an end-to-end 2D/3D convolutional neural network (CNN) composed of mutually-beneficial generators and segmentors for image synthesis and segmentation tasks. The generators are trained with an adversarial loss, a cycle-consistency loss, and also a shape-consistency loss (supervised by segmentors) to reduce the geometric distortion. From the segmentation view, the segmentors are boosted by synthetic data from generators in an online manner. Generators and segmentors prompt each other alternatively in an end-to-end training fashion. We validate our proposed method on three datasets, including cardiovascular CT and magnetic resonance imaging (MRI), abdominal CT and MRI, and mammography X-rays from different data domains, showing both tasks are beneficial to each other and coupling these two tasks results in better performance than solving them exclusively.

Generative Adversarial Networks for the Creation of Realistic Artificial Brain Magnetic Resonance Images

Even as medical data sets become more publicly accessible, most are restricted to specific medical conditions. Thus, data collection for machine learning approaches remains challenging, and synthetic data augmentation, such as generative adversarial networks (GAN), may overcome this hurdle. In the present quality control study, deep convolutional GAN (DCGAN)–based human brain magnetic resonance (MR) images were validated by blinded radiologists. In total, 96 T1-weighted brain images from 30 healthy individuals and 33 patients with cerebrovascular accident were included. A training data set was generated from the T1-weighted images and DCGAN was applied to generate additional artificial brain images. The likelihood that images were DCGAN-created versus acquired was evaluated by 5 radiologists (2 neuroradiologists [NRs], vs 3 non-neuroradiologists [NNRs]) in a binary fashion to identify real vs created images. Images were selected randomly from the data set (variation of created images, 40%–60%). None of the investigated images was rated as unknown. Of the created images, the NRs rated 45% and 71% as real magnetic resonance imaging images (NNRs, 24%, 40%, and 44%). In contradistinction, 44% and 70% of the real images were rated as generated images by NRs (NNRs, 10%, 17%, and 27%). The accuracy for the NRs was 0.55 and 0.30 (NNRs, 0.83, 0.72, and 0.64). DCGAN-created brain MR images are similar enough to acquired MR images so as to be indistinguishable in some cases. Such an artificial intelligence algorithm may contribute to synthetic data augmentation for “data-hungry” technologies, such as supervised machine learning approaches, in various clinical applications.

Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training

To realize the full potential of deep learning for medical imaging, large annotated datasets are required for training. Such datasets are difficult to acquire due to privacy issues, lack of experts available for annotation, underrepresentation of rare conditions, and poor standardization. The lack of annotated data has been addressed in conventional vision applications using synthetic images refined via unsupervised adversarial training to look like real images. However, this approach is difficult to extend to general medical imaging because of the complex and diverse set of features found in real human tissues. We propose a novel framework that uses a reverse flow, where adversarial training is used to make real medical images more like synthetic images, and clinically-relevant features are preserved via self-regularization. These domain-adapted synthetic-like images can then be accurately interpreted by networks trained on large datasets of synthetic medical images. We implement this approach on the notoriously difficult task of depth-estimation from monocular endoscopy which has a variety of applications in colonoscopy, robotic surgery, and invasive endoscopic procedures. We train a depth estimator on a large data set of synthetic images generated using an accurate forward model of an endoscope and an anatomically-realistic colon. Our analysis demonstrates that the structural similarity of endoscopy depth estimation in a real pig colon predicted from a network trained solely on synthetic data improved by 78.7% by using reverse domain adaptation.

Deep learning with cinematic rendering: fine-tuning deep neural networks using photorealistic medical images

Deep learning has emerged as a powerful artificial intelligence tool to interpret medical images for a growing variety of applications. However, the paucity of medical imaging data with high-quality annotations that is necessary for training such methods ultimately limits their performance. Medical data is challenging to acquire due to privacy issues, shortage of experts available for annotation, limited representation of rare conditions and cost. This problem has previously been addressed by using synthetically generated data. However, networks trained on synthetic data often fail to generalize to real data. Cinematic rendering simulates the propagation and interaction of light passing through tissue models reconstructed from CT data, enabling the generation of photorealistic images. In this paper, we present one of the first applications of cinematic rendering in deep learning, in which we propose to fine-tune synthetic data-driven networks using cinematically rendered CT data for the task of monocular depth estimation in endoscopy. Our experiments demonstrate that: (a) convolutional neural networks (CNNs) trained on synthetic data and fine-tuned on photorealistic cinematically rendered data adapt better to real medical images and demonstrate more robust performance when compared to networks with no fine-tuning, (b) these fine-tuned networks require less training data to converge to an optimal solution, and (c) fine-tuning with data from a variety of photorealistic rendering conditions of the same scene prevents the network from learning patient-specific information and aids in generalizability of the model. Our empirical evaluation demonstrates that networks fine-tuned with cinematically rendered data predict depth with 56.87% less error for rendered endoscopy images and 27.49% less error for real porcine colon endoscopy images.