Cervical lesion image enhancement based on conditional entropy generative adversarial network framework.

Early screening and diagnosis of cervical precancerous lesions are very important to prevent cervical cancer. High-quality colposcopy images will help doctors make faster and more accurate diagnoses. To tackle the problem of low image quality caused by complex interference during colposcopy operation, this paper proposed a conditional entropy generative adversarial networks framework for image enhancement. A decomposition network based on Retinex theory is constructed to obtain the reflection images of the low-quality images, then the conditional generative adversarial network is used as the enhancement network. The low-quality images and the decomposed reflection images are both input the enhancement network for training, and the conditional entropy distance is used as a part of the loss of the conditional generative adversarial network to alleviate the over-fitting problem during the training process. The test results show that compared with published methods, the proposed method of this paper can significantly improve the image quality, and can enhance the colposcopy image while retaining image details.

Computed Tomography (CT) Image Quality Enhancement via a Uniform Framework Integrating Noise Estimation and Super-Resolution Networks.

Computed tomography (CT) imaging technology has been widely used to assist medical diagnosis in recent years. However, noise during the process of imaging, and data compression during the process of storage and transmission always interrupt the image quality, resulting in unreliable performance of the post-processing steps in the computer assisted diagnosis system (CADs), such as medical image segmentation, feature extraction, and medical image classification. Since the degradation of medical images typically appears as noise and low-resolution blurring, in this paper, we propose a uniform deep convolutional neural network (DCNN) framework to handle the de-noising and super-resolution of the CT image at the same time. The framework consists of two steps: Firstly, a dense-inception network integrating an inception structure and dense skip connection is proposed to estimate the noise level. The inception structure is used to extract the noise and blurring features with respect to multiple receptive fields, while the dense skip connection can reuse those extracted features and transfer them across the network. Secondly, a modified residual-dense network combined with joint loss is proposed to reconstruct the high-resolution image with low noise. The inception block is applied on each skip connection of the dense-residual network so that the structure features of the image are transferred through the network more than the noise and blurring features. Moreover, both the perceptual loss and the mean square error (MSE) loss are used to restrain the network, leading to better performance in the reconstruction of image edges and details. Our proposed network integrates the degradation estimation, noise removal, and image super-resolution in one uniform framework to enhance medical image quality. We apply our method to the Cancer Imaging Archive (TCIA) public dataset to evaluate its ability in medical image quality enhancement. The experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on de-noising and super-resolution by providing higher peak signal to noise ratio (PSNR) and structure similarity index (SSIM) values.

Unpaired fundus image enhancement based on constrained generative adversarial networks.

Fundus photography (FP) is a crucial technique for diagnosing the progression of ocular and systemic diseases in clinical studies, with wide applications in early clinical screening and diagnosis. However, due to the nonuniform illumination and imbalanced intensity caused by various reasons, the quality of fundus images is often severely weakened, brings challenges for automated screening, analysis, and diagnosis of diseases. To resolve this problem, we developed strongly constrained generative adversarial networks (SCGAN). The results demonstrate that the quality of various datasets were more significantly enhanced based on SCGAN, simultaneously more effectively retaining tissue and vascular information under various experimental conditions. Furthermore, the clinical effectiveness and robustness of this model were validated by showing its improved ability in vascular segmentation as well as disease diagnosis. Our study provides a new comprehensive approach for FP and also possesses the potential capacity to advance artificial intelligence-assisted ophthalmic examination.

Group theoretic particle swarm optimization for gray-level medical image enhancement.

As a principal category in the promising field of medical image processing, medical image enhancement has a powerful influence on the intermedia features and final results of the computer aided diagnosis (CAD) system by increasing the capacity to transfer the image information in the optimal form. The enhanced region of interest (ROI) would contribute to the early diagnosis and the survival rate of patients. Meanwhile, the enhancement schema can be treated as the optimization approach of image grayscale values, and metaheuristics are adopted popularly as the mainstream technologies for medical image enhancement. In this study, we propose an innovative metaheuristic algorithm named group theoretic particle swarm optimization (GT-PSO) to tackle the optimization problem of image enhancement. Based on the mathematical foundation of symmetric group theory, GT-PSO comprises particle encoding, solution landscape, neighborhood movement and swarm topology. The corresponding search paradigm takes place simultaneously under the guidance of hierarchical operations and random components, and it could optimize the hybrid fitness function of multiple measurements of medical images and improve the contrast of intensity distribution. The numerical results generated from the comparative experiments show that the proposed GT-PSO has outperformed most other methods on the real-world dataset. The implication also indicates that it would balance both global and local intensity transformations during the enhancement process.

PSSGAN: Towards spectrum shift based perceptual quality enhancement for fluorescence imaging.

Fluorescence imaging has demonstrated great potential for malignant tissue inspection. However, poor imaging quality of medical fluorescent images inevitably brings challenges to disease diagnosis. Though improvement of image quality can be achieved by translating the images from low-quality domain to high-quality domain, fewer scholars have studied the spectrum translation and the prevalent cycle-consistent generative adversarial network (CycleGAN) is powerless to grasp local and semantic details, leading to produce unsatisfactory translated images. To enhance the visual quality by shifting spectrum and alleviate the under-constraint problem of CycleGAN, this study presents the design and construction of the perception-enhanced spectrum shift GAN (PSSGAN). Besides, by introducing the constraint of perceptual module and relativistic patch, the model learns effective biological structure details of image translation. Moreover, the interpolation technique is innovatively employed to validate that PSSGAN can vividly show the enhancement process and handle the perception-fidelity trade-off dilemma of fluorescent images. A novel no reference quantitative analysis strategy is presented for medical images. On the open data and collected sets, PSSGAN provided 15.32% ∼ 35.19% improvement in structural similarity and 21.55% ∼ 27.29% improvement in perceptual quality over the leading method CycleGAN. Extensive experimental results indicated that our PSSGAN achieved superior performance and exhibited vital clinical significance.

A comparative study of medical image enhancement algorithms and quality assessment metrics on COVID-19 CT images.

Medical imaging can help doctors in better diagnosis of several conditions. During the present COVID-19 pandemic, timely detection of novel coronavirus is crucial, which can help in curing the disease at an early stage. Image enhancement techniques can improve the visual appearance of COVID-19 CT scans and speed-up the process of diagnosis. In this study, we analyze some state-of-the-art image enhancement techniques for their suitability in enhancing the CT scans of COVID-19 patients. Six quantitative metrics, Entropy, SSIM, AMBE, PSNR, EME, and EMEE, are used to evaluate the enhanced images. Two experienced radiologists were involved in the study to evaluate the performance of the enhancement techniques and the quantitative metrics used to assess them.

A non-uniform quantization scheme for visualization of CT images.

Medical science heavily depends on image acquisition and post-processing for accurate diagnosis and treatment planning. The introduction of noise degrades the visual quality of the medical images during the capturing process, which may result in false perception. Therefore, medical image enhancement is an essential topic of research for the improvement of image quality. In this paper, a clustering-based contrast enhancement technique is presented for computed tomography (CT) images. Our approach uses the recursive splitting of data into clusters targeting the maximum error reduction in each cluster. This leads to grouping similar pixels in every cluster, maximizing inter-cluster and minimizing intra-cluster similarities. A suitable number of clusters can be chosen to represent high precision data with the desired bit-depth. We use 256 clusters to convert 16-bit CT scans to 8-bit images suitable for visualization on standard low dynamic range displays. We compare our method with several existing contrast enhancement algorithms and show that the proposed technique provides better results in terms of execution efficiency and quality of enhanced images.

Robust DC optimization and its application in medical image processing.

BACKGROUND: Many medical image processing problems can be translated into solving the optimization models. In reality, there are lots of nonconvex optimization problems in medical image processing. OBJECTIVE: In this paper, we focus on a special class of robust nonconvex optimization, namely, robust optimization where given the parameters, the objective function can be expressed as the difference of convex functions. METHODS: We present the necessary condition for optimality under general assumptions. To solve this problem, a sequential robust convex optimization algorithm is proposed. RESULTS: We show that the new algorithm is globally convergent to a stationary point of the original problem under the general assumption about the uncertain set. The application of medical image enhancement is conducted and the numerical result shows its efficiency.