Generalizable medical image enhancement using structure-preserved diffusion models

Image resolution enhancement is a problem of considerable interest in all medical imaging modalities. Unlike general purpose imaging or video processing, for a very long time, medical image resolution enhancement has been based on optimization of the imaging devices. Although some recent works purport to deal with image postprocessing, much remains to be done regarding medical image enhancement via postprocessing, especially in ultrasound imaging. We face a resolution improvement issue in the case of medical ultrasound imaging. We propose to investigate this problem using multidimensional autoregressive (AR) models. Noting that the estimation of the envelope of an ultrasound radio frequency (RF) signal is very similar to the estimation of classical Fourier-based power spectrum estimation, we theoretically show that a domain change and a multidimensional AR model can be used to achieve super-resolution in ultrasound imaging provided the order is estimated correctly. Here, this is done by means of a technique that simultaneously estimates the order and the parameters of a multidimensional model using relevant regression matrix factorization. Doing so, the proposed method specifically fits ultrasound imaging and provides an estimated envelope. Moreover, an expression that links the theoretical image resolution to both the image acquisition features (such as the point spread function) and a postprocessing feature (the AR model) order is derived. The overall contribution of this work is threefold. First, it allows for automatic resolution improvement. Through a simple model and without any specific manual algorithmic parameter tuning, as is used in common methods, the proposed technique simply and exclusively uses the ultrasound RF signal as input and provides the improved B-mode as output. Second, it allows for the a priori prediction of the improvement in resolution via the knowledge of the parametric model order before actual processing. Finally, to achieve the previous goal, while classical parametric methods would first estimate the model order and then the model parameters, our approach estimates the model parameters and the order simultaneously. The effectiveness of the methodology is validated using two-dimensional synthetic and in vivo data. We show that, compared to other techniques, our method provides better results from a qualitative and a quantitative viewpoint.

Cold SegDiffusion: A novel diffusion model for medical image segmentation

Problem statement: One of the most common degradations in medical images is their poor contrast quality and noise. The DICOM image consists of speckle (multiplicative noise). While the image is enhanced, the multiplicative noise present in the image is also enhanced. Approach: This study describes the hybrid method to improve the image quality of Digital Imaging and Communications in Medicine (DICOM) images. The idea of image enhancement technique is to improve the quality of an image for early diagnosis . Then followed by a noise reduction using speckle reduction anisotropic filter. This suggests the use of contrast enhancement methods as an attempt to modify the intensity distribution of the image and to reduce the multiplicative noise. Results: In this research study, a new approach for DICOM image is done by applying contrast stretching and anisotropic diffusion where denoising of multiplica tive noise is carried out and the level of contrast is improved. The quality of the image is enhanced and noise free for DICOM image analysis. The effectiveness of hybrid method is proved by quantit ative approach. Conclusion and Recommendation: The performance of the proposed study is compared with the existing traditional algorithm and real time medical diagnosis image.

Medical ultrasound images are usually degraded by a specific type of noise, called speckle. The presence of speckle noise in medical ultrasound images will reduce the image quality and affect the effective information, which can potentially cause a misdiagnosis. Therefore, medical image enhancement processing has been extensively studied and several denoising approaches have been introduced and developed. In the current work, a robust fractional partial differential equation (FPDE) model based on the anomalous diffusion theory is proposed and used for medical ultrasound image enhancement. An efficient computational approach based on a combination of a time integration scheme and localized meshless method in a domain decomposition framework is performed to deal with the model. {In order to evaluate the performance of the proposed de-speckling approach, it is used for speckle noise reduction of a synthetic ultrasound image degraded by different levels of speckle noise. The results indicate the superiority of the proposed approach in comparison with classical anisotropic diffusion denoising model (Catt$acute{e}$'s pde model).}

Medical imaging help medical doctors provide faster and more efficient diagnoses to their patients. Medical image quality directly influences diagnosis. However, when medical images are acquired, they often present degradations such as poor detail or low contrast. This work presents an algorithm that improves contrast and detail, preserving the natural brightness of medical images. The proposed method is based on multiscale top-hat transform by reconstruction. It extracts multiple features from the image that are then used to enhance the medical image. To quantify the performance of the proposed method, 100 medical images from a public database were used. Experiments show that the proposal improves contrast, introducing less distortion and preserving the average brightness of medical images.

In this paper we use the HSI color space as an alternative to RGB space. The HSI space considers the image as a combination of the components: hue, saturation and intensity. In this paper we propose to design a chromatic filter in order to obtain improvements in the enhancement of medical images. In image processing systems it is usual specify colors in a form compatible with the hardware used. The RGB color model, where is computationally convenient, is not very useful in the specification and color recognition. The human being does not recognize a color by having an amount of red, green or blue components, but uses attributes perceptual of hue, saturation and intensity. The chromatics models HSI, HLS, HSV, and its variants, encodes the color with the above attributes and are defined as intuitive spaces.

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

Medical image segmentation is a fundamental task in medical image analysis, playing a crucial role in disease diagnosis, treatment planning, and clinical decision-making. Accurate segmentation of anatomical structures, such as blood vessels, organs, and lesions, is essential for reliable medical interpretations. However, existing segmentation models often face challenges in effectively capturing both local and global features within medical images. Traditional convolutional neural networks (CNNs) excel at extracting fine-grained local features but struggle to model long-range dependencies due to their limited receptive fields. Conversely, transformer-based models can capture global contextual relationships but often fail to preserve detailed local structures, leading to suboptimal segmentation performance. The purpose of this study is to develop SEFormer, a novel hybrid network that integrates SENet, ResNet, and Transformer to enhance medical image segmentation. SEFormer aims to effectively capture both local and global features, addressing the limitations of traditional CNNs and transformer-based models.SENet is incorporated to recalibrate feature maps by adaptively emphasizing informative features, thereby compensating for the global representation limitations of CNNs. Meanwhile, the ResNet backbone ensures deep feature extraction while maintaining computational efficiency. Additionally, the Transformer module is introduced to capture long-range dependencies and enhance contextual awareness, complementing the local feature extraction capabilities of CNNs. This hybrid approach allows SEFormer to balance fine-grained spatial details with broader contextual information, leading to more precise segmentation results.Furthermore, to mitigate information loss during feature extraction and ensure a more complete and hierarchical representation of image information, we introduce a feature pyramid structure inspired by multi-scale image pyramid models. By progressively increasing the receptive field across different scales and employing skip connections, SEFormer effectively fuses multi-scale local and global features at each stage of the pyramid. This hierarchical fusion mechanism ensures a richer and more robust feature representation, which is particularly beneficial for segmenting complex medical structures such as blood vessels. We evaluate SEFormer on the CHASE_DB1 dataset, a widely used benchmark for retinal vessel segmentation. Experimental results demonstrate that SEFormer outperforms existing state-of-the-art segmentation methods, achieving a 3.25% improvement in segmentation accuracy. Additionally, we conduct ablation studies to verify the contributions of different components within SEFormer. The results show that incorporating SENet enhances feature recalibration and channel attention, while the Transformer module significantly improves global context awareness. The feature pyramid structure further contributes to performance gains by ensuring a multi-scale representation of vascular structures. Compared to conventional CNN-based methods, our approach achieves better segmentation accuracy with improved robustness to variations in vessel thickness, noise, and image contrast. Furthermore, SEFormer maintains computational efficiency, making it suitable for real-world clinical applications where both accuracy and processing speed are critical. SEFormer provides an efficient and accurate approach for medical image segmentation by leveraging the complementary strengths of CNNs, SENet, and Transformers while integrating a feature pyramid structure to maximize feature representation. Future research directions include extending SEFormer to other medical imaging modalities, such as CT and MRI scans, as well as exploring further optimization techniques to reduce computational costs while maintaining high segmentation performance. Additionally, integrating SEFormer with active learning frameworks could further improve segmentation performance by leveraging expert-annotated data more efficiently.

<p>Pneumonia is a severe lung infection, chest X-ray (CXR) image preferred to find infection. Real images lost its quality, resolution and other feature due to transmission. So good qualitative datasets are very limited. Quality enhancement in medical images is challenging task for researchers. And quality in clinical diagnosis of any disease in deep learning play a very important role. So, this paper presents an aspect with importance of quality in medical images CXR of a particular dataset and how to enhance and create new images with high quality resolution, that is re-used for classification in deep learning. Super resolution convolutional neural netwok (SRCNN) is deep learning based method, which is used for improving resolution in image. Super resolution means low resolution (LR) images from dataset is to be reconstructed or magnified into high resolution (HR). The objective behind this study is to measure the effect of super resolution with quality index, peak signal-to-noise ratio (PSNR), mean squared error (MSE), and structural similarity index measure (SSIM). This experinment performed on 200 images with 10 batches, each batch has 20 images from Kermany dataset, select LR images and converted into HR with SRCNN. Then we find PSNR value of image is increase upto 2 to 5 DB, and MSE of qood quality images is near to zero and MSE decrease up to 20-25, SSIM value have little variation due to same pattern is found in input and output images. Enhancement means highlight or improve the region of interest of pneumonic images. Main goal of this study is to preapare a modified dataset which is further used for classification.</p>

Ultrasound (US) imaging application in medicine and other fields is enormous. It has several advantages over other medical imaging modalities. The use of US in diagnosis is well established because of its noninvasive nature, portable, accurate, low-cost imaging modality, capable of forming real-time imaging and continuing improvement in image quality. Medical images and satellite images are usually degraded by noise during image acquisition and transmission process. It is estimated that 1 out of every form medical diagnostic image studies in the world involves ultrasonic techniques. The objectives of this article are to give an overview of the types of speckle reduction techniques in US imaging, present a new technique of speckle reduction, and carry out a comparative evaluation of despeckle filtering based on image quality metrics. A new speckle suppression method and coherence enhancement of medical US image are proposed: 9 despeckled filtering techniques and 5 edge detection operators, with the result evaluated by image quality metrics. The best edge detection hybrid with best filter, quality evaluation metrics has been found that the proposed method performance better than all other methods, while the structural details and result preserving of small and important image feature that contain diagnostic information in a better way than other despeckling filter.

Large-scale, big-variant, high-quality data are crucial for developing robust and successful deep-learning models for medical applications since they potentially enable better generalization performance and avoid overfitting. However, the scarcity of high-quality labeled data always presents significant challenges. This paper proposes a novel approach to address this challenge by developing controllable diffusion models for medical image synthesis, called DiffBoost. We leverage recent diffusion probabilistic models to generate realistic and diverse synthetic medical image data that preserve the essential characteristics of the original medical images by incorporating edge information of objects to guide the synthesis process. In our approach, we ensure that the synthesized samples adhere to medically relevant constraints and preserve the underlying structure of imaging data. Due to the random sampling process by the diffusion model, we can generate an arbitrary number of synthetic images with diverse appearances. To validate the effectiveness of our proposed method, we conduct an extensive set of medical image segmentation experiments on multiple datasets, including Ultrasound breast (+13.87%), CT spleen (+0.38%), and MRI prostate (+7.78%), achieving significant improvements over the baseline segmentation methods. The promising results demonstrate the effectiveness of our DiffBoost for medical image segmentation tasks and show the feasibility of introducing a first-ever text-guided diffusion model for general medical image segmentation tasks. With carefully designed ablation experiments, we investigate the influence of various data augmentations, hyper-parameter settings, patch size for generating random merging mask settings, and combined influence with different network architectures. Source code with checkpoints are available at https://github.com/NUBagciLab/DiffBoost.

Deep networks require a considerable amount of training data otherwise these networks generalize poorly. Data Augmentation techniques help the network generalize better by providing more variety in the training data. Standard data augmentation techniques such as flipping, and scaling, produce new data that is a modified version of the original data. Generative Adversarial networks (GANs) have been designed to generate new data that can be exploited. In this paper, we propose a new GAN model, named StynMedGAN for synthetically generating medical images to improve the performance of classification models. StynMedGAN builds upon the state-of-the-art styleGANv2 that has produced remarkable results generating all kinds of natural images. We introduce a regularization term that is a normalized loss factor in the existing discriminator loss of styleGANv2. It is used to force the generator to produce normalized images and penalize it if it fails. Medical imaging modalities, such as X-Rays, CT-Scans, and MRIs are different in nature, we show that the proposed GAN extends the capacity of styleGANv2 to handle medical images in a better way. This new GAN model (StynMedGAN) is applied to three types of medical imaging: X-Rays, CT scans, and MRI to produce more data for the classification tasks. To validate the effectiveness of the proposed model for the classification, 3 classifiers (CNN, DenseNet121, and VGG-16) are used. Results show that the classifiers trained with StynMedGAN-augmented data outperform other methods that only used the original data. The proposed model achieved 100%, 99.6%, and 100% for chest X-Ray, Chest CT-Scans, and Brain MRI respectively. The results are promising and favor a potentially important resource that can be used by practitioners and radiologists to diagnose different diseases.

High quality medical images are the foundation of clinical diagnosis and treatment, but their quality may decrease due to imaging noise, artifacts, and uneven lighting. To address this issue, this paper proposes a novel Multi-scale Deep Residual Shrinkage Generative Adversarial Network (MDRSGAN) for non paired medical image enhancement. Its core innovations include: (1) Adopting a customized generator with learnable channel shared soft threshold (DRSN-CS), which can achieve hierarchical feature extraction and adaptive noise suppression; (2) Combining dual core discriminator to ensure global statistical consistency and high fidelity of local structure; (3) Introducing content perception loss and lighting loss to optimize overall details and image features. The performance of MDRSGAN is validated on fundus retina, endoscope, and self built NIR-II mouse dataset, and its performance is superior to five mainstream methods, such as a 5% increase in SNR for NIR-II mouse image enhancement. Downstream retinal vessel segmentation experiments show that IoU and DSC achieved 13% and 8% improvement, respectively, demonstrating the clinical applicability and performance advantages of this method.

In medical science, appropriate monitoring of the function of the human body, physical representations, and accurate disease is a complex task. It helps in diagnosing and treating diseases by revealing internal structures hidden by the skin and bones. Image enhancement techniques play a crucial role in medical imaging, as they improve diagnostic accuracy and visualization. However, the conventional methods were limited by noise sensitivity, lack of adaptability, and computational complexity. Therefore, this paper proposes One-to-One Honey Optimization (OOHO) for medical image enhancement. At first, the input brain Magnetic Resonance Imaging (MRI) image is processed to find the histogram. After that, histogram clipping is performed based on the clipping threshold. Then, the exposure threshold is computed to create sub-histograms. Moreover, the Probability Density Function (PDF) is computed and updated. Likewise, the Cumulative Density Function (CDF) and the mapping function are computed in each sub-histogram. Therefore, the finest enhanced image is obtained by integrating all sub-images. The fitness value is computed utilizing the cost function. Furthermore, the optimal threshold is accomplished by utilizing OOHO, which is developed by the integration of a One-to-One-based Optimizer (OOBO) and Honey Badger optimization (HBO). The evaluation results show that the OOHO attained a Degree of Distortion (DD) of 0.270, a Pear Signal to Noise Ratio (PSNR) of 47.060 dB, a Mean Square Error (MSE) of 0.570, Structural Similarity Index Measure (SSIM) as 0.960, and Root Mean Square Error (RMSE) of 0.755. The high performance is noted by the devised model and the MSE of the OOBO, HBO, hybrid Simulated Annealing-Evaporation Rate-based Water Cycle (SA-ERWCA) algorithm, Particle Swarm Optimization combined with Histogram Equalization (PSO-HE), Genetic Algorithm-based Adaptive Histogram Equalization (GAAHE), High-Quality Guidance Network (HQG-Net), multi-scale attention generative adversarial network (MAGAN), and Gaussian Quantum-behaved Arithmetic Optimization Algorithm (GQAOA) methods are 0.657, 0.637, 0.637, 0.627, 0.670, 0.650, 0.650, and 0.640, respectively.

Medical image segmentation is a crucial step in computer-aided diagnosis, treatment planning, and biomedical image analysis. This paper presents a segmentation approach based on Weighted Identification Level Set Evolution (WILSE), which effectively integrates local edge features to improve boundary detection and region accuracy. Traditional segmentation methods often struggle with noise, weak boundaries, and intensity inhomogeneity in medical images. The proposed method overcomes these challenges by assigning adaptive weights to local image features, enhancing the sensitivity of the level set function to significant edges while suppressing irrelevant noise. The model evolves iteratively to refine object boundaries and achieve precise delineation of anatomical structures. Experimental results on various medical imaging modalities such as MRI, CT, and ultrasound demonstrate that the WILSE approach provides superior segmentation accuracy, robustness, and computational efficiency compared to conventional edge-based or region-based methods. This technique shows promising potential for clinical applications where high-precision segmentation is essential for diagnosis and quantitative analysis.