Aug 2026· International Conference on Circuit, Power and Computing Technologies· pp. 181-186· 0 citations· 7 references
Abstract
Images of medical patients that were taken in low light or low contrast areas frequently have issues with noise, visibility, and important information for physicians to use in deciding on patient care. An Adaptive Hybrid Convolutional Neural Network Discrete Wavelet Transform Enhancement Technique for Low Light Medical Images is presented for use in helping to detect latent disease in X-ray and Magnetic Resonance Images. The method works as follows: The input image first goes through a Discrete Wavelet Transform to break it down into high frequency and low frequency components. Separating out the high frequency (noise) and low frequency parts of the image allows for a more efficient way to reduce noise while still preserving the critical structure of the image. Once the first step has been completed, multi-scale wavelet features are used to create a Convolutional Neural Network (CNN) enhancement module that learns how to adaptively learn how to make illumination corrections and improve contrast. The final part of the process is an Adaptive Histogram Equalization postprocessing step that improves visual clarity, therefore enhancing the final image to allow for good clinical interpretation. There are experimental results that demonstrate the new proposed framework is significantly better than existing methods on several common image quality metrics such as PERMANENT CRYSTAL, PSNR, and SSIM, and that it preserves the critical diagnostic features of the medical image. This method is extremely beneficial to radiologists because it allows for the accurate and reliable analysis of MRI images using Computer Assisted Diagnosis (CAD) systems and can be integrated with existing CAD systems to enhance and improve the radiologist’s ability to interpret the medical images of their patients.
Medical imaging is necessary for the diagnosis, treatment, and monitoring of sickness. Technology, background noise, and patient features can all contribute to low contrast in medical images. Diagnostic errors are caused by poor contrast, which obscures important anatomical structures and disease characteristics. To enhance lowcontrast medical images, the study employed deep learning in conjunction with conventional image processing techniques. Combining CNNs with sophisticated image enhancement techniques such as histogram equalization, contrast stretching, and noise reduction, this system produces high-quality results. Automated contrast enhancement with structural preservation is a capability of deep learning models that learn complicated visual cues. Supervised and unsupervised learning lead to better X-ray, CT, and MRI generalization. By incorporating attention processes, the model is able to better strengthen its focus on diagnostically relevant regions. Images are uniformly and artifact-free post-processed by the system. Improvements have been made to the image’s contrast, clarity, and diagnostic accuracy. PSNR and SSIM improve the quality of the image. Clinical decision-making and patient outcomes can be improved using automated, robust medical image enhancement solutions that deep learning and image processing can provide, as demonstrated in this work.
B. Arivu Selvam, M. Al-Mousa, D. Gandhi et al.· International Conference on...· 0 citations
Accurate medical image segmentation plays an important role in ultrasound triage, colonoscopy screening, and histopathology analysis. However, segmentation performance often degrades substantially when input images are noisy or low-contrast and the model must operate on resource-constrained devices. This challenge mainly arises from two coupled factors. On the one hand, degraded inputs weaken boundary information and interfere with subsequent feature extraction. On the other hand, conventional skip connections with uniform channel allocation cannot simultaneously preserve shallow details and rich deep semantics, thereby limiting the effectiveness of multi-scale feature fusion. To address these issues, we propose UKDW, a lightweight medical image segmentation framework that jointly improves input quality and cross-layer feature interaction under a unified architecture and training protocol. First, we design an Adaptive Wavelet Enhancement Preprocessor (AWEP), which transforms conventional wavelet denoising into an end-to-end trainable, task-driven module. Through a learnable shared soft-threshold, a post-denoising refinement convolution, and fusion weights, AWEP suppresses dataset-level noise while preserving critical structural details. Second, we propose a Dual-Stream Feature Fusion (DSFF) module, which constructs a shallow detail stream and a deep semantic stream with asymmetric channel allocation so that features at different levels receive representational capacities matched to their functional roles. In addition, a semantic-guided attention mechanism emphasizes task-relevant boundaries and suppresses redundant responses, thereby improving cross-scale fusion quality. Experimental results on three heterogeneous public datasets, namely BUSI ultrasound, CVC-ClinicDB colonoscopy, and GLAS histopathology, show that UKDW achieves superior Dice and IoU performance over recent CNN-, Transformer-, and KAN-based methods while maintaining a compact model size of 6.6M parameters in the reported lightweight configuration. These findings suggest that, in lightweight medical image segmentation, jointly addressing input degradation and feature-fusion mismatch is beneficial. It should be noted that the current experiments are based on image-level random splits rather than patient-level, sequence-level, or cross-center validation, and therefore broader clinical effectiveness remains to be further investigated. Code is available at https://github.com/Nafsae/UKDW.
Peiyuan Wang, Yongjie Liang, Bizhong Wei et al.· Journal of King Saud Univers...· 0 citations
Results indicate the WVM-UNet architecture effectively captures discriminative features for precise medical image segmentation, and demonstrates the competitive performance of the method on multiple public datasets.
Yulong Yang, Wenchao Gao, Zheng-Guo Wu et al.· Journal of Imaging· 0 citations
Finding cancer early and making a good treatment plan are both important for boosting survival rates. MRI, PET, and CT are advanced imaging techniques that have greatly improved cancer screening, staging, and therapy monitoring. However, their high costs and need for specialised equipment make them hard to get, especially in places with few resources. In this setting, optical imaging technologies are becoming affordable and portable options for finding cancer early. Image preprocessing techniques were used to improve data quality in order to deal with problems including dataset imbalance and noise. They used the Haar wavelet approach to extract features from medical photos that were important. A hybrid CNN-Transformer architecture was suggested, with four main parts: Shallow Feature Extraction (SFE), CNN/Transformer, Deep Feature Fusion (DFF), and up-sampling. This combination uses CNN to find local features and Transformers to find global dependencies, which makes deep feature learning strong and adaptable. The proposed model had an overall accuracy of 97.13%, a precision of 95.30%, a specificity of 96.74%, and an AUC of 98.74%. This shows that it is quite good at finding cancer. These results show that the model could provide accurate, quick, and easyto-use diagnostic solutions.
Deepika Upadhyay, S. Manikandan, R. V. S. Praveen et al.· International Conference on...· 0 citations
Computed tomography (CT) is a vital medical imaging mode, and radiation dose reduction can result in a higher noise level and worse image quality, which can restrict its use in diagnostics. To overcome this difficulty, this paper will present an AI-based convolutional auto-encoder model to resolve the low dose CT image denoising and quality improvement of paired Quarter Dose CT data and Full Dose CT data. Original DICOM images were utilized so as to have a transparent and reproducible preprocessing pipeline. The technique incorporated metadata-based slice correspondence, Hounsfield Unit transformation, intensity clipping, normalization, patient separate information division, and patch-based supervised education. An untrained basic convolutional auto-encoder was used and trained to produce Full Dose-like images by using Quarter Dose as inputs. The test set that was held out and evaluated experimentally showed that the convergence was stable, and the denoising performance was strong, with a mean MSE of 0.000293, RMSE of 0.015310, MAE of 0.011648, PSNR of 37.3363 dB, and SSIM of 0.8669 Subgroup analysis also revealed that the model worked better with 3 mm slices compared to 1 mm slices and better with the B30 reconstruction kernel compared to D45 kernel with the optimal results being in the 3mm-B30 setting. These results suggest that the suggested framework is useful to reduce the low-dose CT noise and maintain the structural similarity simultaneously, thus offering a feasible and interpretable solution to supervised image restoration of low-dose CT images.
Amit Bhupal Pattar, Thimmaraju· Journal of Intelligent Decis...· 0 citations
Noise removal is an essential preprocessing step, especially with medical images. When dealing with ultrasound images, it is extremely important to ensure the success and accuracy of the diagnosis. Due to some factors accompanying the image capture process, we notice some noise accompanying the image, which leads to difficulty in the process of seeing fine and sensitive tissues and complex areas correctly. There are many techniques used in this field, which are well-known but have certain limitation. On the other hand, there are some techniques such as deep networks, which have proven their worth, but they consume large amounts of data in the training phase.
In this research, a new method is presented that combines a Residual Dense Network (RDN) with adaptive noise estimation techniques, some traditional filters, and deep learning techniques. The goal of this combination is to improve the clarity and contrast of radiological images. The rationale behind this approach is that the two methods will compensate for each other's weaknesses while reinforcing their respective strengths. Experiments on a model showed great improvement in the quality of the images, as validated by the PSNR, SSIM, NIQUE index, direct rate, mean square error rate. The model was tested over a set of large radiological images in benign as well as in malignant cases, and the noise effect was investigated in terms of 20, 50, 80, and 100 levels.
Rafid A. Haleot· Journal of the College of B...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
