Contrast enhancement of medical images using a new version of the World Cup Optimization algorithm

Microarray Images Contrast Enhancement and Gridding Using Genetic Algorithm

Background

Microarray is a sophisticated tool that concurrently analyzes the expression levels of thousands of genes, giving scientists an overview of DNA and RNA study. This procedure is divided into three stages: contact with biological samples, data extraction, and data analysis. Because expression levels are disclosed by the interplay of light with fluorescent markers, the data extraction stage relies on image processing methods. To extract quantitative information from the microarray image (MAI), four steps of preprocessing, gridding, segmentation, and intensity quantification are required. During the generation of MAIs, a large number of error-prone processes occur, leading to structural problems and reduced quality in the resulting data, affecting the identification of expressed genes.

Methods

In this article, the first stage has been examined. In the preprocessing stage, the contrast of the images is first enhanced using the genetic algorithm, then the source noises that appear as small artifacts are removed using morphology, and finally, to confirm the effect of the contrast enhancement (CE) on the main stages of microarray data processing, gridding is checked on complementary deoxyribonucleic acid MAIs.

Results

The comparison of the obtained results with an adaptive histogram equalization (AHE) and multi-decomposition histogram equalization (M-DHE) methods shows the superiority and efficiency of the proposed method. For example, the image contrast of the Genomic Medicine Research Center Laboratory dataset is 3.24, which is 42.91 with the proposed method and 13.48 and 32.40 with the AHE and M-DHE methods, respectively.

Conclusions

The performance of the proposed methods for CE is evaluated on 3 databases and a general conclusion is obtained as to which CE method is more suitable for each dataset.

CAENet: Contrast adaptively enhanced network for medical image segmentation based on a differentiable pooling function

Pixel differences between classes with low contrast in medical image semantic segmentation tasks often lead to confusion in category classification, posing a typical challenge for recognition of small targets. To address this challenge, we propose a Contrastive Adaptive Augmented Semantic Segmentation Network with a differentiable pooling function. Firstly, an Adaptive Contrast Augmentation module is constructed to automatically extract local high-frequency information, thereby enhancing image details and accentuating the differences between classes. Subsequently, the Frequency-Efficient Channel Attention mechanism is designed to select useful features in the encoding phase, where multifrequency information is employed to extract channel features. One-dimensional convolutional cross-channel interactions are adopted to reduce model complexity. Finally, a differentiable approximation of max pooling is introduced in order to replace standard max pooling, strengthening the connectivity between neurons and reducing information loss caused by downsampling. We evaluated the effectiveness of our proposed method through several ablation experiments and comparison experiments under homogeneous conditions. The experimental results demonstrate that our method competes favorably with other state-of-the-art networks on five medical image datasets, including four public medical image datasets and one clinical image dataset. It can be effectively applied to medical image segmentation.

Fully automatic carotid arterial stiffness assessment from ultrasound videos based on machine learning

Arterial stiffness (AS) refers to the loss of arterial compliance and alterations in vessel wall properties. The study of local carotid stiffness (CS) is particularly important since carotid artery stiffening raises the risk of stroke, cognitive impairment, and dementia. So, stiffness measurement as a screening tool approach is crucial because it can reduce mortality and facilitate therapy planning. This study aims to evaluate the stiffness of the CCA using machine learning (ML) through the features of diameter change (ΔD) and stiffness parameters. This study was conducted in seven stages: data collection, preprocessing, CCA segmentation, CCA lumen diameter (DCCA) computing during cardiac cycles, denoising signals of DCCA, computational of AS parameters, and stiffness assessment using ML. The 51 videos (with 25 s) of CCA B-mode ultrasound (US) were used and analyzed. Each US video yielded approximately 750 sequential frames spanning about 24 cardiac cycles. Firstly, US preset settings with time gain compensation with a U-pattern were employed to enhance CCA segmentations. The study showed that auto region-growing, employed three times, is appropriate for segmenting walls with a short running time (4.56 s/frame). The diameter computed for frames constructs a signal (diameter signal) with noisy parts in the shape of peak variance and an un-smooth side. Among the 12 employed smoothing methods, spline fitting with a mean peak difference per cycle (MPDCY) of 0.58 pixels was the most effective for the diameter signal. The authors propose the MPDCY as a new selection criterion for smoothing methods with highly preserved peaks. The ΔD (D_sys-D_dia) determined in this study was validated by statistical analysis as a viable replacement for manual ΔD measurement. Statistical analysis was carried out by Mann-Whitney t-test with a p-value of 0.81, regression line R² = 0.907, and there was no difference in means between the two groups for box plots. The stiffness parameters of the carotid arteries were calculated based on auto-ΔD and pulse pressure. Five ML models, including K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), logistic regression (LR), and random forest (RF), fed by distension (ΔD) and five stiffness parameters, were used to distinguish between the stiffened and un-stiffened CCA. Except for SVM, all models performed excellently in terms of specificity, sensitivity, precision, and area under the curve (AUC). In addition, the scatterplot and statistical analysis of the fed features confirm these remarkable outcomes. The scatter plot demonstrates that a linear hyperline can easily distinguish between the two classes. The statistical analysis shows that the stiffness parameters computed from the database of this work were statistically (p < 0.05) distributed into the non-stiffness and stiffness groups. The presented models are validated by applying them to additional datasets. Applying models to other datasets reveals a model performance of 100%. The proposed ML models could be applied in clinical practice to detect CS early, which is essential for preventing stroke.

A Review of Recent Advances in Deep Learning Models for Chest Disease Detection Using Radiography

Chest X-ray radiography (CXR) is among the most frequently used medical imaging modalities. It has a preeminent value in the detection of multiple life-threatening diseases. Radiologists can visually inspect CXR images for the presence of diseases. Most thoracic diseases have very similar patterns, which makes diagnosis prone to human error and leads to misdiagnosis. Computer-aided detection (CAD) of lung diseases in CXR images is among the popular topics in medical imaging research. Machine learning (ML) and deep learning (DL) provided techniques to make this task more efficient and faster. Numerous experiments in the diagnosis of various diseases proved the potential of these techniques. In comparison to previous reviews our study describes in detail several publicly available CXR datasets for different diseases. It presents an overview of recent deep learning models using CXR images to detect chest diseases such as VGG, ResNet, DenseNet, Inception, EfficientNet, RetinaNet, and ensemble learning methods that combine multiple models. It summarizes the techniques used for CXR image preprocessing (enhancement, segmentation, bone suppression, and data-augmentation) to improve image quality and address data imbalance issues, as well as the use of DL models to speed-up the diagnosis process. This review also discusses the challenges present in the published literature and highlights the importance of interpretability and explainability to better understand the DL models' detections. In addition, it outlines a direction for researchers to help develop more effective models for early and automatic detection of chest diseases.

Geometric Regularized Hopfield Neural Network for Medical Image Enhancement

One of the major shortcomings of Hopfield neural network (HNN) is that the network may not always converge to a fixed point. HNN, predominantly, is limited to local optimization during training to achieve network stability. In this paper, the convergence problem is addressed using two approaches: (a) by sequencing the activation of a continuous modified HNN (MHNN) based on the geometric correlation of features within various image hyperplanes via pixel gradient vectors and (b) by regulating geometric pixel gradient vectors. These are achieved by regularizing proposed MHNNs under cohomology, which enables them to act as an unconventional filter for pixel spectral sequences. It shifts the focus to both local and global optimizations in order to strengthen feature correlations within each image subspace. As a result, it enhances edges, information content, contrast, and resolution. The proposed algorithm was tested on fifteen different medical images, where evaluations were made based on entropy, visual information fidelity (VIF), weighted peak signal-to-noise ratio (WPSNR), contrast, and homogeneity. Our results confirmed superiority as compared to four existing benchmark enhancement methods.

Exploratory models comparing ethiodized oil-glue and gold fiducials for bladder radiotherapy image-guidance

Background and purpose

Image-guidance with fiducials has been shown to improve pelvic radiotherapy outcome. However, bladder fiducials using ethiodized oil (EO) alone can disperse widely, and gold causes Computed Tomography scan (CT) metal artifacts. The study's purpose was to investigate the ability to deliver EO-tissue glue fiducials and compare them to gold for bladder radiotherapy image guidance.

Materials and methods

A fluid-filled porcine bladder model was used to assess the ability to cystoscopically inject visible EO glue fiducials into the submucosa. We then transferred the bladders into a porcine pelvis for imaging and compared them to gold fiducials using CT, Cone Beam CT (CBCT), and kilovoltage (KV) planar views. A tissue-equivalent phantom was utilized to analyze the CT number Hounsfield Unit (HU) characteristics and artifacts of the glue and gold fiducials. Percentile ranges and normal tissue voxel percentages of the subsequent CT number voxel histogram from a 2 cm sphere surrounding the fiducial was used to characterize the artifact.

Results

We successfully delivered all EO glue fiducials into the porcine bladders as discrete fiducials. They were well seen on CT, CBCT, and KV imaging. The glue fiducials had lower CT number values, but less CT number spread of the voxel percentile ranges consistent with the diminished contrast and less artifact than gold. The glue fiducial types had similar CT number characteristics.

Conclusion

This study has shown that EO glue fiducials can be delivered with online visualization qualities comparable to gold fiducials without metal-related artifacts.

Machine learning prediction of axillary lymph node metastasis in breast cancer: 2D versus 3D radiomic features

PURPOSE

The purpose of this study was to distinguish axillary lymph node (ALN) status using preoperative breast DCE-MRI radiomics and compare the effects of two-dimensional (2D) and three-dimensional (3D) analysis.

METHODS

A retrospective study including 154 breast cancer patients all confirmed by pathology; 80 with ALN metastasis and 74 without. All MRI scans were achieved at a 3.0 Tesla scanner with 7 post-contrast MR phases sequentially acquired with a temporal resolution of 60 s. MRI radiomic features were extracted separately from a 2D single slice (i.e., the representative slice) and the 3D tumor volume. Several machine learning classifiers were built and compared using 2D or 3D analysis to distinguish positive vs negative ALN status. We performed independent test and 10-fold cross validation with multiple repetitions, and used bootstrap test, least absolute shrinkage selection operator, and receiver operating characteristic (ROC) curve analysis as statistical tests.

RESULTS

The highest area under the ROC curve (AUC) was 0.81 (95% confidence intervals [CI]: 0.80-0.83) and 0.82 (95% CI: 0.81-0.82) for 2D and 3D analysis, respectively; the corresponding accuracy was 79% and 80%. The linear discriminant analysis (LDA) classifier achieved the highest classification performance. None of the AUC differences between 2D and 3D analysis was statistically significant for the several tested machine learning classifiers (all P> 0.05).

CONCLUSIONS

Radiomic features from segmented tumor region in breast MRI were associated with ALN status. The separate radiomic analysis on 3D tumor volume showed a similar effect to the 2D analysis on the single representative slice in the tested machine learning classifiers.