Enhancement of Mammographic Images Using Histogram-Based Techniques for Their Classification Using CNN.

In the world, one in eight women will develop breast cancer. Men can also develop it, but less frequently. This condition starts with uncontrolled cell division brought on by a change in the genes that regulate cell division and growth, which leads to the development of a nodule or tumour. These tumours can be either benign, which poses no health risk, or malignant, also known as cancerous, which puts patients' lives in jeopardy and has the potential to spread. The most common way to diagnose this problem is via mammograms. This kind of examination enables the detection of abnormalities in breast tissue, such as masses and microcalcifications, which are thought to be indicators of the presence of disease. This study aims to determine how histogram-based image enhancement methods affect the classification of mammograms into five groups: benign calcifications, benign masses, malignant calcifications, malignant masses, and healthy tissue, as determined by a CAD system of automatic mammography classification using convolutional neural networks. Both Contrast-limited Adaptive Histogram Equalization (CAHE) and Histogram Intensity Windowing (HIW) will be used (CLAHE). By improving the contrast between the image's background, fibrous tissue, dense tissue, and sick tissue, which includes microcalcifications and masses, the mammography histogram is modified using these procedures. In order to help neural networks, learn, the contrast has been increased to make it easier to distinguish between various types of tissue. The proportion of correctly classified images could rise with this technique. Using Deep Convolutional Neural Networks, a model was developed that allows classifying different types of lesions. The model achieved an accuracy of 62%, based on mini-MIAS data. The final goal of the project is the creation of an update algorithm that will be incorporated into the CAD system and will enhance the automatic identification and categorization of microcalcifications and masses. As a result, it would be possible to increase the possibility of early disease identification, which is important because early discovery increases the likelihood of a cure to almost 100%.

SPN based RGB image encryption over Gaussian integers.

This research paper proposes a novel approach for constructing substitution boxes (S-boxes) over Gaussian integers, which are complex numbers with integer coefficients. The proposed method is based on the properties of the Gaussian integers and their arithmetic operations and ensures the S-boxes exhibit strong cryptographic properties. Furthermore, the paper demonstrates how these S-boxes can be utilized for image encryption through a substitution-permutation network (SPN) over Gaussian integers. The SPN involves iteratively applying the S-box and a permutation layer to the input image, which effectively scrambles the image data. Experimental results show that the proposed method achieves high security and robustness against various attacks while providing efficient encryption and decryption performance. This research thus provides a promising avenue for developing secure image encryption schemes based on Gaussian integers.

Lumbar Disc Degeneration Is Linked to Dorsal Subcutaneous Fat Thickness at the L1-L2 Intervertebral Disc Level Measured by MRI.

BACKGROUND: Obese individuals have a higher risk of degenerative disc disease (DDD). Currently, body mass index is not sensitive enough to differentiate between muscle and fat distribution, and obesity-related health issues are linked to the way body fat is distributed. Therefore, this study aims to investigate the association between the dorsal subcutaneous fat thickness (DSFT) of the lumbar spine, an alternative measurement tool of body fat distribution, and DDD. METHODS: A total of 301 patients with DDD and 123 participants without the disease were recruited. Using length functions of magnetic resonance imaging (MRI) console, the DSFT of L1 to S1 intervertebral disc levels was measured in mid-sagittal spin-echo T2 weighted image. The Mann-Whitney U test and Chi-squared test (X2) were utilized to examine any variations between the case and control groups. Logistic regression models were built to explore the association of the DSFT with DDD. RESULTS: The logistical regression model showed a positive association between DDD and DSFT [OR: 1.30, 95% CI: 1.02-1.64, p = 0.03]. In the stratified logistic regression analysis, a positive association was found between DDD and DSFT among younger participants and females [OR young: 1.48; 95% CI (1.02-2.20); p = 0.04-OR female: 1.37; 95% CI (1-1.88); p = 0.05]. CONCLUSIONS: Younger females with thicker DSFT at the L1-L2 level are more likely to develop DDD. This suggests that increased DSFT may be a contributing factor to DDD.

B-mode ultrasound characteristics of carotid plaques in symptomatic and asymptomatic patients with low-grade stenosis.

Carotid plaque features assessed using B-mode ultrasound can be useful for the prediction of cerebrovascular symptoms. Therefore, the aim of this retrospective study was to determine the ability of ultrasound B-mode imaging to differentiate between carotid plaques causing less than 50% stenosis in symptomatic and asymptomatic patients. A dataset of 1,593 patients with carotid disease who underwent carotid ultrasound between 2016 and 2021 was evaluated retrospectively between January and April of 2022. A total of 107 carotid plaques from 35 symptomatic and 52 asymptomatic patients causing low-grade stenosis on B-mode images were included in the analysis. Chi-square, independent t-test and Mann-Whitney U test were used to compare the variables. There was a significant association between hypertension and the presence of cerebrovascular symptoms (p = 0.01). Predominantly hypoechoic and hyperechoic carotid plaque were significantly associated with the presence and absence of cerebrovascular symptoms, respectively (predominantly hypoechoic: p = 0.01; predominantly hyperechoic: p = 0.02). Surface irregularity was significantly associated with the presence of cerebrovascular symptoms (p = 0.02). There is was a significant difference in the carotid plaque length and area between the symptomatic and asymptomatic patients (plaque length: symptomatic median 9 mm, interquartile range [IQR] 6 mm; asymptomatic median 6 mm, IQR 4.5 mm, p = 0.01; plaque area: symptomatic median 24 mm, IQR 30 mm; asymptomatic median 14 mm, IQR 17 mm, p = 0.01); however, this difference was not significant for plaque thickness (p = 0.55), or common carotid artery intima-media thickness (p = 0.7). Our findings indicate that hypertension patients with predominantly hypoechoic carotid plaques and plaques with an irregular surface are associated with the presence of cerebrovascular symptoms. In addition, the carotid plaques in symptomatic patients were longer and larger compared to asymptomatic patients.