Background: Breast cancer screening through mammography interpretation is crucial for early detection and improved patient outcomes. However, the manual classification of mammograms using the BIRADS (Breast Imaging-Reporting and Data System) remains challenging due to subtle imaging features, inter-reader variability, and increasing radiologist workload. Traditional computer-aided detection systems often struggle with complex feature extraction and contextual understanding of mammographic abnormalities. To address these limitations, this study proposes MammoViT, a novel hybrid deep learning framework that leverages both ResNet50’s hierarchical feature extraction capabilities and Vision Transformer’s ability to capture long-range dependencies in images. Methods: We implemented a multi-stage approach utilizing a pre-trained ResNet50 model for initial feature extraction from mammogram images. To address the significant class imbalance in our four-class BIRADS dataset, we applied SMOTE (Synthetic Minority Over-sampling Technique) to generate synthetic samples for minority classes. The extracted feature arrays were transformed into non-overlapping patches with positional encodings for Vision Transformer processing. The Vision Transformer employs multi-head self-attention mechanisms to capture both local and global relationships between image patches, with each attention head learning different aspects of spatial dependencies. The model was optimized using Keras Tuner and trained using 5-fold cross-validation with early stopping to prevent overfitting. Results: MammoViT achieved 97.4% accuracy in classifying mammogram images across different BIRADS categories. The model’s effectiveness was validated through comprehensive evaluation metrics, including a classification report, confusion matrix, probability distribution, and comparison with existing studies. Conclusions: MammoViT effectively combines ResNet50 and Vision Transformer architectures while addressing the challenge of imbalanced medical imaging datasets. The high accuracy and robust performance demonstrate its potential as a reliable tool for supporting clinical decision-making in breast cancer screening.

Background/Objectives: Glioblastoma (GBM) is an aggressive and lethal primary brain tumor with a poor prognosis, with a 5-year survival rate of approximately 5%. Despite advances in oncologic treatments, including surgery, radiotherapy, and chemotherapy, survival outcomes have remained stagnant, largely due to the failure of conventional therapies to address the tumor’s inherent heterogeneity. Radiomics, a rapidly emerging field, provides an opportunity to extract features from MRI scans, offering new insights into tumor biology and treatment response. This study evaluates the potential of delta radiomics, the study of changes in radiomic features over time in response to treatment or disease progression, exploring the potential of delta radiomics to track temporal radiation changes in tumor morphology and microstructure. Methods: A cohort of 50 female CD1 nude mice was injected intracranially with G7 glioblastoma cells and divided into irradiated (IR) and non-irradiated (non-IR) groups. MRI scans were performed at baseline (week 11) and post-radiation (weeks 12 and 14), and radiomic features, including shape, histogram, and texture parameters, were extracted and analyzed to capture radiation-induced changes. The most robust features were those identified through intra-observer reproducibility assessment, ensuring reliability in feature selection. A machine learning model was developed to classify irradiated tumors based on delta radiomic features, and statistical analyses were conducted to evaluate feature feasibility, stability, and predictive performance. Results: Our findings demonstrate that delta radiomics effectively captured significant temporal variations in tumor characteristics. Delta radiomics features exhibited distinct patterns across different time points in the IR group, enabling machine learning models to achieve a high accuracy. Conclusions: Delta radiomics offers a robust, non-invasive method for monitoring the treatment of glioblastoma (GBM) following radiation therapy. Future research should prioritize the application of MRI delta radiomics to effectively capture short-term changes resulting from intratumoral radiation effects. This advancement has the potential to significantly enhance treatment monitoring and facilitate the development of personalized therapeutic strategies.

Computed Tomography (CT) is vital for diagnosing and monitoring medical conditions. However, increased usage raises concerns about patient radiation exposure. Diagnostic Reference Levels (DRLs) aim to minimize radiation doses in CT imaging. This study examines CT DRLs in India compared to other countries to identify optimization opportunities. A literature review was conducted to gather data from published studies, guidelines, and regulatory authorities. Findings show significant international variations in CT DRLs, with differences up to 50%. In India, DRLs also vary significantly across states. For head CT exams, Indian DRLs are generally 20–30% lower than international standards (27–47 mGy vs. 60 mGy). Conversely, for abdominal CT scans, Indian DRLs are 10–15% higher (12–16 mGy vs. 13 mGy). Factors influencing DRL variations include equipment differences, imaging protocols, patient demographics, and regulatory conditions. Dose-optimization techniques like automatic exposure control and iterative reconstruction can reduce radiation exposure by 25–60% while maintaining image quality. Comparative data highlight best practices, such as the United Kingdom’s 30% reduction in CT doses from 1984 to 1995 via DRL implementation. This study suggests that adopting similar practices in India could reduce radiation doses by 20–40% for common CT procedures, promoting responsible CT usage and minimizing patient exposure.

(1) Background: Colorectal cancer is the third most common type of cancer with a high mortality rate and poor prognosis. The accurate prediction of key genetic mutations, such as the KRAS status, tumor staging, and extramural venous invasion (EMVI), is crucial for guiding personalized treatment decisions and improving patients’ outcomes. MRI radiomics was assessed to predict the KRAS status and tumor staging in colorectal cancer patients across different imaging platforms to improve the personalized treatment decisions and outcomes. (2) Methods: Sixty colorectal cancer patients (35M/25F; avg. age 56.3 ± 12.9 years) were treated at an oncology unit. The MRI scans included T2-weighted (T2W) and diffusion-weighted imaging (DWI) or the apparent diffusion coefficient (ADC). The manual segmentation of colorectal cancer was conducted on the T2W and DWI/ADC images. The cohort was split into training and validation sets, and machine learning was used to build predictive models. (3) Results: The neural network (NN) model achieved 73% accuracy and an AUC of 0.71 during training for predicting the KRAS mutation status, while during testing, it achieved 62.5% accuracy and an AUC of 0.68. In the case of tumor grading, the support vector machine (SVM) model excelled with a training accuracy of 72.93% and an AUC of 0.7, and during testing, it reached an accuracy of 72% and an AUC of 0.69. (4) Conclusions: ML models using radiomics from ADC maps and T2-weighted images are effective for distinguishing KRAS genes, tumor grading, and EMVI in colorectal cancer. Standardized protocols are essential to improve MRI radiomics’ reliability in clinical practice.

The early and precise identification of Alzheimer’s Disease (AD) continues to pose considerable clinical difficulty due to subtle structural alterations and overlapping symptoms across the disease phases. This study present... | Find, read and cite all the research you need on Tech Science Press

Background/Objectives: Age-related macular degeneration (AMD) is the leading cause of visual impairment among the elderly. Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality that enables detailed visualisation of retinal vascular layers. However, clinical assessment of OCTA images is often challenging due to high data volume, pattern variability, and subtle abnormalities. This study aimed to develop automated algorithms to detect and quantify AMD in OCTA images, thereby reducing ophthalmologists’ workload and enhancing diagnostic accuracy. Methods: Two texture-based algorithms were developed to classify OCTA images without relying on segmentation. The first algorithm used whole local texture features, while the second applied principal component analysis ($PCA$) to decorrelate and reduce texture features. Local texture descriptors, including rotation-invariant uniform local binary patterns ($LB{P}^{2riu}$), local binary patterns ($LBP$), and binary robust independent elementary features ($BRIEF$), were combined with machine learning classifiers such as support vector machine (SVM) and K-nearest neighbour (KNN). OCTA datasets from Manchester Royal Eye Hospital and Moorfields Eye Hospital, covering healthy, dry AMD, and wet AMD eyes, were used for evaluation. Results: The first algorithm achieved a mean area under the receiver operating characteristic curve (AUC) of $1.00\pm 0.00$ for distinguishing healthy eyes from wet AMD. The second algorithm showed superior performance in differentiating dry AMD from wet AMD (AUC $0.85\pm 0.02$). Conclusions: The proposed algorithms demonstrate strong potential for rapid and accurate AMD diagnosis in OCTA workflows. By reducing manual image evaluation and associated variability, they may support improved clinical decision-making and patient care.