An Artificial Intelligence-Based Tool for Enhancing Pectoral Muscle Segmentation in Mammograms: Addressing Class Imbalance and Validation Challenges in Automated Breast Cancer Diagnosis.

Breast cancer remains a major health concern worldwide, requiring the advancement of early detection methods to improve prognosis and treatment outcomes. In this sense, mammography is regarded as the gold standard in breast cancer screening and early detection. However, in a scenario where extensive analysis is required, a large set of mammograms conducted by radiologists may carry out false negative or false positive diagnoses. Therefore, artificial intelligence has emerged in recent years as a method for enhancing timing in breast cancer diagnosis. Nonetheless, preprocessing stages are required to prepare the mammography dataset to enhance learning models to correctly identify breast anomalies. In this paper, we introduce a novel method employing convolutional neural networks (CNNs) to segment the pectoral muscle in 1288 mediolateral oblique mammograms (MLOs), thereby addressing class imbalance and overfitting between classes, and dataset augmentation based on translation, rotation, and scale transformation. The effectiveness of the model was assessed through a confusion matrix and performance metrics, highlighting an average Dice coefficient of 0.98 and a Jaccard index of 0.96. The outcomes demonstrate the model capability to accurately identify three classes: pectoral muscle, breast, and background. This study emphasizes the importance of tackling class imbalance problems and augmenting data for the training of models for reliable early breast cancer detection.

Tuning the Charge Transfer in MWCNTs via the Incorporation of ZnONPs and AgNPs: The Role of Carbon Binding with ZnO/Ag Heterostructures in Reactive Species Formation.

In this research, multi-walled carbon nanotubes (MWCNTs) were decorated with two kinds of nanostructures, (1) silver nanoparticles (AgNPs) and (2) zinc oxide-silver nano-heterostructures (ZnO/Ag-NHs), via an accessible chemical coprecipitation method assisted with ultrasonic radiation. The high-resolution transmission electron microscopy analysis demonstrated the successful decoration of MWCNTs with the nanostructures with a diameter size of 11 nm ± 2 nm and 46 nm ± 5 nm for the AgNPs and the ZnO/Ag-NHs, respectively. The reactive species were promoted in an aqueous medium assisted with UV irradiation on the functionalized MWCNT. UV-Vis spectroscopy demonstrated that production of the reactive species density increased 4.07 times, promoted by the single MWCNT after the functionalization. X-ray photoelectron spectroscopy showed that Sp2 hybridization in carbon atoms of MWCNTs participates in the binding of AgNPs and ZnO/Ag-NH decoration and thus participates in the formation of reactive species in an aqueous medium, as is the case for cancer cells.

Hybrid Feature Mammogram Analysis: Detecting and Localizing Microcalcifications Combining Gabor, Prewitt, GLCM Features, and Top Hat Filtering Enhanced with CNN Architecture.

Breast cancer is a prevalent malignancy characterized by the uncontrolled growth of glandular epithelial cells, which can metastasize through the blood and lymphatic systems. Microcalcifications, small calcium deposits within breast tissue, are critical markers for early detection of breast cancer, especially in non-palpable carcinomas. These microcalcifications, appearing as small white spots on mammograms, are challenging to identify due to potential confusion with other tissues. This study hypothesizes that a hybrid feature extraction approach combined with Convolutional Neural Networks (CNNs) can significantly enhance the detection and localization of microcalcifications in mammograms. The proposed algorithm employs Gabor, Prewitt, and Gray Level Co-occurrence Matrix (GLCM) kernels for feature extraction. These features are input to a CNN architecture designed with maxpooling layers, Rectified Linear Unit (ReLU) activation functions, and a sigmoid response for binary classification. Additionally, the Top Hat filter is used for precise localization of microcalcifications. The preprocessing stage includes enhancing contrast using the Volume of Interest Look-Up Table (VOI LUT) technique and segmenting regions of interest. The CNN architecture comprises three convolutional layers, three ReLU layers, and three maxpooling layers. The training was conducted using a balanced dataset of digital mammograms, with the Adam optimizer and binary cross-entropy loss function. Our method achieved an accuracy of 89.56%, a sensitivity of 82.14%, and a specificity of 91.47%, outperforming related works, which typically report accuracies around 85-87% and sensitivities between 76 and 81%. These results underscore the potential of combining traditional feature extraction techniques with deep learning models to improve the detection and localization of microcalcifications. This system may serve as an auxiliary tool for radiologists, enhancing early detection capabilities and potentially reducing diagnostic errors in mass screening programs.

Acinonyx jubatus-Inspired Quadruped Robotics: Integrating Neural Oscillators for Enhanced Locomotion Control.

This study presents the design, simulation, and prototype creation of a quadruped robot inspired by the Acinonyx jubatus (cheetah), specifically designed to replicate its distinctive walking, trotting, and galloping locomotion patterns. Following a detailed examination of the cheetah's skeletal muscle anatomy and biomechanics, a simplified model of the robot with 12 degrees of freedom was conducted. The mathematical transformation hierarchy model was established, and direct kinematics were simulated. A bio-inspired control approach was introduced, employing a Central Pattern Generator model based on Wilson-Cowan neural oscillators for each limb, interconnected by synaptic weights. This approach assisted in the simulation of oscillatory signals for relative phases corresponding to four distinct gaits in a system-level simulation platform. The design phase was conducted using CAD software (SolidWorks 2018), resulting in a 1:3-scale robot mirroring the cheetah's actual proportions. Movement simulations were performed in a virtual mechanics software environment, leading to the construction of a prototype measuring 35.5 cm in length, 21 cm in width, 27 cm in height (when standing), and weighing approximately 2.1 kg. The experimental validation of the prototype's limb angular positions and trajectories was achieved through the image processing of video-recorded movements, demonstrating a high correlation (0.9025 to 0.9560) in joint angular positions, except for the knee joint, where a correlation of 0.7071 was noted. This comprehensive approach from theoretical analysis to practical implementation showcases the potential of bio-inspired robotics in emulating complex biological locomotion.

Bryophyte-Bioinspired Nanoporous AAO/C/MgO Composite for Enhanced CO2 Capture: The Role of MgO.

A composite material composed of anodized aluminum oxide (AAO), carbon (C), and magnesium oxide (MgO) was developed for CO2 capture applications. Inspired by the bryophyte organism, the AAO/C/MgO composite mirrors two primary features of these species-(1) morphological characteristics and (2) elemental composition-specifically carbon, oxygen, and magnesium. The synthesis process involved two sequential steps: electroanodization of aluminum foil followed by a hydrothermal method using a mixture of glucose and magnesium chloride (MgCl2). The concentration of MgCl2 was systematically varied as the sole experimental variable across five levels-1 mM, 2 mM, 3 mM, 4 mM, and 5 mM-to investigate the impact of MgO formation on the samples' chemical and physical properties, and consequently, their CO2 capture efficiency. Thus, scanning electron microscopy analysis revealed the AAO substrate's porous structure, with pore diameters measuring 250 ± 30 nm. The growth of MgO on the AAO substrate resulted in spherical structures, whose diameter expanded from 15 nm ± 3 nm to 1000 nm ± 250 nm with increasing MgCl2 concentration from the minor to major concentrations explored, respectively. X-ray photoelectron spectroscopy (XPS) analysis indicated that carbon serves as a linking agent between AAO and MgO within the composite. Notably, the composite synthesized with a 4 mM MgCl2 concentration exhibited the highest CO2 capture efficiency, as determined by UV-Vis absorbance studies using a sodium carbonate solution as the CO2 source. This efficiency was quantified with a 'k' constant of 0.10531, significantly higher than those of other studied samples. The superior performance of the 4 mM MgCl2 sample in CO2 capture is likely due to the optimal density of MgO structures formed on the sample's surface, enhancing its adsorptive capabilities as suggested by the XPS results.

Automated Computer-Assisted Medical Decision-Making System Based on Morphological Shape and Skin Thickness Analysis for Asymmetry Detection in Mammographic Images.

Breast cancer is a significant health concern for women, emphasizing the need for early detection. This research focuses on developing a computer system for asymmetry detection in mammographic images, employing two critical approaches: Dynamic Time Warping (DTW) for shape analysis and the Growing Seed Region (GSR) method for breast skin segmentation. The methodology involves processing mammograms in DICOM format. In the morphological study, a centroid-based mask is computed using extracted images from DICOM files. Distances between the centroid and the breast perimeter are then calculated to assess similarity through Dynamic Time Warping analysis. For skin thickness asymmetry identification, a seed is initially set on skin pixels and expanded based on intensity and depth similarities. The DTW analysis achieves an accuracy of 83%, correctly identifying 23 possible asymmetry cases out of 20 ground truth cases. The GRS method is validated using Average Symmetric Surface Distance and Relative Volumetric metrics, yielding similarities of 90.47% and 66.66%, respectively, for asymmetry cases compared to 182 ground truth segmented images, successfully identifying 35 patients with potential skin asymmetry. Additionally, a Graphical User Interface is designed to facilitate the insertion of DICOM files and provide visual representations of asymmetrical findings for validation and accessibility by physicians.

Synthesis and Characterization of Nanoporous ZnO Films by Controlling the Zn Sublimation by Using ZnO/Zn Precursor Films.

A reliable process for the formation of nanoporous ZnO films supported on amorphous quartz and (100) silicon substrates via the processing of ZnO/Zn precursor films is reported. The process is based on the sublimation mechanism of Zn implemented in a novel ZnO/Zn precursor film to produce a nanoporous film. A scanning electron microscopy analysis of the nanoporous ZnO films' surfaces revealed the presence of ZnO nano-features with round tips; in contrast, the nanoporous ZnO films supported on (100) Si substrates showed hexagonal nut-like nanostructures. The crystallite size of the nanoporous ZnO films decreased as the sublimation temperature was increased. X-ray photoelectron spectroscopy studies demonstrated that formations of oxygen vacancies were produced during the processing stages (as the main structural lattice defects in the ZnO nanoporous films). The analysis of the photoluminescence response confirmed that the active deep-level centers were also related to the oxygen vacancies generated during the thermal processing of the ZnO/Zn precursor films. Finally, a qualitative mechanism is proposed to explain the formation of nanoporous ZnO films on quartz and crystalline Si substrates. The results suggest that the substrates used have a strong influence on the nanoporous ZnO structures obtained with the Zn-sublimation-controlled process.