Automated machine learning (AutoML) has been recognized as a powerful tool to build a system that automates the design and optimizes the model selection machine learning (ML) pipelines. In this study, we present a tree-based pipeline optimization tool (TPOT) as a method for determining ML models with significant performance and less complex breast cancer diagnostic pipelines. Some features of pre-processors and ML models are defined as expression trees and optimal gene programming (GP) pipelines, a stochastic search system. Features of radiomics have been presented as a guide for the ML pipeline selection from the breast cancer data set based on TPOT. Breast cancer data were used in a comparative analysis of the TPOT-generated ML pipelines with the selected ML classifiers, optimized by a grid search approach. The principal component analysis (PCA) random forest (RF) classification was proven to be the most reliable pipeline with the lowest complexity. The TPOT model selection technique exceeded the performance of grid search (GS) optimization. The RF classifier showed an outstanding outcome amongst the models in combination with only two pre-processors, with a precision of 0.83. The grid search optimized for support vector machine (SVM) classifiers generated a difference of 12% in comparison, while the other two classifiers, naïve Bayes (NB) and artificial neural network—multilayer perceptron (ANN-MLP), generated a difference of almost 39%. The method’s performance was based on sensitivity, specificity, accuracy, precision, and receiver operating curve (ROC) analysis.

Breast cancer is the most leading cancer occurring in women and is a significant factor in female mortality. Early diagnosis of breast cancer with Artificial Intelligent (AI) developments for breast cancer detection can lead to a proper treatment to affected patients as early as possible that eventually help reduce the women mortality rate. Reliability issues limit the current clinical detection techniques, such as Ultra-Sound, Mammography, and Magnetic Resonance Imaging (MRI) from screening images for precise elucidation. The capability to detect a tumor in early diagnosis, expensive, relatively long waiting time due to pandemic and painful procedure for a patient to perform. This article aims to review breast cancer screening methods and recent technological advancements systematically. In addition, this paper intends to explore the progression and challenges of AI in breast cancer detection. The next state of the art between image and signal processing will be presented, and their performance is compared. This review will facilitate the researcher to insight the view of breast cancer detection technologies advancement and its challenges.

In this study, a series of Li₂O-Al₂O₃-B₂O₃ glasses doped with various concentrations of Dy₂O₃ (where x = 0.0, 0.2, 0.4, 0.6, 0.8, and 1.0 mol%) were prepared by using a conventional melt-quenching technique. The structural, physical and optical properties of the glasses were examined by utilising a variety of techniques instance, X-ray diffraction (XRD), UV–Vis-NIR spectrometer, Fourier transform infrared (FTIR) and photoluminescence (PL). The XRD spectra demonstrate the amorphous phase of all glasses. Furthermore, the UV-vis-NIR spectrometers have registered optical absorption spectra a numbers of peaks which exist at 1703, 1271, 1095, 902, 841, 802, 669, 458, 393 and 352 nm congruous to the transitions from the ground of state (⁶H_15/2) to different excited states, ⁶H_11/2, ⁶F_11/2 + ⁶H_9/2, ⁶F_9/2 + ⁶H_7/2, ⁶F_7/2, ⁶F_5/2, ⁶F_3/2, ⁴F_9/2, ⁴I_15/2, ⁴F_7/2 and ⁶P_7/2, respectively. The spectra of emission exhibit two strong emanation bands at 481 nm and 575 nm in the visible region, which correspond to the transitions ⁴F_9/2 → ⁶H_15/2 and ⁴F_9/2 → ⁶H_13/2. All prepared glass samples doped with Dy₂O₃ show an increase in the emission intensity with an increase in the concentration of Dy³⁺. Based on the obtained results, the aforementioned glass samples may have possible applications, such as optical sensor and laser applications.

Pediatrics are more vulnerable to radiation and are prone to dose compared to adults, requiring more attention to computed tomography (CT) optimization. Hence, diagnostic reference levels (DRLs) have been implemented as part of optimization process in order to monitor CT dose and diagnostic quality. The noise index has recently been endorsed to be included as a part of CT optimization in the DRLs report. In this study, we have therefore set local DRLs for pediatric CT examination with a noise index as an indicator of image quality. One thousand one hundred and ninety-two (1192) paediatric patients undergoing CT brain, CT thorax and CT chest-abdomen-pelvis (CAP) examinations were analyzed retrospectively and categorized into four age groups; group 1 (0–1 year), group 2 (1–5 years), group 3 (5–10 years) and group 4 (10–15 years). For each group, data such as the volume-weighted CT dose index (CTDI_vol), dose-length product (DLP) and the effective dose (E) were calculated and DRLs for each age group set at 50th percentile were determined. Both CT dose and image noise values between age groups have differed significantly with p-value < 0.05. The highest CTDI_vol and DLP values in all age groups with the lowest noise index value reported in the 10–15 age group were found in CT brain examination. In conclusion, there was a significant variation in doses and noise intensity among children of different ages, and the need to change specific parameters to fit the clinical requirement.