Abstract This literature review examines the advancements in automated semantic segmentation in X-ray medical imaging through the lens of deep learning. Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses approach, the review demonstrates the transformative effect of deep learning technologies in enhancing diagnostic accuracy and efficiency in medical imaging, significantly influencing healthcare outcomes. X-ray imaging is essential in medical diagnostics because it is a non-invasive and highly informative diagnostic tool. This review explores the application of deep learning to automate the examination of small, targeted segments of the torrent of information produced by X-ray imaging. The review delves into the specific role of deep learning algorithms in identifying and labeling anatomical structures and pathologies in X-ray images, underscoring the precision and sophistication these models bring to medical imaging. The discussion on automatic segmentation centers around how deep learning algorithms effectively delineate specific regions of interest, thereby facilitating more advanced analysis and interpretation. The review concludes with directions for future research in this field, emphasizing the growing importance and potential of deep learning in X-ray image processing. This comprehensive synthesis provides researchers and practitioners with a clear understanding of the current state and prospects of deep learning in automated X-ray image processing.

ABSTRACT Since its inception in 2015, U‐Net has emerged as a cornerstone architecture that is particularly well‐designed for medical image segmentation. Despite its robustness, precise tumour segmentation persists as a challenge because of tumour heterogeneity, boundary ambiguity, and the partial volume effects exhibited by tumours. Therefore, the U‐Net architecture has been altered many times to expand its capabilities with complex segmentation challenges, particularly with tumours. Following the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) methodology, this systematic review critically evaluates and analyses the effectiveness of recent enhancement strategies developed to optimize the performance of the traditional U‐Net architecture in attaining accurate tumour segmentation in CT and MRI images. The strategies have been divided into five main areas: U‐Net architectural enhancements, including U‐Net backbone optimization; skip connection refinements; bottleneck optimizations; transformer‐based integrations; and metaheuristic algorithms as a self‐adaptive optimization technique. Afterward, each category is thoroughly examined to determine how the strategies address specific limitations inherent to the traditional U‐Net model. In addition, this paper reviews the pivotal role of preprocessing techniques in determining segmentation performance. This review identifies persistent research gaps and offers valuable insights for future research to improve the robustness, accuracy, and clinical applicability of the U‐Net model.

Abstract Forecasting the demand for diphtheria, tetanus, and pertussis (DTaP) vaccines is crucial to efficiently allocating resources, reducing vaccine waste, and improving health outcomes, particularly in rural and underprivileged areas. Challenges specific to these areas include limited access to healthcare facilities, inconsistent supply chains, and a lack of data on vaccination rates and patient demographics. This study presents a predictive modeling framework that is capable of improving resource planning at a federally qualified health center (FQHC) in upstate New York by better predicting demand for the DTaP vaccine from the rural population it serves. Using a large dataset of 160,289 patient visits from 2021 to 2023, patient demographic, clinical, insurance, visit-specific, and temporal features were extracted and incorporated into multiple machine learning (ML) models. Multiple ML algorithms—such as XGBoost, CatBoost, and histogram-based gradient boosting— were benchmarked against widely used baseline models including random forests, logistic regression, and decision trees. CatBoost was the top-performing model, with a receiver operating characteristic–area under the curve (ROC-AUC) score of 99.8% and an F1 score of 89.0% at a decision threshold of 67.2%. Seasonal decomposition revealed peaks during back-to-school periods, highlighting temporal dynamics. In addition, SHapley Additive exPlanations (SHAP) analysis improved model interpretability, allowing the identification of age, insurance type, visit type, and previous immunization history as the key predictors that enhance the models’ performance. The predictive modeling framework delivers very accurate forecasts and actionable insights while opening black-box models to guide immunization strategies and optimize resource planning by the existing healthcare system.

For years, integrated circuit design has been a driver for algorithmic advances. The problems encountered in the design of modern circuits are often intractable -- and with exponentially increasing size. Efficient heuristics and approximations have been essential to sustaining Moore's Law growth, and now almost every aspect of the design process is heavily automated. There is, however, one notable exception: there is often substantial floor planning effort from human designers to position large macro blocks. The lack of full automation on this step has motivated the exploration of novel optimization methods, most recently with reinforcement learning. In this paper, we argue that there are multiple forces which have prevented full automation -- and a lack of algorithmic methods is not the only factor. If the time has come for automation, there are a number of "traditional'' methods that should be considered again. We focus on recursive bisection, and highlight key ideas from partitioning algorithms that have broader impact than one might expect. We also stress the importance of benchmarking as a way to determine which approaches may be most effective.

Integrated circuit design encompasses a wide range of intractable optimization problems. In this paper, we extend linear time hill climbing techniques from graph partitioning to address detailed placement -- this results in a new way to refine circuit designs, dramatically expands the size of practical optimization windows, and enables wire length reductions on a variety of benchmark problems. The approach is versatile and straight-forward to implement, allowing it to be applied to a wide range of problems within design automation, and beyond.

Routing for dense circuits is a major challenge for VLSI physical design. Most routing approaches rely at least partially on a "rip-up and reroute" scheme, where solution quality and run times can be impacted profoundly by the order in which nets are routed. Other routing tools rely on backtracking methods embedded in integer linear programming solvers. In this paper, we present a novel approach which avoids backtracking, and largely eliminates the routing order considerations, by constructing a large number of routings simultaneously. By keeping "options open," our approach sidesteps conflicts. Our approach is a factor of ten faster than other recent work, reduces via counts by 30% or more, and is competitive on both wire length and completion rates. The approach is simple, scalable, and adaptable to the complex constraints of modern circuit fabrication processes.