Ovarian lesions are common and often incidentally detected. A critical shortage of expert ultrasound examiners has raised concerns of unnecessary interventions and delayed cancer diagnoses. Deep learning has shown promising results in the detection of ovarian cancer in ultrasound images; however, external validation is lacking. In this international multicenter retrospective study, we developed and validated transformer-based neural network models using a comprehensive dataset of 17,119 ultrasound images from 3,652 patients across 20 centers in eight countries. Using a leave-one-center-out cross-validation scheme, for each center in turn, we trained a model using data from the remaining centers. The models demonstrated robust performance across centers, ultrasound systems, histological diagnoses and patient age groups, significantly outperforming both expert and non-expert examiners on all evaluated metrics, namely F1 score, sensitivity, specificity, accuracy, Cohen’s kappa, Matthew’s correlation coefficient, diagnostic odds ratio and Youden’s J statistic. Furthermore, in a retrospective triage simulation, artificial intelligence (AI)-driven diagnostic support reduced referrals to experts by 63% while significantly surpassing the diagnostic performance of the current practice. These results show that transformer-based models exhibit strong generalization and above human expert-level diagnostic accuracy, with the potential to alleviate the shortage of expert ultrasound examiners and improve patient outcomes.

The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has become common practice within the field of natural language processing, progress has been slower in computer vision. In this paper we attempt to address this issue by investigating the transferability of various state-of-the-art foundation models to medical image classification tasks. Specifically, we evaluate the performance of five foundation models, namely Sam, Seem, Dinov2, BLIP, and OpenCLIP across four well-established medical imaging datasets. We explore different training settings to fully harness the potential of these models. Our study shows mixed results. Dinov2 consistently outperforms the standard practice of ImageNet pretraining. However, other foundation models failed to consistently beat this established baseline indicating limitations in their transferability to medical image classification tasks.

Artificial intelligence (AI) has emerged as a major frontier in healthcare and finds broad range of applications. It has the potential to revolutionize current procedures of disease diagnosis and treatment, thus influencing the clinical practice. Artificial intelligence (AI) in ophthalmology, primarily concentrates on diagnostic and treatment pathways for eye conditions such as cataract, glaucoma, age-related macular degeneration (MDA) and diabetic retinopathy (DR). The purpose of this article is to systematically review the existing state of literature on the various AI techniques and its applications in the diagnosis and treatment of eye diseases and conduct an in-depth enquiry to identify the challenges in accurate detection, pre-processing of data, monitoring and assessment through various AI algorithms. The results suggest that all AI models proposed reduce the detection time considerably. The potential limitations and challenges in the development and application play a significant role in clinical practice. There is a need for the development of AI-assisted technologies that shall consider the clinical implications based on experience and guided by patient-centred healthcare principles. The diagnostic models should assist ophthalmologists on making quick and accurate decisions in determining the progression of various ocular diseases.

In recent years, immense development in Structural Health Monitoring (SHM) of bridges helps address the life span and reliability of bridge structure at contrasting phases of their service life. This article provides a detailed understanding of bridge monitoring, and it focuses on sensors utilized and all kinds of damage detection (strain, displacement, acceleration, and temperature) according to bridge nature (scour, suspender failure, disconnection of bolt and cables, etc.) and environmental degradation under static and dynamic loading. This paper presents information about various methods, approaches, case studies, advanced technologies, real-time experiments, stimulated models, data acquisition, and predictive analysis. Future scope and research also discussed the implementation of SHM in bridges. The main aim of this research is to assist researchers in better understanding the monitoring mechanism in bridges.

Gender determination is of paramount importance in order to identify the diseased in cases of mass disasters and accidents and to resolve all medico-legal issues in cases of violence. Skeletal bones are the strongest bones in the body and they play a crucial role in identifying a person's gender. ANN is a relatively new technology, is fast emerging as a better prediction model for gender when used with skeletal bones like the femur. Prior studies have extensively used discriminant analysis, logistic regression and other similar statistical tools to understand the role of the mandible and its efficacy in gender determination. This study uses Artificial Neural Networks (ANN) for gender determination and compares results thus obtained with logistic regression and discriminant analysis using mandibular parameters as inputs. Digital panoramic radiographs were used to measure the mandible of 509 individuals. Six linear parameters and one angular parameter of each individual were obtained. Logistic Regression, Discriminant Analysis, and ANN analysis were performed on these parameters. The discriminant analysis had an overall accuracy of 69.1%, logistic regression showed an accuracy of 69.9% and ANN exhibited a higher accuracy of 75%. The results revealed that ANN is a good gender prediction tool that can be applied in the field of forensic sciences for near accurate results. Its application is promising as it automates and eases the method of identifying unknown gender or age with minimal errors.

Dental implants are widely accepted for the rehabilitation of missing teeth due to their aesthetic compliance, functional ability, and great survival rate. The various components in implant design like thread design, thread angle, pitch, and material used for manufacturing play a critical role in its success. Understanding these influencing factors and implementing them properly in implant design can reduce cases of potential implant failure. Recently, finite element analysis (FEA) is being widely used in the field of health sciences to solve problems in designing medical devices. It provides valid and accurate assessment in the clinical and in vitro analysis. Hence, this study was conducted to evaluate the impact of thread design of the implant and 3 different bioactive materials, titanium alloy, graphene, and reduced graphene oxide (rGO) on stress, strain, and deformation in the implant system using FEA. In this study, the FEA model of the bones and the tissues are modeled as homogeneous, isotropic, and linearly elastic material with a titanium implant system with an assumption of it 100% osseointegrated into the bone. The titanium was functionalized with graphene and graphene oxide. A modeling software tool Catia¯ and Ansys Workbench¯ is used to perform the analysis and evaluate the von Mises stress distribution, strain, and deformation at the implant and implant-cortical bone interface. The results showed that the titanium implant with a surface coating of graphene oxide exhibited better mechanical behavior than graphene, with mean von Mises stress of 39.64 MPa in pitch 1, 23.65 MPa in pitch 2, and 37.23 MPa in pitch 3. It also revealed that functionalizing the titanium implant will help in reducing the stress at the implant system. Overall, the study emphasizes the use of FEA analysis methods in solving various biomechanical issues about medical and dental devices, which can further open up for invivo study and their practical uses.

Ovarian lesions are common and often incidentally detected. A critical shortage of expert ultrasound examiners has raised concerns of unnecessary interventions and delayed cancer diagnoses. Deep learning has shown promising results in the detection of ovarian cancer in ultrasound images; however, external validation is lacking. In this international multicenter retrospective study, we developed and validated transformer-based neural network models using a comprehensive dataset of 17,119 ultrasound images from 3,652 patients across 20 centers in eight countries. Using a leave-one-center-out cross-validation scheme, for each center in turn, we trained a model using data from the remaining centers. The models demonstrated robust performance across centers, ultrasound systems, histological diagnoses and patient age groups, significantly outperforming both expert and non-expert examiners on all evaluated metrics, namely F1 score, sensitivity, specificity, accuracy, Cohen’s kappa, Matthew’s correlation coefficient, diagnostic odds ratio and Youden’s J statistic. Furthermore, in a retrospective triage simulation, artificial intelligence (AI)-driven diagnostic support reduced referrals to experts by 63% while significantly surpassing the diagnostic performance of the current practice. These results show that transformer-based models exhibit strong generalization and above human expert-level diagnostic accuracy, with the potential to alleviate the shortage of expert ultrasound examiners and improve patient outcomes.