Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We ...
详细信息
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad
Technology in transportation becomes important nowadays and must be developed overtime. In the era of development, there are so many roads extensions to balance the significant additions of motorized vehicles. The inc...
Technology in transportation becomes important nowadays and must be developed overtime. In the era of development, there are so many roads extensions to balance the significant additions of motorized vehicles. The increasing number of vehicles caused problems such as damaged roads and lack of maintenance to the road itself. Lack of awareness to repair the damaged roads, especially potholes, make it more dangerous for riders to drive safely. This issues are more concerning right now because the increasing number of accident and mortality. To prevent accident to happen, the pothole detection sensor can be used to on car system. The development of pothole detection sensor in this research is adopted from the proximity sensor system where in that system they use camera and digital imaging process. The advantages from our system that we research and develop are more user friendly from the feasibility and the financial aspect. Low cost sensor with the same quality of the existing system is devlop in this work. Despite the use of low cost sensor, the maintenance also on the lower cost and easier to do. As the result of this research and study, an error was obtained between the distance that detected the pothole should be in less than 4% distance range from the sensor.
Minimizing Gaussian curvature of meshes is fundamentally important for obtaining smooth and developable surfaces. However, there is a lack of computationally efficient and robust Gaussian curvature optimization method...
详细信息
The use of computer-aided diagnosis in the reliable and fast detection of corona virus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the medical...
详细信息
Assessing aesthetic preference is a fundamental task related to human cognition. It can also contribute to various practical applications such as image creation for online advertisements. Despite crucial influences of...
详细信息
In hierarchical planning for Markov decision processes (MDPs), temporal abstraction allows planning with macro-actions that take place at different time scale in form of sequential composition. In this paper, we propo...
详细信息
In this paper, we develop approximate dynamic programming methods for stochastic systems modeled as Markov Decision Processes, given both soft performance criteria and hard constraints in a class of probabilistic temp...
详细信息
Mechatronic rehabilitative devices have been proven to provide cost effective solutions to long term physical therapy for patients with musculoskeletal disorders. However, current actuator technologies limit the minim...
详细信息
ISBN:
(纸本)9781538681848
Mechatronic rehabilitative devices have been proven to provide cost effective solutions to long term physical therapy for patients with musculoskeletal disorders. However, current actuator technologies limit the minimization of the overall size and weight of these devices preventing innovation into unobtrusive wearable form factors that are also effective and comfortable. This study is focused on a recently discovered smart actuator made from flexible nylon thread, which has exhibited a great potential for use in wearable mechatronic devices. This is known as the twisted coiled actuator (TCA) due to the hyper twisting and induced coiling involved in its fabrication process. One of the limiting factors of the TCA, is the thermal activation mechanism, which results in a slow cooling phase and a low working bandwidth. This paper is focused on optimizing an active cooling design using numerical analysis. To do this, a simple pipe geometry was designed and tested using fluid dynamics software. Three off-the-shelf fluidic pumps were simulated using varying tube diameters to find a sufficient cooling rate, a minimum fluid volume, and to select a proper pump for future testing. The results indicate that a global maximum cooling rate exists for each specific pump at a unique tube diameter. Additionally, the speed of cooling was under 500 ms concluding that the pumps tested can sufficiently provide the cooling rates required to assist motion in wearable devices. Furthermore, the process developed here provides quantitative support for the optimal selection of initial design parameters and can be translated to designs using different form factors and fluid properties.
In this paper, we propose a sampling-based policy iteration for optimal planning under temporal logic constraints. The method integrates approximate optimal control, importance sampling, and formal methods. For a subc...
详细信息
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology ...
详细信息
暂无评论