Abstract Purpose: Accurate registration of medical images is crucial for doctor’s diagnosis and quantitative analysis. Optimizing the loss function is an significant research direction in medical image registration. From variational method in differential geometry, control function is essential to generate better registration field ϕ. Methods: In this paper, we propose a novel registration loss function based on the VoxelMorph architecture, utilizing the control function and Lagrange multiplier. The proposed method consists of two steps. In the first step, we modify the gradient of the registration field ϕ in Lsmooth(ϕ) using the Laplacian operator. In the second step, we introduce the control function F into the Lsmooth(ϕ) from the first step, which is the main contribution of our method. And we discussed two extensions of our method based on Lagrange multiplier.In the first extension, we add a Lagrange multiplier to control the Lsmooth(ϕ) in the second step. The second extension is based on Lagrange multiplier and Jacobian determinant (JD). We change the Laplacian operator to JD, and control function F to monitor function f of JD. Our proposed method has been validated on two datasets, namely the ADNI and IBSR datasets. Results: The results of our method demonstrate a significant improvement in MR image registration compared to existing methods. The new loss function has better convergence than original loss and gets better average Dice (higher is better) and non-positive Jacobian locations (lower is better) compared with MIT’s original method. Conclusion: The experimental findings indicate that our proposed technique outperforms other existing methods in the task of registering brain MRI images.
The implementation of medical AI has always been a problem. The effect of traditional perceptual AI algorithm in medical image processing needs to be improved. Here we propose a method of knowledge AI, which is a combination of perceptual AI and clinical knowledge and experience. Based on this method, the geometric information mining of medical images can represent the experience and information and evaluate the quality of medical images.
Medical image segmentation, particularly in the context of ultrasound data, is a crucial aspect of computer vision and medical imaging. This paper delves into the complexities of uncertainty in the segmentation process, focusing on fetal head and femur ultrasound images. The proposed methodology involves extracting target contours and exploring techniques for precise parameter measurement. Uncertainty modeling methods are employed to enhance the training and testing processes of the segmentation network. The study reveals that the average absolute error in fetal head circumference measurement is 8.0833mm, with a relative error of 4.7347%. Similarly, the average absolute error in fetal femur measurement is 2.6163mm, with a relative error of 6.3336%. Uncertainty modeling experiments employing Test-Time Augmentation (TTA) demonstrate effective interpretability of data uncertainty on both datasets. This suggests that incorporating data uncertainty based on the TTA method can support clinical practitioners in making informed decisions and obtaining more reliable measurement results in practical clinical applications. The paper contributes to the advancement of ultrasound image segmentation, addressing critical challenges and improving the reliability of biometric measurements.
With the increasing demand from aging population and seasonal blood shortage, recruiting and retaining blood donors has become an urgent issue for the blood collection centers in China. This study aims to understand intention to donate again from a social cognitive perspective among whole blood donors in China through investigating the association between the blood donation fear, perceived rewards, self-efficacy, and intention to return. A cross-sectional survey was conducted in six cities, which are geographically and socioeconomically distinct areas in Jiangsu, China. Respondents completed a self-administrated questionnaire interviewed by two well-trained medical students. A total of 191 blood donors were included in the current study. Descriptive analysis, correlation analysis, and a generalized linear regression model were used to explore the association between demographic characteristics, psychological factors, and intention to donate again. After controlling other covariates, donors with higher fear scores reported lower intention to return (p = 0.008). Association between self-efficacy and intention to return was statistically significant (p < 0.001), whereas the association between intrinsic rewards (p = 0.387), extrinsic rewards (p = 0.939), and intention to return were statistically insignificant. This study found that either intrinsic rewards or extrinsic rewards are not significantly associated with intention to donate again among whole blood donors in China, and fear is negatively associated with intention to donate again. Therefore, purposive strategies could be enacted beyond appeals to rewards and focus on the management of donors' fear.
Super-resolution techniques utilizing generative adversarial network (GAN) have gained significant attention in computer vision research. Nevertheless, the produced high-resolution images often contain undesirable artifacts such as geometric distortions, which can affect their visual quality. In this research, we propose a latest super resolution approach that tackles the aforementioned concern while preserving the advantages of GAN-based approaches to elevate the visual quality even further. More precisely, we utilize geometric information of images to direct the recovery process in two aspects. On the one hand, we extract differential geometric information including Jacobian determinant (JD) and curl vector (CV) using the deformation method in differential geometry, which model the rate of change in local cell size and rotation respectively, then we take them as the conditional inputs of SRGAN to provide additional geometric structure priors for the SR process. On the other hand, we propose a new geometric perceptual loss motivated by JD feature information containing three terms (edges, background, objects), which can better maintain the geometric invariance of manifolds to recover the high-frequency details. The results of experiments strongly demonstrate that our proposed method outperforms existing state-of-the-art perceptual-driven SR approaches in terms of perceptual quality, with the best PI and LPIPS performance achieved.
Objective: Breast cancer screening is of great significance in contemporary women's health prevention. The existing machines embedded in the AI system do not reach the accuracy that clinicians hope. How to make intelligent systems more reliable is a common problem. Methods: 1) Ultrasound image super-resolution: the SRGAN super-resolution network reduces the unclearness of ultrasound images caused by the device itself and improves the accuracy and generalization of the detection model. 2) In response to the needs of medical images, we have improved the YOLOv4 and the CenterNet models. 3) Multi-AI model: based on the respective advantages of different AI models, we employ two AI models to determine clinical resuls cross validation. And we accept the same results and refuses others. Results: 1) With the help of the super-resolution model, the YOLOv4 model and the CenterNet model both increased the mAP score by 9.6% and 13.8%. 2) Two methods for transforming the target model into a classification model are proposed. And the unified output is in a specified format to facilitate the call of the molti-AI model. 3) In the classification evaluation experiment, concatenated by the YOLOv4 model (sensitivity 57.73%, specificity 90.08%) and the CenterNet model (sensitivity 62.64%, specificity 92.54%), the multi-AI model will refuse to make judgments on 23.55% of the input data. Correspondingly, the performance has been greatly improved to 95.91% for the sensitivity and 96.02% for the specificity. Conclusion: Our work makes the AI model more reliable in medical image diagnosis. Significance: 1) The proposed method makes the target detection model more suitable for diagnosing breast ultrasound images. 2) It provides a new idea for artificial intelligence in medical diagnosis, which can more conveniently introduce target detection models from other fields to serve medical lesion screening.
This paper focuses on the classification task of breast ultrasound images and researches on the reliability measurement of classification results. We proposed a dual-channel evaluation framework based on the proposed inference reliability and predictive reliability scores. For the inference reliability evaluation, human-aligned and doctor-agreed inference rationales based on the improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate the predictive reliability via the Test Time Enhancement. The effectiveness of this reliability evaluation framework has been verified on our breast ultrasound clinical dataset YBUS, and its robustness is verified on the public dataset BUSI. The expected calibration errors on both datasets are significantly lower than traditional evaluation methods, which proves the effectiveness of our proposed reliability measurement.
This paper focuses on the classification task of breast ultrasound images and researches on the reliability measurement of classification results. We proposed a dual-channel evaluation framework based on the proposed inference reliability and predictive reliability scores. For the inference reliability evaluation, human-aligned and doctor-agreed inference rationales based on the improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate the predictive reliability via the Test Time Enhancement. The effectiveness of this reliability evaluation framework has been verified on our breast ultrasound clinical dataset YBUS, and its robustness is verified on the public dataset BUSI. The expected calibration errors on both datasets are significantly lower than traditional evaluation methods, which proves the effectiveness of our proposed reliability measurement.
Abstract Chatbots, or bots for short, are multimodal collaborative assistants that can help people complete useful tasks. Usually, when chatbots are referenced in connection with elections, they often draw negative reactions due to the fear of mis‐information and hacking. Instead, in this work, we explore how chatbots may be used to promote voter participation in vulnerable segments of society like senior citizens and first‐time voters. In particular, we have built a system that amplifies official information while personalizing it to users' unique needs transparently (e.g., language, cognitive abilities, linguistic abilities). The uniqueness of this work are (a) a safe design where only responses that are grounded and traceable to an allowed source (e.g., official question/answer) will be answered via system's self‐awareness (metacognition), (b) a do‐not‐respond strategy that can handle customizable responses/deflection, and (c) a low‐programming design‐pattern based on the open‐source Rasa platform to generate chatbots quickly for any region. Our current prototypes use frequently asked questions (FAQ) election information for two US states that are low on an ease‐of‐voting scale, and have performed initial evaluations using focus groups with senior citizens. Our approach can be a win‐win for voters, election agencies trying to fulfill their mandate and democracy at large.
Chatbots, or bots for short, are multi-modal collaborative assistants that can help people complete useful tasks. Usually, when chatbots are referenced in connection with elections, they often draw negative reactions due to the fear of mis-information and hacking. Instead, in this paper, we explore how chatbots may be used to promote voter participation in vulnerable segments of society like senior citizens and first-time voters. In particular, we build a system that amplifies official information while personalizing it to users' unique needs transparently. We discuss its design, build prototypes with frequently asked questions (FAQ) election information for two US states that are low on an ease-of-voting scale, and report on its initial evaluation in a focus group. Our approach can be a win-win for voters, election agencies trying to fulfill their mandate and democracy at large.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)