我们提出了一个基于深度学习的自动咳嗽分类器，可以区分结核病（TB）与Covid-19咳嗽和健康咳嗽。 TB和Covid-19都是呼吸道疾病，具有传染性，咳嗽是一种主要的症状，每年夺走了数千人的生命。在室内和室外设置都收集了咳嗽的录音，并使用来自全球各地受试者的智能手机上传，因此包含各种噪声。该咳嗽数据包括1.68小时的结核病咳嗽，18.54分钟的咳嗽，咳嗽和1.69小时的健康咳嗽，47例TB患者，229例Covid-19患者和1498例健康患者，并用于培训和评估CNN，LSTM和Resnet505050 。这三个深度体系结构在2.14小时的打喷嚏，2.91小时的语音和2.79小时的噪音中也进行了预训练，以提高性能。通过使用SMOTE数据平衡技术并使用诸如F1得分和AUC之类的性能指标来解决我们数据集中的类不平衡。我们的研究表明，从预先训练的RESNET50中获得了最高的0.9259和0.8631的F1分数，两级（TB与CoVID-19）和三级（TB VS VS COVID-19与健康）的咳嗽分类，咳嗽分类，，咳嗽分类任务，三级（TB vs vs covid-19）分别。深度转移学习的应用改善了分类器的性能，并使它们更加坚固，因为它们在交叉验证折叠上更好地概括了。他们的表现超过了世界卫生组织（WHO）设定的结核病分类测试要求。产生最佳性能的功能包含MFCC的高阶，这表明人耳朵无法感知结核病和COVID-19之间的差异。这种类型的咳嗽音频分类是非接触，具有成本效益的，并且可以轻松地部署在智能手机上，因此它可以成为TB和COVID-19筛查的绝佳工具。

我们提出“唤醒咳嗽”，这是使用resnet50咳嗽到咳嗽的应用，并使用i-vectors识别咳嗽者，以实现长期的个性化咳嗽监测系统。咳嗽记录在一个安静（73 $ \ pm $ 5 dB）和嘈杂（34 $ \ pm $ 17 dB）环境中，用于提取I-向量，X-向量和D-向量，用作分类器的功能。当使用MLP使用2-SEC长咳嗽片段在嘈杂的环境中使用MLP区分51个咳嗽者时，该系统可以达到90.02 \％的精度。当在安静环境中使用更长（100秒）段的5和14个咳嗽者区分5至14个咳嗽者时，这种准确性分别提高到99.78％和98.39％。与语音不同，I-向量在识别咳嗽者方面的表现优于X-向量和D-向量。这些咳嗽是在Google语音命令数据集中添加的额外类，并通过在触发短语中保存端到端的时间域信息来提取功能。使用RESNET50在35个其他触发短语中发现咳嗽时，达到了88.58％的最高精度。因此，Wake咳嗽代表了一个个性化的，非侵入性的咳嗽监测系统，该系统的功率有效，因为在设备上的唤醒词检测可以使基于智能手机的监视设备大多处于休眠状态。这使伴尾咳嗽在多床病房环境中极具吸引力，以监测患者从肺部疾病（例如结核病（TB）和Covid-19）中的长期恢复。

Coronary Computed Tomography Angiography (CCTA) provides information on the presence, extent, and severity of obstructive coronary artery disease. Large-scale clinical studies analyzing CCTA-derived metrics typically require ground-truth validation in the form of high-fidelity 3D intravascular imaging. However, manual rigid alignment of intravascular images to corresponding CCTA images is both time consuming and user-dependent. Moreover, intravascular modalities suffer from several non-rigid motion-induced distortions arising from distortions in the imaging catheter path. To address these issues, we here present a semi-automatic segmentation-based framework for both rigid and non-rigid matching of intravascular images to CCTA images. We formulate the problem in terms of finding the optimal \emph{virtual catheter path} that samples the CCTA data to recapitulate the coronary artery morphology found in the intravascular image. We validate our co-registration framework on a cohort of $n=40$ patients using bifurcation landmarks as ground truth for longitudinal and rotational registration. Our results indicate that our non-rigid registration significantly outperforms other co-registration approaches for luminal bifurcation alignment in both longitudinal (mean mismatch: 3.3 frames) and rotational directions (mean mismatch: 28.6 degrees). By providing a differentiable framework for automatic multi-modal intravascular data fusion, our developed co-registration modules significantly reduces the manual effort required to conduct large-scale multi-modal clinical studies while also providing a solid foundation for the development of machine learning-based co-registration approaches.

The release of ChatGPT, a language model capable of generating text that appears human-like and authentic, has gained significant attention beyond the research community. We expect that the convincing performance of ChatGPT incentivizes users to apply it to a variety of downstream tasks, including prompting the model to simplify their own medical reports. To investigate this phenomenon, we conducted an exploratory case study. In a questionnaire, we asked 15 radiologists to assess the quality of radiology reports simplified by ChatGPT. Most radiologists agreed that the simplified reports were factually correct, complete, and not potentially harmful to the patient. Nevertheless, instances of incorrect statements, missed key medical findings, and potentially harmful passages were reported. While further studies are needed, the initial insights of this study indicate a great potential in using large language models like ChatGPT to improve patient-centered care in radiology and other medical domains.

Artificial Intelligence (AI) has become commonplace to solve routine everyday tasks. Because of the exponential growth in medical imaging data volume and complexity, the workload on radiologists is steadily increasing. We project that the gap between the number of imaging exams and the number of expert radiologist readers required to cover this increase will continue to expand, consequently introducing a demand for AI-based tools that improve the efficiency with which radiologists can comfortably interpret these exams. AI has been shown to improve efficiency in medical-image generation, processing, and interpretation, and a variety of such AI models have been developed across research labs worldwide. However, very few of these, if any, find their way into routine clinical use, a discrepancy that reflects the divide between AI research and successful AI translation. To address the barrier to clinical deployment, we have formed MONAI Consortium, an open-source community which is building standards for AI deployment in healthcare institutions, and developing tools and infrastructure to facilitate their implementation. This report represents several years of weekly discussions and hands-on problem solving experience by groups of industry experts and clinicians in the MONAI Consortium. We identify barriers between AI-model development in research labs and subsequent clinical deployment and propose solutions. Our report provides guidance on processes which take an imaging AI model from development to clinical implementation in a healthcare institution. We discuss various AI integration points in a clinical Radiology workflow. We also present a taxonomy of Radiology AI use-cases. Through this report, we intend to educate the stakeholders in healthcare and AI (AI researchers, radiologists, imaging informaticists, and regulators) about cross-disciplinary challenges and possible solutions.

The future of population-based breast cancer screening is likely personalized strategies based on clinically relevant risk models. Mammography-based risk models should remain robust to domain shifts caused by different populations and mammographic devices. Modern risk models do not ensure adaptation across vendor-domains and are often conflated to unintentionally rely on both precursors of cancer and systemic/global mammographic information associated with short- and long-term risk, respectively, which might limit performance. We developed a robust, cross-vendor model for long-term risk assessment. An augmentation-based domain adaption technique, based on flavorization of mammographic views, ensured generalization to an unseen vendor-domain. We trained on samples without diagnosed/potential malignant findings to learn systemic/global breast tissue features, called mammographic texture, indicative of future breast cancer. However, training so may cause erratic convergence. By excluding noise-inducing samples and designing a case-control dataset, a robust ensemble texture model was trained. This model was validated in two independent datasets. In 66,607 Danish women with flavorized Siemens views, the AUC was 0.71 and 0.65 for prediction of interval cancers within two years (ICs) and from two years after screening (LTCs), respectively. In a combination with established risk factors, the model's AUC increased to 0.68 for LTCs. In 25,706 Dutch women with Hologic-processed views, the AUCs were not different from the AUCs in Danish women with flavorized views. The results suggested that the model robustly estimated long-term risk while adapting to an unseen processed vendor-domain. The model identified 8.1% of Danish women accounting for 20.9% of ICs and 14.2% of LTCs.

Quaternion valued neural networks experienced rising popularity and interest from researchers in the last years, whereby the derivatives with respect to quaternions needed for optimization are calculated as the sum of the partial derivatives with respect to the real and imaginary parts. However, we can show that product- and chain-rule does not hold with this approach. We solve this by employing the GHRCalculus and derive quaternion backpropagation based on this. Furthermore, we experimentally prove the functionality of the derived quaternion backpropagation.

In this work, a method for obtaining pixel-wise error bounds in Bayesian regularization of inverse imaging problems is introduced. The proposed method employs estimates of the posterior variance together with techniques from conformal prediction in order to obtain coverage guarantees for the error bounds, without making any assumption on the underlying data distribution. It is generally applicable to Bayesian regularization approaches, independent, e.g., of the concrete choice of the prior. Furthermore, the coverage guarantees can also be obtained in case only approximate sampling from the posterior is possible. With this in particular, the proposed framework is able to incorporate any learned prior in a black-box manner. Guaranteed coverage without assumptions on the underlying distributions is only achievable since the magnitude of the error bounds is, in general, unknown in advance. Nevertheless, experiments with multiple regularization approaches presented in the paper confirm that in practice, the obtained error bounds are rather tight. For realizing the numerical experiments, also a novel primal-dual Langevin algorithm for sampling from non-smooth distributions is introduced in this work.

Multi-class ensemble classification remains a popular focus of investigation within the research community. The popularization of cloud services has sped up their adoption due to the ease of deploying large-scale machine-learning models. It has also drawn the attention of the industrial sector because of its ability to identify common problems in production. However, there are challenges to conform an ensemble classifier, namely a proper selection and effective training of the pool of classifiers, the definition of a proper architecture for multi-class classification, and uncertainty quantification of the ensemble classifier. The robustness and effectiveness of the ensemble classifier lie in the selection of the pool of classifiers, as well as in the learning process. Hence, the selection and the training procedure of the pool of classifiers play a crucial role. An (ensemble) classifier learns to detect the classes that were used during the supervised training. However, when injecting data with unknown conditions, the trained classifier will intend to predict the classes learned during the training. To this end, the uncertainty of the individual and ensemble classifier could be used to assess the learning capability. We present a novel approach for novel detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We present an architecture for multi-class ensemble classification and an approach to quantify the uncertainty of the individual classifiers and the ensemble classifier. We use uncertainty for the anomaly detection approach. Finally, we use the benchmark Tennessee Eastman to perform experiments to test the ensemble classifier's prediction and anomaly detection capabilities.

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training classes and often fail at detecting novel-looking objects. This is because RGB-based models primarily rely on appearance similarity to detect novel objects and are also prone to overfitting short-cut cues such as textures and discriminative parts. To address these shortcomings of RGB-based object detectors, we propose incorporating geometric cues such as depth and normals, predicted by general-purpose monocular estimators. Specifically, we use the geometric cues to train an object proposal network for pseudo-labeling unannotated novel objects in the training set. Our resulting Geometry-guided Open-world Object Detector (GOOD) significantly improves detection recall for novel object categories and already performs well with only a few training classes. Using a single "person" class for training on the COCO dataset, GOOD surpasses SOTA methods by 5.0% AR@100, a relative improvement of 24%.