In response to the worldwide COVID-19 pandemic, advanced automated
technologies have emerged as valuable tools to aid healthcare professionals in
managing an increased workload by improving radiology report generation and
prognostic analysis. This study proposes Multi-modality Regional Alignment
Network (MRANet), an explainable model for radiology report generation and
survival prediction that focuses on high-risk regions. By learning spatial
correlation in the detector, MRANet visually grounds region-specific
descriptions, providing robust anatomical regions with a completion strategy.
The visual features of each region are embedded using a novel survival
attention mechanism, offering spatially and risk-aware features for sentence
encoding while maintaining global coherence across tasks. A cross LLMs
alignment is employed to enhance the image-to-text transfer process, resulting
in sentences rich with clinical detail and improved explainability for
radiologist. Multi-center experiments validate both MRANet's overall
performance and each module's composition within the model, encouraging further
advancements in radiology report generation research emphasizing clinical
interpretation and trustworthiness in AI models applied to medical studies. The
code is available at this https URL

应对全球 COVID-19 大流行，先进的自动化技术已成为有价值的工具，以改善放射学报告生成和预测分析，分担医疗专业人员的工作负担。本研究提出了一种多模态区域对齐网络（MRANet），该网络是一个可解释的模型，用于放射学报告生成和生存预测，重点关注高风险区域。通过学习检测器中的空间相关性，MRANet 在视觉上确定特定区域的描述，提供具备完成策略的鲁棒解剖学区域。采用了一种新颖的生存注意机制来嵌入每个区域的视觉特征，为句子编码提供具有空间感知和风险感知的特征，并在任务间保持整体连贯性。采用交叉 LLMs 对齐以增强图像到文本的转换过程，从而产生富含临床细节且具有改进可解释性的句子，用于提高放射科医师的信任。多中心实验证实了 MRANet 整体性能和模型内各模块的组成，鼓励进一步改进放射学报告生成研究，注重医学研究中的临床解释和可信性。代码可在此 https URL 找到。

多模态区域对齐网络用于 Covid X 光生存预测与报告生成

Multi-modality Regional Alignment Network for Covid X-Ray Survival  Prediction and Report Generation

The variation of solar irradiance is one of the natural forcing mechanisms of
the terrestrial climate. Hence, the time-dependent solar irradiance is an
important input parameter for climate modelling. The solar surface magnetic
field is a powerful proxy for solar irradiance reconstruction. The analyses of
data obtained with the Michelson Doppler Imager (MDI) on board the SOHO mission
are therefore useful for the identification of solar surface magnetic features
to be used in solar irradiance reconstruction models. However, there is still a
need for automated technologies that would enable the identification of solar
activity features from large databases. To achieve this we present a series of
enhanced segmentation algorithms developed to detect and calculate the area
coverages of specific magnetic features from MDI intensitygrams and
magnetograms. These algorithms are part of the Automated Solar Activity
Prediction (ASAP) tool. The segmentation algorithms allow us to identify the
areas on the solar disk covered by magnetic elements inside and outside
boundaries of active regions. Depending on their contrast properties, magnetic
features within an active region boundary are classified as sunspot umbra and
penumbra, or faculae. Outside an active region boundary magnetic elements are
identified as network. We present the detailed steps involved in the
segmentation process and provide the area coverages of the segmented MDI
intensitygrams and magnetograms. The feature segmentation has been carried out
on daily intensitygrams and magnetograms from April 21, 1996 to April 11, 2011.
This offers an exciting opportunity to undertake further investigations that
benefit from solar features segmentations, such as solar irradiance
reconstruction, which we plan to investigate in the future.

利用 Michelson Doppler Imager （MDI）数据，开发了一系列增强型分割算法来探测和计算 MDI 图像中的特定磁学特征的覆盖面积，并根据其在主动区边界内 / 外的对比性质将其分类为太阳黑子至边缘、亮斑、网络等，以期进行更进一步的研究，如太阳辐射的重建。