The hepatotoxicity of some Chinese herbs has been a cause for concern in recent years. However, some herbs, such as rhubarb, have been documented as having both therapeutic and toxic effects on the liver, leading to the complex problem of distinguishing the benefits from the risks of using this herb. To comparatively analyze the dose-response relationship between rhubarb and hepatic health, we administrated total rhubarb extract(RE) to normal and carbon tetrachloride(CCl₄)-treated rats for 12 weeks at 4 dosage levels(2.00, 5.40, 14.69 and 40.00 g·kg⁻¹, measured as the quantity of crude material), followed by biochemical and histopathological tests of the rats' livers. A composite pattern was extracted by factor analysis, using all the biochemical indices as variables, into a visual representation of two mathematically obtained factors, which could be interpreted as the fibrosis factor and the cellular injury factor, according to the values of the variable loadings. The curative effect of administering the two lowest dosages of RE to CCl₄-treated rats was mainly expressed as a decrease in the extent of cellular injury. The hepatoprotective mechanism of RE might be related to its antioxidant effect, the antagonism of the free radical damage to hepatocytes caused by CCl₄. By contrast, the RE-induced liver damage was mainly expressed as a significant increase in the amount of fibrosis in both normal rats at all dosage levels and CCl₄-treated rats at the two highest dosage levels. Therefore, the hepatotoxic potential of RE could be attributable to the liver cell fibrosis induced by high doses of the herb. This study illustrates the bidirectional potential of rhubarb and demonstrates the feasibility of using factor analysis to study the dose-response relationships between herbal medicines and hepatotoxicity or the healing effects of these herbs by extracting the underlying interrelationships among a number of functional bio-indices in a holistic manner.

Image composition involves seamlessly integrating given objects into a specific visual context. Current training-free methods rely on composing attention weights from several samplers to guide the generator. However, since these weights are derived from disparate contexts, their combination leads to coherence confusion and loss of appearance information. These issues worsen with their excessive focus on background generation, even when unnecessary in this task. This not only impedes their swift implementation but also compromises foreground generation quality. Moreover, these methods introduce unwanted artifacts in the transition area. In this paper, we formulate image composition as a subject-based local editing task, solely focusing on foreground generation. At each step, the edited foreground is combined with the noisy background to maintain scene consistency. To address the remaining issues, we propose PrimeComposer, a faster training-free diffuser that composites the images by well-designed attention steering across different noise levels. This steering is predominantly achieved by our Correlation Diffuser, utilizing its self-attention layers at each step. Within these layers, the synthesized subject interacts with both the referenced object and background, capturing intricate details and coherent relationships. This prior information is encoded into the attention weights, which are then integrated into the self-attention layers of the generator to guide the synthesis process. Besides, we introduce a Region-constrained Cross-Attention to confine the impact of specific subject-related tokens to desired regions, addressing the unwanted artifacts shown in the prior method thereby further improving the coherence in the transition area. Our method exhibits the fastest inference efficiency and extensive experiments demonstrate our superiority both qualitatively and quantitatively. The code is available at https://github.com/CodeGoat24/PrimeComposer.

Background: Medical artificial intelligence (AI) has significantly contributed to decision support for disease screening, diagnosis, and management. With the growing number of medical AI developments and applications, incorporating ethics is considered essential to avoiding harm and ensuring broad benefits in the lifecycle of medical AI. One of the premises for effectively implementing ethics in Medical AI research necessitates researchers' comprehensive knowledge, enthusiastic attitude, and practical experience. However, there is currently a lack of an available instrument to measure these aspects. Objective: The aim of this study was to develop a comprehensive scale for measuring the knowledge, attitude, and practice of ethics implementation among medical AI researchers, and to evaluate its measurement properties. Methods: The construct of the Knowledge-Attitude-Practice in Ethics Implementation (KAP-EI) scale was based on the Knowledge-Attitude-Practice (KAP) model, and the evaluation of its measurement properties was in compliance with the COnsensus-based Standards for the selection of health status Measurement INstruments (COSMIN) reporting guidelines for studies on measurement instruments. The study was conducted in 2 phases. The first phase involved scale development through a systematic literature review, qualitative interviews, and item analysis based on a cross-sectional survey. The second phase involved evaluation of structural validity and reliability through another cross-sectional study. Results: The KAP-EI scale had 3 dimensions including knowledge (10 items), attitude (6 items), and practice (7 items). The Cronbach α for the whole scale reached .934. Confirmatory factor analysis showed that the goodness-of-fit indices of the scale were satisfactory (χ2/df ratio:=2.338, comparative fit index=0.949, Tucker Lewis index=0.941, root-mean-square error of approximation=0.064, and standardized root-mean-square residual=0.052). Conclusions: The results show that the scale has good reliability and structural validity; hence, it could be considered an effective instrument. This is the first instrument developed for this purpose.

Deep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representation from single color model with a specific mapping function, a.k.a., color space, during the colorization pipeline. In this paper, we first investigate the modeling of different color spaces, and find each of them exhibiting distinctive characteristics with unique distribution of colors. The complementarity among multiple color spaces leads to benefits for the image colorization task. We present MultiColor, a new learning-based approach to automatically colorize grayscale images that combines clues from multiple color spaces. Specifically, we employ a set of dedicated colorization modules for individual color space. Within each module, a transformer decoder is first employed to refine color query embeddings and then a color mapper produces color channel prediction using the embeddings and semantic features. With these predicted color channels representing various color spaces, a complementary network is designed to exploit the complementarity and generate pleasing and reasonable colorized images. We conduct extensive experiments on real-world datasets, and the results demonstrate superior performance over the state-of-the-arts.

Automatically classifying plant leaves is a challenging fine-grained classification task because of the diversity in leaf morphology, including size, texture, shape, and venation. Although powerful deep learning-based methods have achieved great improvement in leaf classification, these methods still require a large number of well-labeled samples for supervised training, which is difficult to get. In contrast, relying on the specific coarse-to-fine classification strategy, human botanists only require a small number of samples for accurate leaf recognition. Inspired by the classification strategy of human botanists, we propose a novel S ² CL-Leaf Net , which exploits multi-granularity clues with a hierarchical attention mechanism and boosts the learning ability with the supervised sampling contrastive learning with limited training samples to classify plant leaves as human botanists do. Specifically, to fully explore and exploit the subtle details of the leaves, a novel sampling transformation mechanism is combined with the supervised contrastive learning to enhance the network’s perception of details by amplifying the discriminative regions with a weighted sampling of different regions. Furthermore, we construct the hierarchical attention mechanism to produce attention maps of different granularity, which helps to discover details in leaves that are important for classification. Experiments are conducted on the open-access leaf datasets, including Flavia, Swedish, and LeafSnap, which prove the effectiveness of the proposed S ² CL-Leaf Net .