Improving diagnosis and outcome prediction of gastric cancer via multimodal learning using whole slide pathological images and gene expression.

For the diagnosis and outcome prediction of gastric cancer (GC), machine learning methods based on whole slide pathological images (WSIs) have shown promising performance and reduced the cost of manual analysis. Nevertheless, accurate prediction of GC outcome may rely on multiple modalities with complementary information, particularly gene expression data. Thus, there is a need to develop multimodal learning methods to enhance prediction performance. In this paper, we collect a dataset from Ruijin Hospital and propose a multimodal learning method for GC diagnosis and outcome prediction, called GaCaMML, which is featured by a cross-modal attention mechanism and Per-Slide training scheme. Additionally, we perform feature attribution analysis via integrated gradient (IG) to identify important input features. The proposed method improves prediction accuracy over the single-modal learning method on three tasks, i.e., survival prediction (by 4.9% on C-index), pathological stage classification (by 11.6% on accuracy), and lymph node classification (by 12.0% on accuracy). Especially, the Per-Slide strategy addresses the issue of a high WSI-to-patient ratio and leads to much better results compared with the Per-Person training scheme. For the interpretable analysis, we find that although WSIs dominate the prediction for most samples, there is still a substantial portion of samples whose prediction highly relies on gene expression information. This study demonstrates the great potential of multimodal learning in GC-related prediction tasks and investigates the contribution of WSIs and gene expression, respectively, which not only shows how the model makes a decision but also provides insights into the association between macroscopic pathological phenotypes and microscopic molecular features.

Simultaneous extraction of hydrophobic and hydrophilic bioactive compounds from ginger (Zingiber officinale Roscoe).

Ginger is a commonly used spice around the world. Its bioactive compounds contain hydrophobic gingerols and hydrophilic polysaccharides. Huge physiochemical differences between these compounds and the thermal instability of gingerols impede fast and effective extraction of them using conventional methods. In this research, ionic liquid-based ultrasonic-assisted extraction (ILUAE) was applied to simultaneously extract gingerols and polysaccharides from ginger. Parameters influencing the recovery of gingerols were ionic liquid type, ionic liquid concentration, solid/liquid ratio, ultrasonic power, extraction temperature and extraction time. Compared with traditional methods, LUAE significantly increased the yield of total gingerols and shortened the extraction time. Meanwhile, ginger polysaccharides recovery reached up to 92.82% with ILUAE. Our results indicated that ILUAE has a remarkable capacity to extract gingerols and ginger polysaccharides in one step. Therefore, ILUAE represents a promising technology for simultaneous extraction of hydrophilic and hydrophobic bioactive compounds from plant materials.