Understanding the prognosis of cancer patients is crucial for enabling precise diagnosis and treatment by clinical practitioners. Multimodal fusion models based on artificial intelligence (AI) offer a comprehensive depiction of the tumor heterogeneity landscape, facilitating more accurate predictions of cancer patient prognosis. However, in the real-world, the lack of complete multimodal data from patients often hinders the practical clinical utility of such models. To address this limitation, an interpretable bridged multimodal fusion model is developed that combines histopathology, genomics, and transcriptomics. This model assists clinical practitioners in achieving more precise prognosis predictions, particularly when patients lack corresponding molecular features. The predictive capabilities of the model are validated across 12 cancer types, achieving optimal performance in both complete and missing modalities. The work highlights the promise of developing a clinically applicable medical multimodal fusion model. This not only aids in reducing the healthcare burden on cancer patients but also provides improved assistance for clinical practitioners in precise diagnosis and treatment.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/advs.202407060 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Abnormality-aware multimodal learning for WSI classification.
Front Med (Lausanne)
February 2025
Department of Computer Science and Engineering, University of Texas at Arlington, Arlington, TX, United States.
Whole slide images (WSIs) play a vital role in cancer diagnosis and prognosis. However, their gigapixel resolution, lack of pixel-level annotations, and reliance on unimodal visual data present challenges for accurate and efficient computational analysis. Existing methods typically divide WSIs into thousands of patches, which increases computational demands and makes it challenging to effectively focus on diagnostically relevant regions.
View Article and Find Full Text PDFLongitudinal observation of psychophysiological data as a novel approach to personalised postural defect rehabilitation.
Sci Rep
March 2025
Faculty of Biomedical Engineering, Silesian University of Technology, Roosevelta 40, 41-800, Zabrze, Poland.
Postural defects are one of the main diseases reported to be at the top of the list of diseases of civilisation. The present study aimed to develop a novel approach to defining a set of measurable physiological biomarkers and psychological characteristics with identifiable information content and data analysis, enabling the determination of the adaptation period and conditioning the effectiveness of the treatment in personalised rehabilitation. During the rehabilitation, multimodal physiological signals (electrodermal activity, blood volume pulse) and psychological data (anxiety as a state and as a trait, temperament) were recorded on a group of 20 subjects over a period of three months (120 measurement sessions).
View Article and Find Full Text PDFRapid detection of the viability of naturally aged maize seeds using multimodal data fusion and explainable deep learning techniques.
Food Chem
March 2025
College of Agronomy and Biotechnology, China Agricultural University/ The Innovation Center (Beijing) of Crop Seeds Whole-Process Technology Research of Ministry of Agriculture and Rural Affairs/Beijing Key Laboratory of Crop Genetic Improvement, Beijing 100193, China.. Electronic address:
Seed viability, a key indicator for quality assessment, directly impacts the emergence of field seedlings. The existing nondestructive testing model for maize seed vitality based on naturally aged seeds and predominantly relying on single-modal data like MV and RS, achieves an accuracy of less than 70 %. To elucidate the influence of different data on model accuracy, this study proposes the MSCNSVN model for detecting seed viability by collecting multisensor information from maize seeds using sensors, such as MV, RS, TS, FS, and SS.
View Article and Find Full Text PDFLangLoc: Language-Driven Localization via Formatted Spatial Description Generation.
IEEE Trans Image Process
March 2025
Existing localization methods commonly employ vision to perceive scene and achieve localization in GNSS-denied areas, yet they often struggle in environments with complex lighting conditions, dynamic objects or privacy-preserving areas. Humans possess the ability to describe various scenes using natural language to help others infer the location by recognizing or recalling the rich semantic information in these descriptions. Harnessing language presents a potential solution for robust localization.
View Article and Find Full Text PDFArtificial intelligence techniques play a pivotal role in the accurate identification of drug-drug interaction (DDI) events, thereby informing clinical decisions and treatment regimens. While existing DDI prediction models have made significant progress by leveraging sequence features such as chemical substructures, targets, and enzymes, they often face limitations in integrating and effectively utilizing multi-modal drug representations. To address these limitations, this study proposes a novel multi-modal feature fusion model for DDI event prediction: MMDDI-SSE.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!