StratifAI’s Post

From Whole-Slide Image to Biomarker Prediction – Discover how weakly supervised deep learning is revolutionizing computational pathology! This end-to-end workflow allows clinical researchers and engineers to predict biomarkers directly from whole-slide images, streamlining clinical research. 🔍 Dive into the latest in computational pathology and learn how to set up a complete project, making biomarker prediction more accessible and efficient than ever. 📄 Read the full article: https://lnkd.in/gpc5BzY6 #ComputationalPathology #DeepLearning #Biomarkers #AI

[PDF] A Study of Neutrosophic Sets and Deep Learning Models for Breast Cancer Classification W Abdullah - Multicriteria Algorithms with Applications, 2024 Medical image classification and detection using artificial intelligence (AI) can help enhance medical care services. Unfortunately, most medical image modalities suffer from some noise and uncertainty, which decreases the performance of disease detection and classification. Neutrosophic sets (NS) can handle uncertainty data within medical images. NS can present images into three subsets: true (T), indeterminacy (I), and fuzzy sets (FS). In this study, we investigate the performance of … •Cites: ‪Neutrosophic masses & indeterminate models‬ 

#artificialintelligence #cancerresearch #oncology https://lnkd.in/gnYrDwRW Abstract Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every #cancer #researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

CHOP makes available AI model that can enhance tumor analysis

💻 AI empowering cancer research 🔬   I recently read this interesting review: "A guide to artificial intelligence for cancer researchers" (Nature Reviews Cancer). This article highlights how AI is being used to streamline workflows and unlock hidden data, providing both non-computational and computational researchers a practical guide to understand how AI-based tools can benefit them. The article covers applications of AI in: - Image analysis 🖼️ - Natural language processing 💬 - Drug discovery 💊 A must-read for anyone interested in leveraging AI to uncover new insights and accelerate discoveries in cancer research. 🚀 #CancerResearch #ArtificialIntelligence #AIinHealthcare #BiomedicalResearch #DrugDiscovery

🚀 AI in Medicne at #ASH2024 The 2024 meeting of the American Society of Hematology in #SanDiego is embracing the transformative power of #artificialintelligence in diagnostics and therapeutics. 💡 Our study on “Generation of Multimodal Longitudinal Synthetic Data by Artificial Intelligence to Improve Personalized Medicine in Hematology” is highlighted The study explored the critical challenges of using real-world data such as clinical information to develop more effective predictive models and improve patient outcomes. 🚨 By generating #SyntheticData through advanced machine learning frameworks such as the conditional generative adversarial network (#GAN), tabular variational autoencoder (#VAE), and tabular generative pre-training transformer (#GPT) architectures, we were able to replicate the statistical properties and complexity of real-world patient data while preserving privacy. Novel diagnostic approaches like these can revolutionize research and clinical care, enabling hypothesis testing, model validation, and the potential acceleration of clinical trials — all without compromising patient data. 🔎 Importantly, we found high fidelity between the synthetic and real data sets, as well as demonstrated nearly identical transcriptomic signatures and survival outcomes between the two, indicating the reliability of AI-generated synthetic data for clinical research. Humanitas Research Hospital Humanitas University GenoMed4All Synthema IHI-SYNTHIA Fondazione AIRC per la Ricerca sul Cancro ETS Saverio D'Amico Train https://lnkd.in/dDpW8W_W

AI is transforming cancer research! AI-based tools are now accessible to all researchers. This practical guide helps non-computational scientists leverage AI for image analysis, NLP, and drug discovery, paving the way for groundbreaking discoveries. A must read for cancer biologists if you are planning to use AI for your research! #AI#CancerResearch#Bioinformatics https://lnkd.in/dbzSC45Z

🔬 Exciting News from SYNTHEMA! 🚀 We're thrilled to invite you to explore our latest publication: "MOSAIC: An Artificial Intelligence–Based Framework for Multimodal Analysis, Classification, and Personalized Prognostic Assessment in Rare Cancers." This groundbreaking research is a collaborative effort between members of the SYNTHEMA consortium and our sister project, GenoMed4All. 🔍 Key Highlights: 📌 Tackling Rare Cancers: Rare cancers make up over 20% of human neoplasms, presenting unique challenges due to their clinical and genomic complexities. MOSAIC is designed to improve decision-making and treatment strategies for these underserved patients. 📌 Advanced AI Integration: MOSAIC utilizes cutting-edge AI methods, including deep learning for data imputation, UMAP + HDBSCAN clustering for patient stratification, and Gradient Boosting for survival prediction, outperforming traditional statistical techniques. 📌 Explainable and Federated Learning: The framework employs Explainable AI (SHAP) for model transparency and federated learning to enhance model performance and ensure data privacy across multiple clinical centers. 📌 Clinical Validation: Tested on myelodysplastic syndrome (MDS), a rare hematologic cancer, MOSAIC achieved higher accuracy in patient classification and prognostic assessment, demonstrating its potential for broader clinical application. Join us in advancing the fight against rare cancers by reading our publication here: https://lnkd.in/dTZSvh_y Saverio D'Amico #SYNTHEMA #Genomed4All #RareCancers #AIinHealthcare #PersonalizedMedicine #ClinicalResearch #FederatedLearning #ExplainableAI #MOSAICFramework #horizoneurope

Hi Network,  The recent study I came across and want to share with you today describes the four-phase CT lesion recognition algorithm. To enhance liver cancer diagnostics researchers utilized a multiphase information fusion framework and spatiotemporal prediction module. The model integrates ResNet18 for feature extraction and a GRU architecture to capture temporal enhancement between CT slices. The model achieved 85.5% accuracy and an AUC of 89.73% in distinguishing between two types of cancer. The multi-task learning framework strengthens classification performance.  Regarding further improvements mentioned in the study, I can also add that it’s indeed crucial to prove further algorithm robustness, and this could be achieved by testing the model on larger, more diverse datasets and varying disease stages to ensure consistent performance in real-world scenarios. The same goes with study scope expansion, which is an inevitable part and involves incorporating data from different medical institutions, and regions, and including a wider variety of liver diseases. All of these will enable the algorithm to handle more complex and varied cases.    💬 How do you think the effectiveness of AI-driven diagnostics can be improved through collaborations between AI developers and oncologists? https://lnkd.in/d4PK-kCd #cancerdiagnostics #ai