European Society of Digital and Integrative Pathology - ESDIP’s Post

Alhumdulillah! I am excited to share my latest research paper, "An Explainable AI-Based Blood Cell Classification Using Optimized Convolutional Neural Network," published in the Journal of Pathology Informatics on ScienceDirect! In this study, we developed an enhanced CNN model for precise and efficient white blood cell (WBC) classification, achieving a testing accuracy of 99.12%. By employing various image pre-processing techniques and optimizing architectural structures and hyperparameters, our model outperforms existing transfer learning models. To improve interpretability, we utilized SHAP, LIME, Grad-CAM, and Grad-CAM++ techniques, providing valuable insights into model decisions. I am grateful to my mentors, Md. Assaduzzaman Sir and Md. Zahid Hasan Sir, for your invaluable guidance and support. Their mentorship was crucial to this achievement. I am also proud to have developed real-time Android applications and interactive web tools that aid medical professionals in early blood cell identification. Check out the full paper here: https://lnkd.in/gYTZtJct #AI #MachineLearning #MedicalResearch #acheievement #HealthcareInnovation #DeepLearning #MedicalAI #biomedicalengineering #research #inovation

Watch now! ⏯ A new AI in Medicine talk is now available on our YouTube channel. Farah Kidwai-Khan, Senior Data Scientist at Yale School of Medicine Yale Department of Internal Medicine and affiliated faculty in BIDS, presents: "A Roadmap to Artificial Intelligence Methods for Designing and Building AI-ready Data to Promote Fairness". This talk was recorded at the 2024 AI in Medicine Symposium, hosted by the Section of Biomedical Informatics & Data Science. #aireadiness #aiready #aireadydata #data #artificialintelligence #datafairness #aifairness #datascience https://lnkd.in/eC_XT6en

🎉 We're thrilled to announce the publication of our latest research paper, "Detection of Covid-19 and Pneumonia in Chest X-ray Images Using Deep Learning Techniques”. with contribution Tasneem Kandil which has been published in IEEE Xplore. The fight against COVID-19 requires rapid and accurate diagnostics, and our study enhances this capability by utilizing deep learning to distinguish between COVID-19 and pneumonia from chest X-ray images. This distinction is notoriously difficult due to the overlapping visual features of the two diseases in X-rays. 🔍 Key Highlights: Objective: Improve the accuracy of COVID-19 and pneumonia detection from chest X-ray images. Methodology: Employing the VGG-16 model, with and without image augmentation and enhancement techniques, on a dataset of 5970 X-ray images. Results: The enhanced VGG-16 model achieved an impressive accuracy of 92.72%, demonstrating significant improvements over traditional diagnostic methods. This breakthrough demonstrates the potential of deep learning to aid in the rapid and effective diagnosis of respiratory illnesses, which is critical in the ongoing battle against COVID-19 and other similar infections. 🔗 Read the full paper here: https://lnkd.in/d8_FPN-r Presented at the 6th International Conference on Computing and Informatics, our findings are a step forward in medical imaging and diagnostics, proving that advanced technologies can significantly impact public health. A big thank to all our colleagues and collaborators involved in this research. #COVID19Research #DeepLearning #MedicalImaging #HealthTech #XrayImaging #Pneumonia #ResearchPublication

In this week’s Duke AI Health Friday Roundup: White House issues policies for AI use by federal agencies; NEJM AI requires registration of interventional AI studies; 3D specimen imaging project reaches finish line; insights into the human immune system, courtesy of COVID; using “digital twins” in biomedical research; hallucinated software gets called by real computer code; who should be responsible for policing integrity in scientific publication?; much more: https://lnkd.in/esE3WAAB

OCTOBER 29 IS WORLD STROKE DAY! VASCage clinical stroke research focusses on AI in image processing for stroke detection and prevention. Here our latest news on an algorithm to assess dangerous plaques in carotid arteries. The VASCage Data Sciences Team not only performs cutting edge research in machine learning and artificial intelligence in medical diagnostics and research planning but also offers expert consulting and prototyping for medical data challenges. Get in touch with our experts Karl D Fritscher and Marie-Christine Pali! #stroke #AI #imageprocessing

🎉 Exciting news! Our paper, "Intelligent Systems in Healthcare: A Systematic Survey of Explainable User Interfaces," has been accepted for publication in the journal Computers in Biology and Medicine (Impact Factor: 7.0). This work is particularly close to our hearts as it addresses a crucial gap in medical AI - the need for explainable AI (XAI) to foster trust among medical professionals. With radiology shortages impacting over half the global population, the adoption of AI in healthcare is more urgent than ever. Our survey is the first to explore explainable user interfaces (XUI) from a medical domain perspective, analyzing how current systems manage visualization and interaction to make AI decisions transparent and understandable. Congratulations to our PhD student João Cálem and the supervisory team Catarina Moreira and Joaquim Jorge on leading this publication. Please feel free to read our full paper and share your thoughts on how we can further enhance trust in AI within the medical community: Paper: https://lnkd.in/dynUJamF #AIinHealthcare #ExplainableAI #UserInterface #MedicalResearch #Innovation #HCI #XAI #ExplainableUserInterfaces #XUI #PhD #DataScienceInstitute #UTS #UniversityOfTechnologySydney #InstitutoSuperiorTecnico #tecnicolisboa #wearetecnico

Just wrapped up an extremely insightful chat with Professor Andrew Janowczyk on my show, Saurish Speaks! I'm incredibly grateful to Professor Janowczyk for sharing his expertise on AI, ML, Deep Learning, Digital Pathology, Histology, and Computer-Aided Diagnostics (CAD). Our conversation explored the impact of AI on disease diagnosis, the future of digital pathology, the challenges in developing healthcare AI tools, and the critical importance of ethics and safety. Professor Janowczyk's insights on CAD were eye-opening, particularly in how algorithms assist clinicians in analyzing data from (f)MRI, histology, X-ray, CT, and more. He emphasized that CAD enhances efficiency and robustness in medical diagnoses by leveraging vast and continuously growing datasets. For instance, histology slides, which can be as large as 100,000 × 100,000 pixels and how CAD supports doctors by identifying trends and subtle image patterns which may not be visually discernible - providing decision support to pathologists rather than replacing them. This approach paves the way for precision medicine, where treatments are tailored to individual patients based on extensive retrospective evidence and data. The video will be out in July; stay tuned for more updates by following Saurish Speaks! #AI #MachineLearning #DeepLearning #DigitalPathology #Histology #ComputerAidedDiagnostics #HealthcareInnovation #SaurishSpeaks #AndrewJanowczyk #Pathology #PrecisionMedicine #MRI #CT #GB #Pixels #Patient #Hospital #Healthcare #Technology #Histology #Computer #CAD #EmoryUniversity #GeorgiaTech #Geneva #Data #July

Hey family, I am excited to share that my first research paper, titled "Advancing Medical Imaging Through Generative Adversarial Networks: A Comprehensive Review and Future Prospects," has been published in the Cognitive Computation journal by Springer, which boasts an impact factor of 4.3 (SCI-indexed). Collaborating with my colleague Abiy Mamo, we explored how Generative Adversarial Networks (GANs) can revolutionize diagnostic imaging. Our paper highlights the immense possibilities of this technology in reshaping medical imaging. Special thanks to Associate Dr. Vikas Hassija, Prof. Vinay Chamola, and Aniruddha Mukherjee for their support and mentorship. 🙏 Heartfelt gratitude to everyone who has been part of this journey. This is just the beginning—more research papers will be coming ahead as I continue to explore the exciting field of Generative AI and ML. 🔗 Check out our paper: https://lnkd.in/gnYH5rqc Feel free to inbox me for a free PDF. Here's to a future filled with innovation and positive impact! #ResearchPaper #MedicalImaging #GenerativeAdversarialNetworks #GANs #ArtificialIntelligence #AIResearch #HealthcareInnovation #CognitiveComputation #SpringerJournal #ScientificPublication #InnovationInHealthcare

🔍 Redefining the Future of Stroke Detection: A Look into My Recent Research! 🔍 🌟 I'm ecstatic to announce the publication of my research paper, "A Comprehensive Review and Experimental Comparison of Deep Learning Methods for Automated Hemorrhage Detection," in the esteemed Engineering Applications of Artificial Intelligence (EAAI) journal. 🧠 Hemorrhagic strokes are urgent medical crises demanding swift and accurate diagnosis. 🚀 This study involved a systematic review and comprehensive gap analysis of various deep learning approaches for automating hemorrhagic stroke identification. 🔬 Our research stands out for its meticulous examination of existing literature, the careful selection of high-performing deep learning models, and the rigorous experimentation using publicly available dataset. 🌐 By evaluating these models in a tapestry of geographically diverse datasets, we crafted a comprehensive picture, revealing hidden biases and ensuring their adaptability across diverse landscapes. 🌀 From a clinical perspective, it's crucial for the algorithm to effectively identify stroke based on appearance and complexity, rather than solely focusing on easy-to-spot cases. A biased test set towards such cases can inflate performance metrics. 🔑 This study illuminates the current landscape of automated hemorrhagic stroke identification, offering insights that not only provide a blueprint for future research and development but also debunk myths about model robustness by revealing potential biases and inaccuracies. 📚 Dive into the full paper https://lnkd.in/gHMUbRTs to discover the future of automated medical imaging analysis. The journey has been quite long, and I'm grateful to Dr. Jeny Rajan for his unwavering support and motivation as my guide. #MedicalImaging #DeepLearning #HealthcareInnovation #StrokeDetection #ResearchBreakthrough #AIinHealthcare #Neuroimaging #MachineLearning #HealthTech #DataScience

📢 Excited to share our latest blog post on deep learning based detection of collateral circulation in coronary angiographies. Detecting coronary collateral circulation is crucial for personalized CAD medicine. Our novel method uses deep learning and convolutional techniques to extract spatial features from angiographic images, resulting in promising results for CCC detection. Check out the full post here: https://bit.ly/3Pp6JTS #medicalimaging #deeplearning #CADresearch