Siavash Es'haghi’s Post

Quantum Hybrid Model Enhances Lung Cancer Detection https://buff.ly/3WYqVzU

A new hybrid quantum framework for lung cancer detection is detection is showing great promise. By blending quantum computing with deep learning, it’s boosting the accuracy and speed of diagnosing lung tumours from CT and X-ray images, achieving over 92% accuracy. This could significantly enhance early detection, leading to better patient outcomes. However, the approach may not be suitable for all lung cancer types due to distinct molecular characteristics, so it should be used alongside other diagnostic methods. #lungscreen #quantum #research

🫁 Exploring AI-Driven Solutions for Early Lung Cancer Detection in Medical Imaging 🤖 Kise (Keith) shares his journey in developing an AI-driven system to detect lung nodules using the LUNA16 dataset and a 3D Convolutional Neural Network (3D CNN). This exploration tackles challenges like handling high-dimensional data, class imbalance, and achieving sensitivity in medical diagnostics. With a promising test accuracy of 82%, Kise reflects on key insights and plans for future improvements, including interpretability with Grad-CAM and data augmentation for better generalization. ➡️ Link to the article: https://lnkd.in/gMYJcjKM 📖 Learn more about the AI Advocate Program here: bit.ly/AIAdvocateProgram #MachineLearningAlgorithms #LungCancerDetection #AIInHealthcare #MachineLearning #AIPilipinasCebu #AIAdvocateProgram

⚠️ Attention Clinical researchers and Bioinformaticians! Tomorrow, #canSERV_EU 🎗️partner Euro-BioImaging is organising a Virtual Pub on 🎗️Preparing for Clinical Translation: Guidelines for Validating and Reporting Algorithm Performance in Biomedical Imaging Analysis ⭐ 🗓️ June 28, 2024 13.00 CEST ➡️https://lnkd.in/e8Rx3u_A #AI #biomedicalimageanalysis #algorithmvalidation #clinicaltranslation

With great excitement and enthusiasm, I am happy to share that my research paper got published in the journal 𝗠𝘂𝗹𝘁𝗶𝗺𝗲𝗱𝗶𝗮 𝗧𝗼𝗼𝗹𝘀 𝗮𝗻𝗱 𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 (𝗜𝗺𝗽𝗮𝗰𝘁 𝗙𝗮𝗰𝘁𝗼𝗿: 3.6). The domain is 𝗔𝗽𝗽𝗹𝘆𝗶𝗻𝗴 𝗔𝗿𝘁𝗶𝗳𝗶𝗰𝗶𝗮𝗹 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲 𝘁𝗼 𝗯𝘂𝗶𝗹𝗱 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿-𝗔𝗶𝗱𝗲𝗱 𝗗𝗶𝗮𝗴𝗻𝗼𝘀𝗶𝘀 (𝗖𝗔𝗗) 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗳𝗼𝗿 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗜𝗺𝗮𝗴𝗲 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴. A 𝗻𝗼𝘃𝗲𝗹 𝗱𝗲𝗲𝗽 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴-𝗯𝗮𝘀𝗲𝗱 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗖𝗹𝗮𝘀𝘀𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗼𝗳 𝗣𝗿𝗼𝘀𝘁𝗮𝘁𝗲 𝗖𝗮𝗻𝗰𝗲𝗿 (𝗣𝗖-𝗡𝗲𝘁) was devised for the classification of cancer from the T2-weighted (T2w) MRI modality that outperformed the existing state-of-the-art models like Xception, ResNet50, DenseNet121, VGG16, and Inception V3. Special thanks to Prof. Mamta Juneja Ma'am, Prashant Jindal Sir for letting me lead this opportunity and my co-author Kunal Sharma for a great team work. Here's the link to the research paper: https://lnkd.in/gXy6wKGx #research #prostatecancer #pcnet #ai #deeplearning #ml #tensorflow

📢 Join the next Turing-Roche Partnership Knowledge Share Event: Dynamic Precision Medicine - A New Approach to Cancer Therapy Resistance 📅 27 Jan 3-4pm GMT The aim of the Turing-Roche Knowledge Share series is to bring together members of Roche, Turing Institute and the wider scientific community to hear partnership updates and different academic and industry perspectives on data science topics, to gain insights and help build new connections and collaborations. This month Prof. Robert Beckman from Georgetown University Medical Center will tell us about Dynamic Precision Medicine, a proactive approach to designing personalized treatment that delay relapse and prolong survival in cancer patients. Abstract:  Genetic heterogeneity within an individual cancer is even greater than previously recognized. Rare subclones, below the level of detection by current DNA sequencing methods, are a major source of therapy resistance and moderate to late term relapse. Dynamic precision medicine (DPM) is a proactive approach to designing personalized treatment sequences that delay relapse and prolong survival. This talk will present mathematical modeling, computer simulation, and emerging experimental data about genetic heterogeneity in cancer and DPM. Ongoing work on developing clinical study designs to efficiently test these ideas will be discussed, as well as the potentially critical future roles of digital twins, data science, and artificial intelligence and machine learning in these efforts.   Registration Link: https://lnkd.in/ew-VzgmX The Alan Turing Institute Roche #health #healthdata #AI #ai #artificialintelligence #datascience  

Navigating AI in Cancer Detection 🚀 AI shows potential in detecting cancer, but it’s still figuring things out! - Great at recognizing patterns, but still a work in progress. - Not enough digitized data limits AI’s learning. - It can’t yet replace molecular tests. More data needed! Remember: - AI helps speed up processes, but accuracy isn’t there yet. - Diverse data = success for AI models! - Molecular insights are still under development.

I'm thrilled to share our project, "Leveraging AI and Machine Learning for Early Detection of Oral Squamous Cell Carcinoma with EfficientNetB3," which I developed alongside Bhuvana Murki under the guidance of Professor Weihua Zhou at Michigan Tech College of Computing. Our project is a testament to how AI technologies like EfficientNetB3 can revolutionize the early detection of oral cancer. By harnessing the power of AI, we've significantly improved diagnostic accuracy, opening up new horizons in medical diagnostics and potentially saving countless lives. Check out the details here: https://lnkd.in/gH-QwFyH A huge thanks to Michigan Technological University for providing us with the opportunity to learn and build our skills.  I’d love to hear your thoughts and feedback on our project. Let’s discuss how AI is shaping the future of healthcare! #AIinHealthcare #MachineLearning #OralCancerAwareness #TechInnovation #Dataanalysis

New research has demonstrated that scientists can train #ArtificialIntelligence (#AI) models to distinguish brain tumours from healthy tissue: https://lnkd.in/ePYZa-gY #Cancer

💡 Innovating Lung Cancer Detection with Quantum Machine Learning: A Breakthrough in Healthcare 👨⚕️ Lung cancer remains a significant challenge in the medical field, with traditional detection methods like CT scans and biopsies being often costly and time-consuming. 🕰️ Meanwhile, researchers are exploring the potential of Quantum Machine Learning (QML) to improve detection accuracy and efficiency. 💡 A recent study investigated the application of two QML models - Pegasos QSVC and Variational Quantum Classifier - to a lung cancer dataset. The results showed that Pegasos QSVC outperformed VQC, achieving an impressive 85% classification accuracy. This is a notable finding, especially considering that Pegasos QSVC can process large amounts of data more efficiently than traditional machine learning models. However, the researchers also highlight the need to address scalability and hardware limitations, which are essential for broader healthcare applications. As QML continues to evolve, it has the potential to become a game-changer in the healthcare sector. What specific benefits do you think QML can bring to healthcare, and how can we overcome the existing challenges in its adoption? 💬 Read the full article here: https://lnkd.in/eRdyHneH #QuantumMachineLearning #LungCancerDetection #HealthcareInnovation #ArtificialIntelligence #MedicalResearch #QuantumComputing #FutureOfHealthcare #ai #MachineLearning