Painsense’s Post

📢 Paper Published! I'm delighted to share that my research article titled "SpectroNet-LSTM: An Interpretable Deep Learning Approach to Cardiac Anomaly Detection Through Heartbeat Sound Analysis" has been published in the Journal of Computers in Biology and Medicine at Elsevier (IF 6.3). This research addresses a critical healthcare challenge in the early detection of cardiac anomalies, which remain a leading cause of mortality worldwide. Utilizing Mel-Frequency Cepstral Coefficients (MFCCs) and spectrogram analysis, we propose SpectroNet-LSTM as an advanced deep learning fusion architecture that achieves superior detection in need and provides interpretability through SHAP and LIME algorithms. Our goal is to bridge the gap between automation and clinical trust, paving way for more accessible cardiovascular diagnostics. A heartfelt thank you to my faculty guide Dr Krithiga Rajeshwaran, my team of co-authors (Utkarsh Mishra, Krishna Priyadarshan Behara) and others at Vellore Institute of Technology for their support throughout this journey. You can access the full paper here: https://lnkd.in/gaYSg5fr #CardiacAnomalies #DeepLearning #ExplainableAI #Innovation #MedicalAI #SpectroNetLSTM #ResearchPublication #Elsevier #AIinHealthcare #Journal #VIT #VITChennai #Healthcare

For Some Patients, the ‘Inner Voice’ May Soon Be Audible In a recent study, scientists successfully decoded not only the words people tried to say but the words they merely imagined saying. For decades, neuroengineers have dreamed of helping people who have been cut off from the world of language. A disease like amyotrophic lateral sclerosis, or A.L.S., weakens the muscles in the airway. A stroke can kill neurons that normally relay commands for speaking. Perhaps, by implanting electrodes, scientists could instead record the brain’s electric activity and translate that into spoken words. Now a team of researchers has made an important advance toward that goal. Previously they succeeded in decoding the signals produced when people tried to speak. In the new study, published on Thursday in the journal Cell, their computer often made correct guesses when the subjects simply imagined saying words. Christian Herff, a neuroscientist at Maastricht University in the Netherlands who was not involved in the research, said the result went beyond the merely technological and shed light on the mystery of language. “It’s a fantastic advance,” Dr. Herff said. The new study is the latest result in a long-running clinical trial, called BrainGate2, that has already seen some remarkable successes. One participant, Casey Harrell, now uses his brain-machine interface to hold conversations with his family and friends.   Full article with videos and pictures: https://lnkd.in/eUj8FQ_2  #als #mnd #bci #assistivetechnology #assistivetech  

A recent study found that 70.7% of neuroscientists believe memories could be extracted from deceased brains, with potential advancements projected for 2045 in roundworms, 2065 in mice, and 2125 in humans. Key challenges include understanding how memories are stored and ethical implications of such technologies. https://lnkd.in/g44Ptjp5

Researchers at Washington University in St. Louis have developed a computational method that predicts fetal conditions through the analysis of placental texture in prenatal ultrasound imagery. By leveraging algorithms to perform texture analysis, including but not limited to filter-based, spectral, structural, and deep-learning methods, this invention provides a more objective and quantifiable assessment of fetal health. Technology Inventors: Michelle Oyen, Yuyang Hu, Ulugbek Kamilov, Anthony Odibo, Adrienne Scott, Emily Sheehan, and Patrick Yang To learn more about this #WashU technology, visit https://lnkd.in/gJSWxr4E

Thrilled to announce that our research paper, "A Feature-Optimized Approach for Blood Glucose Forecasting Using Explainable AI (XAI)," has been accepted at the International Conference on Multidisciplinary Computer Science, Electrical, Business & Literature (ICMCEL 2025). This work focuses on enhancing the accuracy and interpretability of blood glucose predictions, a crucial step for diabetes management. A sincere thank you to my co-authors and mentors for their invaluable collaboration and support. Looking forward to presenting our findings at the conference! #Research #AI #MachineLearning #ExplainableAI #XAI #Healthcare #Diabetes #ICMCEL2025 #Publication

🔬 Proud moment for our research lab! Another milestone in our lab’s journey! The paper titled “𝐃𝐑𝐃-𝐍𝐞𝐭: 𝐃𝐢𝐚𝐛𝐞𝐭𝐢𝐜 𝐑𝐞𝐭𝐢𝐧𝐨𝐩𝐚𝐭𝐡𝐲 𝐃𝐢𝐚𝐠𝐧𝐨𝐬𝐢𝐬 𝐔𝐬𝐢𝐧𝐠 𝐚 𝐇𝐲𝐛𝐫𝐢𝐝 𝐂𝐨𝐧𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐚𝐥 𝐍𝐞𝐮𝐫𝐚𝐥 𝐍𝐞𝐭𝐰𝐨𝐫𝐤” has just been published — addressing early and accurate detection of diabetic retinopathy using a hybrid CNN model. 💡 What makes DRD-Net special? It blends multiscale feature fusion with lesion-level precision, achieving an impressive 98.6% accuracy on real-world datasets like APTOS and IDRiD. It’s inspiring to see the vision of AI-driven healthcare becoming more real and reliable, one paper at a time. 🧠👁️ 📄 Read the full paper: https://lnkd.in/dTbCb_3B Huge congratulations to the authors Muhammad Hassaan Ashraf and Co., and appreciation to all fellow lab members for contributing to this exciting journey. Glad to have played a small part in the process! 🙌 #DRDNet #MedicalAI #DiabeticRetinopathy #DeepLearning #FundusImaging #ComputerVision #AIinHealthcare #ResearchLab #BehindTheScenes #ProudContributor

🧠 Another milestone in my 𝐫𝐞𝐬𝐞𝐚𝐫𝐜𝐡 𝐣𝐨𝐮𝐫𝐧𝐞𝐲! Excited to share our newly published research titled “𝐃𝐑𝐃-𝐍𝐞𝐭: 𝐃𝐢𝐚𝐛𝐞𝐭𝐢𝐜 𝐑𝐞𝐭𝐢𝐧𝐨𝐩𝐚𝐭𝐡𝐲 𝐃𝐢𝐚𝐠𝐧𝐨𝐬𝐢𝐬 𝐔𝐬𝐢𝐧𝐠 𝐚 𝐇𝐲𝐛𝐫𝐢𝐝 𝐂𝐨𝐧𝐯𝐨𝐥𝐮𝐭𝐢𝐨𝐧𝐚𝐥 𝐍𝐞𝐮𝐫𝐚𝐥 𝐍𝐞𝐭𝐰𝐨𝐫𝐤” focusing on early detection of diabetic retinopathy using deep learning. 💡 What makes it different? We designed DRD-Net, a hybrid model combining multiscale feature fusion and lesion-level precision, aimed at accurately diagnosing diabetic retinopathy from retinal fundus images. 🔬 With 98.6% accuracy, it sets a new benchmark on real-world datasets like APTOS and IDRiD. This research brings us one step closer to smarter, faster, and more reliable AI-assisted eye care. 👁️💻 📄 Read the full paper: https://lnkd.in/dmfwmMeT Grateful to my co-authors Muhammad Hassaan Ashraf, Musharraf Ahmed , Ahmed Khan, and Dr. Jawaid Iqbal for their collaboration and support throughout this work. Also thankful to our lab members Zain Ul Abideen, Abdullah Mateen Janjua, Muhammad Nabeel Mehmood, and Haider Ali for their valuable support throughout this work. #DRDNet #MedicalAI #DiabeticRetinopathy #DeepLearning #CNN #FundusImaging #SmartDiagnosis #HealthcareInnovation #ComputerVision #Research #Publication

⭐ 𝐀𝐦𝐚𝐳𝐨𝐧 𝟓-𝐒𝐭𝐚𝐫 𝐑𝐚𝐭𝐞𝐝 : 𝐅𝐫𝐨𝐦 𝐂𝐲𝐛𝐨𝐫𝐠𝐬 𝐭𝐨 𝐂𝐮𝐫𝐢𝐧𝐠 𝐏𝐚𝐫𝐚𝐥𝐲𝐬𝐢𝐬 — 𝐓𝐡𝐞 𝐅𝐮𝐭𝐮𝐫𝐞 𝐈𝐬 𝐇𝐞𝐫𝐞   How can brain–computer interfaces restore movement? Will DNA supercomputers revolutionize medicine? Can AI make diagnoses faster and more accurate than ever before?   𝙏𝙝𝙚 𝙁𝙪𝙩𝙪𝙧𝙚 𝙤𝙛 𝙏𝙚𝙘𝙝𝙣𝙤𝙡𝙤𝙜𝙮 𝙞𝙣 𝙈𝙚𝙙𝙞𝙘𝙞𝙣𝙚 reveals 14 groundbreaking advances — from prosthetics that respond to thought, to the first real steps toward curing paralysis.   Authored by leading experts Julian Gendreau MD, MS (The Johns Hopkins University, USA), Nolan J. Brown (UC Irvine, USA), Shane Shahrestani, MD, PhD (University of Southern California, USA), Ron Sahyouni, M.D., Ph.D. (University of California San Diego, USA), this is your definitive guide to the innovations reshaping healthcare.   Order now and be inspired by what’s next in medicine 🔗 https://lnkd.in/gKM_hdpn?

🚀 Research Breakthrough Alert! 🚀 Thrilled to share that my Ph.D. scholar Mili Rosine Mathews has published her groundbreaking work in SN Computer Science (Springer Nature) 🎉 📄 Title: An Attention Driven Retinal Classification Model for the Joint Grading of Diabetic Retinopathy and Macular Edema 💡 Impact: A lightweight AI model achieving >99% accuracy in detecting & grading vision-threatening diabetic complications — paving the way for faster, cost-effective, and scalable screening in healthcare. 🔗 Read here: https://lnkd.in/gsT_augq Proud to see cutting-edge AI meeting real-world medical challenges! 👏 #ProudMentor #AIinHealthcare #DeepLearning #MedicalAI #DiabeticRetinopathy #MacularEdema #SpringerNature #ResearchInnovation

As a solicitor inspired by the healthcare space working alongside medical experts, advancements in medical science interest me hugely. This one is quite literally mind blowing. In a space no larger than a pinhead, deep within the human brain, lies an entire universe — and for the first time ever, it's been mapped in extraordinary detail. Led by researcher Alexander Shapson-Coe, a team turned the power of electron microscopy onto just one cubic millimeter of the temporal cortex. What they uncovered is nothing short of mind-blowing: a nano-resolution map revealing neurons, synapses, blood vessels, and intricate connections never before visible to science. That tiny fragment of brain produced 1.4 petabytes of data — over a thousand times more than what’s stored in a typical library. Even more incredible? They didn’t keep it to themselves. They created a free tool that allows anyone—from neuroscientists to curious minds—to explore this vast microscopic world. Published in Science, this isn’t just a breakthrough in technology—it’s a gateway to deeper understanding of the human brain. A map not only of what we are, but of what we’ve yet to uncover. More Information 👉🏻 https://lnkd.in/dvmcFu44