Lee Kebler’s Post

Researchers have developed an assistive machine learning model that greatly improves the ability of medical professionals to read the electroencephalography (EEG) charts of intensive care patients. #electroencephalography #medicalinnovation https://lnkd.in/eB4h_VJx

 Classification of hand and wrist movements via surface electromyogram using the random convolutional kernels transform Authors From Afeka: Dr. Alex Segal Prosthetic devices are vital for enhancing personal autonomy and the quality of life for amputees. However, the rejection rate for electric upper-limb prostheses remains high at around 30%, often due to issues like functionality, control, reliability, and cost. Thus, developing reliable, robust, and cost-effective human-machine interfaces is crucial for user acceptance. Machine learning algorithms using Surface Electromyography (sEMG) signal classification hold promise for natural prosthetic control. This study aims to enhance hand and wrist movement classification using sEMG signals, treated as time series data. A novel approach is employed, combining a variation of the Random Convolutional Kernel Transform (ROCKET) for feature extraction with a cross-validation ridge classifier. Traditionally, achieving high accuracy in time series classification required complex, computationally intensive methods. However, recent advances show that simple linear classifiers combined with ROCKET can achieve state-of-the-art accuracy with reduced computational complexity. The algorithm was tested on the UCI sEMG hand movement dataset, as well as on the Ninapro DB5 and DB7 datasets. We demonstrate how the proposed approach delivers high discrimination accuracy with minimal parameter tuning requirements, offering a promising solution to improve prosthetic control and user satisfaction. Read the full article>> https://bit.ly/3XbRnX9

🔹Researchers have succeeded in developing the first functional human brain tissue through 3D printing. This tissue, created with an innovative approach of horizontal printing instead of the conventional vertical method, can grow and function in a manner similar to typical brain tissue.  The 3D printing technique allows precise control over cell types and arrangements, overcoming the limitations of traditional methods. Unlike vertical printing, this new approach facilitates the connection and communication of neurons across layers, forming complex networks similar to those in the human brain.  This significant breakthrough provides a precise means to study the communication and development of complex networks observed in brain tissue, paving the way for significant advances in understanding brain biology and treating various neurological conditions.  Find the complete research here 👉🏼 https://lnkd.in/dz_jZ8sk  #techtitute #3Dbioprinting #neurology #medicine

We love printing potential. Leveraging B9Creations 3D printing technology, The Johns Hopkins University researchers have developed a device called the Freeform Stimulator that can safely deliver prolonged direct current to neurons in the human body. This is significant because traditional methods risk causing harm due to toxicity from electrolysis, but the Freeform Stimulator avoids this issue using a special microfluidic channel network and innovative valve system. This advancement could be incredibly useful for treatments like vestibular implants, blocking pain signals, and treating epilepsy, where prolonged direct current stimulation is needed. #3DPrinting #Technology #PrintingPotential

𝐏𝐑𝐎𝐒𝐓𝐇𝐄𝐓𝐈𝐂𝐒 A prosthetic is a device that substitutes for a body part or function that is defective or missing. The aim of a prosthetic is to replace the missing or damaged body part so perfectly that when a function is performed it is as if the original body part performed it. The Brain-Computer Interface (BCI) is a device that captures nerve signals that the brain produces when there is an intention to act, translates the signals through algorithms and then produces the action through a machine; thereby, circumventing the damaged limbs or missing body parts. The system requires no muscular control and it can consequently liberate someone who is paralyzed, or it can create a prosthetic limb that acts as the original limb. 𝐇𝐨𝐰 𝐁𝐂𝐈 𝐰𝐨𝐫𝐤𝐬. The BCI works through a basic four step process: • Signal acquisition. • Signal processing. • Device output. • Operating protocol. Signal acquisition is when the brain signals are recorded and amplified, by electrodes. The brain signals can be recorded through many methods •Electroencephalography (EEG) {Non invasive}. •Electrocorticography (ECog) & Local Field Potentials (LFPs) {Invasive}. After signal acquisition, the signals are digitized and then the more complicated process of signal processing occurs. Signal processing is broken down into two components: •Feature extraction •Signal translation. Whenever there is signal acquisition, “noise”, otherwise known as artifacts, such as other brain signals or even muscular movements, will get mixed in and can even sometimes be thought of as the target signal. Therefore, feature extraction removes the desired signals from the total signals. The signals are then sent to the device output section of the BCI which is the actual machine that produces the action. The action can be anything, whether it is controlling a cursor on a screen or the movement of a robotic arm. The device output then translates the signals into physical control signals that can then power the device. The operating protocol is how the device is controlled. How it is turned on and off, the feedback that is provided (such as the speed of the reactions), and the timing of the commands and actions. It is the basic operating manual of the prosthetic. #HealthcareAI #Healthcarerevolution.

3D-printed brain tissue with functional neural networks: This was achieved by printing one layer next to another horizontally rather than the conventional stacking of vertical layers. #3dbioprinting #brainhealth #brainresearch https://lnkd.in/gXvK5JMm

I'm excited to share (a little late) that another chapter of my dissertation was recently published in Advanced Engineering Materials. This paper, titled "Toward the Development of a Shape Memory Polymer for Individualized Endovascular Therapy of Intracranial Aneurysms Using a 3D-Printing/Leaching Method", was a very exciting one to do. It was my "aha!" moment in my PhD, as a very simple idea was the solution to a very complext problem: how to 3D-print a highly crosslinked polyurethane using biocompatible techniques if fused deposition modeling is not possible? The answer in this paper. Thanks to every undergraduate researcher who assisted on this paper and, specially, to Tanner Cabaniss who made this possible with his love for 3D printing. Stay tuned with his work! Here's the link: https://lnkd.in/gnQ9TGQz If you can't access the paper, let me know so I can send you a PDF.

They say a good joke is all about the right angle... so let's hinge on this one!!!! our latest research on valgus high tibial osteotomy (HTO) and the critical role of the lateral hinge in maintaining proper healing and correction retention is out !! A numerical model of an HTO stabilized with a locked plate was created using Autodesk Fusion 360 and Altair HyperWorks software, based on the geometry of a healthy proximal tibia. - **Primary Measure:** Maximum stress values (Von Mises stress, in MPa) in the plate and lateral hinge. 📈 Results: - **Plate Stress:** Approximately 20.29 MPa. - **Hinge Stress:** About 5.6 MPa. - **Model Optimization:** A 4 mm mesh for general elements and a 0.7 mm element size for high-stress areas. Thanks matthieu ehlinger for leading this cool project #Orthopedics #Research #FiniteElementAnalysis #HTO #KneeSurgery #MedicalInnovation #Biomechanics # https://lnkd.in/ds_Gr5CP

Our proposed mechanism for memory engram formation is the "multi-trace systems consolidation," which involves the sequential printing of engrams from one brain circuit to the next using a specific neuroanatomical pathway. Enjoy the press release and the paper. https://lnkd.in/dRqaX4ng

We are pleased to inform you that our article "On Automated Object Grasping for Intelligent Prosthetic Hands Using Machine Learning" has been published in Bioengineering. In this paper, we proposed an automated method that leverages computer vision-based techniques using machine learning technologies to improve the autonomy of prosthetics. To read more on this, kindly check the link below. A big thank you to Jethro Odeyemi for the opportunity to work with you on this research and Bioengineering MDPI for publishing this paper. https://lnkd.in/g4Tjg7sP #prosthetics #machinelearning #design #policymaking #softrobotics #handgestures