> ## Content Index > Fetch the complete content index at: https://www.ai-360.online/llms.txt > Use this file to discover other available public pages before exploring further. # MIT Team Speeds Up AI-Based Particle Size Estimator for Drug Manufacturing - URL: https://www.ai-360.online/mit-team-speeds-up-ai-based-particle-size-estimator-for-drug-manufacturing/ - Published: 2024-09-27T13:38:00.000Z - Updated: 2024-10-03T09:02:28.000Z - Description: MIT researchers use AI to estimate particle size 60x faster in pharma manufacturing, reducing analysis time from 15 to 0.25 seconds. - Author: AI-360 - Tags: Pharmaceutical, MIT, News Researchers at the Massachusetts Institute of Technology (MIT) have developed a faster method for estimating particle size distributions in pharmaceutical manufacturing. The study, published on September 23, in the journal Light: Science & Application, describes a technique that accelerates analysis time by 60 times. The new method, based on pupil engineering and machine learning, can estimate powder size distribution from a single snapshot speckle image. This reduces reconstruction time from 15 seconds to just 0.25 seconds, offering real-time monitoring capabilities for pharmaceutical manufacturing. The technique uses a low-cost, noninvasive particle size probe that collects back-scattered light from powder surfaces. Its compact and portable design makes it compatible with most drying systems in the market, requiring only an observation window. ## Sign up for AI-360 AI from all perspectives: Where business & innovation meets application & regulation. Subscribe Email sent! Check your inbox to complete your signup. No spam. Unsubscribe anytime. This breakthrough addresses a longstanding challenge in pharmaceutical manufacturing: monitoring the characteristics of drying mixtures, a critical step in producing medication and chemical compounds. Traditional methods either involved time-intensive imaging and particle counting, or used scattered light to estimate particle size distribution (PSD). The accelerated PSD estimation method offers several potential benefits, including improved manufacturing efficiency and accuracy, fewer failed batches of products, real-time monitoring of fast dynamical systems, and a platform for studying models of processes including drying, mixing, and blending. Professor George Barbastathis of MIT's Department of Mechanical Engineering, the study's senior author, led a collaborative effort involving researchers from three MIT departments: Mechanical Engineering, Chemical Engineering, and Electrical Engineering and Computer Science. This research, part of the MIT-Takeda program, demonstrates the power of interdisciplinary collaboration between physicists and engineers. As pharmaceutical companies adopt this technology, it could lead to more efficient drug manufacturing processes and potentially lower medication costs for consumers. --- [To read more articles like this, and be notified of new content published each week, Sign Up to our FREE newsletter](#/portal/signup/free) ---