Pennsylvania Patent of the Month – April 2024

Proscia, Inc, a leading innovator in the field of digital pathology, has unveiled a groundbreaking method for classifying human cutaneous tissue samples. Leveraging the power of machine learning, Proscia’s invention promises to revolutionize dermatopathological diagnosis, offering enhanced accuracy and efficiency.

At the heart of Proscia’s method lies a sophisticated machine learning system trained with a diverse array of dermatological images. By analyzing patterns and features within these images, the system can accurately classify cutaneous tissue samples, distinguishing between various dermatological conditions with remarkable precision.

The process begins with the acquisition of high-resolution images of human cutaneous tissue samples, typically obtained through whole-slide scanning. These images serve as the input data for Proscia’s machine learning system. Through a series of preprocessing steps, the images are prepared for analysis, ensuring optimal clarity and resolution.

Once prepared, the images are fed into the trained machine learning system, which applies advanced algorithms to label each pixel based on its probability of representing a particular dermatological diagnosis. Drawing upon a vast repository of training data, which includes both diagnostic goal images and distractor images, the system can effectively differentiate between various dermatopathological conditions.

Proscia’s method is not limited to a single diagnostic goal but can accommodate multiple dermatological conditions, including basal cell carcinoma, dermal nevus, and seborrheic keratosis. By training separate deep learning neural networks for each diagnostic goal, the system can provide accurate diagnoses across a diverse range of skin conditions.

One of the key advantages of Proscia’s approach is its ability to automate the diagnostic process, reducing the reliance on human interpretation and minimizing the risk of subjective errors. The system outputs a specimen-level diagnosis based on the analysis of contiguous regions of pixels, providing healthcare professionals with valuable insights into the nature of the tissue sample.

Proscia’s innovative method represents a significant advancement in the field of dermatopathology. By harnessing the power of machine learning, Proscia is paving the way for more efficient, accurate, and reliable diagnosis of cutaneous tissue samples, ultimately improving patient outcomes and advancing the practice of pathology.

Are you developing new technology for an existing application? Did you know your development work could be eligible for the R&D Tax Credit and you can receive up to 14% back on your expenses? Even if your development isn’t successful your work may still qualify for R&D credits (i.e. you don’t need to have a patent to qualify). To find out more, please contact a Swanson Reed R&D Specialist today or check out our free online eligibility test.

Who We Are:

Swanson Reed is one of the U.S.’ largest Specialist R&D tax advisory firms. We manage all facets of the R&D tax credit program, from claim preparation and audit compliance to claim disputes.

Swanson Reed regularly hosts free webinars and provides free IRS CE and CPE credits for CPAs. For more information please visit us at www.swansonreed.com/webinars or contact your usual Swanson Reed representative.

Recent Posts