December 15, 2022 – Vast Data, the high-performance data platform built for AI, announces that Therapixel, a French company specializing in the detection of breast cancer using artificial intelligence, has chosen its full data platform -flash and high-capacity, Universal Storage, to accelerate the training of its AI algorithms and the testing of more than one million mammograms.
With Universal Storage, Therapixel now has a high-performance, scalable data platform to train its algorithms using a full-flash system that delivers the random-read performance required to accelerate breast cancer mutation detection. Therapixel’s choice of Universal Storage eliminated challenges with storage, data capacity and performance. The solution is a platform that can now scale easily as Therapixel’s business grows.
“Vast Data is a game-changer by giving us the simplicity, scalability, and storage space we need to run our algorithm training. Before implementing Vast Data, we relied on storage solutions slower hard drives that lacked enough storage space for the data needed to train the algorithms that solve breast cancer, but you can’t develop any AI solution without fast access to data “, explains Aurélien Chick, Data Manager at Therapixel. “Today, that’s no longer a problem, thanks to Vast Data.”
Vast’s full-flash storage gives Therapixel faster access to training and iteration to refine the mammogram interpretation algorithm, enabling highly reliable first-read breast cancer detection . Vast’s similarity-based data reduction allowed Therapixel to double its data storage capacity and get even more space than it ever imagined. This allowed it to collect more data from its partners to train its models to a higher level of accuracy by exposing them to more data samples. Since deploying Vast Data’s Universal Storage, Therapixel can now interpret more than one million mammograms for training and testing its algorithms.
Focusing on breast cancer detection using AI-based tools, Therapixel uses its AI knowledge to enable radiologists to make better and faster decisions. The company’s software flags only the most unusual lesions and also provides characterizations that help radiologists determine whether to spend more time on a particular case. Until recently, many AI-based solutions for medical imaging pinpointed every lesion, delivering a diagnosis without any additional information and creating fatigue among radiologists. Therapixel allows radiologists to see in real time what the AI-driven algorithm predicts.
“In the same way that we allow our radiologists to perform at their best and focus on what matters, Vast Data has allowed us to focus on our research and development. It’s a good synergy” , added Mr. Chick. “We are already doing great things with Vast Data on a system that we deployed only a few months ago. It’s very encouraging. We can develop ideas and test them quickly, then confirm those ideas with more data to train algorithms.”
We would love to give thanks to the writer of this short article for this outstanding content
Vast Data Accelerates Therapixel’s Deep Learning for Breast Cancer Detection
Our social media profiles here , as well as other pages on related topics here.https://www.ai-magazine.com/related-pages/