As the prevalence of prostate cancer continues to rise, the widespread adoption of MRI scans as the standard-of-care for diagnosis has overwhelmed many radiology departments, lacking the necessary resources for efficient analysis. To address this challenge, Quibim has introduced QP-Prostate, an AI-powered solution designed to expedite image processing, enhance radiologist accuracy, and facilitate the transmission of actionable data points to oncology departments.

Distinguishing itself in the market, QP-Prostate accelerates processes while maintaining high quality. A validated international study has demonstrated an 88% accuracy in efficiently segmenting imagery of the prostate gland. The algorithm not only segments critical subregions and zones but also calculates prostate volume, aiding in the determination of prostate-specific antigen density and planning fusion biopsies.

In a pioneering move, starting this year, EU and UK clinicians can leverage QP-Prostate for AI-driven lesion detection. The algorithms are trained using post-biopsy pathology data as ground truth, a groundbreaking industry-first approach. This innovation is expected to contribute to heightened diagnostic accuracy, emphasizing high specificity alongside high sensitivity, and reducing reporting times.

Dr. Angel Alberich Bayarri, the founder and CEO of Quibim, expressed enthusiasm about the milestone, stating, "After much hard work, it's gratifying to see our lesion detection capability for prostate expanding across the EU and the UK. We are committed to making a real-life impact, continually refining our products in alignment with scientific and health industry advancements. Our goal is to collaborate with radiologists to enhance early-stage care for patients with suspected or confirmed prostate cancer, a group that unfortunately is growing rapidly in many countries."

David Bazaga, the product manager for QP-Prostate, emphasized the importance of improving lesion detection in medical imaging analysis and highlighted the collaborative efforts with technical experts and healthcare sector partners. The utilization of pathology data for algorithm training and validation is deemed critical, with anticipated real-life results in the near future.