"We were deeply impressed by Galen's performance in the study, that based on our validation, clearly showed how Ibex can support our clinicians in improving diagnostic quality and efficiency, and as a result we have decided to implement it routinely," said Prof. Junya Fukuoka, MD, PhD, Chair of the Department of Pathology at Kameda Medical Center, Chair of the Department of Pathology Informatics at Nagasaki University and the study's primary investigator. "Interestingly, Galen identified both malignant and non-malignant findings previously undetected by pathologists and we are proud to have become the first pathology department in Japan to use digital pathology and AI routinely for primary cancer diagnosis, significantly improving our pathologists' user experience and confidence."
Cancer incidence in Japan is rising, with prostate and breast cancers being the most commonly diagnosed cancers in men and women respectively last year. As incidence grows and diagnosis becomes more complex in this era of precision medicine, accuracy is critical for enabling personalized and tailored therapies. This is further compounded by the global shortage of pathologists, resulting in unprecedented workloads, impacting diagnostic quality and turnaround time. Ibex helps overcome these challenges with AI-powered workflows and decision-support tools that pathologists use in their everyday practice.
The study, and subsequent publication authored by Kris Lami, MD, PhD, evaluated the performance of Ibex's AI platform in detecting a broad range of pathologies in 100 breast and 100 prostate biopsies taken from a Japanese patient cohort. Ibex's platform demonstrated excellent outcomes, showcasing its ability to accurately detect both cancerous and non-cancerous features. During the study, Galen Prostate demonstrated high accuracy in detecting prostate adenocarcinoma with an Area Under the Curve (AUC) of 0.988. The AI algorithm was also highly accurate in cancer grading, specifically differentiating between low and medium/high-grade Gleason scores with an AUC of 0.994, as well as in identifying perineural invasion. In several cases, Galen Prostate's AI algorithm accurately identified higher Gleason scores than previously evaluated by a pathologist and unveiled previously undetected cancer, showcasing its potential to enhance diagnostic accuracy and reduce inter-observer variability. Similarly, Galen Breast showed high accuracy in detecting invasive breast cancer (AUC of 0.997) and in detecting ductal carcinoma in situ (DCIS) (AUC of 0.996), as well as in identifying other important pathologies, such as lymphovascular invasion.
"We are proud to announce the study outcomes and publication led by such a prestigious Japanese medical center, which come as an addition to successful studies of Ibex's AI solutions recently presented by leading United States healthcare institutions across various tissue types," remarked Dr. Manuela Vecsler, VP of Clinical and Scientific Affairs at Ibex Medical Analytics. "Galen is the most widely deployed AI technology in pathology, and we are excited to see it adopted in Japan and become the new standard in cancer diagnosis, helping clinicians improve patient care."
About Ibex Medical Analytics
Ibex Medical Analytics (Ibex) is transforming cancer diagnostics with world-leading clinical grade AI-powered solutions for pathology. Empowering physicians and supporting pathologists, Ibex is on a mission to provide accurate, timely and personalized cancer diagnosis for every patient. Ibex's Galen™ is the first and most widely deployed AI-powered platform in pathology and demonstrated outstanding outcomes in multiple clinical studies2,3,4,5,6. Pathologists worldwide use Galen as part of their everyday routine practice to improve the accuracy of cancer diagnosis, implement comprehensive quality control measures, reduce turnaround times and boost productivity with more efficient workflows. For additional company information, please visit https://ibex-ai.com/ and follow us on LinkedIn and X.
The Galen™ platform includes solutions which are for Research Use Only (RUO) in Japan and in the United States and not cleared by the FDA. Multiple Galen solutions are CE marked (IVDD and IVDR) and registered with the UK MHRA. For more information, including indication for use and regulatory approval in other countries, contact Ibex Medical Analytics.
About Kameda Medical Center
Kameda Medical Center is a network of medical services centered around Kameda General Hospital and Kameda Clinic, encompassing various facilities across multiple locations. As the flagship hospital in southern Chiba Prefecture, Kameda Medical Center offers a comprehensive range of medical services, from acute care to convalescent and home care. In 2009, Kameda became the first hospital in Japan to receive JCI accreditation, aiming to provide medical care to global standards. This commitment to world-class medical excellence continues today, and Kameda has been named one of Newsweek magazine's World's Best Hospitals for five consecutive years. The hospital is at the forefront of innovative challenges in the field of pathology, boasting one of the largest pathology teams in Japan. The Remote Image Digital Diagnosis Center, located at the Kameda Kyobashi Clinic in Tokyo, serves as a hub where top physicians from Nagasaki University, the Kameda Group, and around the globe collaborate and share knowledge in a virtual space. For more information, please visit our website: https://medical.kameda.com/general/en/.
[1] Lami K et al., Validation of prostate and breast cancer detection artificial intelligence algorithms for accurate histopathological diagnosis and grading: a retrospective study with a Japanese cohort, Pathology, May 2024; https://doi.org/10.1016/j.pathol.2024.02.009
[2] Sandbank et al., Validation and real-world clinical application of an artificial intelligence algorithm for breast cancer detection in biopsies, npj Breast Cancer, December 2022
[3] Pantanowitz et al., An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment study, THE LANCET Digital Health Aug 2020
[4] Rodriguez-Justo et al., Multi-Site Multi Reader Study on Artificial Intelligence-Assisted Primary Diagnosis of Gastric Biopsies, Virchows Arch (2023) 483 (Suppl 1): S1
[5] Comperat et al., Clinical Level AI-Based Solution for Primary Diagnosis and Reporting of Prostate Biopsies in Routine Use: A Prospective Reader Study, European Congress of Pathology 2021
[6] Raoux et al., Novel AI-Based Solution for Supporting Primary Diagnosis of Prostate Cancer Increases the Accuracy and Efficiency of Reporting in Clinical Routine, Modern Pathology (2021) 34 (suppl 2): 598-599
Logo - https://mma.prnewswire.com/media/1839936/Ibex_Logo.jpg
Logo - https://mma.prnewswire.com/media/2416440/4714088/Kameda_Medical_Center_Logo.jpg
SOURCE Ibex Medical Analytics; Kameda Medical Center
Share this article