Saturday, September 23, 2023
Saturday, September 23, 2023

Lunit’s AI-Powered Mammography Analysis Solution Achieves Comparable Diagnostic Performance with Human Readers

Lunit (KRX:328130.KQ), a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, has unveiled the results of a collaborative study with Dr. Yan Chen, Ph.D., Professor of digital screening at the University of Nottingham, United Kingdom. The study, recently published in Radiology, demonstrates that Lunit’s AI-powered mammography analysis solution, Lunit INSIGHT MMG, matches the diagnostic performance of human readers. The study, which involved comparing Lunit’s solution with assessments by 552 human readers, represents a significant milestone in the field of medical imaging and the future of breast cancer detection.

“This first study to apply the Personal Performance in Mammographic Screening (PERFORMS) scheme to AI algorithms marks a remarkable achievement, showcasing our AI’s ability to match human performance in detecting breast cancer. It offers hope to patients worldwide and underscores AI’s potential to enhance cancer detection and treatment outcomes,” said Brandon Suh, CEO of Lunit. “This follows our recent study in The Lancet Digital Health, validating Lunit INSIGHT MMG as a game-changing alternative in breast cancer screening. We’re committed to leveraging AI to transform healthcare and save lives.”

Conducted retrospectively, the study evaluated two PERFORMS test sets, each consisting of 60 challenging cases from the NHSBSP (National Health Service Breast Screening Program), over a three-year period. Human readers assessed these cases between May 2018 and March 2021, while Lunit’s AI-powered mammography analysis solution evaluated them in 2022. The AI algorithm assessed each breast individually and assigned a suspicion of malignancy score to the detected features.

In the study, no significant difference was observed in the AUC (area under the ROC curve) between Lunit’s AI-powered mammography analysis solution (0.93) and human readers (0.88), demonstrating the solution’s ability to excel in breast cancer detection. Additionally, when using recall thresholds to match the mean performance of human readers (90% sensitivity, 76% specificity), Lunit’s AI-powered mammography analysis solution exhibited no significant differences or even stronger performance in sensitivity (91%) or specificity (77%) compared to human readers, highlighting its reliability and consistency.

In conclusion, the study demonstrates that Lunit’s AI-powered mammography analysis solution performs at a level equivalent to that of an experienced radiologist when assessing cases from two enriched test sets provided by the PERFORMS scheme.

“There are no other studies to date that have compared such a large number of human reader performance in routine quality assurance test sets to AI, so this study may provide a model for assessing AI performance in a real-world setting,” said Prof. Chen. “The results of this study provide strong supporting evidence that AI for breast cancer screening can perform as well as human readers.”

Medical Device News Magazine
Our publication is dedicated to bringing our readers the latest medical device news. We are proud to boast that our subscribers include medical specialists, device industry executives, investors, and other allied health professionals, as well as patients who are interested in researching various medical devices. We hope you find value in our easy-to-read publication and its overall purpose and objectives! Medical Device News Magazine is a division of PTM Healthcare Marketing, Inc. Pauline T. Mayer is the managing editor.

More News!

PADCEV® (enfortumab vedotin-ejfv) and KEYTRUDA® (pembrolizumab) Significantly Improve Overall Survival and Progression-Free Survival in Patients With Previously Untreated Advanced Bladder Cancer in Pivotal Phase...

The EV-302 study met its dual primary endpoints of overall survival (OS) and progression-free survival (PFS), compared to chemotherapy. An Independent Data Monitoring Committee determined that OS crossed the pre-specified efficacy boundary at interim analysis. The safety results of the combination are consistent with those of enfortumab vedotin in combination with pembrolizumab previously reported in cisplatin-ineligible patients with la/mUC.

NeuroBo Pharmaceuticals Doses First Patient in Its Phase 2a Clinical Trial Evaluating DA-1241 for the Treatment of NASH

"Dosing the first patient, on time, is a testament to our commitment to the clinical development of DA-1241 in patients with NASH," stated Hyung Heon Kim, President and Chief Executive Officer of NeuroBo. "Based on the pre-clinical and clinical evidence generated to date, DA-1241 has demonstrated reduced hepatic steatosis, hepatic inflammation, and liver fibrosis, while also improving glucose control, and was shown to be well tolerated in both healthy volunteers and in patients with type 2 diabetes mellitus (T2DM). Given this data, we believe that the mechanism of action of this promising cardiometabolic asset will translate into a safe and effective treatment for NASH, a disease with no current treatment options. The two-part design of this trial provides optionality for a potential interim analysis in the first half of 2024 and we expect to report the full data in the second half of 2024."

Medmain Inc. Has Been Selected for the U.S. Market Gateway Accelerator for BioSciences and MedTech

The "U.S. Market Gateway Accelerator for BioSciences and MedTech", sponsored by WorldUpstart, LLC, is an acceleration program that provides medical tech and life sciences startups with a proven track record outside the U.S. with the opportunity to enter and grow their business in the U.S. market.

Karger Publishers New Journal – Immune System

“Immune System is an innovative Open Access journal, welcoming articles with a broad background from basic science to clinical research, as long as the manuscript focuses on certain aspects of our immune response,” states editor-in-chief Désirée Larenas-Linnemann."

MindMed Completes Enrollment of Phase 2b Trial of MM-120 in Generalized Anxiety Disorder (GAD)

Robert Barrow, Chief Executive Officer and Director of MindMed. “Thanks in large part to the enthusiasm we have seen regarding MM-120 among investigators and patients, as well as the strong execution of our team, we were able to enroll almost 200 participants in this trial in just over a year. We anticipate sharing topline results during the fourth quarter of this year.”

By using this website you agree to accept Medical Device News Magazine Privacy Policy