Galen Prostate demonstrates diagnostic value in prostate cancer

News
Article

Overall, participating pathologists felt that there is potential to increase diagnostic efficiency by using Galen Prostate in a clinical setting.

The Galen Prostate AI-powered solution demonstrated the ability to accurately identify and grade prostate cancer in the primary diagnosis of prostate needle biopsy (PNB) specimens, according to data presented at the United States and Canadian Academy of Pathology (USCAP) annual meeting in Baltimore, Maryland.1

"The solution demonstrated its capability to accurately detect cancer and contribute to diagnostic quality and can serve as a valuable tool for pathologists in clinical decision-making in routine pathology practice," wrote the investigators.

"The solution demonstrated its capability to accurately detect cancer and contribute to diagnostic quality and can serve as a valuable tool for pathologists in clinical decision-making in routine pathology practice," wrote the investigators.

The study was conducted through a collaboration between Ibex Medical Analytics and the University of Pittsburgh Medical Center in Pennsylvania.

In addition to Galen Prostate, Ibex Medical Analytics offers 2 other AI-based solutions with indications in breast cancer and gastric cancer. Data on those tools were also presented at the USCAP meeting.

"Galen offers an unparalleled breadth of detection capabilities going well beyond cancer and becoming an integral part of everyday clinical practice in laboratories, hospitals, and health systems globally. With these outstanding outcomes achieved in leading US health care institutions across various tissue types, amplified by very positive user feedback, our technology continues to set the standard for AI solutions in pathology, helping clinicians improve patient outcomes,” said Chaim Linhart, PhD, in a news release on the data.2 Linhart is thechief technology officer and co-founder of Ibex Medical Analytics.

Overall, data from the Galen Prostate study showed that in pre-classifying parts with the likelihood to be benign or malignant, Galen Prostate demonstrated an area under the curve of 0.994 (95% CI, 0.99-0.998), a negative predictive value of 97.5% (95% CI, 95.1%-98.9%), and a positive predictive value of 99.2% (95% CI, 97.8%-99.8%). In total, the AI solution marked 17.9% of parts as suspicious (medium likelihood), with 78% of those being classified as benign and 22% as malignant per the pathologist.

Further, agreement between the AI tool and the pathologists in regard to Gleason group (GG) grading was high at 90% (defined as a complete agreement or a difference of 1 GG).

The user feedback from pathologists was also positive, with a satisfaction mark of 95% in regard to Gleason scoring, 90% in perineural invasion detection, and 95% in tissue and tumor length automated measurements. Overall, participating pathologists felt that there is potential to increase diagnostic efficiency by using the AI-powered tool in a clinical setting.

In total, the investigators in the study assessed 206 cases, which were composed of 860 parts and 1159 hematoxylin and eosin (H&E)-stained slides. The H&E-stained slides were scanned at 40x magnification. PNB specimens were collected from October 2022 to February 2023 and selected at random for AI analysis and subsequent review by genitourinary (GU) pathologists.

The AI solution was used for the prospective primary diagnosis of PNBs by 4 trained GU pathologists. The slides were also reviewed by pathologists via microscopic examination. Final diagnoses were either categorized as malignant, atypical small acinar proliferation, or benign.

The investigators concluded, “We report the successful implementation of a multi-feature AI solution that automatically imparts clinically relevant diagnostic parameters regarding prostate cancer, grading, measurements, and other pathologic features. The solution demonstrated its capability to accurately detect cancer and contribute to diagnostic quality and can serve as a valuable tool for pathologists in clinical decision-making in routine pathology practice.”1

References

1. Korentzelos D, Deebajah MM, Quiroga-Garza GM, et al. Routine Use of an Artificial Intelligence Solution for Primary Diagnosis of Prostate Biopsies in Clinical Practice. Presented at: United States and Canadian Academy of Pathology Annual Meeting. March 23-28, 2024. Baltimore, Maryland. Poster 110

2. Ibex presents new data from multiple studies showcasing accuracy of AI in prostate, breast and gastric cancer diagnosis. News release. Ibex Medical Analytics. March 21, 2024. Accessed March 26, 2024. https://www.prnewswire.com/news-releases/ibex-presents-new-data-from-multiple-studies-showcasing-accuracy-of-ai-in-prostate-breast-and-gastric-cancer-diagnosis-302095787.html

Recent Videos
Kyrollis Attalla, MD, an expert on prostate cancer
Kyrollis Attalla, MD, an expert on prostate cancer
Tony Abraham, DO, MPA, a nuclear radiologist
Tony Abraham, DO, MPA, a nuclear radiologist
Adity Dutta, MSN, AGACNP-BC, gives an answer during a video interview
Prostate cancer cells dividing | Image Credit: © PRB ARTS - stock.adobe.com
A panel of 4 experts on prostate cancer
Jacqueline Zillioux, MD, answers a question during a Zoom video interview
Prostate cancer cells | Image Credit: © Dr_Microbe - stock.adobe.com
© 2024 MJH Life Sciences

All rights reserved.