Algorithm Validated Using Data from Company’s 1404 Phase 2 Study
NEW YORK, June 25, 2018 (GLOBE NEWSWIRE) — Progenics Pharmaceuticals, Inc. (Nasdaq:PGNX), an oncology company developing innovative medicines and imaging technology for targeting and treating cancer, reported data demonstrating the utility of its imaging analysis technology, which uses artificial intelligence and machine learning to quantify and automate the reading of PSMA targeted imaging. The data were presented in an oral presentation at the 2018 Society of Nuclear Medicine and Molecular Imaging (SNMMI) Annual Meeting on June 23rd in Philadelphia, Pennsylvania.
In the presentation, titled “Automated Detection and Quantification of Prostatic PSMA Uptake in SPECT/CT using a Deep Learning Model for Segmentation of Pelvic Anatomy,” researchers described the validation of a deep learning algorithm for the automatic detection and quantification of 1404 uptake from SPECT/CT images. 1404 is Progenics’ PSMA-targeted SPECT/CT imaging agent, currently in Phase 3 development.
“This study successfully validates Progenics’ imaging analysis technology platform for use with PSMA-targeted SPECT/CT, and shows the promise of using artificial intelligence to automate the reading and interpretation of prostate cancer scans,” stated Lars Edenbrandt, MD, PhD, Professor and Senior Specialist, Department of Molecular and Clinical Medicine, University of Gothenburg, “PSMA-targeted imaging, together with sophisticated algorithms and machine learning, have the potential to significantly improve how clinicians stage prostate cancer, monitor disease progression and manage treatment, which could potentially lead to better patient outcomes.”
“Progenics is leading the way in applying the use of artificial intelligence and machine learning to improve how we find, fight and follow prostate cancer,” stated Mark Baker, Chief Executive Officer of Progenics. “We have previously shown how our artificial intelligence-based imaging analysis technology can have clinical utility as a prognostic tool for bone scan images in metastatic prostate cancer. This study builds on that evidence and illustrates how our AI technology can be applied across imaging modalities, such as SPECT/CT. We look forward to advancing the development of this platform, together with our novel, PSMA-targeted imaging agents, to potentially transform the prostate cancer treatment management.”
The algorithm developed by Progenics’ imaging analysis technology was validated using the data from the Company’s Phase 2 study of 1404, which included 102 high-risk prostate cancer patients who all underwent PSMA imaging prior to radical prostatectomy. The validation scans were manually quantified by measuring the maximum uptake of 1404 in a circular region of interest of the prostate where the highest uptake values were determined visually. The algorithm used volumetric segmentation to measure uptake at every voxel in the prostate and determined the maximum uptake of 1404 automatically. The Pearson correlation coefficient was used to assess the concordance between manual and automated quantification of uptake. The automated maximum uptake value was significantly correlated to the manually obtained uptake value (p<0.0001). The algorithm was fully automated and deterministic, resulting in 100% repeatability.
Progenics develops innovative medicines and other technologies to target and treat cancer. Progenics’ pipeline includes: 1) therapeutic agents designed to precisely target cancer (AZEDRA®, 1095, and PSMA TTC), 2) PSMA-targeted imaging agents for prostate cancer (1404 and PyL™), and 3) imaging analysis technology. Progenics’ first commercial product, RELISTOR® (methylnaltrexone bromide) for opioid-induced constipation, is partnered with Valeant Pharmaceuticals International, Inc.
This press release contains projections and other “forward-looking statements” regarding future events. Statements contained in this communication that refer to Progenics’ estimated or anticipated future results or other non-historical facts are forward-looking statements that reflect Progenics’ current perspective of existing trends and information as of the date of this communication. Forward looking statements generally will be accompanied by words such as “anticipate,” “believe,” “plan,” “could,” “should,” “estimate,” “expect,” “forecast,” “outlook,” “guidance,” “intend,” “may,” “might,” “will,” “possible,” “potential,” “predict,” “project,” or other similar words, phrases or expressions. Such statements are predictions only, and are subject to risks and uncertainties that could cause actual events or results to differ materially. These risks and uncertainties include, among others, the cost, timing and unpredictability of results of clinical trials and other development activities and collaborations; the unpredictability of the duration and results of regulatory review of New Drug Applications (NDA) and Investigational NDAs, including our NDA for AZEDRA; market acceptance for approved products; possible product safety or efficacy concerns, general business, financial, regulatory and accounting matters, litigation and other risks. More information concerning Progenics and such risks and uncertainties is available on its website, and in its press releases and reports it files with the U.S. Securities and Exchange Commission, including those risk factors included in its Annual Report on Form 10-K for the annual period ended December 31, 2017. Progenics is providing the information in this press release as of its date and, except as expressly required by law, Progenics disclaims any intent or obligation to update or revise any forward-looking statements, whether as a result of new information, future events or circumstances or otherwise.
Additional information concerning Progenics and its business may be available in press releases or other public announcements and public filings made after this release. For more information, please visit www.progenics.com. Information on or accessed through our website or social media sites is not included in the company’s SEC filings.