NantOmics and NantHealth Announce Results of Proprietary Machine Vision AI Software Study Demonstrating the Ability to Identify Aggressive Subtypes of Breast Cancer From Digital Pathology Images
Study Published In Breast Cancer Research Shows How Deep-Learning Of Over 650 Breast Cancer Digital Pathology Images And Omics Data Can Be Used Together To Unlock Precise Mechanisms Of Therapy Resistance
NantOmics scientists trained a deep-neural network on diagnostic slide images from 443 breast tumors that had previously undergone PAM50 subtyping to classify patches of the tumor images into four major molecular subtypes of breast cancer (basal-like, HER2-enriched, luminal A, and luminal B). The algorithm was then validated and demonstrated the capability to establish accurate breast cancer sub-typing in 222 samples from a retained set of tumors. By focusing the neural-network’s attention on cancer-rich regions in the diagnostic images, this deep-learning algorithm identifies patient biopsies that are a mixture of different molecular subtypes, a classification that is less definable from molecular pathology techniques. Patients with heterogeneous biopsies such as mixtures of basal-like and luminal disease have a different survival profile than patients with homogeneous disease, and may potentially benefit from a more tailored therapy regimen.
“Breast cancer can be subtyped into at least five distinct disease-types with very different prognoses and responses to therapy. These subtypes are characterized as clinically important, yet are typically only achievable by RNA expression profiling,” Dr.
“Our analysis builds on our breadth of advanced machine learning technologies to better support providers in therapeutic decision-making and to improve the capabilities of the underlying molecular analysis technology platforms that we use at
About NantOmics: NantOmics, a member of the
This news release contains certain statements of a forward-looking nature relating to future events or future business performance. Forward-looking statements can be identified by the words “expects,” “anticipates,” “believes,” “intends,” “estimates,” “plans,” “will,” “outlook” and similar expressions. Forward-looking statements are based on management’s current plans, estimates, assumptions and projections, and speak only as of the date they are made. Risks and uncertainties include, but are not limited to: our ability to successfully integrate a complex learning system to address a wide range of healthcare issues; our ability to successfully amass the requisite data to achieve maximum network effects; appropriately allocating financial and human resources across a broad array of product and service offerings; raising additional capital as necessary to fund our operations; achieving significant commercial market acceptance for our sequencing and molecular analysis solutions; establish relationships with, key thought leaders or payers’ key decision makers in order to establish GPS Cancer as a standard of care for patients with cancer; our ability to grow the market for our Systems Infrastructure, and applications; successfully enhancing our Systems Infrastructure and applications to achieve market acceptance and keep pace with technological developments; customer concentration; competition; security breaches; bandwidth limitations; our ability to continue our relationship with NantOmics; our ability to obtain regulatory approvals; dependence upon senior management; the need to comply with and meet applicable laws and regulations; unexpected adverse events; clinical adoption and market acceptance of GPS Cancer; and anticipated cost savings. We undertake no obligation to update any forward-looking statement in light of new information or future events, except as otherwise required by law. Forward-looking statements involve inherent risks and uncertainties, most of which are difficult to predict and are generally beyond our control. Actual results or outcomes may differ materially from those implied by the forward-looking statements as a result of the impact of a number of factors, many of which are discussed in more detail in our reports filed with the