Paige.AI Created to Transform Cancer Diagnosis and Treatment by Applying Artificial Intelligence to Pathology

February 9, 2018  Source: tmcnet 121

Paige.AI, a new company focused on revolutionizing clinical diagnosis and treatment in oncology through use of artificial intelligence (AI), launches today as it announces two major milestones:

1. Paige.AI signed a comprehensive license agreement with Memorial Sloan Kettering Cancer Center (MSK) to gain exclusive access to MSK's intellectual property in the field of computational pathology, as well as exclusive rights to MSK's library of 25 million pathology slides. This de-identified data set represents one of the world's largest tumor pathology archives and will be invaluable to Paige.AI as it builds out a suite of AI applications in pathology. MSK began digitizing pathology slides five years ago; Paige.AI has exclusive access to these in the field of computational pathology and will expand these efforts with a commitment to digitize millions of additional archived slides in the next few years. All licensed digital slides are accompanied by de-identified pathologic and clinical annotation, as well as anonymized genomic sequencing results.

2. Paige.AI closed on a $25 million Series A financing round, giving the company sufficient capital to invest in building the world's leading offering in digital and computational pathology. The Series A is led by a number of legendary investors, including Jim Breyer, founder and chief executive officer of Breyer Capital, a premier global venture capital firm based in Menlo Park, California.

Pathology is the cornerstone of most cancer diagnoses, yet most pathologic diagnoses rely on manual, subjective processes developed more than a century ago. Currently, highly-trained pathologists interpret numerous individual glass slides using a microscope to analyze tissues and cells. For instance, there can be as many as 60 slides in one breast biopsy, though often only a few are relevant to the diagnosis. The manual nature of this work is inherently inefficient and can contribute to diagnostic variability. Technology to convert glass slides to digital images has existed for over a decade, but it has not been broadly adopted because digitization alone does not allow pathologists to improve workflow.

Computational pathology will provide the missing link in the adoption of digital pathology, moving this vital field forward with support tools to help pathologists make decisions with greater speed, accuracy, objectivity and reproducibility - all at a lower cost. Computational pathology is a complete, probabilistic treatment of scientific and clinical workflows, combining experimental design, statistical pattern recognition and survival analysis for a unified framework in answering scientific and clinical questions. The outcome: pathologists' time will shift from compiling data - literally counting cell nuclei and measuring tumors point-to-point - to focusing on interpreting data and detailing the implications for a patient's diagnosis and treatment planning.

The company aims to catalyze a fundamental medical AI paradigm shift, transforming pathology and diagnostics from a qualitative to a more rigorous, quantitative discipline.

Paige.AI enters the market with three unique strengths, making it the first company in computational pathology capable of producing clinically-validated AI applications:

By Ddu