Augmentiqs Enables Pivotal UPMC AR Microscopy Study for Ki-67
The Study, Conducted at the UPMC Lab of Dr. Liron Pantanowitz, Demonstrates Significant Cost Savings of AR Microscopy for Ki-67 Samples, and Opens Up a New Paradigm in Digital Pathology and Microscope Based Workflows
The recently published peer-reviewed study in the Journal of Cancer Cytopathology is titled, “Ki-67 Proliferation Index in Neuroendocrine Tumors: Can Augmented Reality Microscopy with Image Analysis Improve Scoring?”. The authors of the study include Swati Satturwar, Joshua Pantanowitz, Christopher Manko, Lindsey Seigh, Sara E Monaco, and Liron Pantanowitz.
UPMC AR Microscopy Study For Ki-67 Overview
The grading of neuroendocrine tumors (NETs) is performed by quantifying their mitotic activity and/or Ki-67 index, which is determined by counting the percentage of positively stained tumor cells in an area of the tumor with the highest nuclear labeling (i.e. hot spot) based on 500-2000 tumor cells. Currently, it remains questionable whether a Ki-67 index obtained on cytology material, such as a cell block, is truly representative of the entire tumor compared to the resection specimen.
Several studies have attempted to establish the best counting method for determining the Ki-67 index. However, there is no accepted standard yet and the best scoring method is still debatable.
Different methods for Ki-67 index quantification include:
- The ‘eyeball’ estimation (EE) performed manually by a pathologist counting in real time through their microscope eyepiece,
- Manual counting using a printed image that was captured using a camera mounted to a microscope at 20x magnification, and
- Computer-assisted quantification using digital image analysis (DIA).
Manual methods suffer from low reproducibility and high inter-reader variability among pathologists, especially for the low-grade NETs. Moreover, the manual methods, especially if they involve printing of images, are impractical in certain clinical practice settings and are labor intensive. To overcome inter-observer variabilities inherent in human counting, researchers have accordingly explored automated counting methods using digital images and a variety of image analysis algorithms. Although faster and more precise, DIA systems can be costly as they may require an expensive whole slide scanner to digitize slides and information technology support.
Recently, augmented reality microscopy (ARM) has become available that enables real time image analysis to be conducted using a traditional light microscope and glass slides which avoids having to first photograph or digitize slides.
An augmented reality microscope is a modified (“smart”) microscope that includes a small computer unit. This computer unit can be attached to the side of any microscope or it can be inserted between the microscope’s objectives and eyepiece unit. It incorporates a built-in camera to capture high quality images. The images acquired by this unit occur in real time and can be displayed on an attached computer monitor. Additionally, if the end user looks through the eyepieces of the microscope they can see computer-generated output, such as annotations, being projected as an overlay directly on the glass slide. ARM thus permits real time image analysis to be performed on glass slides with the output of the algorithm superimposed on the slide, thereby generating a composite field of view that can be utilized to supervise data collection.
This can be used to perform simple measurements (e.g. depth of tumor invasion), coupled with image analysis software to quantify immunohistochemical stains (e.g. Ki-67 proliferation index), or it can be combined with more sophisticated deep learning algorithms (e.g. to rapidly detect metastases in lymph nodes).
As opposed to DIA applied to whole slide images (WSI), ARM is quicker to use, provides real time and seamless integration of algorithms without the need to first acquire digital images, may be cheaper than buying a whole slide scanner, and does not require special technical skills to operate.
To the best of our knowledge, no studies have applied ARM to cytology. We anticipate that ARM may overcome many of the aforementioned issues related to Ki-67 quantification. The aim of this study was to therefore compare ARM to different (manual and DIA with WSI) scoring methods used for determining the Ki-67 proliferation index of NETs in cell block material.
Light microscope with Augmentiqs device (red circle) fitted between the objectives and eyepiece. Screenshot showing a field of view using the ARM counting method where the image analysis segments individual nuclei (white circles) and the end user manually selects positive nuclei (red circles).
The Grounbreaking UPMC Study on AR Microscopy Demonstrates an Open Platform Approach to Digital Image Analysis
Augmentiqs CEO Gabe Siegel congratulates UPMC and all the study authors, “The UPMC ARM study is truly groundbreaking in that it demonstrates a low-cost and easily integrated technology for reducing diagnostic time and improving reproducibility. The combination of ARM technology with an open source image analysis software like QuPath should continue to be studied by forward-thinking pathology departments like UPMC, which are interested in improving performance and keeping overhead costs low.”
UPMC ARM Study Conclusions
The authors finish the AR Microscopy Study with the following words: “To the best of our knowledge, this is the first study to evaluate the utility of ARM in cytology. Augmented reality (AR) refers to technology that combines reality and digital information. This is created by superimposing a computer-generated digital image onto an object or user’s view of the “real world”. This differs from virtual reality (VR) where a complete digital or computer-generated environment gets generated. AR technology (e.g. HoloLens) has been successfully applied to anatomic pathology for unique applications such as 3D image viewing and real-time pathology-radiology correlation.
Recently, investigators introduced the novel AR microscope. By attaching an AR unit to a conventional microscope this accessory device converts the microscope into a digital pathology solution that can now be used to perform real-time telepathology and computer-assisted diagnostics (e.g. image analysis, apply artificial intelligence algorithms) in addition to AR.
In our study, the AR microscope permitted us to rapidly execute image analysis in order to quantify Ki-67 directly from cytology glass slides while they were present on the microscope’s stage. This allowed us to avoid having to first photograph these slides or digitize the entire slide with a whole slide scanner. Moreover, since we were able to adjust the microscope’s fine and coarse magnification in real-time during this undertaking we overcame any focus issues that typically plaque digital imaging of cytology material. In summary, we found that ARM with DIA directly supervised by a human streamlined and hastened the task of assessing Ki-67 index in NETs.
Given the versatility and cost benefit of microscope-based AR technology, we anticipate that there will be other innovative studies using ARM in the near future.”
Augmentiqs is a microscope-centric approach to digital pathology, providing pathologists a cost-efficient and low-data method for realizing clinical and workflow enhancements. By connecting the analog microscope to the computer, Augmentiqs maintains the advantages of the microscope for workflow and primary diagnosis, while improving efficiency with the introduction of pathology software applications directly from the microscope.
By functioning as a platform for real-time software deployment within the microscope, Augmentiqs allows pathologists immediate access to imaging, analytical software, telepathology, LIMS integration and other digital pathology applications.
For more information about Augmentiqs, please visit www.augmentiqs.com or contact email@example.com.
As Pennsylvania’s largest nongovernmental employer, with more than 87,000 employees, UPMC is comprised of:
- More than 40 hospitals
- More than 700 doctors’ offices and outpatient sites
- An international division
- An enterprises division
A passion for innovation lies at the heart of UPMC’s success. UPMC’s unique strategy of combining clinical and research excellence with business-like discipline translates into high-quality patient care for both western Pennsylvanians and the global community.