Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T7/00—Image analysis
  • G06T7/0002—Inspection of images, e.g. flaw detection
  • G06T7/0012—Biomedical image inspection
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/10—Image acquisition modality
  • G06T2207/10056—Microscopic image
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T2207/00—Indexing scheme for image analysis or image enhancement
  • G06T2207/30—Subject of image; Context of image processing
  • G06T2207/30004—Biomedical image processing
  • G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H30/00—ICT specially adapted for the handling or processing of medical images
  • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing

Definitions

• the present invention relates to a system and a method for standardized, optimized and pre- configured digital pathology.
• a representative system includes a computer that receives a magnified digital representation of the tissue or cell sample from a camera and processes the received digital representation.
• Virtual or digital slide systems utilize, often automated, digital slide scanners that create a digital image file of an entire glass slide (whole slide image).
• the digital slides (images) are normally maintained in an information management system that allows for archival and intelligent retrieval.
• the digital image files that can be visualized and navigated, just as Google Earth, allowing pathologists to use computers for warping from a low-magnitude overview image of an entire tissue specimen, into a high- magnitude field-of-view, where minute cell structures can be scrutinized.
• the present invention provides a solution to the lack of a standardized method for quantitative digital pathology including a standardized method for preparing the biological sample, acquiring the digital image, and analysing the image. Accordingly, the invention relates in one aspect to a system for standardized, optimized and pre-configured quantitative digital pathology on biological samples comprising a library of application packages wherein each application package comprises
• an optimized image analysis algorithm comprising image analysis instructions, wherein the algorithm is optimized and documented based on data being:
• the invention relates to a method for a user for viewing a digital slide representing structural content of a biological sample, in a system as defined above searching the webbased presentation of application descriptions and selecting an application description corresponding to a specific structural content, requesting access through the access request capability, viewing the digital slide(s) corresponding to the selected application description.
• Figure 1 shows a webbased presentation of a plurality of application description fronts showing different specific applications.
• Figure 2 shows an example of a staining protocol as part of a sample preparation protocol
• Figure 3 shows a schematic view of the system according to the invention
• the present invention provides a solution to the provision of standardized quantitative digital pathology by providing means for standardizing the whole workflow from tissue preparation to analysis of the digital slide and eventually quantification.
• the term standardized is used to describe that the image analysis may be standardized due to the fact that the digital slides are obtained by following the instructions for preparing the biological sample and for acquiring the digital slide of the biological sample.
• the solution is a system comprising a library of application packages wherein each application package comprises
• an optimized image analysis algorithm comprising image analysis instructions
• an application description a webbased presentation of the application description as defined in d) of a plurality of application packages in the library comprising access request capability an execution platform
• the user is provided with all instructions for preparing the sample as well as the digital slide followed by automated image analysis which is optimised towards the instruction for preparation and consequently it is possible to standardize all the variables during preparations whereby the automated image analysis may be carried out on digital slides not suffering from a great variability.
• the term "optimized image analysis” means that the algorithm is optimized towards slides prepared according to the instructions leading to an optimal image analysis of slides prepared according to the instructions.
• Stereology may be defined as "the spatial interpretation of sections". It is concerned with the three-dimensional interpretation of planar sections of tissues. It provides practical techniques for extracting quantitative information about a three-dimensional material from measurements made on two-dimensional planar sections of the material (see examples below). Stereology is a method that utilizes random, systematic sampling to provide unbiased and quantitative data.
• system is pre-configured which in the present context means that it comprises all the steps needed for execution of the algorithms.
• the biological sample according to the invention may be any biological sample for which there is an interest for quantification.
• the biological sample is a tissue sample or a body fluid sample, or a cell sample.
• the sample is mostly stained with at least one chemical marker, such as at least one fluorescent marker. It is preferred that the sample is illuminated while the images are obtained, such as by using UV or illumination visible to the human eye.
• Tissue samples are normally prepared as tissue section, such as a histological section. Library of application packages
• the standardization is obtained by the provision of a library of application packages, wherein each package provides instructions as well as algorithms necessary to carry out the quantitative digital pathology for one specific biological sample, and there is a one-to-one correlation between each of the items in an application package.
• each application package comprises a) a verifiable and optimized biological sample preparation protocol
• the image analysis algorithm is optimized towards the sample preparation protocol, and both the algorithm and the sample preparation protocol are optimized through a scientific process and verified on a dataset from clinical testing wherein the dataset is sufficient for providing the relevant statistical results.
• the instructions for preparation of a biological sample includes the relevant steps for securing a standardized and optimized preparation, including but not limited to tissue collection, fixation, section thickness, and the staining processes itself.
• the preparation protocol comprises instructions for preparation methods selected from the group consisting of sample collection, sample trimming, sample fixation, sample embedding, sample sectioning, sample staining and sample storage.
• Protocols are optimized to the specific biological sample, such as the specific tissue and the specific types of cells or other structures to be enhanced and quantified. Examples of protocols are for example found here: vww. nor jQC.org and one example of a protocol is shown in Figure 2.
• the protocol also includes an interactive aspect in that the protocol provides the customer with at least one relevant digital slide showing a sample of tissue optimally prepared according to the instructions. These slides will allow the user to compare with slides produced internally in their lab, and thereby validate whether the staining procedure has been followed correctly or whether their own slides have been stained too much or too little.
• This aspect of the optimized protocols will eliminate a significant part of the variability at the front-end of the process leading to a much higher precision in the quantification, and make end- points based upon morphometry and staining intensity far more useful.
• the instructions for image acquisition comprises instructions for acquisition selected from the group consisting of magnification, exposure time, modality, resolution, gamma, gain, calibration, scanner, and slides or combinations thereof.
• the application package may contain one or more auxiliary algorithms, such as an auxiliary algorithm for region-of-interest (ROI) detection, and/or removal of artefacts.
• ROI region-of-interest
• the algorithms may be tuned or customized to specific user variables.
• the application package furthermore comprises an optimized image analysis algorithm.
• the algorithm is optimized and documented based on data being: at least one biological sample prepared according to the instructions in the sample preparation protocol and imaged according to the instructions for image acquisition, - at least one corresponding reference standard of the at least one biological sample
• the problems of variability as discussed above have been solved or at least diminished to a level acceptable for obtaining correct results during the image analysis.
• the intended purpose of the image analysis algorithm is to provide end-points that are concordant with pathologists or preferably a "Gold-standard", if such exist, referred to as the reference standard. Accordingly, the image analysis algorithm is also optimized and documented based on at least one corresponding reference standard of the at least one biological sample which means that the results obtained using the image analysis algorithm are concordant with results obtained by for example a pathologist on the same slides.
• the relevant reference standards may be outlining of relevant tissue Regions Of Interest (e.g. tumor regions) linked with a grade, score, rank, number/count, area, circumference, length, and/or thickness, or other relevant end-point.
• the reference standard is established by a human, such as wherein reference standard is established by a human as a grade, score, rank, number/count, area,
• the system provides a library targeting highly specialized research applications each being described in a unique application description and the library may be searched based on the application descriptions, wherein each application description corresponds to a specific structural content of a specific biological sample.
• the application description contains information about the capabilities of the application package, such as highly specialized information of how it is analyzing the image, the computed end-points, screenshots, links to scientific literature, Webinars describing the application, user manual, information about with whom the application was developed, and a listing of other users.
• the system further comprises a webbased presentation of a plurality of application descriptions as well as an access request capability.
• the access request capability is a button or a link to be activated and which allows the user to access the rest of the application package, since the accessibility of the part of the application package comprising the sample preparation protocol, the instructions for image acquisition as well as the image analysis algorithm requires request of access through the access request capability.
• the access may be granted for a period of time, or for a number of slides analysed or any other limitation that is suitable.
• Execution platform For viewing and executing the system also comprises an execution platform providing capabilities of a) viewing digital slides b) viewing instructions for as defined above, and
• the execution platform provides capabilities for viewing the results from executing the algorithm, ie. the image analysis results.
• the execution platform may be provided at any suitable position, such as at the user end as a deployed application, ie. a client application.
• a deployed application ie. a client application.
• the algorithm is executed through the application at the user end.
• the software related to the system is a Software-as-a-Service (SaaS), ie, "on-demand software” being a software delivery model in which software and its associated data are hosted centrally, typically in a cloud.
• the execution platform is provided as a cloud application service or also denoted cloud based software delivery.
• Cloud computing may be defined as a model for enabling convenient, on- demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services).
• the execution platform Independent of location the execution platform provides capabilities of viewing and analysing the user's digital slides.
• the execution platform also provides capabilities of viewing the at least one digital slide provided with the sample preparation protocol.
• the digital slides may be located at user end or uploaded to a server hosting the execution platform.
• the execution platform is provided as a cloud application service
• the slides may be uploaded to the cloud or the execution platform may further provide capabilities of viewing digital slides positioned on a remote computer system.
• the image analysis optionally including stereology, may be provided as a Web application, it is preferred to base the software delivery on Application Virtualization rather than on Web applications.
• Application virtualization is defined as software technologies that improve portability, manageability and compatibility of applications by encapsulating them from the underlying operating system on which they are executed. A fully virtualized application is not installed in the traditional sense, although it is still executed as if it were.
• Virtualized applications eliminate web browser compatibility issues. Virtualized application is does not rely on the web browser so the application will run no matter which web browser has been installed, e.g. Internet explorer 7, 8, 9... , Mozolla, Crome etc.
• Virtualized applications minimizes client side IT installation and maintenance issues. Virtualized application does not require installation of Java, Flash... or other common dependencies on the client computer.
• the invention further provides a method for a user for viewing a digital slide representing structural content of a biological sample, said method comprising in a system as defined above searching the webbased presentation of application descriptions and selecting an application description corresponding to a specific structural content, requesting access through the access request capability, viewing the digital slide(s) corresponding to the selected application description.
• the user may start accessing the system for testing the slides available in the sample preparation protocol and comparing with his or her own slides.
• the main purpose of the system is for use in the analysis of the user's slides prepared according to the standardized and optimized sample preparation protocol and obtained through an image acquisition process according to the image acquisition instructions whereby the analysis is carried out using the optimized image analysis algorithm.
• the user may compare the digital slides prepared at their end with the digital slides in the sample preparation protocol to ensure that the quality of their digital slides is acceptable.
• the method further includes quantitative digital pathology on the biological sample.
• the quantitative digital pathology includes stereology. Accordingly, in one embodiment the method includes preparation of at least one slide at the user end, wherein the slide is prepared according to the standardized and optimized sample preparation protocol.
• the method includes acquisition of images of the slides, wherein the acquisition is performed in accordance with the image acquisition instructions.
• the method includes image analysis of the images of the slides prepared according to the standardized and optimized sample preparation protocol, wherein the image analysis is performed using the optimized image analysis algorithm.
• execution platform may be provided as a cloud application service, or as a deployed application.
• the execution platform further provides capabilities of viewing digital slides positioned on a remote computer system, such as wherein the digital slides are uploaded from the user to the cloud.
• the sample may be any of the samples discussed above.

Landscapes

• Engineering & Computer Science (AREA)
• Health & Medical Sciences (AREA)
• General Health & Medical Sciences (AREA)
• Medical Informatics (AREA)
• Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
• Radiology & Medical Imaging (AREA)
• Quality & Reliability (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Theoretical Computer Science (AREA)
• Investigating Or Analysing Biological Materials (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=47754252

Family Applications (1)

Country Status (1)

Cited By (1)

Citations (2)

• 2013
  • 2013-01-21 WO PCT/DK2013/050018 patent/WO2013107463A1/fr not_active Ceased

Patent Citations (2)

Non-Patent Citations (5)

Similar Documents

Legal Events