SOLICITATION NOTICE
R -- R&D in Computer-Assisted Processing of Digitized Histology Images
- Notice Date
- 8/29/2012
- Notice Type
- Combined Synopsis/Solicitation
- NAICS
- 611310
— Colleges, Universities, and Professional Schools
- Contracting Office
- Department of Health and Human Services, National Institutes of Health, National Library of Medicine, 6707 Democracy Blvd., Suite 105, Bethesda, Maryland, 20894, United States
- ZIP Code
- 20894
- Solicitation Number
- NIHLM2012536
- Archive Date
- 9/19/2012
- Point of Contact
- Keturah D. Busey, Phone: 3014966546
- E-Mail Address
-
buseyk@mail.nlm.nih.gov
(buseyk@mail.nlm.nih.gov)
- Small Business Set-Aside
- N/A
- Description
- In accordance with FAR Parts 12 and 15, the National Institutes of Health (NIH) National Library of Medicine (NLM) intend to procure professional services on a sole source basis from the University of Missouri-Rolla, Office of Sponsored Programs,1870 Miner Circle, 215 ME Annex, Rolla, MO 65409-1330 under the authority of FAR 6.302-1(a)(2) to build upon their prior work for the analysis, design and development of techniques for (1) analyzing structure and content of digitized histology images, centered on the epithelial regions; this analysis includes color, texture, geometry, and object identification within regions, as well as identifying biologically-relevant structures, such as cell nuclei, cytoplasm, and stroma/epithelium boundaries. The North American Industry Classification System Code (NAICS) is 611310-Colleges, Universities, and Professional Schools with a small business size standard of $7.0 million. The period of performance shall be twelve (12) months from the Date of Award with two twelve-month Option Years. Background: The proliferation of medical information in the form of digital images has created an opportunity and a challenge for technology to play a role in the analysis and understanding of this data for both research and clinical purposes. In the field of pathology, efforts are underway to use technology to digitally acquire, manage, and analyze histology images with the goals of gaining efficiency and accuracy in interpreting the image data for assessing disease at the tissue level in support of treatment and management programs for health care improvement. The increasing amounts of image data acquired in clinical care centers have created a burden for interpretation by human experts that may reach unsustainable levels. Computer-assisted methods may be able to play a significant role in off-loading demands on experts. These methods must address (1) the acquisition, storage, retrieval, and display of the histology image data, (2) the analysis and interpretation of the histology image data, and (3) the integration of the computer-assisted methods into the clinician (or biomedical researcher) workflow. The work proposed here is largely concerned with (2) above, the analysis and understanding of the histology image data. An immediate challenge in this work is the large size of histology images. A typical digitized histology image of the uterine cervix spans tens of thousands of pixels in both width and height, and has three color planes. The contents of the images may very roughly be described as epithelium, stroma, and background. The relative proportions of each of these categories is highly variable from image to image, and the epithelium and stroma categories show a high degree of geometrical configurations and commonly contain complex or diffuse structures including glands, red blood cells, squamous cells, columnar cells, cytoplasm, and cell nuclei. The proposed work focuses on disease in the epithelial tissue of the uterine cervix, so the region of interest is the epithelial region. The first challenge, then, is the development of methods to reliably locate this region within the image. NLM has initiated work toward this goal, which is ongoing, and it is envisioned that the proposed analysis work will take advantage of the available methods developed by NLM for location of epithelial tissue and/or take advantage of sets of epithelial regions of interest which have been acquired by NLM by manual or other methods. After the epithelial regions has been located in the image, the proposed analysis work includes (A) characterizing the geometry and orientation of the epithelium, (B) implementing methods to segment, characterize, and/or measure structures within the epithelium that are believed to be of relevance for disease classification, and (C) apply classification algorithms to the data acquired in step (B) to classify sub regions within the epithelium into disease categories. Some elaboration of these steps follows: For (A), since disease is believed to progress in a unidirectional manner, from the basal membrane which separates stroma from epithelium, toward the apical ("surface") side of the epithelium, it is necessary to distinguish and label these two sides of the epithelium; to track disease progression across the epithelium, a natural approach is to trace minimal length paths from the basal membrane to the apical surface, and to analyze epithelium characteristics along these paths; if the epithelium were a rectangle, these path would be simple perpendiculars between the longer sides of the rectangle; since the epithelium is instead highly irregular, it is first necessary to compute a medial axis which is point wise equidistant from the two sides of the epithelium; perpendiculars to this axis can then be used as the desired paths across the epithelium. For (B) structures and measurements that are believed to be relevant for disease classification include number of nuclei per unit area, optical density of nuclei, nuclei/cytoplasm ratio, nuclei shape characteristics, and quantity of mitotic cells; nuclei segmentation methods are expected to be highly important; for characterizing number of nuclei per unit area, methods such as Delaunay triangularization have been used, where the related measurements are average triangle area and/or average length of triangle leg. For (C) the prevailing disease categories for the uterine cervix are Normal, CIN1, CIN2, and CIN3, where CIN refers to Cervical Intraepithelial Neoplasia. It should be noted that the definition of these categories is a subject of ongoing discussion and review within the medical community, and there is particular uncertainty with regard to the definition of the intermediate CIN2 category. Roughly speaking, the prevailing diagnostic method is to examine the epithelium for the presence of abnormalities from the basal membrane to the apical side of the epithelium. If abnormalities are confined to approximately the first 1/3 of this region, it is CIN1; to the first 2/3, CIN2; and, if the abnormalities extend across the entire epithelium, CIN3. The abnormalities may include high cell proliferation (large numbers of nuclei per unit area), abnormal nuclei/cytoplasm ratio, and abnormal nuclei cell characteristics. Since the disease characteristics of epithelium are believed to be heterogeneous, that is, one sub region may be, for example, CIN1, and another sub region, within the same region of epithelium, may be CIN3, it is a goal of this work to devise methods to characterize disease within sub regions of the epithelium. A major challenge will be to develop meaningful classification methods, based on the relatively small amount of expert-provided ground truth available, and to progressively improve the classification as more ground truth becomes available. Purpose/Objective: The purpose of this requirement is described in the Background steps (A) characterize the epithelium geometry, (B) segment, measure and characterize epithelium contents, and (C) classify sub-regions in the epithelium in disease categories of Normal, CIN1, CIN2, and CIN3. For (A), research currently sponsored by NLM, a hybrid distance transforms and end-segment adaptive algorithm has been investigated for medial axis determination. The investigated technique has been successful in estimating the medial axis for epithelium regions where the epithelium region is somewhat rectangular in structure. For more rounded epithelium regions, the current algorithm is not able to detect the medial axis correctly. This is primarily due to the fact that the algorithm currently only uses geometrical information to compute the medial axis. As a possible method of overcoming this difficulty, the contractor will investigate the integration of epithelium region shape, cell density and texture features to estimate the orientation and direction of the epithelium region as a preprocessing step to guide the distance transform method for initial medial axis determination for the hybrid algorithm. This would combine both geometrical (structural) and texture-based information for computing the medial axis. For (B), the contractor will extend research currently sponsored by NLM to segment and extract mathematical features from contents of epithelium; this will include the quantitative characterization of biological features such as number of nuclei per unit area, nuclei optical density, nuclei/cytoplasm ratio, and nuclei shape characteristics. For (C), in the research currently sponsored by NLM, the classification of sub regions within the epithelium is begin done by use of digitized uterine cervix images supplied by NLM, where expert truth classifications for epithelium regions are available, but where the only sub region truth set is created by a research engineer. The contractor will seek an expert medical consultant at the Phelps County Regional Medical Center (Rolla, MO), or other medical centers of opportunity, for guidance in establishing truth classifications for these sub regions, and for extending the current ground truth data set. In addition, for (C), the contractor will investigate state-of-the-art classification techniques for disease classification in these images and will implement and test the performance of these techniques. The classification work will include (a) classification of sub regions within epithelium segments and (b) methods to intelligently combine sub region classifications into classifications of the image data at larger spatial levels, such as entire epithelium segments, and the image as a whole. The contractor will investigate and take advantage of classification techniques that have been reported as effective in the technical literature, including specifically techniques used in the field of skin lesion discrimination. The overall goal of the government is to incorporate this work into an integrated system for the analysis and understanding of whole-slide histology images for improvements in clinical care and biological research. Toward this goal, the contractor will • take advantage of code previously developed by the government for the location of epithelium regions within the whole slide images by using this code, where practical, for the location of epithelium regions for analysis and disease classification; • make recommendations for modifications and improvements to this code, in consultation with the government; • implement modifications and improvements to this code, in consultation with the government. Required Task: The following tasks are to be completed. Full detail is given in the Proposed Work section of this Statement of Work. All image analysis and annotation software delivered shall be written in MATLAB or as negotiated with the government. Task description: Task 1: Develop initial algorithms for disease classification of digitized uterine cervix histology images The investigator will conduct R&D for computer-assisted classification of digitized uterine cervix histology images, will create an initial version of classification algorithms, and produce preliminary test results, using a government-provided set of images. Task 2: Extend and evaluate algorithms for disease classification of digitized uterine cervix histology images The investigator will conduct R&D for computer-assisted classification of digitized uterine cervix histology images, and will extend and comprehensively evaluate the algorithms developed in Task 1. The contractor will also provide test results on any additional uterine cervix images that have been acquired, or that were provided by the government during the first half of the contract performance period. Deliverables: Partial payments will be authorized to the Contractor upon receipt of deliverables. The deliverables under this statement of work shall be provided by the Contractor according to the following schedule: Deliverable 1: 6 months after contract begins Partial payment: $ 25,000 Deliverable 2: 12 months after contract begins Partial payment: $ 25,000 In addition to these deliverables, the investigator shall provide bimonthly reports providing updates on the progress of the research. All software deliverables shall include documentation and shall be implemented in MATLAB, or as negotiated with the government. All software shall include source code. The contents of the deliverables shall be as follows: Deliverable 1: Semi-annual technical progress report, plus the results of Task 1. Deliverable 2: Final technical report, plus the results of Task 2. For all tasks the deliverables shall consist of the following: 1. A comprehensive report on all work, in summary form and in detail, including a description of algorithms, theoretical and heuristic rationale for the approach taken, conclusions, recommendations and references. This includes research articles published in the literature as a result of this contract. 2. Test results from all experiments, summarized in graphical and tabular form, with detailed results as appropriate to explain both typical and exceptional cases. 3. Well documented software source codes files as well as executable, if any. 4. Program documentation, such as use guide/help data, on the developed software. 5. All data collected from this research, such as segmented shapes, data files, and images. 6. Prototype to demonstrate research results. 7. Training or assistance for integration of the software. Period of Performance: The anticipated period of performance will be twelve (12) months from the Date of Award with two twelve-month Option Years. Notice of Government Unlimited Rights to Work First Produced Under This Contract Government rights to work first produced under this contract are established by Federal law including, but not limited to, this specific reference: FAR 42.227-14, Rights in Data - General, (b) (1). Requirement to Notify Government of Proprietary Work Dependencies Offerors are required to notify the Government in writing of any dependencies of the deliverables under this contract on proprietary, copyrighted, or patented work that potentially inhibits, restricts, or requires permission for the dissemination of the deliverables to the public, other governmental agencies or research groups, or to any other parties whatsoever Sole Source Justification: The University of Missouri-Rolla is uniquely qualified for this work because of the principal investigator's prior work with the National Library of Medicine. The expertise and experience of the principal investigator at the University of Missouri-Rolla in the area of feature classification of digitized uterine cervix images, meet the specific requirements identified in the Sources Sought notice. He has prior published work in color normalization for medical images, combined with his extensive educational background and experience in advanced image processing. He has also demonstrated expertise in the development of image processing and machine learning software algorithms for color, texture, geometry, and object identification within histological image regions, and prior experience in creating a computer assisted system for diagnosis of digitized histology images of the uterine cervix. Furthermore, with the successful outcome from the previous contract, it would be a high burden in time, effort, and cost to the Government to replicate this work at this advanced stage through alternative sources. No other Contractor possesses the existing network of ongoing research into designing a biomedical information system that supports CBIR and Clinical Decision Support for Evidence-Based Practice for critical evaluation by biomedical specialists worldwide. Therefore, it would be in the best interest of the Government to award the contract to the University of Missouri-Rolla because of its unique ability to perform these tasks in a cost-efficient and timely manner. The following provisions and clauses apply to this acquisition and are incorporated by reference. Full text may be found at https://www.acquisition.gov/Far FEDERAL ACQUISITION REQULATION (FAR) CLAUSES FAR 52.224-1 Privacy Act Notification - This SOW requires the Contractor to do one or more of the following: design, develop, or operate a system of records on individuals to accomplish an agency function in accordance with the Privacy Act of 1974, Public Law 93-579, December 31, 1974 (5 USC 552a) and applicable agency regulations. Violation of the Act may involve the imposition of criminal penalties. The Privacy Act System of Records applicable to this project is Number 09-25-0106. FAR 52.224-2 Privacy Act FAR 52.212-4 Contract Terms and Conditions-Commercial Items FAR 52.212-5 Contract Terms and Conditions Required to Implement Statutes and Executive orders This is not a Request for Proposals (RFP), nor is a RFP available; however, all responsive sources may submit a proposal in a timely manner which will be considered by NLM. Firms interested in responding to this notice must be able to provide the referenced service as specified above. Responses must be in writing and must be received electronically at the Government infrastructure by 12:00 PM EST on Tuesday, September 4, 2012. Proposals must include pricing information and should reference Solicitation No. NIHLM2012536 and should be submitted to buseyk@mail.nlm.nih.gov. Inquiries regarding this procurement shall be submitted electronically to buseyk@mail.nlm.nih.gov and shall be received by 12:00 PM EST on Friday August 31, 2012.
- Web Link
-
FBO.gov Permalink
(https://www.fbo.gov/spg/HHS/NIH/OAM/NIHLM2012536/listing.html)
- Record
- SN02861327-W 20120831/120830001212-25afd9ae019c5825d52138969ad1a4dd (fbodaily.com)
- Source
-
FedBizOpps Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |