If the amount of blurring is minimal (acceptable levels are to be determined in advance), the resulting images can still be presented to pathologists or algorithms. If these areas can be identified, the slides can be rescanned with additional focus points in areas of blurring. When parts of an image are blurry, this affects the performance of both pathologists and automated image analysis algorithms. the larger the distance, the more blurriness it will result. The distance of the focus points from the actual tissue plane is proportional to the amount of blurriness, i.e. However, commercial scanners may still produce digital images with out-of-focus/blurry areas if their AF optics system erroneously selects focus points that lie in a different plane than the proper height of the tissue. From these focal planes, scanners capture images to produce sharp tissue representation. AF optics systems determine a set of focus points at different focal planes to be perfectly aligned with tissue height that may slightly vary within a slide. Most modern scanners come equipped with autofocus (AF) optics system to select focal planes to accurately capture three-dimensional tissue morphology as the best two-dimensional digital image. Along with spatial resolution and color depth, image sharpness is often used to gauge the quality of digital slides. High-quality digital slides are becoming a ubiquitous and indispensable clinical workflow and research in pathology. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.Ĭompeting interests: The authors have declared that no competing interests exist. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Cancer Institute, or the National Institutes of Health. įunding: The project described was supported in part by Awards Number R01CA134451 (PIs: Gurcan, Lozanski), U24CA199374 (PI: Gurcan), and U01CA198945 from the National Cancer Institute. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.ĭata Availability: All files are available from DeepFocus image databaset (DOI: ) and the source code is available from. Received: SeptemAccepted: SeptemPublished: October 25, 2018Ĭopyright: © 2018 Senaras et al. PLoS ONE 13(10):Įditor: Chung-Ming Lo, Taipei Medical University, TAIWAN DeepFocus has the potential to be integrated with whole slide scanners to automatically re-scan problematic areas, hence improving the overall image quality for pathologists and image analysis algorithms.Ĭitation: Senaras C, Niazi MKK, Lozanski G, Gurcan MN (2018) DeepFocus: Detection of out-of-focus regions in whole slide digital images using deep learning. When trained and tested on two independent datasets, DeepFocus resulted in an average accuracy of 93.2% (± 9.6%), which is a 23.8% improvement over an existing method. DeepFocus was trained by using 16 different H&E and IHC-stained slides that were systematically scanned on nine different focal planes, generating 216,000 samples with varying amounts of blurriness. DeepFocus is built on TensorFlow, an open source library that exploits data flow graphs for efficient numerical computation. The aim of this study is to develop a deep learning based software called, DeepFocus, which can automatically detect and segment blurry areas in digital whole slide images to address these problems. Moreover, this process is both tedious, and time-consuming. These areas are typically identified by visual inspection, which leads to a subjective evaluation causing high intra- and inter-observer variability. Moreover, these artifacts hamper the performance of computerized image analysis systems. Unfortunately, whole slide scanners often produce images with out-of-focus/blurry areas that limit the amount of tissue available for a pathologist to make accurate diagnosis/prognosis. The development of whole slide scanners has revolutionized the field of digital pathology.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |