Digital Pathology
Whole-slide imaging and everything it enables: scanners and viewers, image analysis, AI-assisted diagnosis, and telepathology. This hub collects the vendors, platforms, talks, and articles that map the field; the software itself is catalogued in Digital Pathology Software and analysis methods in Image Analysis, with the machine-learning foundations in Machine Learning.
For a focused reading set on robustness, reader effects, quantitative histology, and validation, start with [[digital-pathology-evidence]]. Use [[ai-study-appraisal]] to distinguish what a paper reports from what its design supports.
5 Ways to Make Histopathology Image Models More Robust to Domain Shifts: Exploring a variety of approaches: stain normalization, color augmentation, adversarial domain adaptation, model adaptation, and finetuning
CRoMa: an interactive robustness leaderboard for pathology foundation models
Per-sample robustness distributions, Pareto frontiers and shortcut-susceptibility results for 25 pathology encoders across four multi-centre cohorts. Evaluated in CRoMa.
Digital Pathology & AI in routine clinical practice:From quality control to primary cancer diagnosis
https://www.youtube.com/watch?v=7pRmonus9iM
Microvisioneer
Argenit
X-WOW
QuPath
Mac OS için.svsdosyalarını açacak program ararken bulmuştum QuPath'ı.
QuPath'ın validasyonu kolon tümörlerinde CD3, CD8, p53 ve PD-L1 skorlaması yanısıra H&E preparatlarındaki tümör-stroma oranı ile yapılmış. Örnekler TMA üzerinde, kod ile ve otomatik analiz ile skorlanmış. Önemli bir nokta skorlamalar sağ kalım ile de karşılaştırılmış.
[QuPath: Open source software for digital pathology image analysis
Scientific Reports volume 7, Article number: 16878 (2017)
doi:10.1038/s41598-017-17204-5](https://www.nature.com/articles/s41598-017-17204-5)
QuPath'ın oldukça iyi eğitim dökümanları var:
https://github.com/qupath/qupath/wiki
Makaledeki videolar şunlar:
Makalenin referans verdiği diğer dijital analiz araçlarının makaleleri ise şunlar:
Immunoratio 'yu rutin tanılarda ben kullanıyordum. Elbette tanı için direk oradaki çıkan sayıyı vermiyordum ama kendimi eğitmek için iyi bir araçtı. Immunomembrane 'den ise pek iyi sonuç alamamıştım.
https://digitalpathologyassociation.org/whole-slide-imaging-repository
https://digitalpathologyassociation.org/
Websites
http://cancer.digitalslidearchive.net/
Cancer Digital Slide Archive: an informatics resource to support integrated in silico analysis of TCGA pathology data
https://academic.oup.com/jamia/article/20/6/1091/703483
Johns Hopkins Pathology Unknowns
https://digital.pathology.johnshopkins.edu/repos/451
Softwares
http://www.microvisioneer.com/
Easy Scanner
https://twitter.com/argenitt/status/814824189345624064
Smartphone Whole Slide Imaging(sWSI) Demo--Low Cost Slide Scanner.
https://www.youtube.com/watch?v=orcYKy19mjQ
Google's interest in digital pathology is very important for our field. See 55th minute
https://youtu.be/Y2VF8tmLFHw?t=55m11s
https://research.googleblog.com/2017/03/assisting-pathologists-in-detecting.html
Detecting Cancer Metastases on Gigapixel Pathology Images
https://arxiv.org/abs/1703.02442
Manual Microscope Image Stitching
https://www.meyerinst.com/digital/image-stitching/
Motic EASY SCAN PRO Pathology Slide Scanner
https://www.viewsiq.com/panoptiq
Metadata matters: access to image data in the real world
http://jcb.rupress.org/content/189/5/777
Detecting cancer in real-time with machine learning
https://www.youtube.com/watch?v=9Mz84cwVmS0
An Augmented Reality Microscope for Cancer Detection
An Augmented Reality Microscope for Real-time Automated Detection of Cancer
About the Usage of Digital Pathology
Whole Slide Imaging Versus Microscopy for Primary Diagnosis in Surgical Pathology: A Multicenter Blinded Randomized Noninferiority Study of 1992 Cases (Pivotal Study).
The Gold Standard Paradox in Digital Image Analysis Manual Versus Automated Scoring as Ground Truth
Arch Pathol Lab Med. 2017 May 30. PMID: 28557614 DOI: 10.5858/arpa.2016-0386-RA
Single slide scanner
In this section
In this section
Last updated