This 90-minute workshop is a hands-on introduction to computational pathology both for pathologists and for computer scientists. Participants can choose according to their expertise between three tracks where they will, in small groups, analyse histological images interactively, using scripted image processing, or using AI techniques:
Whole-Slide Image Analysis with QuPath
In this tutorial “WSI Analysis with QuPath”‚ we will explore the open source software QuPath*, a free to use platform, which provides tools for analysis of scanned histopathological slides, so called whole slide images (WSI). You will learn: (1) How to install QuPath and use it for viewing and annotating a WSI. (2) How to train the AI-based classification algorithm, which is provided by QuPath, so that this algorithm can find tumor and non-tumor areas on a WSI. (3) How to use QuPath to determine the Ki-67 index, a well known method for assessment of cancer cell proliferation in various tumors. Neither programming skills nor pathology knowledge are needed to participate in this tutorial.
Participants should bring their own laptop.
Mitosis Detection using Image Processing Techniques in Python
In “Mitosis Detection using Image Processing Techniques in Python” we gain a fundamental understanding of basic image processing techniques using mitosis detection in PHH3 slides as an example. We will cover the following topics: a)Digital image representation, b) Basic operations (color deconvolution, thresholding, morphological operators and segmentation) c) Extraction of geometrical and statistical features d) Classification of mitosis candidates
Python knowledge is useful but not mandatory, as the concepts of image processing are the main focus.
Histology Toy Example on Machine Learning
In the tutorial “Histology Toy Example Machine Learning,” we will teach a computer to distinguish between tissue images of two classes. You will setup a simple machine learning pipeline consisting of learning, applying and displaying the results. You will learn to interpret the results, the relationship of model complexity and training data as well as the importance of testing to detect some pitfalls of binary classifiers. To participate, you should have registered a google account in advance and should be willing to read (and maybe modify) a few lines of Python code.
Please register for this workshop for free here: https://docs.google.com/forms/d/e/1FAIpQLSdI6Rn68dINRQWR6xJseasn6v1QWaSTSas-dHTSiTvqGA_UGA/viewform
Whole-Slide Image Analysis with QuPath
In this tutorial “WSI Analysis with QuPath”‚ we will explore the open source software QuPath*, a free to use platform, which provides tools for analysis of scanned histopathological slides, so called whole slide images (WSI). You will learn: (1) How to install QuPath and use it for viewing and annotating a WSI. (2) How to train the AI-based classification algorithm, which is provided by QuPath, so that this algorithm can find tumor and non-tumor areas on a WSI. (3) How to use QuPath to determine the Ki-67 index, a well known method for assessment of cancer cell proliferation in various tumors. Neither programming skills nor pathology knowledge are needed to participate in this tutorial.
Participants should bring their own laptop.
Mitosis Detection using Image Processing Techniques in Python
In “Mitosis Detection using Image Processing Techniques in Python” we gain a fundamental understanding of basic image processing techniques using mitosis detection in PHH3 slides as an example. We will cover the following topics: a)Digital image representation, b) Basic operations (color deconvolution, thresholding, morphological operators and segmentation) c) Extraction of geometrical and statistical features d) Classification of mitosis candidates
Python knowledge is useful but not mandatory, as the concepts of image processing are the main focus.
Histology Toy Example on Machine Learning
In the tutorial “Histology Toy Example Machine Learning,” we will teach a computer to distinguish between tissue images of two classes. You will setup a simple machine learning pipeline consisting of learning, applying and displaying the results. You will learn to interpret the results, the relationship of model complexity and training data as well as the importance of testing to detect some pitfalls of binary classifiers. To participate, you should have registered a google account in advance and should be willing to read (and maybe modify) a few lines of Python code.
Please register for this workshop for free here: https://docs.google.com/forms/d/e/1FAIpQLSdI6Rn68dINRQWR6xJseasn6v1QWaSTSas-dHTSiTvqGA_UGA/viewform
Maria D. Lozano and Alex Haragan
In this Roche sponsored symposium, we will present applications of the uPath PD-L1 (SP263) image analysis for NSCLC algorithm. Maria D. Lozano MD, PhD, MIAC, Department of Pathology, Clinica University of Navarra. Pamplona, Spain and Alex Haragan MD, Pathologist, MBChB, PhD. Royal Liverpool University Hospital will present data on the performance of the uPath PD-L1 (SP263) image analysis for NSCLC algorithm in assessing PD-L1 status in lung cancer and describe the utility of AI and image analysis in evaluating PD-L1.
In this Roche sponsored symposium, we will present applications of the uPath PD-L1 (SP263) image analysis for NSCLC algorithm. Maria D. Lozano MD, PhD, MIAC, Department of Pathology, Clinica University of Navarra. Pamplona, Spain and Alex Haragan MD, Pathologist, MBChB, PhD. Royal Liverpool University Hospital will present data on the performance of the uPath PD-L1 (SP263) image analysis for NSCLC algorithm in assessing PD-L1 status in lung cancer and describe the utility of AI and image analysis in evaluating PD-L1.
Juan A. Retamero
AI models can improve pathologists’ diagnostic performance, but these models must be trained correctly. To be applied for clinical use, AI models must be fully generalizable and ensure their output is not affected by patient variables, preanalytical factors, or other issues.
This pre-conference will also be livestreamed. Please register for free here: https://www.workcast.com/register?cpak=9354683773548543
AI models can improve pathologists’ diagnostic performance, but these models must be trained correctly. To be applied for clinical use, AI models must be fully generalizable and ensure their output is not affected by patient variables, preanalytical factors, or other issues.
This pre-conference will also be livestreamed. Please register for free here: https://www.workcast.com/register?cpak=9354683773548543
What the Workshop is about: Should we consider digitisation of intraoperative analyses?
In surgical pathology, digitisation does not seem to be nearly as widespread as in clinical pathology. In my presentation, I will talk about why this is the case and, more importantly, what pathologists can gain from digitisation and telepathology in the context of intraoperative consultations.
What to expect at the workshop:
You will also learn why Whole Slide Images (WSI) are not necessarily beneficial for intraoperative work, workflow considerations and what else can be done to bring rapid intraoperative workflows into the digital age.
Structure of the workshop:
At the workshop you will be able to see live how the device works and see for yourself how easy it is to use by trying it out.
Don't hesitate to bring your own slides and scan them under our microscope!
Please register for this workshop for free here: https://www.linkedin.com/events/6930460283177951232/
In surgical pathology, digitisation does not seem to be nearly as widespread as in clinical pathology. In my presentation, I will talk about why this is the case and, more importantly, what pathologists can gain from digitisation and telepathology in the context of intraoperative consultations.
What to expect at the workshop:
You will also learn why Whole Slide Images (WSI) are not necessarily beneficial for intraoperative work, workflow considerations and what else can be done to bring rapid intraoperative workflows into the digital age.
Structure of the workshop:
At the workshop you will be able to see live how the device works and see for yourself how easy it is to use by trying it out.
Don't hesitate to bring your own slides and scan them under our microscope!
Please register for this workshop for free here: https://www.linkedin.com/events/6930460283177951232/
Bruno Märkl and Martin Kristensson
Prof. Märkl will discuss the need for digital transformation in pathology and share his department’s experiences with setting up a digital workflow as well as the challenges they encountered on the way. An outlook on what digital pathology can do will conclude the talk.
Following this, Martin Kristensson will give an overview of how Visiopharm’s AI-based CE-IVD APPs and Qualitopix support pathology labs.
Prof. Märkl will discuss the need for digital transformation in pathology and share his department’s experiences with setting up a digital workflow as well as the challenges they encountered on the way. An outlook on what digital pathology can do will conclude the talk.
Following this, Martin Kristensson will give an overview of how Visiopharm’s AI-based CE-IVD APPs and Qualitopix support pathology labs.
Emmanuel Pirson, Florian Hein, and Martin Weihrauch
Experience how you can work efficiently with digital pathology: from scanning slides with the NanoZoomer® S360 to using the convenient diagnostic platform PathoZoom® Digital Lab. If you use both, you can rely on an optimal workflow. It starts with the automatic quality check of the prepared slides. It continues with barcode marking and automatic scanning of up to 82 slides per hour with up to 40x magnification. By digitizing the image data, the cases can be optimally distributed and tracked by your medical team on a daily basis. Diagnostics take place on the screen - PC/laptop, tablet, or even on the go via smartphone. You can use helpful tools such as measurement function, annotations, high-power field measurement, and much more. Learn more about these forward-looking solutions for routine diagnostics in the workshop.
Please register for this workshop for free: https://www.hamamatsu-news.de/promo/ecdp/
Experience how you can work efficiently with digital pathology: from scanning slides with the NanoZoomer® S360 to using the convenient diagnostic platform PathoZoom® Digital Lab. If you use both, you can rely on an optimal workflow. It starts with the automatic quality check of the prepared slides. It continues with barcode marking and automatic scanning of up to 82 slides per hour with up to 40x magnification. By digitizing the image data, the cases can be optimally distributed and tracked by your medical team on a daily basis. Diagnostics take place on the screen - PC/laptop, tablet, or even on the go via smartphone. You can use helpful tools such as measurement function, annotations, high-power field measurement, and much more. Learn more about these forward-looking solutions for routine diagnostics in the workshop.
Please register for this workshop for free: https://www.hamamatsu-news.de/promo/ecdp/