Helmholtz Imaging CONNECT

Go back Home Experts K. Gotkowski

MR. Karol Gotkowski

Deutsches Krebsforschungszentrum, Applied Computer Vision Lab

Interested in deep interactive learning, active learning, semantic/instance segmentation, object detection, interpretability, image manipulation detection. Working with both 2D and 3D data.

Publications

M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning

Gotkowski K, Gonzalez C, Bucher A, Mukhopadhyay A - arXiv - 2020

10.48550/arXiv.2007.00453

Fake News Detection by Image Montage Recognition

Steinebach M, Gotkowski K, Liu H - Proceedings of the 14th International Conference on Availability, Reliability and Security - 2019

10.1145/3339252.3341487

Send mail to Karol Gotkowski (karol.gotkowski@dkfz-heidelberg.de)

mail form

Mail sender *

Mail subject *

Mail text *

Send a copy of my message to my own e-mail address.

Deutsches Krebsforschungszentrum - Heidelberg

Weblinks

Git
helmholtz-imaging.d…

Karol Gotkowski in Helmholtz Imaging CONNECT:

Application

Active Learning

Active learning is a special case of machine learning in which a learning algorithm can interactively query a human user (or some other information source), to label new data points with the desired outputs. The …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 4 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 8 ➤Solutions: 0

Application

COVID-19 Lesion Segmentation

Semantic segmentation of Ground Glass Opacities (GGO) in CT images of patients diagnosed with COVID-19.

Resources used
MosMedData: Chest CT Scans with COVID-19 Related Findings Dataset
S.P. Morozov, A.E. Andreychenko, N.A. Pavlov, A.V. Vladzymyrskyy, N.V. …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 2 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 1 ➤Experts: 3 ➤Solutions: 0

Application

Deep Interactive Learning

Deep interactive learning or deep interactive segmentation tries to reduce the annotation effort of the expert when annotating new image data. By inferring a refined prediction from an already existing annotation and additional user input, …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 3 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 4 ➤Solutions: 0

Application

Instance Segmentation

In digital image processing and computer vision, image segmentation is the process of partitioning a digital image into multiple image segments, also known as image regions or image objects (sets of pixels). The goal of …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 3 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 10 ➤Solutions: 2

Application

Interpretability

Explainable AI (XAI), often overlapping with interpretable AI, or explainable machine learning (XML), either refers to an artificial intelligence (AI) system over which it is possible for humans to retain intellectual oversight, or refers to …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 2 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 2 ➤Solutions: 0

Application

Mineral Particle Composition Identification

Mineralogist often deal with samples of unknown minerals. In order to identify them, the minerals are crushed, CT scanned and its particles segmented. Based on the segmentation, the compositon of the particles is identifed.

Resources …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 3 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 1 ➤Experts: 3 ➤Solutions: 0

Application

Nodule Detection

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 2 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 2 ➤Solutions: 0

Application

Object Detection

Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 7 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 12 ➤Solutions: 1

Application

Semantic Segmentation

Semantic segmentation refers to classification of individual pixels in an image to a set of predefined categories/classes. Semantic segmentation is a fundamental type of image analysis that has a plethora of applications across all imaging …

In Helmholtz Imaging CONNECT
➤Facilities: 0 ➤Centers: 8 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 7 ➤Experts: 15 ➤Solutions: 4

Modality

Computed tomography (CT)

Computed tomography (CT) is a non-invasive medical imaging technique allowing a detailed internal view of body structures.
A CT measures X-ray attenuations by different tissues inside the body by using a rotating X-ray tube and …

In Helmholtz Imaging CONNECT
➤Applications: 5 ➤Facilities: 1 ➤Centers: 7 ➤Instruments: 1 ➤Labs: 2 ➤Experts: 21 ➤Solutions: 5

Modality

Magnetic resonance imaging (MRI)

Magnetic resonance imaging (MRI) is a medical imaging technique used in radiology to form pictures of the anatomy and the physiological processes inside the body. MRI scanners use strong magnetic fields, magnetic field gradients, and …

In Helmholtz Imaging CONNECT
➤Applications: 4 ➤Facilities: 2 ➤Centers: 8 ➤Instruments: 1 ➤Labs: 4 ➤Experts: 16 ➤Solutions: 1

No facility found.

Center

Deutsches Krebsforschungszentrum (DKFZ)

More than 450,000 people are diagnosed with cancer each year in Germany. Cancer is a disease that poses enormous challenges to research, because every cancer is different and its course can vary immensely even from …

In Helmholtz Imaging CONNECT
➤Applications: 40 ➤Facilities: 0 ➤Instruments: 6 ➤Labs: 17 ➤Modalities: 30 ➤Experts: 29 ➤Solutions: 9

No instrument found.

Lab

Applied Computer Vision Lab

The Helmholtz Imaging Service Unit ‘Applied Computer Vision Lab’ supports Helmholtz researchers in the application of AI algorithms to their custom image analysis problems. Our services include designing tailored AI solutions, consulting in training data …

In Helmholtz Imaging CONNECT
➤Applications: 1 ➤Facilities: 0 ➤Centers: 3 ➤Instruments: 0 ➤Modalities: 0 ➤Experts: 6 ➤Solutions: 5

Solution

Computer Vision Experimentation Frameworks - Generalized-YOLOv5

Generalized-YOLOv5 is a modified version of YOLOv5. YOLOv5 itself is a realtime object detection framework designed for natural images. Our Generalized-YOLOv5 version has two crucial extensions. First, an extension that generalizes YOLOv5 also to non-natural …

In Helmholtz Imaging CONNECT
➤Applications: 0 ➤Facilities: 0 ➤Centers: 0 ➤Instruments: 0 ➤Labs: 0 ➤Modalities: 0 ➤Experts: 4