andreped Goto Github PK

followers: 109.0 following: 279.0 repos: 328.0 gists: 10.0

Name: André Pedersen

Type: User

Company: Sopra Steria

Bio: Senior ML Engineer @SopraSteria

Location: Trondheim, Norway

Blog: https://andreped.dev

Hello there! 👋

Working in R&D focusing on deep learning, computer vision, large language models, software development, and statistical analysis.

🏡 Homepage | :link: Google Scholar | :computer: LinkedIn | 🧙‍ ResearchGate

Selected open-source projects within medicine and other applications

Radiology (CT/MRI/FFDM): Raidionics, AeroPath, neukit, DDMR, livermask, GSI-RADS, LungTumorMask, DMDetect, PLS-Net, ct_mediastinal_structures_segmentation, mri_brain_tumor_segmentation
Histopathological images (WSI): FastPathology, NoCodeSeg, torchstain, H2G-Net, fast-stain-normalization, FP-DSA-plugin, vsi2tif
Free-text (chat/notes): chatbot-streamlit-demo, ReferenceBot, adverse-events, NLP-MTL
Sensors (mobile): DSS, DeepSleep
Other: FAST, GradientAccumulator, super-ml-pets, breast-cancer-stats, t-loss-tf, ohif4hf
Dataset contributions: AeroPath, NoCodeSeg, LyNoS

Languages and Tools

André Pedersen's Projects

quickpkg

wrapper for pkgbuild to quickly build simple packages from an installed app, a dmg or zip archive.

qupath

QuPath - Bioimage analysis & digital pathology

qupath-extension-sam

QuPath extension for Segment Anything Model (SAM)

qupath-project-fixer

Simple program that makes it possible to directly run other people's qupath projects, without the need to re-importing all images again.

raidionics-dependencies

Pre-compiled libraries needed for building Raidionics

raidionics-slicer

Automatic segmentation and generation of standardized clinical reports for the most common brain tumors, using MRI volumes

raidionics_rads_lib

Processing backend for Raidionics to execute pipelines performing tumor segmentation and standardized reporting (RADS)

randstainna

RandStainNA: Simple and efficient augmentations for histology [MICCAI 2022]

readthedocs.org

The source code that powers readthedocs.org

Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs, Bitmaps.

referencebot

KnowledgeGPT + Azure OpenAI = <3

reg-cyclical-self-train

Unsupervised 3D registration through cyclical self-training

remix

research-information-system

How to setup a research information system with PACS and RIS components

resume.github.com

Resumes generated using the GitHub informations

retccl

rho-loss

rickstaa

My personal readme.md

robustvit

[NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows to finetune the explainability maps of Vision Transformers to enhance robustness.