Nikos Tsiknakis's repositories
multiresolution-clam
This is the repo for our EMBC-2023 paper, "Multiresolution Self-Supervised Feature Integration via Attention Multiple Instance Learning for Histopathology Analysis"
alvis-intro
Introduction slides for Alvis
Atten_Deep_MIL
Attention-based Deep MIL implementation and application
AttentionDeepMIL
Implementation of Attention-based Deep Multiple Instance Learning in PyTorch
tsik.me
My personal website powered by Jekyll and al-folio.
CLAM
Data-efficient and weakly supervised computational pathology on whole slide images - Nature Biomedical Engineering
DeepLearningExamples
Deep Learning Examples
DeepPATH
Classification of Lung cancer slide images using deep-learning
evaluateCutpoints
evaluateCutpoints is a R package for multiple cutpoints determination in biomedical research.
hass-config
✨ A different take on designing a Lovelace UI (Dashboard)
he_preprocessing
A collection of preprocessing tools for H&E slide analysis, developed and used for my PhD project.
histocartography
Histocartography is a framework bringing together AI and Digital Pathology
machine-learning-articles
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
Machine-Learning-Collection
A resource for learning about ML, DL, PyTorch and TensorFlow. Feedback always appreciated :)
multiresolution_histopathology
Code for paper: "Unveiling the Power of Model-Agnostic Multiscale Analysis for Enhancing Artificial Intelligence Models in Breast Cancer Histopathology Images"
my_utils
Several utility functions used in all my (deep-learning) projects.
NeighborhoodCoordination
Code accompanying our manuscript "Coordinated cellular neighborhoods orchestrate antitumoral immunity at the colorectal cancer invasive front"
pathology-he-auto-augment
H&E tailored Randaugment: automatic data augmentation policy selection for H&E-stained histopathology.
pathology-snippets
Pieces of code likely to be useful as part of larger projects
pathology-streaming-pipeline
Use streaming to train whole-slides images with single image-level labels, by reducing GPU memory requirements with 99%.
pathology-whole-slide-data
A package for working with whole-slide data including a fast batch iterator that can be used to train deep learning models.
ProLesA-Net
The current repository serves as the placeholder for the ProLesA-Net model
PytorchDigitalPathology
An implementation of Unet for pytorch designed for digital pathology segmentation
QuPath-IntelliJ-Template
This is a template project for QuPath development on IntelliJ
spams-python
A rehost of the python version of SPArse Modeling Software (SPAMS)
stainlib
Python 3 library for the augmentation & normalization of H&E images
XAI
Papers and code of Explainable AI esp. w.r.t. Image classificiation