cell-classification

Inference code for GrEp : Graph-based epithelial cell sub-classification refinement

Project on Neural Networks for Nanoparticle Breast Cell Classification - Machine Learning (MSc), supervised by Prof. C. Sansone and PhD M. Gravina(2024)

An intuitive web app for cell image segmentation, labeling, classification, active learning, prediction correction, visualization, and ML model management.

Deep learning for melanoma histopathology: nuclei classification and tissue segmentation using CellViT++, nnU-Net, and HoVer-Net.

Cervical Cancer Classification Repository

Notes about single cell technology and computational analysis methods, including but not limitted to Genome, Epigenome, Transcriptome, Morphology, Connectome and the integrative analysis of information from these layers.

Non invasive live cell cycle monitoring using a supervised deep neural autoencoder onquantitative phase images

TensorFlow implementation of CNN architectures for microscopic malaria cell image classification

Computer vision single cell Tradescantia clone 4430 set of 204 images.

Comparative machine-learning analysis for clustering and cell classification using single-cell RNA-seq gene-expression data.

CNN-based bioimage classification for biological phenotype detection using machine learning and Explainable AI

An app for segmentation and classification of images of cells from optical microscope. This project uses marker controlled watershed (openCv), and pretrained ResNet-50 model (tensorflow)

Repository for publication outlining a number of computational models for complex wound analysis in both mice and humans.

Deep learning research (PyTorch) for cancer disease diagnosis using medical image analysis and cell classification.

Project for the Applied Machine Learning (EI70360) class at TUM Summer Semester 2023.

Interactive modules to digitally annotate H&E whole slide images, construct cell and tissue level features and classify cell types. Specifically for a case study of differentiating borderline and high-grade serous ovarian tumors.

Cell image analysis pipeline for RPE cell identification, counting and maturity classification

DualU-Net is a multi-task deep learning model for nuclei segmentation and classification. It employs a dual-decoder design that predicts both pixel-wise segmentation maps and Gaussian-based centroid density maps, enabling fast and accurate instance segmentation in histopathological images.

Predict which cell is cancerous with 96% accuracy using SVM machine learning algorithm.