Pinned Repositories
Binary-classification-malignant-or-benign-breast-cancer-KNN-GE-lab
A two class classification problem. The dataset contains 569 subjects from each 30 features were extracted and labeled as 1 or 0 to present the malignant or benign breast cancer
Binary-classification-ovarian-cancer-or-healthy-subject-SVM-GE-lab
Support Vector Machines (SVM) review as a powerful class of supervised classification and clinical Proteomics example
Brain-Tumor-Segmentation-and-Survival-Prediction-using-Deep-Neural-Networks
Use of state of the art Convolutional neural network architectures including 3D UNet, 3D VNet and 2D UNets for Brain Tumor Segmentation and using segmented image features for Survival Prediction of patients through deep neural networks.
Chest_X_Ray_Medical_Diagnosis_with_Deep_Learning
A deep learning classifier model for a dataset annotated by consensus among four different radiologists for 5 of our 14 pathologies
Classification-benign-or-malignant-pulmonary-nodules-Random-Forest-GE-lab
Classification problem benign or malignant pulmonary nodules on CT images solved with Random Forest and k-fold cross validated
Data-centric-approach-adressing-class-imbalance-and-overfitting-in-Convolutional-Neural-Network-CNN
The paradigm behind Deep Learning is now facing a shift from model-centric to data-centric. Data intricacies may affect the outcome of a model. Data changes are applied without addressing the model. A simple Convolutional Neural Network (CNN) is being used to show how data augmentation can help with the following common problems: class imbalance and overfitting.
Deep-classifier-skis-cancer-images-into-Melanoma-and-Nevi-classes-Transfer-learning-GE-lab
Aim is to classify skis cancer images into 2 classes (Melonoma and Nevi) by using the concept of transfer learning (feature extraction from a pre-trained model + Multi-Layer Perceptron)
Distance-of-distance-tSNE-BioEng
Medical-biomarkers-mining-Feature-Extraction-GE-lab
Extracting first order statistics and textural features on tumour deliniated PET-CT images for the survival status prediction
Multi-task-models-with-Keras-handwritten-digit-and-color-recognition
A model architecture with two outputs given one input. Two tasks: classifying handwritten digits into 10 classes (0 to 9) and binary classification btw two predominant color channels (red & green)
GingerSpacetail's Repositories
GingerSpacetail/Multi-task-models-with-Keras-handwritten-digit-and-color-recognition
A model architecture with two outputs given one input. Two tasks: classifying handwritten digits into 10 classes (0 to 9) and binary classification btw two predominant color channels (red & green)
GingerSpacetail/Classification-benign-or-malignant-pulmonary-nodules-Random-Forest-GE-lab
Classification problem benign or malignant pulmonary nodules on CT images solved with Random Forest and k-fold cross validated
GingerSpacetail/Medical-biomarkers-mining-Feature-Extraction-GE-lab
Extracting first order statistics and textural features on tumour deliniated PET-CT images for the survival status prediction
GingerSpacetail/Binary-classification-malignant-or-benign-breast-cancer-KNN-GE-lab
A two class classification problem. The dataset contains 569 subjects from each 30 features were extracted and labeled as 1 or 0 to present the malignant or benign breast cancer
GingerSpacetail/Binary-classification-ovarian-cancer-or-healthy-subject-SVM-GE-lab
Support Vector Machines (SVM) review as a powerful class of supervised classification and clinical Proteomics example
GingerSpacetail/Brain-Tumor-Segmentation-and-Survival-Prediction-using-Deep-Neural-Networks
Use of state of the art Convolutional neural network architectures including 3D UNet, 3D VNet and 2D UNets for Brain Tumor Segmentation and using segmented image features for Survival Prediction of patients through deep neural networks.
GingerSpacetail/Chest_X_Ray_Medical_Diagnosis_with_Deep_Learning
A deep learning classifier model for a dataset annotated by consensus among four different radiologists for 5 of our 14 pathologies
GingerSpacetail/Data-centric-approach-adressing-class-imbalance-and-overfitting-in-Convolutional-Neural-Network-CNN
The paradigm behind Deep Learning is now facing a shift from model-centric to data-centric. Data intricacies may affect the outcome of a model. Data changes are applied without addressing the model. A simple Convolutional Neural Network (CNN) is being used to show how data augmentation can help with the following common problems: class imbalance and overfitting.
GingerSpacetail/Deep-classifier-skis-cancer-images-into-Melanoma-and-Nevi-classes-Transfer-learning-GE-lab
Aim is to classify skis cancer images into 2 classes (Melonoma and Nevi) by using the concept of transfer learning (feature extraction from a pre-trained model + Multi-Layer Perceptron)
GingerSpacetail/Distance-of-distance-tSNE-BioEng
GingerSpacetail/GingerSpacetail
Config files for my GitHub profile.
GingerSpacetail/github-slideshow
A robot powered training repository :robot:
GingerSpacetail/GPT-actions
Fabrika Actions for Assistants powered by OpenAI
GingerSpacetail/hello-world
GingerSpacetail/itkwidgets
An elegant Python interface for visualization on the web platform to interactively generate insights into multidimensional images, point sets, and geometry.
GingerSpacetail/Labelling-rules-influence-on-Multinomial-Naive-Bayes-classifier-SPAM-noSPAM
Explore how different strategies affect the performance of a machine learning model by simulating the process of having different labelers label the data
GingerSpacetail/OpenCRISPR
AI-generated gene editing systems
GingerSpacetail/python_for_microscopists
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
GingerSpacetail/SimpliPyTEM-sandbox
Package to make analysis of transmission electron microscopy images simple.
GingerSpacetail/stable-diffusion-webui
Stable Diffusion web UI
GingerSpacetail/test
GingerSpacetail/trackpy
Python particle tracking toolkit
GingerSpacetail/workout_assistant1.0
llama.cpp with BakLLaVA model compares your body pose with the reference and provides natural language feedback