Md. Kamrul Hasan's Projects
Keras 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation
Code examples for training AlexNet using Keras and Theano
This project presents a Single Input Multiple Output (SIMO) deep convolutional neural network, a so-called ART-Net (Augmented Reality Tool Network) consisting of an encoder-decoder architecture to obtain the surgical tool detection, segmentation, and geometric features concurrently in an end-to-end fashion.
:metal: awesome-semantic-segmentation
3D Kinect Scanner
In this project, background tissue types, class of abnormality types, severity class types of the breast will be implemented from the single CNN network.
Cancer classification, detection and segmentation
Visualizing intermediate activation in Convolutional Neural Networks with Keras
COVID-19 imaging-based AI paper collection
A robust CNN-based network, called CVR-Net (Coronavirus Recognition Network), for the automatic recognition of the coronavirus from CT or X-ray images.
Cyclic learning rate TensorFlow implementation.
Multi-scale, Data-driven and Anatomically Constrained Deep Learning Image Registration for Adult and Fetal Echocardiography
In this article, we proposed a new labeled diabetes dataset from a South Asian country (Bangladesh). Additionally, we recommended an automated classification pipeline, introducing a weighted ensemble of several Machine Learning (ML) classifiers: Naive Bayes (NB), Random Forest (RF), Decision Tree (DT), XGBoost (XGB), and LightGBM (LGB). The critical hyperparameters of these ML models are tuned using a grid search hyperparameter optimization approach. Missing values imputation, feature selection, and K-fold cross-validation were also incorporated into the designed framework.
A robust framework was proposed where outlier rejection, filling the missing values, data standardization, K-fold validation, and different Machine Learning (ML) classifiers were used. Finally, to improve the result, weighted ensembling of different ML models also proposed.
We propose an end-to-end encoder-decoder network, named DRNet, for the segmentation and localization of OD and Fovea centers. In our DRNet, we propose a skip connection, named residual skip connection, for compensating the lost spatial information due to pooling in the encoder.
A list of all public EEG-datasets
This is our new multi-joint annotation for EndoVis MICCAI Challenge dataset ( https://endovissub-instrument.grand-challenge.org/), which can be used for multi-instrument pose estimation.
Deep face recognition with Keras, Dlib and OpenCV
This repository is dedicated to classify images (T-shirt/top, Trouser, Pullover, Dress, Coat, Sandal, Shirt, Sneaker, Bag and Ankle boot) using CNN
a PGF/TikZ-based LaTeX package for drawing (linguistic) trees
Git extension for versioning large files
Implementation of Segnet, FCN, UNet and other models in Keras.
Perform image segmentation and background removal in javascript using superpixes