Md. Kamrul Hasan

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.

In this repository, the source code and segmented mask from semantic segmentation network so-called Dermoscopic Skin Network (DSNet) of the skin lesion have been added.

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.

Almost in every image processing or analysis work, image pre-preprocessing is crucial step. In medical image analysis, pre-processing is a very important step because the further success or performance of the algorithm mostly dependent on pre-processed image. In this lab, we are working with 3D Brain MRI data. In case of working with brain MRI removing the noise and bias field (which is due to inhomogeneity of the magnetic field) is very important part of preprocessing of brain MRI. To do so, we widely used algorithm Anisotropic diffusion, isotropic diffusion which can diffuse in any direction, and Multiplicative intrinsic component optimization (MICO) have been used for noise removal and bias field correction respectfully. Both quantitative and qualitative performance of the algorithms also have been analyzed.

First of all, the brain has been segmented using image Analysis method from the dicom MRI. After that 3D reconstruction has been implemented for the 3D view of the segmented brain region.

Easy understanding of the semantic segmentation using CNN with some recommended links.

We propose a scalable Temporal Attention Module (TAM) to inject cardiac motion information into segmentation models. TAM captures dynamic changes across temporal frames using multi-headed, cross-temporal attention. It is adaptable across imaging modalities, scalable from 2D to 3D, and adds minimal computational overhead.

A spatial feedback attention module (FBA) to enhance unsupervised 3D DLIR

Deep learning image registration for cardiac motion estimation in adult and fetal echocardiography via a focus on anatomic plausibility and texture quality of warped image

The problem definition is to implement from scratch the algorithm of expectation maximization (EM) using Matlab. This algorithm has been applied to brain images (T1 and FLAIR). Three regions have to be segmented: the cerebrospinal fluid (CSF), the gray matter (GM), and the white matter (WM). https://ieeexplore.ieee.org/abstract/document/9420761