• Corpus ID: 220364485

Automatic semantic segmentation for prediction of tuberculosis using lens-free microscopy images

  title={Automatic semantic segmentation for prediction of tuberculosis using lens-free microscopy images},
  author={Dennis N'unez-Fern'andez and Lamberto Ballan and Gabriel Jim'enez-Avalos and Jorge Coronel and Mirko Zimic},
Tuberculosis (TB), caused by a germ called Mycobacterium tuberculosis, is one of the most serious public health problems in Peru and the world. The development of this project seeks to facilitate and automate the diagnosis of tuberculosis by the MODS method and using lens-free microscopy, due they are easier to calibrate and easier to use (by untrained personnel) in comparison with lens microscopy. Thus, we employ a U-Net network in our collected dataset to perform the automatic segmentation of… 

Figures from this paper

A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification

The improved methods of U-Net are summarized and the existing significances of image segmentation techniques and their improvements that has introduced over the years are listed.



U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

A Modified U-Net Convolutional Network Featuring a Nearest-neighbor Re-sampling-based Elastic-Transformation for Brain Tissue Characterization and Segmentation

The goal of this work was to improve the U-net model by replacing the de-convolution component with an up- sampled by the Nearest-neighbor algorithm and also employing an elastic transformation to augment the training dataset to render the model more robust, especially for the segmentation of low-grade tumors.

Performance of convolutional neural networks for identification of bacteria in 3D microscopy datasets

A 3D convolutional neural network is applied to distinguish bacteria and non-bacterial objects in 3D light sheet fluorescence microscopy images of larval zebrafish intestines, and is found to be as accurate as human experts, outperforms the feature-based methods, and generalizes well to a different bacterial species through the use of transfer learning.

U-Net: deep learning for cell counting, detection, and morphometry

An ImageJ plugin is presented that enables non-machine-learning experts to analyze their data with U-Net on either a local computer or a remote server/cloud service.

Intracranial Vessel Wall Segmentation Using Convolutional Neural Networks

An automated vessel wall segmentation method based on FCN as well as the IVA framework for 3-D intracranial MR VWI would make large-scale quantitative plaque analysis more realistic and promote the adoption of MRVWI in ICAD management.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier]

An overview of the mainstream deep learning approaches and research directions proposed over the past decade is provided and some perspective into how it may evolve is presented.

Face Detection Using Convolutional Neural Networks and Gabor Filters

This paper proposes a method for detecting facial regions by combining a Gabor filter and a convolutional neural network, which yields better classification performance in comparison to the results obtained by the convolutionals alone.

Implementación de un sistema de telediagnóstico de tuberculosis y determinación de multidrogorresistencia basada en el método Mods en Trujillo

  • Perú. Revista Peruana de Medicina Experimental y Salud Publica