Tuberculosis MODS Image Diagnosis - Test

Best regards. Here I enable an online tuberculosis diagnosis using the Microscopic observation drug susceptibility (MODS)  assay [1]. This tool has been developed using Convolutional Neural Networks , with 15 layers. The performance this model got:
  • Dev set.- Images: 256, specificity: 0.8828, sensitiviy: 0.7969, accuracy: 0.8398.
  • Test-set: Images 5104, specificity: 0.5329, sensitivity: 0.9510, accuracy: 0.7420
This is a test example to put future models online. This is part of the work being developed at Cayetano Heredia Peruvian Univeristy, R&D Laboratories, Bioinformatics and Molecular Biology laboratory. This is not the best performance achieved though.

This tool will classify a MODS image into positive or negative and will show the score for this selection. 


The backend is hosted in heroku with a free plan so it might be slow, have failures of communication and might really take a long time for the first run after a long period of time.

How to use this tool

  1. First check if there is connectivity with the server by pressing the button Send test data to server this will send a small amount of data to the server and if it is UP you will receive a message Test data received 200. If it remains in Sending test data for a long time, open the web developer console to see if there is any errors, this is a tool in your web browser, if it results too complicated try again later maybe the server is busy or I am doing some maintenance. 
  2. Once you have validated that the server is running, upload an image and then press Send Image for processing. This is might take a while, 1 to 2 minutes, if it is taking too long repeat the step 1 to see if you may lose communication with the server.
Some notes: The model was trained with 256x256 images, so this interface will reshape your image to this dimensions. In the best case try to upload images with same width and length. 

The tool


Send image for processing
Send test data to server

References


 [1] D. A. J. Moore et al., “Microscopic observation drug susceptibility assay, a rapid, reliable diagnostic test for multidrug-resistant tuberculosis suitable for use in resource-poor settings,” J. Clin. Microbiol., vol. 42, no. 10, pp. 4432–4437, Oct. 2004.


Comentarios

Publicar un comentario

Entradas populares de este blog

Image segmentation by color mean and standard deviation

I present an online segmentation javascript implementation of segmentation given the r,g,b means an standard deviation of each one. Since it is javascript it means it will run on your browser using your computation power, thus, you should test it with small images first.   The pixels that fall in the range [ mean - std; mean + std ] will remain in the visualization. Those who don't, will be turned into black. The std factor will multiply the std value of every channel. It is easier to follow the changes by changing a factor than the std values independently.  Upload Image File: Controls Mean: Red Mean Green Mean Blue Mean Controls Std: Red std Green std Blue std Std factor
Leer más

Tensorflow Batch norm not working

Have you experienced that when using  tf.contrib.layers.batch_norm during test time, the performance is diminished or is completely a mess? If yes, this post is for you. Quick summary: 1) As suggested in [1]:   you have do add this additional code:   update_ops = tf . get_collection ( tf . GraphKeys . UPDATE_OPS )   with tf . control_dependencies ( update_ops ):     train_op = optimizer . minimize ( loss ) 2) You have to use a placeholder to indicate that you are training or not, so you put this in the batch_norm param  is_training = your_place_holder, True for training. 3) If after this it doesn't show a good behavior, change the default  decay = 0.999, to a lower value such as  0.5. Other way to apply batch norm is presented in [2], for a manual setup. Nonetheless, if by using this second approach you still have a bad performance, use the point 3). If you want to use this second approach with Convolutional Neural Netw...
Leer más

Google Chart Sankey Diagram online for non software developers

Imagen
I saw lots of tutorials of how to create a Sankey diagram but I couldn't find a quick way to see my data without installing or configuring parameters. Thus, here I present a Sankey Diagram to visualize your data. In case you are a software developer this may result to be something simple for you, but in case you don't have programming skills but want a Sankey diagram, this post is for you. You have to upload a CSV file, comma separated in the format: NodeA, NodeB, Weight An example of a CSV file could be: Root A,Branch X,3 Root B,Branch X,8 Root B,Branch Y,2 Root B,Branch Z,3 Branch X,End 1,19 Branch X,End 2,2 Branch X,End 3,4 Branch Y,End 1,10 Branch Y,End 4,17 Root B,Branch ZX,4 Branch ZX,End 1,1 This will create the following Graph: Instructions of use: Way one Click on Chose File and search for your CSV file. In the text field you will see your data loaded. You should see "NodeX1,NodeY1,N1;NodeX2,NodeY2,N2... Click in the button Process ...
Leer más