Skip to main content

Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks

In this paper, the authors explore the use of Deep Convolutional Neural Networls (DCNN) in classifying Tuberculosis (TB) in chest radiographs. One of the advantages of deep learning is its ability to excel with high dimensional datasets, such as images, which can be represented at multiple levels. 

Dataset

Four deidentified HIPAA-compliant datasets were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs.

DCNN Models and Training

AlexNet and GoogLeNet models, including pre-trained (on ImageNet from Caffe Model Zoo) and untrained models were used in the study. It was found that the AUCs of the pretrained networks were greater. The following solver parameters were used for training: 120 epochs; base learning rate for untrained models and for pretrained models, 0.01 and 0.001, respectively with stochastic gradient descent.  Both of the DCNNs in this studied used dropout or model regularization strategies to help overcome overfitting.

Data Augmentation

The following data augmentation techniques further increased the performance

  1. Random cropping of 227x227
  2. Mean subtraction and mirror images
  3. Rotation of 90, 180 and 270.
  4. Contrast Limited Adaptive Histogram Equalization processing

Ensembling


The ensembling technique was used to increase the AUC even further. Ensembles were performed by taking different weighted averages of the probability scores generated by the classifiers 
The best performing ensemble model had an AUC of 0.99. Refer below the table borrowed from the paper for complete results

 The sensitivity of pre-trained AlexNet was 92.0% and the specificity was 94.7%. The sensitivity of pre-trained GoogLeNet was 92.0% and the specificity was 98.7%. The sensitivity of the ensemble was 97.3% and the specificity was 94.7%. 

Radiologist-augmented approach

This is were the paper takes turn to beyond the realms of deep learning, were they use a certain human to classify the images were the models fail.

 For cases where the AlexNet and GoogLeNet classifiers had disagreement, an independent board-certified cardiothoracic radiologist (B.S., with 18 years of experience) blindly interpreted the images as either having manifestations of TB or as normal. This resulted in a sensitivity of 97.3% and a specificity of 100%.

Comments

Post a Comment

Popular Posts

A non-local algorithm for image denoising

Published in   2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, this paper introduces two main ideas Method noise Non-local (NL) means algorithm to denoise images Method noise It is defined as the difference between the original (noisy) image and its denoised version. Some of the intuitions that can be drawn by analysing method noise are Zero method noise means perfect denoising (complete removal of noise without lose of image data). If a denoising method performed well, the method noise must look like a noise and should contain as little structure as possible from the original image The authors then discuss the method noise properties for different denoising filters. They are derived based on the filter properties. We will not be going in detail for each filter as the properties of the filters are known facts. The paper explains those properties using the intuitions of method noise. NL-means idea Denoised value at...
Post a Comment
Read more

4D Panoptic LiDAR Segmentation (4D-PLS)

Introduction In the realm of computer vision, LiDAR segmentation remains a challenging area. Often, we have to rely on the downscaling of scans, followed by individual detections and temporal associations. The recently published paper, "4D Panoptic LiDAR Segmentation (4D-PLS)", seeks to address these challenges with an innovative approach and techniques, offering a fresh perspective on LiDAR segmentation. LiDAR Segmentation: Challenges and Opportunities LiDAR segmentation, specifically sequence segmentation, is a task with substantial hurdles. Due to memory constraints, scans must be downscaled, even for a single scan. This results in detection being performed on individual scans, and then followed by temporal association. It's a piecemeal approach that lacks efficiency and accuracy.  A New Take: The 4D-PLS Framework This is where the 4D-PLS approach comes into play. Drawing inspiration from space-time, the authors developed a system to overlap 4D volumes, assigning seman...
Post a Comment
Read more

TX-CNN: DETECTING TUBERCULOSIS IN CHEST X-RAY IMAGES USING CONVOLUTIONAL NEURAL NETWORK

In this paper , the authors propose a method to classify tuberculosis from chest X-ray images using Convolutional Neural Networks (CNN). They achieve a classification accuracy of 85.68%. They attribute the effectiveness of their approach to shuffle sampling with cross-validation while training the network. Methodology Convolutional Neural Network This has been the ultimate tool for researchers and engineers for computer vision tasks. It has been widely used for many general purpose image and video related tasks. There are many great resources to learn about them. I will link a few of them at the end of this post. In this paper, the authors study the famous AlexNet and GoogLeNet architectures in classifying tuberculosis images. A CNN model usually consists of convolutional layers, pooling layers and fully connected layers. Each layer is connected to the previous layers via kernels or filters. A CNN model learns parameters of the kernel to represent global and local features ...
Post a Comment
Read more