Automatic detection of tuberculosis related abnormalities in Chest X-ray Images using hierarchical feature extraction scheme
ABSTARCT :
Machine learning techniques have been widely used for abnormality detection in medical images. Chest X-ray images (CXR) are among the non-invasive diagnostic tools used to detect various disease pathologies. The ambiguous anatomical structure of soft tissues is one of the major challenges for segregating normal and abnormal images. The main objective of this study is to mimic the expert radiologist’s interpretation procedure in computer-aided diagnosis (CAD) systems. We propose an automatic technique for detection of abnormal CXR images containing one or more pathologies like pleural effusion, infiltration, fibrosis, hila enlargement, dense consolidation, etc. due to tuberculosis (TB). The proposed abnormality detection technique is based on the hierarchical feature extraction scheme in which the features are usedin two-level of hierarchy to categorize healthy and unhealthy groups. In level one the handcrafted geometrical features like shape, size, eccentricity, perimeter, etc. and in level 2 traditional first order statistical feature along with texture features like energy, entropy, contrast, correlation, etc. are extracted from segmented lung-fields. Further, a supervised classification approach is employed on the extracted features to detect normal and abnormal CXR images. The performance of the algorithm is validated on a total of 800 CXR images from two public datasets, namely the Montgomery set and Shenzhen set. The obtained results (accuracy = 95.60 ± 5.07% and area under curve (AUC) = 0.95 ± 0.06 for Montgomery collection, and accuracy = 99.40 ± 1.05% and AUC = 0.99 ± 0.01 for Shenzhen collection) shows the promising performance of the proposed technique for TB detection compared to the existing state of the art approaches. Further, the obtained results are statistically validated using Friedman post-hoc multiple comparison methods, which confirms the significance of the proposed method.
EXISTING SYSTEM :
The use of Image Net pre-trained networks is becoming widespread in the medical imaging community. It enables training on small datasets, commonly available in medical imaging tasks. The recent emergence of a large ChestX-ray dataset opened the possibility for learning features that are specific to the X-ray analysis task.
DISADVANTAGE :
? These CAD systems have limited clinical acceptability due to low accuracy.
? Further, the CAD system, which has the capability of providing accurate pathological decisions and can detect multiple pathologies, is required.
PROPOSED SYSTEM :
In this work, we demonstrate that the features learned allow for better classification results for the problem of Tuberculosis detection and enable generalization to an unseen dataset. To accomplish the task of feature learning, we train aDenseNet-121 CNN on 112K images from the ChestXray14dataset which includes labels of 14 common thoracic pathologies. In addition to the pathology labels, we incorporate meta-data which is available in the dataset: Patient Positioning, Gen-der and Patient Age. We term this architecture Meta Chex Net.As a by-product of the feature learning, we demonstrate state of the art performance on the task of patient Age & Gender estimation using CNN’s. Finally, we show the features learned using ChestXray14 allow for better transfer learning on small scale datasets for Tuberculosis.
ADVANTAGE :
? TB detection network is constructed on top of Meta Chexnet or ChexNet feature layer. We use a single sigmoid activated neuron for the TB class. During the training for TB detection, we fine tune the entire network with the same hyper-parameters as used.
? This is because the automatic chest x-ray analysis needs highly accurate techniques. Higher the accuracy in segmentation of the lungs, higher is the accuracy in classification and detection of diseases like cardiomegaly, pneumonia and other lung related diseases. In recent times, hybrid techniques are being investigated to improve the accuracy of segmentation of lungs.
|