Automatic detection of abnormalities in chest radiographs using local texture analysis

Leveraging anatomical constraints with uncertainty for pneumothorax segmentation

Background

Pneumothorax is a medical emergency caused by the abnormal accumulation of air in the pleural space-the potential space between the lungs and chest wall. On 2D chest radiographs, pneumothorax occurs within the thoracic cavity and outside of the mediastinum, and we refer to this area as "lung + space." While deep learning (DL) has increasingly been utilized to segment pneumothorax lesions in chest radiographs, many existing DL models employ an end-to-end approach. These models directly map chest radiographs to clinician-annotated lesion areas, often neglecting the vital domain knowledge that pneumothorax is inherently location-sensitive.

Methods

We propose a novel approach that incorporates the lung + space as a constraint during DL model training for pneumothorax segmentation on 2D chest radiographs. To circumvent the need for additional annotations and to prevent potential label leakage on the target task, our method utilizes external datasets and an auxiliary task of lung segmentation. This approach generates a specific constraint of lung + space for each chest radiograph. Furthermore, we have incorporated a discriminator to eliminate unreliable constraints caused by the domain shift between the auxiliary and target datasets.

Results

Our results demonstrated considerable improvements, with average performance gains of 4.6%, 3.6%, and 3.3% regarding intersection over union, dice similarity coefficient, and Hausdorff distance. These results were consistent across six baseline models built on three architectures (U-Net, LinkNet, or PSPNet) and two backbones (VGG-11 or MobileOne-S0). We further conducted an ablation study to evaluate the contribution of each component in the proposed method and undertook several robustness studies on hyper-parameter selection to validate the stability of our method.

Conclusions

The integration of domain knowledge in DL models for medical applications has often been underemphasized. Our research underscores the significance of incorporating medical domain knowledge about the location-specific nature of pneumothorax to enhance DL-based lesion segmentation and further bolster clinicians' trust in DL tools. Beyond pneumothorax, our approach is promising for other thoracic conditions that possess location-relevant characteristics.

Synergizing Deep Learning-Enabled Preprocessing and Human-AI Integration for Efficient Automatic Ground Truth Generation

The progress of incorporating deep learning in the field of medical image interpretation has been greatly hindered due to the tremendous cost and time associated with generating ground truth for supervised machine learning, alongside concerns about the inconsistent quality of images acquired. Active learning offers a potential solution to these problems of expanding dataset ground truth by algorithmically choosing the most informative samples for ground truth labeling. Still, this effort incurs the costs of human labeling, which needs minimization. Furthermore, automatic labeling approaches employing active learning often exhibit overfitting tendencies while selecting samples closely aligned with the training set distribution and excluding out-of-distribution samples, which could potentially improve the model's effectiveness. We propose that the majority of out-of-distribution instances can be attributed to inconsistent cross images. Since the FDA approved the first whole-slide image system for medical diagnosis in 2017, whole-slide images have provided enriched critical information to advance the field of automated histopathology. Here, we exemplify the benefits of a novel deep learning strategy that utilizes high-resolution whole-slide microscopic images. We quantitatively assess and visually highlight the inconsistencies within the whole-slide image dataset employed in this study. Accordingly, we introduce a deep learning-based preprocessing algorithm designed to normalize unknown samples to the training set distribution, effectively mitigating the overfitting issue. Consequently, our approach significantly increases the amount of automatic region-of-interest ground truth labeling on high-resolution whole-slide images using active deep learning. We accept 92% of the automatic labels generated for our unlabeled data cohort, expanding the labeled dataset by 845%. Additionally, we demonstrate expert time savings of 96% relative to manual expert ground-truth labeling.

Development of Debiasing Technique for Lung Nodule Chest X-ray Datasets to Generalize Deep Learning Models

Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening.

Artificial intelligence-based computer aided detection (AI-CAD) in the fight against tuberculosis: Effects of moving health technologies in global health

Computer Aided Detection software based on Artificial Intelligence (AI-CAD), combined with chest X-rays have recently been promoted as an easy fix for a complex problem: ending TB by 2030. WHO has recommended the use of such imaging devices in 2021 and many partnerships have helped propose benchmark analysis and technology comparisons to facilitate their "market access". Our aim is to examine the socio-political and health issues that stem from using AI-CAD technology in a global health context conceptualized as a set of practice and ideas organizing global intervention "in the life of others". We also question how this technology, which is not yet fully implemented in routine use, may limit or amplify some inequalities in the care of tuberculosis. We describe AI-CAD through Actor-Network-Theory framework to understand the global assemblage and composite activities associated with detection through AI-CAD, and interrogate how the technology itself may consolidate a specific configuration of "global health". We explore the various dimensions of AI-CAD "health effects model": technology design, development, regulation, institutional competition, social interaction and health cultures. On a broader level, AI-CAD represents a new version of global health's accelerationist model centered on "moving and autonomous-presumed technologies". We finally present key aspects in our research which help discuss the theories mobilized: AI-CAD ambivalent insertion in global health, the social lives of its data: from efficacy to markets and AI-CAD human care and maintenance it requires. We reflect on the conditions that will affect AI-CAD use and its promises. In the end, the risk of new detection technologies such as AI-CAD is indeed that the fight against TB could be reduced to one that is purely technical and technological, with neglect to its social determinants and effects.

Automatic Segmentation of Teeth, Crown-Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

BACKGROUND

The aim of our study is to provide successful automatic segmentation of various objects on orthopantomographs (OPGs).

METHODS

8138 OPGs obtained from the archives of the Department of Dentomaxillofacial Radiology were included. OPGs were converted into PNGs and transferred to the segmentation tool's database. All teeth, crown-bridge restorations, dental implants, composite-amalgam fillings, dental caries, residual roots, and root canal fillings were manually segmented by two experts with the manual drawing semantic segmentation technique.

RESULTS

The intra-class correlation coefficient (ICC) for both inter- and intra-observers for manual segmentation was excellent (ICC > 0.75). The intra-observer ICC was found to be 0.994, while the inter-observer reliability was 0.989. No significant difference was detected amongst observers (p = 0.947). The calculated DSC and accuracy values across all OPGs were 0.85 and 0.95 for the tooth segmentation, 0.88 and 0.99 for dental caries, 0.87 and 0.99 for dental restorations, 0.93 and 0.99 for crown-bridge restorations, 0.94 and 0.99 for dental implants, 0.78 and 0.99 for root canal fillings, and 0.78 and 0.99 for residual roots, respectively.

CONCLUSIONS

Thanks to faster and automated diagnoses on 2D as well as 3D dental images, dentists will have higher diagnosis rates in a shorter time even without excluding cases.

Assessing the Impact of Image Resolution on Deep Learning for TB Lesion Segmentation on Frontal Chest X-rays

Deep learning (DL) models are state-of-the-art in segmenting anatomical and disease regions of interest (ROIs) in medical images. Particularly, a large number of DL-based techniques have been reported using chest X-rays (CXRs). However, these models are reportedly trained on reduced image resolutions for reasons related to the lack of computational resources. Literature is sparse in discussing the optimal image resolution to train these models for segmenting the tuberculosis (TB)-consistent lesions in CXRs. In this study, we investigated the performance variations with an Inception-V3 UNet model using various image resolutions with/without lung ROI cropping and aspect ratio adjustments and identified the optimal image resolution through extensive empirical evaluations to improve TB-consistent lesion segmentation performance. We used the Shenzhen CXR dataset for the study, which includes 326 normal patients and 336 TB patients. We proposed a combinatorial approach consisting of storing model snapshots, optimizing segmentation threshold and test-time augmentation (TTA), and averaging the snapshot predictions, to further improve performance with the optimal resolution. Our experimental results demonstrate that higher image resolutions are not always necessary; however, identifying the optimal image resolution is critical to achieving superior performance.

Computer-Aided Diagnosis of Coal Workers' Pneumoconiosis in Chest X-ray Radiographs Using Machine Learning: A Systematic Literature Review

Computer-aided diagnostic (CAD) systems can assist radiologists in detecting coal workers' pneumoconiosis (CWP) in their chest X-rays. Early diagnosis of the CWP can significantly improve workers' survival rate. The development of the CAD systems will reduce risk in the workplace and improve the quality of chest screening for CWP diseases. This systematic literature review (SLR) amis to categorise and summarise the feature extraction and detection approaches of computer-based analysis in CWP using chest X-ray radiographs (CXR). We conducted the SLR method through 11 databases that focus on science, engineering, medicine, health, and clinical studies. The proposed SLR identified and compared 40 articles from the last 5 decades, covering three main categories of computer-based CWP detection: classical handcrafted features-based image analysis, traditional machine learning, and deep learning-based methods. Limitations of this review and future improvement of the review are also discussed.

Reliable Sarcoidosis Detection Using Chest X-rays with EfficientNets and Stain-Normalization Techniques

Sarcoidosis is frequently misdiagnosed as tuberculosis (TB) and consequently mistreated due to inherent limitations in radiological presentations. Clinically, to distinguish sarcoidosis from TB, physicians usually employ biopsy tissue diagnosis and blood tests; this approach is painful for patients, time-consuming, expensive, and relies on techniques prone to human error. This study proposes a computer-aided diagnosis method to address these issues. This method examines seven EfficientNet designs that were fine-tuned and compared for their abilities to categorize X-ray images into three categories: normal, TB-infected, and sarcoidosis-infected. Furthermore, the effects of stain normalization on performance were investigated using Reinhard's and Macenko's conventional stain normalization procedures. This procedure aids in improving diagnostic efficiency and accuracy while cutting diagnostic costs. A database of 231 sarcoidosis-infected, 563 TB-infected, and 1010 normal chest X-ray images was created using public databases and information from several national hospitals. The EfficientNet-B4 model attained accuracy, sensitivity, and precision rates of 98.56%, 98.36%, and 98.67%, respectively, when the training X-ray images were normalized by the Reinhard stain approach, and 97.21%, 96.9%, and 97.11%, respectively, when normalized by Macenko's approach. Results demonstrate that Reinhard stain normalization can improve the performance of EfficientNet -B4 X-ray image classification. The proposed framework for identifying pulmonary sarcoidosis may prove valuable in clinical use.

Segmentation and classification on chest radiography: a systematic survey

Chest radiography (X-ray) is the most common diagnostic method for pulmonary disorders. A trained radiologist is required for interpreting the radiographs. But sometimes, even experienced radiologists can misinterpret the findings. This leads to the need for computer-aided detection diagnosis. For decades, researchers were automatically detecting pulmonary disorders using the traditional computer vision (CV) methods. Now the availability of large annotated datasets and computing hardware has made it possible for deep learning to dominate the area. It is now the modus operandi for feature extraction, segmentation, detection, and classification tasks in medical imaging analysis. This paper focuses on the research conducted using chest X-rays for the lung segmentation and detection/classification of pulmonary disorders on publicly available datasets. The studies performed using the Generative Adversarial Network (GAN) models for segmentation and classification on chest X-rays are also included in this study. GAN has gained the interest of the CV community as it can help with medical data scarcity. In this study, we have also included the research conducted before the popularity of deep learning models to have a clear picture of the field. Many surveys have been published, but none of them is dedicated to chest X-rays. This study will help the readers to know about the existing techniques, approaches, and their significance.

Automated COVID-19 detection from X-ray and CT images with stacked ensemble convolutional neural network

Automatic and rapid screening of COVID-19 from the radiological (X-ray or CT scan) images has become an urgent need in the current pandemic situation of SARS-CoV-2 worldwide. However, accurate and reliable screening of patients is challenging due to the discrepancy between the radiological images of COVID-19 and other viral pneumonia. So, in this paper, we design a new stacked convolutional neural network model for the automatic diagnosis of COVID-19 disease from the chest X-ray and CT images. In the proposed approach, different sub-models have been obtained from the VGG19 and the Xception models during the training. Thereafter, obtained sub-models are stacked together using softmax classifier. The proposed stacked CNN model combines the discriminating power of the different CNN’s sub-models and detects COVID-19 from the radiological images. In addition, we collect CT images to build a CT image dataset and also generate an X-ray images dataset by combining X-ray images from the three publicly available data repositories. The proposed stacked CNN model achieves a sensitivity of 97.62% for the multi-class classification of X-ray images into COVID-19, Normal and Pneumonia Classes and 98.31% sensitivity for binary classification of CT images into COVID-19 and no-Finding classes. Our proposed approach shows superiority over the existing methods for the detection of the COVID-19 cases from the X-ray radiological images.

Pulmonary tuberculosis diagnosis, differentiation and disease management: A review of radiomics applications

Pulmonary tuberculosis is a worldwide epidemic that can only be fought effectively with early and accurate diagnosis and proper disease management. The means of diagnosis and disease management should be easily accessible, cost effective and be readily available in the high tuberculosis burdened countries where it is most needed. Fortunately, the fast development of computer science in recent years has ensured that medical images can accurately be quantified. Radiomics is one such tool that can be used to quantify medical images. This review article focuses on the literature currently available on the application of radiomics explicitly for the purpose of diagnosis, differentiation from other pulmonary diseases and disease management of pulmonary tuberculosis. Despite using a formal search strategy, only five articles could be found on the application of radiomics to pulmonary tuberculosis. In all five articles reviewed, radiomic feature extraction was successfully used to quantify digital medical images for the purpose of comparing, or differentiating, pulmonary tuberculosis from other pulmonary diseases. This demonstrates that the use of radiomics for the purpose of tuberculosis disease management and diagnosis remains a valuable data mining opportunity not yet realised.

Decoding intra-tumoral spatial heterogeneity on radiological images using the Hilbert curve

Background

Current intra-tumoral heterogeneous feature extraction in radiology is limited to the use of a single slice or the region of interest within a few context-associated slices, and the decoding of intra-tumoral spatial heterogeneity using whole tumor samples is rare. We aim to propose a mathematical model of space-filling curve-based spatial correspondence mapping to interpret intra-tumoral spatial locality and heterogeneity.

Methods

A Hilbert curve-based approach was employed to decode and visualize intra-tumoral spatial heterogeneity by expanding the tumor volume to a two-dimensional (2D) matrix in voxels while preserving the spatial locality of the neighboring voxels. The proposed method was validated using three-dimensional (3D) volumes constructed from lung nodules from the LIDC-IDRI dataset, regular axial plane images, and 3D blocks.

Results

Dimensionality reduction of the Hilbert volume with a single regular axial plane image showed a sparse and scattered pixel distribution on the corresponding 2D matrix. However, for 3D blocks and lung tumor inside the volume, the dimensionality reduction to the 2D matrix indicated regular and concentrated squares and rectangles. For classification into benign and malignant masses using lung nodules from the LIDC-IDRI dataset, the Inception-V4 indicated that the Hilbert matrix images improved accuracy (85.54% vs. 73.22%, p < 0.001) compared to the original CT images of the test dataset.

Conclusions

Our study indicates that Hilbert curve-based spatial correspondence mapping is promising for decoding intra-tumoral spatial heterogeneity of partial or whole tumor samples on radiological images. This spatial-locality-preserving approach for voxel expansion enables existing radiomics and convolution neural networks to filter structured and spatially correlated high-dimensional intra-tumoral heterogeneity.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-021-01100-8.

Could automated analysis of chest X-rays detect early bronchiectasis in children?

Non-cystic fibrosis bronchiectasis is increasingly described in the paediatric population. While diagnosis is by high-resolution chest computed tomography (CT), chest X-rays (CXRs) remain a first-line investigation. CXRs are currently insensitive in their detection of bronchiectasis. We aim to determine if quantitative digital analysis allows CT features of bronchiectasis to be detected in contemporaneously taken CXRs. Regions of radiologically (A) normal, (B) severe bronchiectasis, (C) mild airway dilation and (D) other parenchymal abnormalities were identified in CT and mapped to corresponding CXR. An artificial neural network (ANN) algorithm was used to characterise regions of classes A, B, C and D. The algorithm was then tested in 13 subjects and compared to CT scan features. Structural changes in CT were reflected in CXR, including mild airway dilation. The areas under the receiver operator curve for ANN feature detection were 0.74 (class A), 0.71 (class B), 0.76 (class C) and 0.86 (class D). CXR analysis identified CT measures of abnormality with a better correlation than standard radiological scoring at the 99% confidence level.Conclusion: Regional abnormalities can be detected by digital analysis of CXR, which may provide a low-cost and readily available tool to indicate the need for diagnostic CT and for ongoing disease monitoring. What is Known: • Bronchiectasis is a severe chronic respiratory disorder increasingly recognised in paediatric populations. • Diagnostic computed tomography imaging is often requested only after several chest X-ray investigations. What is New: • We show that a digital analysis of chest X-ray could provide more accurate identification of bronchiectasis features.

Texture Analysis and its Applications in Biomedical Imaging: A Survey

Texture analysis describes a variety of image analysis techniques that quantify the variation in intensity and pattern. This paper provides an overview of several texture analysis approaches addressing the rationale supporting them, their advantages, drawbacks, and applications. This surveys emphasis is in collecting and categorising over five decades of active research on texture analysis. Brief descriptions of different approaches are presented along with application examples. From a broad range of texture analysis applications, this surveys final focus is on biomedical image analysis. An up-to-date list of biological tissues and organs in which disorders produce texture changes that may be used to spot disease onset and progression is provided. Finally, the role of texture analysis methods as biomarkers of disease is summarised.

A voting-based ensemble deep learning method focusing on image augmentation and preprocessing variations for tuberculosis detection

Tuberculosis (TB) is known as a potentially dangerous and infectious disease that affects mostly lungs worldwide. The detection and treatment of TB at an early stage are critical for preventing the disease and decreasing the risk of mortality and transmission of it to others. Nowadays, as the most common medical imaging technique, chest radiography (CXR) is useful for determining thoracic diseases. Computer-aided detection (CADe) systems are also crucial mechanisms to provide more reliable, efficient, and systematic approaches with accelerating the decision-making process of clinicians. In this study, we propose voting and preprocessing variations-based ensemble CNN model for TB detection. We utilize 40 different variations in fine-tuned CNN models based on InceptionV3 and Xception by also using CLAHE (contrast-limited adaptive histogram equalization) preprocessing technique and 10 different image transformations for data augmentation types. After analyzing all these combination schemes, three or five best classifier models are selected as base learners for voting operations. We apply the Bayesian optimization-based weighted voting and the average of probabilities as a combination rule in soft voting methods on two TB CXR image datasets to get better results in various numbers of models. The computational results indicate that the proposed method achieves 97.500% and 97.699% accuracy rates on Montgomery and Shenzhen datasets, respectively. Furthermore, our method outperforms state-of-the-art results for the two TB detection datasets in terms of accuracy rate.

Proposing a novel multi-instance learning model for tuberculosis recognition from chest X-ray images based on CNNs, complex networks and stacked ensemble

Mycobacterium Tuberculosis (TB) is an infectious bacterial disease. In 2018, about 10 million people has been diagnosed with tuberculosis (TB) worldwide. Early diagnosis of TB is necessary for effective treatment, higher survival rate, and preventing its further transmission. The gold standard for tuberculosis diagnosis is sputum culture. Nevertheless, posterior-anterior chest radiographs (CXR) is an effective central method with low cost and a relatively low radiation dose for screening TB with immediate results. TB diagnosis from CXR is a challenging task requiring high level of expertise due to the diverse presentation of the disease. Significant intra-class variation and inter-class similarity in CXR images makes TB diagnosis from CXR a more challenging task. The main aim of this study is tuberculosis recognition from CXR images for reducing the disease burden. For this purpose, a novel multi-instance classification model is proposed in this study which is based on CNNs, complex networks and stacked ensemble (CCNSE). A main advantage of CCNSE is not requiring an accurate lung segmentation to localize the suspicious regions. Several overlapping patches are extracted from each CXR image. Features describing each patch are obtained by CNNs and then the feature vectors are clustered. Local complex networks (LCN) and global ones (GCN) of the cluster representatives are formed and feature engineering on LCN (GCN) generates other features at image-level (patch-level and image-level). Global clustering on these feature sets is performed for all patches. Each patch is assigned the purity score of its corresponding cluster. Patch-level features and purity scores are aggregated for each image. Finally, the images are classified with a proposed stacked ensemble classifier to normal and TB classes. Two datasets are used in this study including Montgomery County CXR set (MC) and Shenzhen dataset (SZ). MC/SZ includes 138/662 chest X-rays (CXR) from which 80 and 58/326 and 336 images belong to normal/TB classes, respectively. The experimental results show that the proposed method with AUC of 99.00 ± 0.28/98.00 ± 0.16 for MC/SZ and accuracy of 99.26 ± 0.40/99.22 ± 0.32 for MC/SZ with fivefold cross validation strategy is superior than the compared ones for diagnosis of TB from CXR images. The proposed method can be used as a computer-aided diagnosis system to reduce the manual time, effort and dependency to specialist's expertise level.

Ensemble learning based automatic detection of tuberculosis in chest X-ray images using hybrid feature descriptors

Tuberculosis (TB) remains one of the major health problems in modern times with a high mortality rate. While efforts are being made to make early diagnosis accessible and more reliable in high burden TB countries, digital chest radiography has become a popular source for this purpose. However, the screening process requires expert radiologists which may be a potential barrier in developing countries. A fully automatic computer-aided diagnosis system can reduce the need of trained personnel for early diagnosis of TB using chest X-ray images. In this paper, we have proposed a novel TB detection technique that combines hand-crafted features with deep features (convolutional neural network-based) through Ensemble Learning. Handcrafted features were extracted via Gabor Filter and deep features were extracted via pre-trained deep learning models. Two publicly available datasets namely (i) Montgomery and (ii) Shenzhen were used to evaluate the proposed system. The proposed methodology was validated with a k-fold cross-validation scheme. The area under receiver operating characteristics curves of 0.99 and 0.97 were achieved for Shenzhen and Montgomery datasets respectively which shows the superiority of the proposed scheme.

Texture features from computed tomography correlate with markers of severity in acute alcohol-associated hepatitis

The aim of this study was to use texture analysis to establish quantitative CT-based imaging features to predict clinical severity in patients with acute alcohol-associated hepatitis (AAH). A secondary aim was to compare the performance of texture analysis to deep learning. In this study, mathematical texture features were extracted from CT slices of the liver for 34 patients with a diagnosis of AAH and 35 control patients. Recursive feature elimination using random forest (RFE-RF) was used to identify the best combination of features to distinguish AAH from controls. These features were subsequently used as predictors to determine associated clinical values. To compare machine learning with deep learning approaches, a 2D dense convolutional neural network (CNN) was implemented and trained for the classification task of AAH. RFE-RF identified 23 top features used to classify AAH images, and the subsequent model demonstrated an accuracy of 82.4% in the test set. The deep learning CNN demonstrated an accuracy of 70% in the test set. We show that texture features of the liver are unique in AAH and are candidate quantitative biomarkers that can be used in prospective studies to predict the severity and outcomes of patients with AAH.

Triple attention learning for classification of 14 thoracic diseases using chest radiography

Chest X-ray is the most common radiology examinations for the diagnosis of thoracic diseases. However, due to the complexity of pathological abnormalities and lack of detailed annotation of those abnormalities, computer-aided diagnosis (CAD) of thoracic diseases remains challenging. In this paper, we propose the triple-attention learning (A ³ Net) model for this CAD task. This model uses the pre-trained DenseNet-121 as the backbone network for feature extraction, and integrates three attention modules in a unified framework for channel-wise, element-wise, and scale-wise attention learning. Specifically, the channel-wise attention prompts the deep model to emphasize the discriminative channels of feature maps; the element-wise attention enables the deep model to focus on the regions of pathological abnormalities; the scale-wise attention facilitates the deep model to recalibrate the feature maps at different scales. The proposed model has been evaluated on 112,120images in the ChestX-ray14 dataset with the official patient-level data split. Compared to state-of-the-art deep learning models, our model achieves the highest per-class AUC in classifying 13 out of 14 thoracic diseases and the highest average per-class AUC of 0.826 over 14 thoracic diseases.

Contour-based lung shape analysis in order to tuberculosis detection: modeling and feature description

Statistical shape analysis of lung is a reliable alternative method for diagnosing pulmonary diseases such as tuberculosis (TB). The 2D contour-based lung shape analysis is investigated and developed using Fourier descriptors (FDs). The proposed 2D lung shape analysis is carried out in threefold: (1) represent the normal and the abnormal (i.e. pulmonary tuberculosis (PTB)) lung shape models using Fourier descriptors modeling (FDM) framework from chest X-ray (CXR) images, (2) estimate and compare the 2D inter-patient lung shape variations for the normal and abnormal lungs by applying principal component analysis (PCA) techniques, and (3) describe the optimal type of contour-based feature vectors to train a classifier in order to detect TB using one publicly available dataset-namely the Montgomery dataset. Since almost all of the previous works in lung shape analysis are content-based analysis, we proposed contour-based lung shape analysis for statistical modeling and feature description of PTB cases. The results show that the proposed approach is able to explain more than 95% of total variations in both of the normal and PTB cases using only 6 and 7 principal component modes for the right and the left lungs, respectively. In case of PTB detection, using 138 lung cases (80 normal and 58 PTB cases), we achieved the accuracy (ACC) and the area under the curve (AUC) of 82.03% and 88.75%, respectively. In comparison with existing state-of-art studies in the same dataset, the proposed approach is a very promising supplement for diagnosis of PTB disease. The method is robust and valuable for application in 2D automatic segmentation, classification, and atlas registration. Moreover, the approach could be used for any kind of pulmonary diseases. Graphical abstract Contour-based lung shape analysis in order to detect tuberculosis: modeling and feature description.

Computer-Aided System for the Detection of Multicategory Pulmonary Tuberculosis in Radiographs

The early screening and diagnosis of tuberculosis plays an important role in the control and treatment of tuberculosis infections. In this paper, an integrated computer-aided system based on deep learning is proposed for the detection of multiple categories of tuberculosis lesions in chest radiographs. In this system, the fully convolutional neural network method is used to segment the lung area from the entire chest radiograph for pulmonary tuberculosis detection. Different from the previous analysis of the whole chest radiograph, we focus on the specific tuberculosis lesion areas for the analysis and propose the first multicategory tuberculosis lesion detection method. In it, a learning scalable pyramid structure is introduced into the Faster Region-based Convolutional Network (Faster RCNN), which effectively improves the detection of small-area lesions, mines indistinguishable samples during the training process, and uses reinforcement learning to reduce the detection of false-positive lesions. To compare our method with the current tuberculosis detection system, we propose a classification rule for whole chest X-rays using a multicategory tuberculosis lesion detection model and achieve good performance on two public datasets (Montgomery: AUC = 0.977 and accuracy = 0.926; Shenzhen: AUC = 0.941 and accuracy = 0.902). Our proposed computer-aided system is superior to current systems that can be used to assist radiologists in diagnoses and public health providers in screening for tuberculosis in areas where tuberculosis is endemic.

Hybrid Learning of Hand-Crafted and Deep-Activated Features Using Particle Swarm Optimization and Optimized Support Vector Machine for Tuberculosis Screening

Tuberculosis (TB) is a leading infectious killer, especially for people with Human Immunodeficiency Virus (HIV) and Acquired Immunodeficiency Syndrome (AIDS). Early diagnosis of TB is crucial for disease treatment and control. Radiology is a fundamental diagnostic tool used to screen or triage TB. Automated chest x-rays analysis can facilitate and expedite TB screening with fast and accurate reports of radiological findings and can rapidly screen large populations and alleviate a shortage of skilled experts in remote areas. We describe a hybrid feature-learning algorithm for automatic screening of TB in chest x-rays: it first segmented the lung regions using the DeepLabv3+ model. Then, six sets of hand-crafted features from statistical textures, local binary pattern, GIST, histogram of oriented gradients (HOG), pyramid histogram of oriented gradients and bags of visual words (BoVW), and nine sets of deep-activated features from AlexNet, GoogLeNet, InceptionV3, XceptionNet, ResNet-50, SqueezeNet, ShuffleNet, MobileNet, and DenseNet, were extracted. The dominant features of each feature set were selected using particle swarm optimization, and then separately input to an optimized support vector machine classifier to label ‘normal’ and ‘TB’ x-rays. GIST, HOG, BoVW from hand-crafted features, and MobileNet and DenseNet from deep-activated features performed better than the others. Finally, we combined these five best-performing feature sets to build a hybrid-learning algorithm. Using the Montgomery County (MC) and Shenzen datasets, we found that the hybrid features of GIST, HOG, BoVW, MobileNet and DenseNet, performed best, achieving an accuracy of 92.5% for the MC dataset and 95.5% for the Shenzen dataset.

Deep Learning-Based Decision-Tree Classifier for COVID-19 Diagnosis From Chest X-ray Imaging

The global pandemic of coronavirus disease 2019 (COVID-19) has resulted in an increased demand for testing, diagnosis, and treatment. Reverse transcription polymerase chain reaction (RT-PCR) is the definitive test for the diagnosis of COVID-19; however, chest X-ray radiography (CXR) is a fast, effective, and affordable test that identifies the possible COVID-19-related pneumonia. This study investigates the feasibility of using a deep learning-based decision-tree classifier for detecting COVID-19 from CXR images. The proposed classifier comprises three binary decision trees, each trained by a deep learning model with convolution neural network based on the PyTorch frame. The first decision tree classifies the CXR images as normal or abnormal. The second tree identifies the abnormal images that contain signs of tuberculosis, whereas the third does the same for COVID-19. The accuracies of the first and second decision trees are 98 and 80%, respectively, whereas the average accuracy of the third decision tree is 95%. The proposed deep learning-based decision-tree classifier may be used in pre-screening patients to conduct triage and fast-track decision making before RT-PCR results are available.

Lung X-ray Segmentation using Deep Convolutional Neural Networks on Contrast-Enhanced Binarized Images

Automatically locating the lung regions effectively and efficiently in digital chest X-ray (CXR) images is important in computer-aided diagnosis. In this paper, we propose an adaptive pre-processing approach for segmenting the lung regions from CXR images using convolutional neural networks-based (CNN-based) architectures. It is comprised of three steps. First, a contrast enhancement method specifically designed for CXR images is adopted. Second, adaptive image binarization is applied to CXR images to separate the image foreground and background. Third, CNN-based architectures are trained on the binarized images for image segmentation. The experimental results show that the proposed pre-processing approach is applicable and effective to various CNN-based architectures and can achieve comparable segmentation accuracy to that of state-of-the-art methods while greatly expediting the model training by up to 20.74 % and reducing storage space for CRX image datasets by down to 94.6 % on average.

Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children

BACKGROUND

The chest radiograph is the most common imaging modality to assess childhood pneumonia. It has been used in epidemiological and vaccine efficacy/effectiveness studies on childhood pneumonia.

OBJECTIVE

To develop computer-aided diagnosis (CAD4Kids) for chest radiography in children and to evaluate its accuracy in identifying World Health Organization (WHO)-defined chest radiograph primary-endpoint pneumonia compared to a consensus interpretation.

MATERIALS AND METHODS

Chest radiographs were independently evaluated by three radiologists based on WHO criteria. Automatic lung field segmentation was followed by manual inspection and correction, training, feature extraction and classification. Radiographs were filtered with Gaussian derivatives on multiple scales, extracting texture features to classify each pixel in the lung region. To obtain an image score, the 95^th percentile score of the pixels was used. Training and testing were done in 10-fold cross validation.

RESULTS

The radiologist majority consensus reading of 858 interpretable chest radiographs included 333 (39%) categorised as primary-endpoint pneumonia, 208 (24%) as other infiltrate only and 317 (37%) as no primary-endpoint pneumonia or other infiltrate. Compared to the reference radiologist consensus reading, CAD4Kids had an area under the receiver operator characteristic (ROC) curve of 0.850 (95% confidence interval [CI] 0.823-0.876), with a sensitivity of 76% and specificity of 80% for identifying primary-endpoint pneumonia on chest radiograph. Furthermore, the ROC curve was 0.810 (95% CI 0.772-0.846) for CAD4Kids identifying primary-endpoint pneumonia compared to other infiltrate only.

CONCLUSION

Further development of the CAD4Kids software and validation in multicentre studies are important for future research on computer-aided diagnosis and artificial intelligence in paediatric radiology.

Computer-Aided Diagnosis of Pulmonary Fibrosis Using Deep Learning and CT Images

OBJECTIVES

The objective of this study is to assess the performance of a computer-aided diagnosis (CAD) system (INTACT system) for the automatic classification of high-resolution computed tomography images into 4 radiological diagnostic categories and to compare this with the performance of radiologists on the same task.

MATERIALS AND METHODS

For the comparison, a total of 105 cases of pulmonary fibrosis were studied (54 cases of nonspecific interstitial pneumonia and 51 cases of usual interstitial pneumonia). All diagnoses were interstitial lung disease board consensus diagnoses (radiologically or histologically proven cases) and were retrospectively selected from our database. Two subspecialized chest radiologists made a consensual ground truth radiological diagnosis, according to the Fleischner Society recommendations. A comparison analysis was performed between the INTACT system and 2 other radiologists with different years of experience (readers 1 and 2). The INTACT system consists of a sequential pipeline in which first the anatomical structures of the lung are segmented, then the various types of pathological lung tissue are identified and characterized, and this information is then fed to a random forest classifier able to recommend a radiological diagnosis.

RESULTS

Reader 1, reader 2, and INTACT achieved similar accuracy for classifying pulmonary fibrosis into the original 4 categories: 0.6, 0.54, and 0.56, respectively, with P > 0.45. The INTACT system achieved an F-score (harmonic mean for precision and recall) of 0.56, whereas the 2 readers, on average, achieved 0.57 (P = 0.991). For the pooled classification (2 groups, with and without the need for biopsy), reader 1, reader 2, and CAD had similar accuracies of 0.81, 0.70, and 0.81, respectively. The F-score was again similar for the CAD system and the radiologists. The CAD system and the average reader reached F-scores of 0.80 and 0.79 (P = 0.898).

CONCLUSIONS

We found that a computer-aided detection algorithm based on machine learning was able to classify idiopathic pulmonary fibrosis with similar accuracy to a human reader.

Diagnosing Tuberculosis Using Deep Convolutional Neural Network

One of the global topmost causes of death is Tuberculosis (TB) which is caused by mycobacterium bacillus. The increase rate of infected people and the recorded deaths from TB disease is as a result of its transmissibility, lack of early diagnosis, and inadequate professional radiologist in developing regions where TB is more prevalent. Tuberculosis is unquestionably curable but needs to be detected early for necessary treatment to be effective. Many screening techniques are available, but chest radiograph has proven to be valuable for screening pulmonary diseases but hugely dependent on the interpretational skill of an expert radiologist. We propose a Computer-Aided Detection model using Deep Convolutional Neural Networks to automatically detect TB from Montgomery County (MC) Tuberculosis radiographs. Our proposed model performed at 87.1% validation accuracy and evaluated using confusion matrix and accuracy as metrics.

Impact of androgen deprivation therapy on apparent diffusion coefficient and T2w MRI for histogram and texture analysis with respect to focal radiotherapy of prostate cancer

PURPOSE

Accurate prostate cancer (PCa) detection is essential for planning focal external beam radiotherapy (EBRT). While biparametric MRI (bpMRI) including T2-weighted (T2w) and diffusion-weighted images (DWI) is an accurate tool to localize PCa, its value is less clear in the case of additional androgen deprivation therapy (ADT). The aim of this study was to investigate the value of a textural feature (TF) approach on bpMRI analysis in prostate cancer patients with and without neoadjuvant ADT with respect to future dose-painting applications.

METHODS

28 PCa patients (54-80 years) with (n = 14) and without (n = 14) ADT who underwent bpMRI with T2w and DWI were analyzed retrospectively. Lesions, central gland (CG), and peripheral zone (PZ) were delineated by an experienced urogenital radiologist based on localized pre-therapeutic histopathology. Histogram parameters and 20 Haralick TF were calculated. Regional differences (i. e., tumor vs. PZ, tumor vs. CG) were analyzed for all imaging parameters. Receiver-operating characteristic (ROC) analysis was performed to measure diagnostic performance to distinguish PCa from benign prostate tissue and to identify the features with best discriminative power in both patient groups.

RESULTS

The obtained sensitivities were equivalent or superior when utilizing the TF in the no-ADT group, while specificity was higher for the histogram parameters. However, in the ADT group, TF outperformed the conventional histogram parameters in both specificity and sensitivity. Rule-in and rule-out criteria for ADT patients could exclusively be defined with the aid of TF.

CONCLUSIONS

The TF approach has the potential for quantitative image-assisted boost volume delineation in PCa patients even if they are undergoing neoadjuvant ADT.

Deep learning in medical imaging and radiation therapy

The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

Review: On Segmentation of Nodules from Posterior and Anterior Chest Radiographs

Lung cancer is one of the major types of cancer in the world. Survival rate can be increased if the disease can be identified early. Posterior and anterior chest radiography and computerized tomography scans are the most used diagnosis techniques for detecting tumor from lungs. Posterior and anterior chest radiography requires less radiation dose and is available in most of the diagnostic centers and it costs less compared to the remaining diagnosis techniques. So PA chest radiography became the most commonly used technique for lung cancer detection. Because of superimposed anatomical structures present in the image, sometimes radiologists cannot find abnormalities from the image. To help radiologists in diagnosing tumor from PA chest radiographic images range of CAD scheme has been developed for the past three decades. These computerized tools may be used by radiologists as a second opinion in detecting tumor. Literature survey on detecting tumors from chest graphs is presented in this paper.

Fully Convolutional Architectures for Multiclass Segmentation in Chest Radiographs

The success of deep convolutional neural networks (NNs) on image classification and recognition tasks has led to new applications in very diversified contexts, including the field of medical imaging. In this paper, we investigate and propose NN architectures for automated multiclass segmentation of anatomical organs in chest radiographs (CXRs), namely for lungs, clavicles, and heart. We address several open challenges including model overfitting, reducing number of parameters, and handling of severely imbalanced data in CXR by fusing recent concepts in convolutional networks and adapting them to the segmentation problem task in CXR. We demonstrate that our architecture combining delayed subsampling, exponential linear units, highly restrictive regularization, and a large number of high-resolution low-level abstract features outperforms state-of-the-art methods on all considered organs, as well as the human observer on lungs and heart. The models use a multiclass configuration with three target classes and are trained and tested on the publicly available Japanese Society of Radiological Technology database, consisting of 247 X-ray images the ground-truth masks for which are available in the segmentation in CXR database. Our best performing model, trained with the loss function based on the Dice coefficient, reached mean Jaccard overlap scores of 95% for lungs, 86.8% for clavicles, and 88.2% for heart. This architecture outperformed the human observer results for lungs and heart.

Automated Chest X-Ray Screening: Can Lung Region Symmetry Help Detect Pulmonary Abnormalities?

Our primary motivator is the need for screening HIV+ populations in resource-constrained regions for exposure to Tuberculosis, using posteroanterior chest radiographs (CXRs). The proposed method is motivated by the observation that radiological examinations routinely conduct bilateral comparisons of the lung field. In addition, the abnormal CXRs tend to exhibit changes in the lung shape, size, and content (textures), and in overall, reflection symmetry between them. We analyze the lung region symmetry using multi-scale shape features, and edge plus texture features. Shape features exploit local and global representation of the lung regions, while edge and texture features take internal content, including spatial arrangements of the structures. For classification, we have performed voting-based combination of three different classifiers: Bayesian network, multilayer perception neural networks, and random forest. We have used three CXR benchmark collections made available by the U.S. National Library of Medicine and the National Institute of Tuberculosis and Respiratory Diseases, India, and have achieved a maximum abnormality detection accuracy (ACC) of 91.00% and area under the ROC curve (AUC) of 0.96. The proposed method outperforms the previously reported methods by more than 5% in ACC and 3% in AUC.

Feature fusion for lung nodule classification

PURPOSE

This article examines feature-based nodule description for the purpose of nodule classification in chest computed tomography scanning.

METHODS

Three features based on (i) Gabor filter, (ii) multi-resolution local binary pattern (LBP) texture features and (iii) signed distance fused with LBP which generates a combinational shape and texture feature are utilized to provide feature descriptors of malignant and benign nodules and non-nodule regions of interest. Support vector machines (SVMs) and k-nearest neighbor (kNN) classifiers in serial and two-tier cascade frameworks are optimized and analyzed for optimal classification results of nodules.

RESULTS

A total of 1191 nodule and non-nodule samples from the Lung Image Data Consortium database is used for analysis. Classification using SVM and kNN classifiers is examined. The classification results from the two-tier cascade SVM using Gabor features showed overall better results for identifying non-nodules, malignant and benign nodules with average area under the receiver operating characteristics (AUC-ROC) curves of 0.99 and average f1-score of 0.975 over the two tiers.

CONCLUSION

In the results, higher overall AUCs and f1-scores were obtained for the non-nodules cases using any of the three features, showing the greatest distinguishability over nodules (benign/malignant). SVM and kNN classifiers were used for benign, malignant and non-nodule classification, where Gabor proved to be the most effective of the features for classification. The cascaded framework showed the greatest distinguishability between benign and malignant nodules.

Computer-Aided Diagnosis for Chest Radiographs in Intensive Care

The chest radiograph is an essential tool for the diagnosis of several lung diseases in intensive care units (ICU). However, several factors make the interpretation of the chest radiograph difficult including the number of X-rays done daily in ICU, the quality of the chest radiograph, and the lack of a standardized interpretation. To overcome these limitations in the interpretation of chest radiographs, researchers have developed computer-aided diagnosis (CAD) systems. In this review, the authors report the methodology used to develop CAD systems including identification of the region of interest, analysis of these regions, and classification. Currently, only a few CAD systems for chest X-ray interpretation are commercially available. Some promising research is ongoing, but the involvement of the pediatric research community is needed for the development and validation of such CAD systems dedicated to pediatric intensive care.

Two-dimensional MR Spectroscopic Characterization of Breast Cancer In Vivo

The major goal of this work was to characterize invasive ductal carcinoma and healthy fatty breast tissues noninvasively using the classification and regression tree analysis (CART) of 2D MR spectral data. 2D L-COSY spectra were acquired in 14 invasive breast carcinoma and 21 healthy fatty breasts using a GE 1.5 Tesla MRI/MRS scanner equipped with a 2-channel phased-array breast MR coil. The 2D spectra were recorded in approximately 10 minutes using a minimum voxel size of 1 ml without any water suppression technique. For healthy breasts, spectra were acquired from at least one fatty region. 2D L-COSY spectra were recorded in a total of 43 voxels. Five diagonal and six cross peak volumes were integrated and at least eighteen ratios were selected as potential features for the statistical method, namely CART. The 2D L-COSY data showed a significant increase for the majority of these ratios in invasive breast carcinomas compared to healthy fatty tissues. Better accuracy of identifying carcinomas and fatty tissues is reported using CART analysis of different combinations of ratios calculated from the relative levels of water, choline, and saturated and unsaturated lipids. This is a first report on the statistical classification of 2D L-COSY in human breast carcinomas in vivo.

Edge map analysis in chest X-rays for automatic pulmonary abnormality screening

PURPOSE

Our particular motivator is the need for screening HIV+ populations in resource-constrained regions for the evidence of tuberculosis, using posteroanterior chest radiographs (CXRs).

METHOD

The proposed method is motivated by the observation that abnormal CXRs tend to exhibit corrupted and/or deformed thoracic edge maps. We study histograms of thoracic edges for all possible orientations of gradients in the range [Formula: see text] at different numbers of bins and different pyramid levels, using five different regions-of-interest selection.

RESULTS

We have used two CXR benchmark collections made available by the U.S. National Library of Medicine and have achieved a maximum abnormality detection accuracy (ACC) of 86.36 % and area under the ROC curve (AUC) of 0.93 at 1 s per image, on average.

CONCLUSION

We have presented an automatic method for screening pulmonary abnormalities using thoracic edge map in CXR images. The proposed method outperforms previously reported state-of-the-art results.

Early detection of Alzheimer's disease using MRI hippocampal texture

Cognitive impairment in patients with Alzheimer's disease (AD) is associated with reduction in hippocampal volume in magnetic resonance imaging (MRI). However, it is unknown whether hippocampal texture changes in persons with mild cognitive impairment (MCI) that does not have a change in hippocampal volume. We tested the hypothesis that hippocampal texture has association to early cognitive loss beyond that of volumetric changes. The texture marker was trained and evaluated using T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and subsequently applied to score independent data sets from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL) and the Metropolit 1953 Danish Male Birth Cohort (Metropolit). Hippocampal texture was superior to volume reduction as predictor of MCI-to-AD conversion in ADNI (area under the receiver operating characteristic curve [AUC] 0.74 vs. 0.67; DeLong test, p = 0.005), and provided even better prognostic results in AIBL (AUC 0.83). Hippocampal texture, but not volume, correlated with Addenbrooke's cognitive examination score (Pearson correlation, r = -0.25, p < 0.001) in the Metropolit cohort. The hippocampal texture marker correlated with hippocampal glucose metabolism as indicated by fluorodeoxyglucose-positron emission tomography (Pearson correlation, r = -0.57, p < 0.001). Texture statistics remained significant after adjustment for volume in all cases, and the combination of texture and volume did not improve diagnostic or prognostic AUCs significantly. Our study highlights the presence of hippocampal texture abnormalities in MCI, and the possibility that texture may serve as a prognostic neuroimaging biomarker of early cognitive impairment.

Automatic Detection of Tuberculosis in Chest Radiographs Using a Combination of Textural, Focal, and Shape Abnormality Analysis

Tuberculosis (TB) is a common disease with high mortality and morbidity rates worldwide. Automatic systems to detect TB on chest radiographs (CXRs) can improve the efficiency of diagnostic algorithms for pulmonary TB. The diverse manifestation of TB on CXRs from different populations requires a system that can be adapted to deal with different types of abnormalities. A computer aided detection (CAD) system was developed which combines several subscores of supervised subsystems detecting textural, shape, and focal abnormalities into one TB score. A general framework was developed to combine an arbitrary number of subscores: subscores were normalized, collected in a feature vector and then combined using a supervised classifier into one combined score. The method was evaluated on two databases, both consisting of 200 digital CXRs, from: (A) Western high-risk group screening, (B) TB suspect screening in Africa. The subscores and combined score were compared to (1) an external, non-radiological, reference and (2) a radiological reference determined by a human expert. Performance was measured using Receiver Operator Characteristic (ROC) analysis. Different subscores performed best in the two databases. The combined TB score performed better than the individual subscores, except for the external reference in database B. The performances of the independent observer were slightly higher than the combined TB score. Compared to the external reference, differences in performance between the combined TB score and the independent observer were not significant in both databases. Supervised combination to compute an overall TB score allows for a necessary adaptation of the CAD system to different settings or different operational requirements.

Quantification of Pulmonary Inflammatory Processes Using Chest Radiography: Tuberculosis as the Motivating Application

The purpose of this work was to develop a quantitative method for evaluating the pulmonary inflammatory process (PIP) through the computational analysis of chest radiography exams in posteroanterior (PA) and lateral views. The quantification procedure was applied to patients with tuberculosis (TB) as the motivating application.A study of high-resolution computed tomography (HRCT) examinations of patients with TB was developed to establish a relation between the inflammatory process and the signal difference-to-noise ratio (SDNR) measured in the PA projection. A phantom essay was used to validate this relation, which was implemented using an algorithm that is able to estimate the volume of the inflammatory region based solely on SDNR values in the chest radiographs of patients.The PIP volumes that were quantified for 30 patients with TB were used for comparisons with direct HRCT analysis for the same patient. The Bland-Altman statistical analyses showed no significant differences between the 2 quantification methods. The linear regression line had a correlation coefficient of R = 0.97 and P < 0.001, showing a strong association between the volume that was determined by our evaluation method and the results obtained by direct HRCT scan analysis.Since the diagnosis and follow-up of patients with TB is commonly performed using X-rays exams, the method developed herein can be considered an adequate tool for quantifying the PIP with a lower patient radiation dose and lower institutional cost. Although we used patients with TB for the application of the method, this method may be used for other pulmonary diseases characterized by a PIP.

Application of phase congruency for discriminating some lung diseases using chest radiograph

A novel procedure using phase congruency is proposed for discriminating some lung disease using chest radiograph. Phase congruency provides information about transitions between adjacent pixels. Abrupt changes of phase congruency values between pixels may suggest a possible boundary or another feature that may be used for discrimination. This property of phase congruency may have potential for deciding between disease present and disease absent where the regions of infection on the images have no obvious shape, size, or configuration. Five texture measures calculated from phase congruency and Gabor were shown to be normally distributed. This gave good indicators of discrimination errors in the form of the probability of Type I Error (δ) and the probability of Type II Error (β). However, since 1 -  δ is the true positive fraction (TPF) and β is the false positive fraction (FPF), an ROC analysis was used to decide on the choice of texture measures. Given that features are normally distributed, for the discrimination between disease present and disease absent, energy, contrast, and homogeneity from phase congruency gave better results compared to those using Gabor. Similarly, for the more difficult problem of discriminating lobar pneumonia and lung cancer, entropy and homogeneity from phase congruency gave better results relative to Gabor.

Role of Gist and PHOG features in computer-aided diagnosis of tuberculosis without segmentation

Purpose

Effective diagnosis of tuberculosis (TB) relies on accurate interpretation of radiological patterns found in a chest radiograph (CXR). Lack of skilled radiologists and other resources, especially in developing countries, hinders its efficient diagnosis. Computer-aided diagnosis (CAD) methods provide second opinion to the radiologists for their findings and thereby assist in better diagnosis of cancer and other diseases including TB. However, existing CAD methods for TB are based on the extraction of textural features from manually or semi-automatically segmented CXRs. These methods are prone to errors and cannot be implemented in X-ray machines for automated classification.

Methods

Gabor, Gist, histogram of oriented gradients (HOG), and pyramid histogram of oriented gradients (PHOG) features extracted from the whole image can be implemented into existing X-ray machines to discriminate between TB and non-TB CXRs in an automated manner. Localized features were extracted for the above methods using various parameters, such as frequency range, blocks and region of interest. The performance of these features was evaluated against textural features. Two digital CXR image datasets (8-bit DA and 14-bit DB) were used for evaluating the performance of these features.

Results

Gist (accuracy 94.2% for DA, 86.0% for DB) and PHOG (accuracy 92.3% for DA, 92.0% for DB) features provided better results for both the datasets. These features were implemented to develop a MATLAB toolbox, TB-Xpredict, which is freely available for academic use at http://sourceforge.net/projects/tbxpredict/. This toolbox provides both automated training and prediction modules and does not require expertise in image processing for operation.

Conclusion

Since the features used in TB-Xpredict do not require segmentation, the toolbox can easily be implemented in X-ray machines. This toolbox can effectively be used for the mass screening of TB in high-burden areas with improved efficiency.

Computer-aided diagnosis system for the Acute Respiratory Distress Syndrome from chest radiographs

This paper presents a computer-aided diagnosis (CAD) system for the assessment of Acute Respiratory Distress Syndrome (ARDS) from chest radiographs. Our method consists in automatically extracting intercostal patches from chest radiographs belonging to the test database using a semiautomatic segmentation method of the ribs. Statistical and spectral features are computed from each patch then a method of feature transformation is applied using the Linear Discriminant Analysis (LDA). A training database of 321 patches was classified by an expert in two classes, a class of normal patches and a class of abnormal patches. Patches belonging to the test database are then classified using the SVM classifier. Finally, the rate of abnormal patches is calculated for each quadrant to decide if the chest radiograph presents an ARDS. The method has been evaluated on 90 radiographs where 53 images present ARDS. The results show a sensitivity of 90.6% at a specificity of 86.5%.

Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration

The National Library of Medicine (NLM) is developing a digital chest X-ray (CXR) screening system for deployment in resource constrained communities and developing countries worldwide with a focus on early detection of tuberculosis. A critical component in the computer-aided diagnosis of digital CXRs is the automatic detection of the lung regions. In this paper, we present a nonrigid registration-driven robust lung segmentation method using image retrieval-based patient specific adaptive lung models that detects lung boundaries, surpassing state-of-the-art performance. The method consists of three main stages: 1) a content-based image retrieval approach for identifying training images (with masks) most similar to the patient CXR using a partial Radon transform and Bhattacharyya shape similarity measure, 2) creating the initial patient-specific anatomical model of lung shape using SIFT-flow for deformable registration of training masks to the patient CXR, and 3) extracting refined lung boundaries using a graph cuts optimization approach with a customized energy function. Our average accuracy of 95.4% on the public JSRT database is the highest among published results. A similar degree of accuracy of 94.1% and 91.7% on two new CXR datasets from Montgomery County, MD, USA, and India, respectively, demonstrates the robustness of our lung segmentation approach.

Automatic tuberculosis screening using chest radiographs

Tuberculosis is a major health threat in many regions of the world. Opportunistic infections in immunocompromised HIV/AIDS patients and multi-drug-resistant bacterial strains have exacerbated the problem, while diagnosing tuberculosis still remains a challenge. When left undiagnosed and thus untreated, mortality rates of patients with tuberculosis are high. Standard diagnostics still rely on methods developed in the last century. They are slow and often unreliable. In an effort to reduce the burden of the disease, this paper presents our automated approach for detecting tuberculosis in conventional posteroanterior chest radiographs. We first extract the lung region using a graph cut segmentation method. For this lung region, we compute a set of texture and shape features, which enable the X-rays to be classified as normal or abnormal using a binary classifier. We measure the performance of our system on two datasets: a set collected by the tuberculosis control program of our local county's health department in the United States, and a set collected by Shenzhen Hospital, China. The proposed computer-aided diagnostic system for TB screening, which is ready for field deployment, achieves a performance that approaches the performance of human experts. We achieve an area under the ROC curve (AUC) of 87% (78.3% accuracy) for the first set, and an AUC of 90% (84% accuracy) for the second set. For the first set, we compare our system performance with the performance of radiologists. When trying not to miss any positive cases, radiologists achieve an accuracy of about 82% on this set, and their false positive rate is about half of our system's rate.

Smart spotting of pulmonary TB cavities using CT images

One third of the world's population is thought to have been infected with mycobacterium tuberculosis (TB) with new infection occurring at a rate of about one per second. TB typically attacks the lungs. Indication of cavities in upper lobes of lungs shows the high infection. Traditionally, it has been detected manually by physicians. But the automatic technique proposed in this paper focuses on accurate detection of disease by computed tomography (CT) using computer-aided detection (CAD) system. The various steps of the detection process include the following: (i) image preprocessing, which is done by techniques such as resizing, masking, and Gaussian smoothening, (ii) image egmentation that is implemented by using mean-shift model and gradient vector flow (GVF) model, (iii) feature extraction that can be achieved by Gradient inverse coefficient of variation and circularity measure, and (iv) classification using Bayesian classifier. Experimental results show that its perfection of detecting cavities is very accurate in low false positive rate (FPR).

Suppression of translucent elongated structures: applications in chest radiography

Projection images, such as those routinely acquired in radiological practice, are difficult to analyze because multiple 3-D structures superimpose at a single point in the 2-D image. Removal of particular superimposed structures may improve interpretation of these images, both by humans and by computers. This work therefore presents a general method to isolate and suppress structures in 2-D projection images. The focus is on elongated structures, which allows an intensity model of a structure of interest to be extracted using local information only. The model is created from profiles sampled perpendicular to the structure. Profiles containing other structures are detected and removed to reduce the influence on the model. Subspace filtering, using blind source separation techniques, is applied to separate the structure to be suppressed from other structures. By subtracting the modeled structure from the original image a structure suppressed image is created. The method is evaluated in four experiments. In the first experiment ribs are suppressed in 20 artificial radiographs simulated from 3-D lung computed tomography (CT) images. The proposed method with blind source separation and outlier detection shows superior suppression of ribs in simulated radiographs, compared to a simplified approach without these techniques. Additionally, the ability of three observers to discriminate between patches containing ribs and containing no ribs, as measured by the area under the receiver operating characteristic curve (AUC), reduced from 0.99-1.00 on original images to 0.75-0.84 on suppressed images. In the second experiment clavicles are suppressed in 253 chest radiographs. The effect of suppression on clavicle visibility is evaluated using the clavicle contrast and border response, showing a reduction of 78% and 34%, respectively. In the third experiment nodules extracted from CT were simulated close to the clavicles in 100 chest radiographs. It was found that after suppression contrast of the nodules was higher than of the clavicles (1.35 and 0.55, respectively) than on original images (1.83 and 2.46, respectively). In the fourth experiment catheters were suppressed in chest radiographs. The ability of three observers to discriminate between patches originating from 36 images with and 21 images without catheters, as measured by the AUC, reduced from 0.98-0.99 on original images to 0.64-0.74 on suppressed images. We conclude that the presented method can markedly reduce the visibility of elongated structures in chest radiographs and shows potential to enhance diagnosis.

Out-of-atlas likelihood estimation using multi-atlas segmentation

PURPOSE

Multi-atlas segmentation has been shown to be highly robust and accurate across an extraordinary range of potential applications. However, it is limited to the segmentation of structures that are anatomically consistent across a large population of potential target subjects (i.e., multi-atlas segmentation is limited to "in-atlas" applications). Herein, the authors propose a technique to determine the likelihood that a multi-atlas segmentation estimate is representative of the problem at hand, and, therefore, identify anomalous regions that are not well represented within the atlases.

METHODS

The authors derive a technique to estimate the out-of-atlas (OOA) likelihood for every voxel in the target image. These estimated likelihoods can be used to determine and localize the probability of an abnormality being present on the target image.

RESULTS

Using a collection of manually labeled whole-brain datasets, the authors demonstrate the efficacy of the proposed framework on two distinct applications. First, the authors demonstrate the ability to accurately and robustly detect malignant gliomas in the human brain-an aggressive class of central nervous system neoplasms. Second, the authors demonstrate how this OOA likelihood estimation process can be used within a quality control context for diffusion tensor imaging datasets to detect large-scale imaging artifacts (e.g., aliasing and image shading).

CONCLUSIONS

The proposed OOA likelihood estimation framework shows great promise for robust and rapid identification of brain abnormalities and imaging artifacts using only weak dependencies on anomaly morphometry and appearance. The authors envision that this approach would allow for application-specific algorithms to focus directly on regions of high OOA likelihood, which would (1) reduce the need for human intervention, and (2) reduce the propensity for false positives. Using the dual perspective, this technique would allow for algorithms to focus on regions of normal anatomy to ascertain image quality and adapt to image appearance characteristics.

Quantitative computed tomography imaging of interstitial lung diseases

PURPOSE

High-resolution chest computed tomography (HRCT) is essential in the characterization of interstitial lung disease. The HRCT features of some diseases can be diagnostic. Longitudinal monitoring with HRCT can assess progression of interstitial lung disease; however, subtle changes in the volume and character of abnormalities can be difficult to assess. Accuracy of diagnosis can be dependent on expertise and experience of the radiologist, pathologist, or clinician. Quantitative analysis of thoracic HRCT has the potential to determine the extent of disease reproducibly, classify the types of abnormalities, and automate the diagnostic process.

MATERIALS AND METHODS

Novel software that utilizes histogram signatures to characterize pulmonary parenchyma was used to analyze chest HRCT data, including retrospective processing of clinical CT scans and research data from the Lung Tissue Research Consortium. Additional information including physiological, pathologic, and semiquantitative radiologist assessment was available to allow comparison of quantitative results, with visual estimates of the disease, physiological parameters, and measures of disease outcome.

RESULTS

Quantitative analysis results were provided in regional volumetric quantities for statistical analysis and a graphical representation. These results suggest that quantitative HRCT analysis can serve as a biomarker with physiological, pathologic, and prognostic significance.

CONCLUSIONS

It is likely that quantitative analysis of HRCT can be used in clinical practice as a means to aid in identifying a probable diagnosis, stratifying prognosis in early disease, and consistently determining progression of the disease or response to therapy. Further optimization of quantitative techniques and longitudinal analysis of well-characterized subjects would be helpful in validating these methods.