Lung CT Images Research Articles

A preliminary study on establishment of AI-assisted remote imaging diagnosis system for major infectious diseases

Objective In response to the outbreak of severe infectious diseases such as new coronavirus pneumonia, an artificial intelligence based image diagnosis system is established to improve the efficiency of disease diagnosis, reduce the burden of front-line doctors, and improve the medical resource allocation. Methods Using the deep convolution neural network and regional prevention and control auxiliary information system, the image data and other information of the confirmed patients were analyzed and processed comprehensively. Results A set of AI based medical image auxiliary data processing system is proposed. Combined with multimodal medical data collaborative diagnosis, it can effectively and accurately segment the diseased areas in patients' lung CT images, and generate standardized reports. Relying on the multi-center collaborative diagnosis and treatment platform, the system can introduce multi-expert remote consultation mechanism to improve the diagnosis quality of severe patients. Conclusions By segmenting pathological regions, generating standardized reports and introducing multicenter mechanism, the system can help to optimize the medical resources allocation and improve the utilization of these resources. Key words: COVID-19; AI; Image diagnosis; Collaborative diagnosis

Joint DBN and Fuzzy C-Means unsupervised deep clustering for lung cancer patient stratification

Patient stratification has made a great contribution to efficient and personalized medicine. An important task in patient stratification is to discover quite distinct disease subtypes for effective treatment. In this paper, we propose a new deep learning and clustering model which combines Deep Belief Network (DBN) and Fuzzy C-Means(FCM), called Unsupervised Deep Fuzzy C-Means clustering Network(UDFCMN), to cluster lung cancer patients from lung CT images. In our deep clustering network, images after preprocessing are first encoded into multiple layers of hidden variables to extract hierarchical features and feature distribution and form the high-level representations. Here, to solve the problem of feature homogenization in DBN, we introduce the Winner-Take-All (WTA) idea to meliorate the traditional DBN structure, called WTADBN. Then FCM is used to produce the initial cluster labels with the new representations learnt by stacked WTARBM. Therefore, the FCM-generated cluster labels are used for the fine-tuning of the DBN as ground-truth labels. And an unsupervised image clustering and patient stratification process is completed by cross iteration. We tested our deep FCM clustering algorithm to do experiment on both public dataset from the internet and private dataset from cooperate hospital. For the latter one, the clinical and biological verification was also performed. Experimental results reveal outperformance of UDFCMN as compared to the state-of-the-art unsupervised classification methods. These results also indicate that our approach may have practical applications in lung cancer pathogenesis studies and provide useful guidelines for personalized cancer therapy.

A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases.

The common CT imaging signs of lung diseases (CISLs) which frequently appear in lung CT images are widely used in the diagnosis of lung diseases. Computer-aided diagnosis (CAD) based on the CISLs can improve radiologists' performance in the diagnosis of lung diseases. Since similarity measure is important for CAD, we propose a multi-level method to measure the similarity between the CISLs. The CISLs are characterized in the low-level visual scale, mid-level attribute scale, and high-level semantic scale, for a rich representation. The similarity at multiple levels is calculated and combined in a weighted sum form as the final similarity. The proposed multi-level similarity method is capable of computing the level-specific similarity and optimal cross-level complementary similarity. The effectiveness of the proposed similarity measure method is evaluated on a dataset of 511 lung CT images from clinical patients for CISLs retrieval. It can achieve about 80% precision and take only 3.6ms for the retrieval process. The extensive comparative evaluations on the same datasets are conducted to validate the advantages on retrieval performance of our multi-level similarity measure over the single-level measure and the two-level similarity methods. The proposed method can have wide applications in radiology and decision support. Graphical abstract.

Simulation of bronchial airway acoustics in healthy and asthmatic subjects.

The onset and development of many airway pathologies affect sound propagation throughout the respiratory system; changes in respiratory sounds are detected primarily by auscultation, which is highly skill dependent. The aim of the present study was to compare healthy and asthmatic pulmonary acoustics by applying a 1D model of wave propagation on CT-based patient-specific geometries. High-resolution CT lung images were acquired in five healthy volunteers and five asthmatic patients at total lung capacity (TLC) and functional residual capacity (FRC). Tracheobronchial trees were reconstructed from CT images. Acoustic pressure, impedance and wall radial velocity were measured by simulating acoustic wave propagation of two external, acoustic pressure waves (1 Pa, 200 and 600 Hz) from the trachea level to the 4th generation. In asthmatic patients, acoustic pressure averaged across the last three generations showed a reduction equal to 29.7% (p<0.01) at FRC, at 200 Hz; input and terminal impedance were 34.5% (p<0.05) higher both at FRC and TLC; wall radial velocity was more than 80% (p<0.05) lower in higher generations both at FRC and TLC. Airway differences in asthma alter acoustic parameters at FRC and TLC, with the greatest difference at FRC and 200 Hz. Acoustic wave propagation analysis represents a quantitative approach that has potential to objectively characterize airway differences in individuals with diseases such as asthma.

Automatic highlighting of the region of interest in computed tomography images of the lungs

This article discusses the creation of masks for highlighting the lungs in computed tomography images using three methods – the Otsu method, a simple convolutional neural network consisting of 10 identical layers, and the convolutional neural network U-Net. We perform a study and comparison of methods used for automatically highlighting the region of interest (ROI) in computed tomography images of the lungs, which were provided as a courtesy from the Clinics of Samara State Medical University. The solution to this problem is relevant, because medical workers have to manually select the ROI as the first step of the automated processing of lung CT images. An algorithm for post-processing images based on the search for contours, which allows one to improve the quality of segmentation, is proposed. It is concluded that the U-Net highlights the ROI relating to the lung better than the other two methods. At the same time, the simple convolutional neural network highlights the ROI with an accuracy of 97.5%, which is better than the accuracy of 96.7% of the Otsu method and 96.4% of the U-Net.

Research on Lung Nodule Recognition Based on Stacking Algorithm

In recent years, the incidence of cancer has been increasing year by year, and lung cancer has ranked the first place. In order to detect lung nodules quickly and accurately, since the lung CT images in the data set used in this experiment are original medical images, image preprocessing is first required, including noise reduction, segmentation and region of interest extraction, Therefore, this paper proposes a lung nodule recognition method based on Stacking algorithm to detect lung nodules quickly and accurately. Secondly, the three-dimensional gray co-occurrence matrix texture features of the region of interest are extracted. Finally, the Stacking evaluation model is used to identify and classify lung nodules.The experimental results show: Under ten-fold cross-validation, the training accuracy rate and the test accuracy rate can reach 90.9%,82.3%, respectively.This method is feasible for pulmonary nodule recognition and provides data reference value for doctors' auxiliary diagnosis.

Automatic lung segmentation in CT images using mask R-CNN for mapping the feature extraction in supervised methods of machine learning using transfer learning

According to the World Health Organization, severe lung pathologies bring about 250,000 deaths each year, and by 2030 it will be the third leading cause of death in the world. The usage of (CT) Computed Tomography is a crucial tool to aid medical diagnosis. Several studies, based on the computer vision area, in association with the medical field, provide computational models through machine learning and deep learning. In this study, we created a new feature extractor that works as the Mask R-CNN kernel for lung image segmentation through transfer learning. Our approaches minimize the number of images used by CNN’s training step, thereby also decreasing the number of interactions performed by the network. The model obtained results surpassing the standard results generated by Mask R-CNN, obtaining more than 99% about the metrics of real lung position on CT with our best model Mask + SVM, surpassing methods in the literature reaching 11 seconds for pulmonary segmentation. To present the effectiveness of our approach also in the generalization of models (methods capable of generalizing machine knowledge to other different databases), we carried out experiments also with various databases. The method was able, with only one training based on a single database, to segment CT lung images belonging to another lung database, generating excellent results getting 99% accuracy.

A CNN-Based Approach for Lung 3D-CT Registration

Deep learning techniques have been applied to certain rigid or non-rigid medical image registration due to its potential advantages in meeting the clinical requirements of real-time and accuracy. Based on the deep learning model, this study aims to explore specific network models suitable for lung CT images. The proposed model took unlabeled 3D image pairs as input, and the convolutional neural network (CNN) was utilized and identified as a function with ability of sharing parameters to obtain displacement field. The image pair could be aligned by applying the acquired displacement field to the target image through spatial transformation. The similarity between the aligned image pair combined with the constraints on the displacement field was taken as the objective function to obtain the optimal parameters. Two models with different depths were designed and the consequent registration effects with different optimization methods and convolution kernel sizes were explored. The results proved that the designs with deeper level using Adam optimizer and smaller convolution kernels in obtaining displacement fields had higher accuracy and stronger robustness. The accuracy of the unsupervised model was comparable to state-of-the-art methods, while operating orders of magnitude faster. This study proposed a feasible registration method for lung 3D-CT, and its usefulness in aligning CT images has been demonstrated.

A Two-Dimensional Sparse Matrix Profile DenseNet for COVID-19 Diagnosis Using Chest CT Images

COVID-19 is a newly identified disease, which is very contagious and has been rapidly spreading across different countries around the world, calling for rapid and accurate diagnosis tools. Chest CT imaging has been widely used in clinical practice for disease diagnosis, but image reading is still a time-consuming work. We aim to integrate an image preprocessing technology for anomaly detection with supervised deep learning for chest CT imaging-based COVID-19 diagnosis. In this study, a matrix profile technique was introduced to CT image anomaly detection in two levels. At one-dimensional level, CT images were simply flatted and transformed to a one-dimensional vector so that the matrix profile algorithm could be implemented for them directly. At two-dimensional level,a matrix profile was calculated in a sliding window way for every segment in the image. An anomaly severity score (CT-SS) was calculated, and the difference of the CT-SS between the COVID-19 CT images and Non-COVID-19 CT images was tested. A sparse anomaly mask was calculated and applied to penalize the pixel values of each image. The anomaly weighted images were then used to train standard DenseNet deep learning models to distinguish the COVID-19 CT from Non-COVID-19 CT images. A VGG19 model was used as a baseline model for comparison. Although extra finetuning needs to be done manually, the one-dimensional matrix profile method could identify the anomalies successfully. Using the two-dimensional matrix profiling method, CT-SS and anomaly weighted image can be successfully generated for each image. The CT-SS significantly differed among the COVID-19 CT images and Non-COVID-19 CT images ($p-value <; 0.05$ ). Furthermore, we identified a potential causal association between the number of underlying diseases of a COVID-19 patient and the severity of the disease through statistical mediation analysis. Compared to the raw images, the anomaly weighted images showed generally better performance in training the DenseNet models with different architectures for diagnosing COVID-19, which was validated using two publicly available COVID-19 lung CT image datasets. The metric Area Under the Curve(AUC) on one dataset were 0.7799(weighted)vs. 0.7391(unweighted), 0.7812(weighted) vs. 0.7410(unweighted), 0.7780(weighted) vs. 0.7399(unweighted), 0.7045(weighted) vs. 0.6910(unweighted) for DenseNet121, DenseNet169, DenseNet201, and the baseline model VGG19, respectively. The same trend was observed using another independent dataset. The significant results revealed the critical value of using this existing state-of-the-art algorithm for image anomaly detection. Furthermore, the end-to-end model structure has the potential to work as a rapid tool for clinical imaging-based diagnosis.

Deep Learning Assisted Predict of Lung Cancer on Computed Tomography Images Using the Adaptive Hierarchical Heuristic Mathematical Model

Lung cancer is known to be one of the most dangerous diseases which are the main reason for disease and death when diagnosed in primitive stages. Since lung cancer can only be detected more broadly after it spread to lung parts and the occurrence of lung cancer in the earlier stage is very difficult to predict. It causes a greater risk as radiologists and specialist doctors assess the existence of lung cancer. For this reason, it is important to build a smart and automatic cancer prediction system that is accurate and at which stage of cancer or to improve the accuracy of the previous cancer prediction that will help determines the type of treatment and treatment depth depending on the severity of the disease. In this paper, the Adaptive Hierarchical Heuristic Mathematical Model (AHHMM) has been proposed for the deep learning approach. To analyze deep learning based on the historical therapy scheme in the development of Non-Small Cell Lung Cancers (NSCLC) automated radiation adaptation protocols that aim at optimizing local tumor regulation at lower rates of grade 2 RP2 radiation pneumonitis. Furthermore, the system proposed consists of several steps including acquiring the image, preprocessing, binarization, thresholding, and segmentation, extraction of features and detection of deep neural network (DNN). Segmentation of the lung CT image is carried out to extract any significant feature of a segmented image, and a specific feature extraction method is implemented. The test evaluation showed that the model proposed could detect 96.67 % accuracy of the absence or presence of lung cancer.

Convolutional neural network in the detection of lung carcinoma using transfer learning approach

AbstractBackgroundLung carcinoma is the leading cause of 1.76 million deaths worldwide. GLOBOCAN 2018 report says lung cancer occupies the first position in terms of incidence and mortality rate. Reasons include limited access to timely diagnosis and treatment.ObjectiveThis research work presents the viability of using convolutional neural network (CNN) for lung carcinoma detection. The proposed network automatically detects the lung carcinomas tissues through transfer learning without the difficulty of specifying features for image classification.Subjects and methodsThe study involves lung CT images of 12 male and 4 female subjects, aging between 35 and 77 years. These images are obtained in Bitmap image format with a resolution of 512 × 512. Two cases namely healthy and carcinoma are taken for study. Carcinoma cases include poorly differentiated carcinoma, moderately differentiated carcinoma. The training data consists of 800 lung CT slices, validation set consists of 100 CT images, and test data consist of 100 images, respectively.ResultsExperimental results demonstrate the VGG16 and VGG 19 network implementation with the area under the receiver operating characteristics of 0.930 and 0.90, respectively. VGG19 compete well with a sensitivity and specificity of 80% and 100% compared to VGG16 with 98% and 88%, respectively.ConclusionHence, the implementation of VGG16 and VGG19 with good accuracy proves that CNN used for lung carcinoma detection leading to timely diagnosis and treatment may decrease the mortality rate.

LUNG CANCER DETECTION FROM CT IMAGES USING SALP-ELEPHANT OPTIMIZATION-BASED DEEP LEARNING

Lung cancer detection has been a trending research area, as automating the medical diagnosis has significant benefits. Automatic identification of lung cancer from the CT images is considered as a significant technique in recent years. Even though various techniques are developed in the literature for lung cancer detection, designing an effective technique that can automatically detect lung cancer is challenging. Hence, this research aims to develop an automated lung cancer detection scheme through deep learning and hybrid optimization algorithm. Here, the CT images from the lung cancer database are pre-processed and provided to the lung segmentation, which is carried out by active contour. Then, the nodules in the segmented image are identified using the grid-based scheme. Several features, like intensity, wavelet, and scattering transform, are mined from the segmented image and given to the proposed salp-elephant herding optimization algorithm-based deep belief network (SEOA-DBN), for the classification. Here, SEOA is newly developed by considering the qualities of salp swarm algorithm (SSA) and elephant herding optimization (EHO). For the experimentation, lung CT images are considered from the standard database and compared with the various states of art techniques. From the results, it is evident that the proposed SEOA-based DBN achieved significant performance with 96% accuracy.

An inception module CNN classifiers fusion method on pulmonary nodule diagnosis by signs

A “sign” on a lung CT image refers to a radiologic finding that suggests a pathological progression of some specific disease. Analysis of CT signs is helpful to understand the pathological origin of the lesion. In-depth study of lung nodules classification with different CT signs will help to distinguish benign and malignant nodules more clearly and accurately. To this end, we propose an Inception module-based ensemble classification method for pulmonary nodule diagnosis with different nodule signs. We first construct a Convolutional Neural Network (CNN) classifier adopting Inception modules and pre-train it on ImageNet. We then fine-tune this pre-trained classifier on 10 different lung nodule sign sample sets, and fuse these 10 classifiers with an artificial immune ensemble algorithm. The overall sensitivity, specificity, and accuracy of our proposed Artificial Immune Algorithm-based Inception Networks Fusion (AIA-INF) algorithm are 82.22%, 93.17%, and 88.67%, respectively, which are significantly higher than those of the alternative Bagging and Boosting methods. The experimental results show that our Inception-based ensemble classifier offers promising performance, and compared with other CADx systems, this scheme can offer a more detailed reference for diagnosis, and can be valuable for junior radiologist training.

Automated pulmonary nodule detection system in computed tomography images based on Active-contour and SVM classification algorithm

Lung cancer is a common type of cancer that requires early diagnosis. Computer systems by particular different image processing techniques can use for increase the speed and accuracy of lung nodule detection. CT images used in this work in order to process medical images. In this paper proposed an automatic lung nodule detection algorithm using active contour method and SVM classification method. In proposed method, at first in order to achieve better results, lung CT image pre-processing is performed. Then the lung area is segmented by thresholding method followed by some reconstruction techniques to transfer non-isolated nodules into isolated ones. In the next step the nodule candidates are determined using active contour method. Then, nodules are detected by the support vector machine (SVM) classifier using efficient 2D stochastic and 3D anatomical features. In the result, nodules are detected with an overall detection rate of 87%; the number of false positive is 7.5/scan and the location of all detected nodules are recognized correctly.

Computer Aided Diagnosis System using Watershed Segmentation with Xception Based Classification Model for Lung CT Images

Early recognition and classification of pulmonary nodules by the use of computer-aided diagnosis (CAD) tools finds useful to reduce the death rate due to the illness of lung cancer. This paper devises a new CAD tool utilizing a segmentation based classification process for lung CT images. Initially, the input CT images are pre-processed by image enhancement and noise removal process. Then, watershed segmentation model is employed for the segmentation of the pre-processed images. Subsequently, the feature extraction process is carried out using Xecption model and random forest (RF) classifier is used of the identification of lung CT images as normal, benign or malignant. The use of RF model results to effective classification of the applied images. This model undergoes extensive experimentation against a benchmark lung CT image dataset and the results are investigated under several aspects. The obtained outcome pointed out the significant performance of the presented model over the compared methods.

Multiple Object Detection in Images using Template Matching

Template matching is an application in computer vision for finding similar objects between the images. Template matching is a key component in image analysis process for mapping similar patterns between images. The detection and matching of objects has gained widespread application in quality control, manufacturing and medical applications. The major challenges in template matching process are occlusion, background noise and non-rigid transformation particularly in medical images. The present work proposes a template matching method based on correlation analysis techniques to detect multiple objects occurrence in an image. The method has been experimented for various real-time applications. In medical images, the proposed method gave an accuracy of 86% in detecting the nodules in lung CT images.

Abnormality Detection of TB using Instance Learned Classifier on Lung CT Images

Tuberculosis is one of the serious health threatening disease which is more ubiquitous in African countries. According to World Health Organization[1], it is the second leading cause of death from an infection after HIV and 10.4 million cases of TB and 1.3 million deaths were reported worldwide in 2017 based on the estimates of Centre for Disease Control and Prevention (CDC). This paper presents abnormality detection of TB using an instance based learning classifier known as the KNN classifier an SVM classifier. If input image classified as abnormal then abnormal region is extracted using the segmentation. The system has been tested on the number of lung CT scan images.

Deep Learning Based Depthwise Separable Model For Effective Diagnosis And Classification of Lung Ct Images

Lung cancer is a serious illness which leads to increased mortality rate globally. The identification of lung cancer at the beginning stage is the probable method of improving the survival rate of the patients. Generally, Computed Tomography (CT) scan is applied for finding the location of the tumor and determines the stage of cancer. Existing works has presented an effective diagnosis classification model for CT lung images. This paper designs an effective diagnosis and classification model for CT lung images. The presented model involves different stages namely pre-processing, segmentation, feature extraction and classification. The initial stage includes an adaptive histogram based equalization (AHE) model for image enhancement and bilateral filtering (BF) model for noise removal. The pre-processed images are fed into the second stage of watershed segmentation model for effectively segment the images. Then, a deep learning based Xception model is applied for prominent feature extraction and the classification takes place by the use of logistic regression (LR) classifier. A comprehensive simulation is carried out to ensure the effective classification of the lung CT images using a benchmark dataset. The outcome implied the outstanding performance of the presented model on the applied test images.

Lung Cancer Segmentation in CT Images Using Fuzzy-C Means Clustering and Artificial Bee Colony Algorithm

One of the challenging issues to most of the researches is to segment pulmonary nodules from the CT Lung images. This Research focus on rapid segmentation of pulmonary nodules from the CT Lung images based on Fuzzy-C Means Clustering and Artificial Bee Colony Algorithm. Classic 2D otsu algorithm is used for segmentation and Artificial Bee colony algorithm is used for finding optimum threshold values. Finally, FCM (Fuzzy-C Means) clustering is used over the CT segmented images to cluster the images.

Statistical considerations for testing an AI algorithm used for prescreening lung CT images

Artificial intelligence, as applied to medical images to detect, rule out, diagnose, and stage disease, has seen enormous growth over the last few years. There are multiple use cases of AI algorithms in medical imaging: first-reader (or concurrent) mode, second-reader mode, triage mode, and more recently prescreening mode as when an AI algorithm is applied to the worklist of images to identify obvious negative cases so that human readers do not need to review them and can focus on interpreting the remaining cases. In this paper we describe the statistical considerations for designing a study to test a new AI prescreening algorithm for identifying normal lung cancer screening CTs. We contrast agreement vs. accuracy studies, and retrospective vs. prospective designs. We evaluate various test performance metrics with respect to their sensitivity to changes in the AI algorithm's performance, as well as to shifts in reader behavior to a revised worklist. We consider sample size requirements for testing the AI prescreening algorithm.