CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images

Artificial intelligence system-based histogram analysis of computed tomography features to predict tumor invasiveness of ground-glass nodules

Background

The use of an artificial intelligence (AI)-based diagnostic system can significantly aid in analyzing the histogram of pulmonary nodules. The aim of our study was to evaluate the value of computed tomography (CT) histogram indicators analyzed by AI in predicting the tumor invasiveness of ground-glass nodules (GGNs) and to determine the added value of contrast-enhanced CT (CECT) compared with nonenhanced CT (NECT) in this prediction.

Methods

This study enrolled patients with persistent GGNs who underwent preoperative NECT and CECT scanning. AI-based histogram analysis was performed for pathologically confirmed GGNs, which was followed by screening invasiveness-related factors via univariable analysis. Multivariable logistic models were developed based on candidate CT histogram indicators measured on either NECT or CECT. Receiver operating characteristic (ROC) curve and precision-recall (PR) curve were used to evaluate the models' performance.

Results

A total of 116 patients comprising 121 GGNs were included and divided into the precancerous lesion and adenocarcinoma groups based on invasiveness. In the AI-based histogram analysis, the mean CT value [NECT: odds ratio (OR) =1.009; 95% confidence interval (CI): 1.004-1.013; P<0.001] and solid component volume (NECT: OR =1.005; 95% CI: 1.000-1.010; P=0.032) were associated with the adenocarcinoma and used for multivariable logistic modeling. The area under ROC curve (AUC) and PR curve (AUPR) were not significantly different between the NECT model (AUC =0.765, 95% CI: 0.679-0.837; AUPR =0.907, 95% CI: 0.825-0.953) and the optimal CECT model (delayed phase: AUC =0.772, 95% CI: 0.687-0.843; AUPR =0.895, 95% CI: 0.812-0.944). No significantly different metrics were observed between the NECT and CECT models (precision: 0.707 vs. 0.742; P=0.616).

Conclusions

The AI diagnostic system can help in the diagnosis of GGNs. The system displayed decent performance in GGN detection and alert to malignancy. Mean CT value and solid component volume were independent predictors of tumor invasiveness. CECT provided no additional improvement in diagnostic performance as compared with NECT.

A proposed methodology for detecting the malignant potential of pulmonary nodules in sarcoma using computed tomographic imaging and artificial intelligence-based models

The presence of lung metastases in patients with primary malignancies is an important criterion for treatment management and prognostication. Computed tomography (CT) of the chest is the preferred method to detect lung metastasis. However, CT has limited efficacy in differentiating metastatic nodules from benign nodules (e.g., granulomas due to tuberculosis) especially at early stages (<5 mm). There is also a significant subjectivity associated in making this distinction, leading to frequent CT follow-ups and additional radiation exposure along with financial and emotional burden to the patients and family. Even 18F-fluoro-deoxyglucose positron emission technology-computed tomography (18F-FDG PET-CT) is not always confirmatory for this clinical problem. While pathological biopsy is the gold standard to demonstrate malignancy, invasive sampling of small lung nodules is often not clinically feasible. Currently, there is no non-invasive imaging technique that can reliably characterize lung metastases. The lung is one of the favored sites of metastasis in sarcomas. Hence, patients with sarcomas, especially from tuberculosis prevalent developing countries, can provide an ideal platform to develop a model to differentiate lung metastases from benign nodules. To overcome the lack of optimal specificity of CT scan in detecting pulmonary metastasis, a novel artificial intelligence (AI)-based protocol is proposed utilizing a combination of radiological and clinical biomarkers to identify lung nodules and characterize it as benign or metastasis. This protocol includes a retrospective cohort of nearly 2,000-2,250 sample nodules (from at least 450 patients) for training and testing and an ambispective cohort of nearly 500 nodules (from 100 patients; 50 patients each from the retrospective and prospective cohort) for validation. Ground-truth annotation of lung nodules will be performed using an in-house-built segmentation tool. Ground-truth labeling of lung nodules (metastatic/benign) will be performed based on histopathological results or baseline and/or follow-up radiological findings along with clinical outcome of the patient. Optimal methods for data handling and statistical analysis are included to develop a robust protocol for early detection and classification of pulmonary metastasis at baseline and at follow-up and identification of associated potential clinical and radiological markers.

LncRNA FAM138B inhibits the progression of non-small cell lung cancer through miR-105-5p

As a type of lung cancer, non-small cell lung cancer (NSCLC) has the characteristics of high mortality and high recurrence rate, which poses a great threat to human life and health. Due to the high risk of surgical treatment and the slow recovery of wounds, non-coding RNAs, especially lncRNAs are used as new potential clinical prognostic markers to prevent and treat cancer in advance. This study aims to explore the role of FAM138B in NSCLC and its possibility as a prognostic biomarker. Real-timequantitative polymerase chain reaction (RT-qPCR) was used to detect the expression and overexpression level of lncRNA FAM138B (FAM138B) in cells and tissues. The CCK-8, Transwell migration and invasion methods were performed to observe the cell transfection.The interaction between FAM138B and miR-105-5p was predicted by the bioinformatics tool starBase v2.0, and verified by the luciferase reporter gene experiment. Kaplan-Meier and Cox regression analyses were used to determine the prognostic significance of FAM138B in NSCLC. The expression of FAM138B is down-regulated in NSCLC cells and tissues. Overexpression of FAM138B can inhibit the expression level of miR-105-5p in NSCLC cells, and the ability of NSCLC cells to proliferate, migrate and invade is downregulated. FAM138B targets miR-105-5p, and there is a negative correlation between FAM138B and miR-105-5p. It is confirmed that FAM138B inhibits the progression of NSCLC by targeting miR-105-5p and can be a potential prognostic biomarker for NSCLC.

Review on chest pathogies detection systems using deep learning techniques

Chest radiography is the standard and most affordable way to diagnose, analyze, and examine different thoracic and chest diseases. Typically, the radiograph is examined by an expert radiologist or physician to decide about a particular anomaly, if exists. Moreover, computer-aided methods are used to assist radiologists and make the analysis process accurate, fast, and more automated. A tremendous improvement in automatic chest pathologies detection and analysis can be observed with the emergence of deep learning. The survey aims to review, technically evaluate, and synthesize the different computer-aided chest pathologies detection systems. The state-of-the-art of single and multi-pathologies detection systems, which are published in the last five years, are thoroughly discussed. The taxonomy of image acquisition, dataset preprocessing, feature extraction, and deep learning models are presented. The mathematical concepts related to feature extraction model architectures are discussed. Moreover, the different articles are compared based on their contributions, datasets, methods used, and the results achieved. The article ends with the main findings, current trends, challenges, and future recommendations.

A Comprehensive Survey on the Progress, Process, and Challenges of Lung Cancer Detection and Classification

Lung cancer is the primary reason of cancer deaths worldwide, and the percentage of death rate is increasing step by step. There are chances of recovering from lung cancer by detecting it early. In any case, because the number of radiologists is limited and they have been working overtime, the increase in image data makes it hard for them to evaluate the images accurately. As a result, many researchers have come up with automated ways to predict the growth of cancer cells using medical imaging methods in a quick and accurate way. Previously, a lot of work was done on computer-aided detection (CADe) and computer-aided diagnosis (CADx) in computed tomography (CT) scan, magnetic resonance imaging (MRI), and X-ray with the goal of effective detection and segmentation of pulmonary nodule, as well as classifying nodules as malignant or benign. But still, no complete comprehensive review that includes all aspects of lung cancer has been done. In this paper, every aspect of lung cancer is discussed in detail, including datasets, image preprocessing, segmentation methods, optimal feature extraction and selection methods, evaluation measurement matrices, and classifiers. Finally, the study looks into several lung cancer-related issues with possible solutions.

Multi-Perspective Hierarchical Deep-Fusion Learning Framework for Lung Nodule Classification

Lung cancer is the leading cancer type that causes mortality in both men and women. Computer-aided detection (CAD) and diagnosis systems can play a very important role for helping physicians with cancer treatments. This study proposes a hierarchical deep-fusion learning scheme in a CAD framework for the detection of nodules from computed tomography (CT) scans. In the proposed hierarchical approach, a decision is made at each level individually employing the decisions from the previous level. Further, individual decisions are computed for several perspectives of a volume of interest. This study explores three different approaches to obtain decisions in a hierarchical fashion. The first model utilizes raw images. The second model uses a single type of feature image having salient content. The last model employs multi-type feature images. All models learn the parameters by means of supervised learning. The proposed CAD frameworks are tested using lung CT scans from the LIDC/IDRI database. The experimental results showed that the proposed multi-perspective hierarchical fusion approach significantly improves the performance of the classification. The proposed hierarchical deep-fusion learning model achieved a sensitivity of 95% with only 0.4 fp/scan.

Auto diagnostic system for detecting solitary and juxtapleural pulmonary nodules in computed tomography images using machine learning

Lung cancer is one of the most serious cancers in the world with the minimum survival rate after the diagnosis as it appears in Computed Tomography scans. Lung nodules may be isolated from (solitary) or attached to (juxtapleural) other structures such as blood vessels or the pleura. Diagnosis of lung nodules according to their location increases the survival rate as it achieves diagnostic and therapeutic quality assurance. In this paper, a Computer Aided Diagnosis (CADx) system is proposed to classify solitary nodules and juxtapleural nodules inside the lungs. Two main auto-diagnostic schemes of supervised learning for lung nodules classification are achieved. In the first scheme, (bounding box + Maximum intensity projection) and (Thresholding + K-means clustering) segmentation approaches are proposed then first- and second-order features are extracted. Fisher score ranking is also used in the first scheme as a feature selection method. The higher five, ten, and fifteen ranks of the feature set are selected. In the first scheme, Support Vector Machine (SVM) classifier is used. In the second scheme, the same segmentation approaches are used with Deep Convolutional neural networks (DCNN) which is a successful tool for deep learning classification. Because of the limited data sample and imbalanced data, tenfold cross-validation and random oversampling are used for the two schemes. For diagnosis of the solitary nodule, the first scheme with SVM achieved the highest accuracy and sensitivity 91.4% and 89.3%, respectively, with radial basis function and applying the (Thresholding + Kmeans clustering) segmentation approach and the higher 15 ranks of the feature set. In the second scheme, DCNN achieved the highest accuracy and sensitivity 96% and 95%, respectively, to detect the solitary nodule when applying the bounding box and maximum intensity projection segmentation approach. Receiver operating characteristic curve is used to evaluate the classifier’s performance. The max. AUC = 90.3% is achieved with DCNN classifier for detecting solitary nodules. This CAD system acts as a second opinion for the radiologist to help in the early diagnosis of lung cancer. The accuracy, sensitivity, and specificity of scheme I (SVM) and scheme II (DCNN) showed promising results in comparison to other published studies.

An Effective Approach for Automated Lung Node Detection using CT Scans

BACKGROUND

Pulmonary or benign nodules are classified as nodules with a diameter of 3 cm or less and defined as non-cancerous nodules. The early diagnosis of malignant lung nodules is important for a more reliable prognosis of lung cancer and less invasive chemotherapy and radiotherapy procedures.

OBJECTIVE

This study aimed to introduce an improved hybrid approach for efficient nodule mask generation and false-positive reduction.

MATERIAL AND METHODS

In this experimental study, nodule segmentation preprocessing was conducted to prepare the input computed tomography (CT) scans for the U-Net convolutional neural network (CNN) model, and includes the normalization of CT scans and transfer of pixel values corresponding to the radiodensity of Hounsfield Units (HU). A U-Net CNN was developed based on lung CT scans for nodule identification.

RESULTS

The U-net model converged to a dice coefficient of 0.678 with a sensitivity of 75%. Many false positives were considered in every real positive, at 11.1, reduced in the proposed CNN to 2.32 FPs (False Positive) per TP (True Positive).

CONCLUSION

Based on the disadvantages of the largest nodule, the similarity of extracted features of the current study with those of others was imperative. The improved hybrid approach introduced was useful for other image classification tasks as expected.

Improved Diagnostic Accuracy of Ameloblastoma and Odontogenic Keratocyst on Cone-Beam CT by Artificial Intelligence

OBJECTIVE

The purpose of this study was to utilize a convolutional neural network (CNN) to make preoperative differential diagnoses between ameloblastoma (AME) and odontogenic keratocyst (OKC) on cone-beam CT (CBCT).

METHODS

The CBCT images of 178 AMEs and 172 OKCs were retrospectively retrieved from the Hospital of Stomatology, Wuhan University. The datasets were randomly split into a training dataset of 272 cases and a testing dataset of 78 cases. Slices comprising lesions were retained and then cropped to suitable patches for training. The Inception v3 deep learning algorithm was utilized, and its diagnostic performance was compared with that of oral and maxillofacial surgeons.

RESULTS

The sensitivity, specificity, accuracy, and F1 score were 87.2%, 82.1%, 84.6%, and 85.0%, respectively. Furthermore, the average scores of the same indexes for 7 senior oral and maxillofacial surgeons were 60.0%, 71.4%, 65.7%, and 63.6%, respectively, and those of 30 junior oral and maxillofacial surgeons were 63.9%, 53.2%, 58.5%, and 60.7%, respectively.

CONCLUSION

The deep learning model was able to differentiate these two lesions with better diagnostic accuracy than clinical surgeons. The results indicate that the CNN may provide assistance for clinical diagnosis, especially for inexperienced surgeons.

Improving Classification Accuracy of Pulmonary Nodules using Simplified Deep Neural Network

Background:

Lung cancer is among the major causes of death in the world. Early detection of lung cancer is a major challenge. These encouraged the development of Computer-Aided Detection (CAD) system.

Objectives:

We designed a CAD system for performance improvement in detecting and classifying pulmonary nodules. Though the system will not replace radiologists, it will be helpful to them in order to accurately diagnose lung cancer.

Methods:

The architecture comprises of two steps, among which in the first step CT scans are pre-processed and the candidates are extracted using the positive and negative annotations provided along with the LUNA16 dataset, and the second step consists of three different neural networks for classifying the pulmonary nodules obtained from the first step. The models in the second step consist of 2D-Convolutional Neural Network (2D-CNN), Visual Geometry Group-16 (VGG-16) and simplified VGG-16, which independently classify pulmonary nodules.

Results:

The classification accuracies achieved for 2D-CNN, VGG-16 and simplified VGG-16 were 99.12%, 98.17% and 99.60%, respectively.

Conclusion:

The integration of deep learning techniques along with machine learning and image processing can serve as a good means of extracting pulmonary nodules and classifying them with improved accuracy. Based on these results, it can be concluded that the transfer learning concept will improve system performance. In addition, performance improves proper designing of the CAD system by considering the amount of dataset and the availability of computing power.

Texture recognition of pulmonary nodules based on volume local direction ternary pattern

In recent years, the incidence of lung cancer has been increasing. Lung cancer detection is based on computed tomography (CT) imaging of the lung area to determine whether there are pulmonary nodules. And then judge what’s good and what’s bad. However, due to the traditional way of manual reading and lack of experience and other problems. This leads to visual fatigue and misdiagnosis and missed diagnosis. In order to detect pulmonary nodules early and accurately, a new assistant diagnosis method for pulmonary nodules is proposed. Firstly, the image is preprocessed and denoised by median filter, the lung parenchyma is segmented by random walk algorithm and the region of interest is extracted, and then, according to the continuity of the CT slices, the texture feature extraction method of pulmonary nodules based on volume local direction ternary pattern is used to extract the features. Finally, the pulmonary nodules are identified and classified by the assistant diagnosis model of pulmonary nodules based on Stacking algorithm. In order to illustrate the validity of the diagnosis model, the experiments are carried out by cross-validation of ten folds. Experiments using data from LIDC database show that the accuracy, sensitivity and specificity of the proposed method are 82.2%, 85.7%, and 78.8%, respectively. Texture Recognition method based on volume vocal direction ternary pattern is feasible for the identification of pulmonary nodules and provides a reference value for doctor-assisted diagnosis.

Seven tumor-associated autoantibodies as a serum biomarker for primary screening of early-stage non-small cell lung cancer

Objective

The purpose of this study was to analyze the levels of tumor‐associated autoantibodies (TAAbs) in lung diseases and determine their diagnostic efficiency in early‐stage non‐small cell lung cancer (NSCLC).

Methods

We retrospectively analyzed the levels of 7‐TAAbs in 177 newly diagnosed early‐stage NSCLC patients, 202 patients with lung benign diseases and 137 healthy cases. The levels of a panel of 7‐TAAbs, including p53, GAGE7, PGP9.5, CAGE, MAGE A1, SOX2, GBU4‐5, were measured by ELISA.

Results

The serum levels of p53, GAGE7, PGP9.5, CAGE, MAGE A1, SOX2, and GBU4‐5 were not statistically different among NSCLC, benign and healthy groups (p > 0.05). The area under the curve (AUC) of 7‐TAAbs was all lower than 0.70. The sensitivity of combined detection was the highest (23.73%), while the specificity was the lowest (88.79%). The positive rates of PGP9.5, SOX2, and combined detection were significantly different among the three groups (p < 0.05). Among them, PGP9.5 and combined detection were significantly different between the NSCLC and benign groups (p < 0.05), PGP9.5, SOX2 and combined detection were significantly different between the NSCLC and healthy groups (p < 0.05).

Conclusions

The diagnostic efficiency of 7‐TAAbs in early‐stage NSCLC was not high, so it cannot be used alone as a screening method for NSCLC.

Unraveling the interplay of image formation, data representation and learning in CT-based COPD phenotyping automation: The need for a meta-strategy

PURPOSE

In the literature on automated phenotyping of chronic obstructive pulmonary disease (COPD), there is a multitude of isolated classical machine learning and deep learning techniques, mostly investigating individual phenotypes, with small study cohorts and heterogeneous meta-parameters, e.g., different scan protocols or segmented regions. The objective is to compare the impact of different experimental setups, i.e., varying meta-parameters related to image formation and data representation, with the impact of the learning technique for subtyping automation for a variety of phenotypes. The identified associations of these parameters with automation performance and their interactions might be a first step towards a determination of optimal meta-parameters, i.e., a meta-strategy.

METHODS

A clinical cohort of 981 patients (53.8 ± 15.1 years, 554 male) was examined. The inspiratory CT images were analyzed to automate the diagnosis of 13 COPD phenotypes given by two radiologists. A benchmark feature set that integrates many quantitative criteria was extracted from the lung and trained a variety of learning algorithms on the first 654 patients (two thirds) and the respective algorithm retrospectively assessed the remaining 327 patients (one third). The automation performance was evaluated by the area under the receiver operating characteristic curve (AUC). 1717 experiments were conducted with varying meta-parameters such as reconstruction kernel, segmented regions and input dimensionality, i.e., number of extracted features. The association of the meta-parameters with the automation performance was analyzed by multivariable general linear model decomposition of the automation performance in the contributions of meta-parameters and the learning technique.

RESULTS

The automation performance varied strongly for varying meta-parameters. For emphysema-predominant phenotypes, an AUC of 93%-95% could be achieved for the best meta-configuration. The airways-predominant phenotypes led to a lower performance of 65%-85%, while smooth kernel configurations on average were unexpectedly superior to those with sharp kernels. The performance impact of meta-parameters, even that of often neglected ones like the missing-data imputation, was in general larger than that of the learning technique. Advanced learning techniques like 3D deep learning or automated machine learning yielded inferior automation performance for non-optimal meta-configurations in comparison to simple techniques with suitable meta-configurations. The best automation performance was achieved by a combination of modern learning techniques and a suitable meta-configuration.

CONCLUSIONS

Our results indicate that for COPD phenotype automation, study design parameters such as reconstruction kernel and the model input dimensionality should be adapted to the learning technique and may be more important than the technique itself. To achieve optimal automation and prediction results, the interaction between input those meta-parameters and the learning technique should be considered. This might be particularly relevant for the development of specific scan protocols for novel learning algorithms, and towards an understanding of good study design for automated phenotyping.

Micronodular lung disease on high-resolution CT: patterns and differential diagnosis

With the advent of high-resolution computed tomography (HRCT), micronodular lung disease is a routinely encountered pathology in thoracic imaging. This article will review how to differentiate the three main micronodular patterns and review the differential diagnosis for each. Differential diagnosis of micronodular lung disease may be extensive, but by identifying the pattern and using additional clues, such as distribution, additional imaging findings, and clinical history, a radiologist can make an accurate diagnosis. First, three micronodular patterns - centrilobular, peri-lymphatic, and random - can be identified by using a simple algorithm based on the location of nodules. This algorithm requires understanding of the anatomy and function of the secondary pulmonary lobule. Each micronodular pattern offers a unique differential diagnosis. Centrilobular nodules can be seen with inflammatory, infectious, or vascular aetiologies; peri-lymphatic nodules with sarcoidosis and lymphangitic carcinomatosis; and random nodules with haematogenous metastases or infections.

Lung cancer identification: a review on detection and classification

Lung cancer is one of the most common diseases among humans and one of the major causes of growing mortality. Medical experts believe that diagnosing lung cancer in the early phase can reduce death with the illustration of lung nodule through computed tomography (CT) screening. Examining the vast amount of CT images can reduce the risk. However, the CT scan images incorporate a tremendous amount of information about nodules, and with an increasing number of images make their accurate assessment very challenging tasks for radiologists. Recently, various methods are evolved based on handcraft and learned approach to assist radiologists. In this paper, we reviewed different promising approaches developed in the computer-aided diagnosis (CAD) system to detect and classify the nodule through the analysis of CT images to provide radiologists' assistance and present the comprehensive analysis of different methods.

A bilinear convolutional neural network for lung nodules classification on CT images

PURPOSE

Lung cancer is the most frequent cancer worldwide and is the leading cause of cancer-related deaths. Its early detection and treatment at the stage of a lung nodule improve the prognosis. In this study was proposed a new classification approach named bilinear convolutional neural network (BCNN) for the classification of lung nodules on CT images.

METHODS

Convolutional neural network (CNN) is considered as the leading model in deep learning and is highly recommended for the design of computer-aided diagnosis systems thanks to its promising results on medical image analysis. The proposed BCNN scheme consists of two-stream CNNs (VGG16 and VGG19) as feature extractors followed by a support vector machine (SVM) classifier for false positive reduction. Series of experiments are performed by introducing the bilinear vector features extracted from three BCNN combinations into various types of SVMs that we adopted instead of the original softmax to determine the most suitable classifier for our study.

RESULTS

The method performance was evaluated on 3186 images from the public LUNA16 database. We found that the BCNN [VGG16, VGG19] combination with and without SVM surpassed the [VGG16]2 and [VGG19]2 architectures, achieved an accuracy rate of 91.99% against 91.84% and 90.58%, respectively, and an area under the curve (AUC) rate of 95.9% against 94.8% and 94%, respectively.

CONCLUSION

The proposed method improved the outcomes of conventional CNN-based architectures and showed promising and satisfying results, compared to other works, with an affordable complexity. We believe that the proposed BCNN can be used as an assessment tool for radiologists to make a precise analysis of lung nodules and an early diagnosis of lung cancers.

Classification of Lung Nodules Based on Deep Residual Networks and Migration Learning

The classification process of lung nodule detection in a traditional computer-aided detection (CAD) system is complex, and the classification result is heavily dependent on the performance of each step in lung nodule detection, causing low classification accuracy and high false positive rate. In order to alleviate these issues, a lung nodule classification method based on a deep residual network is proposed. Abandoning traditional image processing methods and taking the 50-layer ResNet network structure as the initial model, the deep residual network is constructed by combining residual learning and migration learning. The proposed approach is verified by conducting experiments on the lung computed tomography (CT) images from the publicly available LIDC-IDRI database. An average accuracy of 98.23% and a false positive rate of 1.65% are obtained based on the ten-fold cross-validation method. Compared with the conventional support vector machine (SVM)-based CAD system, the accuracy of our method improved by 9.96% and the false positive rate decreased by 6.95%, while the accuracy improved by 1.75% and 2.42%, respectively, and the false positive rate decreased by 2.07% and 2.22%, respectively, in contrast to the VGG19 model and InceptionV3 convolutional neural networks. The experimental results demonstrate the effectiveness of our proposed method in lung nodule classification for CT images.

Scoring pleurisy in slaughtered pigs using convolutional neural networks

Diseases of the respiratory system are known to negatively impact the profitability of the pig industry, worldwide. Considering the relatively short lifespan of pigs, lesions can be still evident at slaughter, where they can be usefully recorded and scored. Therefore, the slaughterhouse represents a key check-point to assess the health status of pigs, providing unique and valuable feedback to the farm, as well as an important source of data for epidemiological studies. Although relevant, scoring lesions in slaughtered pigs represents a very time-consuming and costly activity, thus making difficult their systematic recording. The present study has been carried out to train a convolutional neural network-based system to automatically score pleurisy in slaughtered pigs. The automation of such a process would be extremely helpful to enable a systematic examination of all slaughtered livestock. Overall, our data indicate that the proposed system is well able to differentiate half carcasses affected with pleurisy from healthy ones, with an overall accuracy of 85.5%. The system was better able to recognize severely affected half carcasses as compared with those showing less severe lesions. The training of convolutional neural networks to identify and score pneumonia, on the one hand, and the achievement of trials in large capacity slaughterhouses, on the other, represent the natural pursuance of the present study. As a result, convolutional neural network-based technologies could provide a fast and cheap tool to systematically record lesions in slaughtered pigs, thus supplying an enormous amount of useful data to all stakeholders in the pig industry.

Automatic Plaque Segmentation in Coronary Optical Coherence Tomography Images

Coronary optical coherence tomography (OCT) is a new high-resolution intravascular imaging technology that clearly depicts coronary artery stenosis and plaque information. Study of coronary OCT images is of significance in the diagnosis of coronary atherosclerotic heart disease (CAD). We introduce a new method based on the convolutional neural network (CNN) and an improved random walk (RW) algorithm for the recognition and segmentation of calcified, lipid and fibrotic plaque in coronary OCT images. First, we design CNN with three different depths (2, 4 or 6 convolutional layers) to perform the automatic recognition and select the optimal CNN model. Then, we device an improved RW algorithm. According to the gray-level distribution characteristics of coronary OCT images, the weights of intensity and texture term in the weight function of RW algorithm are adjusted by an adaptive weight. Finally, we apply mathematical morphology in combination with two RWs to accurately segment the plaque area. Compared with the ground truth of clinical segmentation results, the Jaccard similarity coefficient (JSC) of calcified and lipid plaque segmentation results is 0.864, the average symmetric contour distance (ASCD) is 0.375[Formula: see text]mm, the JSC and ASCD reliabilities are 88.33% and 92.50% respectively. The JSC of fibrotic plaque is 0.876, the ASCD is 0.349[Formula: see text]mm, the JSC and ASCD reliabilities are 90.83% and 95.83% respectively. In addition, the average segmentation time (AST) does not exceed 5 s. Reliable and significantly improved results have been achieved in this study. Compared with the CNN, traditional RW algorithm and other methods. The proposed method has the advantages of fast segmentation, high accuracy and reliability, and holds promise as an aid to doctors in the diagnosis of CAD.

Deep CNN models for pulmonary nodule classification: Model modification, model integration, and transfer learning

BACKGROUND

Deep learning has made spectacular achievements in analysing natural images, but it faces challenges for medical applications partly due to inadequate images.

OBJECTIVE

Aiming to classify malignant and benign pulmonary nodules using CT images, we explore different strategies to utilize the state-of-the-art deep convolutional neural networks (CNN).

METHODS

Experiments are conducted using the Lung Image Database Consortium image collection (LIDC-IDRI), which is a public database containing 1018 cases. Three strategies are implemented including to 1) modify some state-of-the-art CNN architectures, 2) integrate different CNNs and 3) adopt transfer learning. Totally, 11 deep CNN models are compared using the same dataset.

RESULTS

Study demonstrates that, for the model modification scheme, a concise CifarNet performs better than the other modified CNNs with more complex architectures, achieving an area under ROC curve of AUC = 0.90. Integrated CNN models do not significantly improve the classification performance, but the model complexity is reduced. Transfer learning outperforms the other two schemes and ResNet with fine-tuning leads to the best performance with an AUC = 0.94, as well as the sensitivity of 91% and an overall accuracy of 88%.

CONCLUSIONS

Model modification, model integration, and transfer learning can play important roles to identify and generate optimal deep CNN models in classifying pulmonary nodules based on CT images efficiently. Transfer learning is preferred when applying deep learning to medical imaging applications.