A Deep Convolutional Neural Network Based Lung Disorder Diagnosis

An architecture for automatic lung tissue classification method based on the Deep Learning techniques is designed in this paper. Recent works on Deep Learning techniques achieved impressive results in the field of medical image classification. So, we designed a Convolution Neural Network (CNN) for the classification of five categories of Interstitial Lung Diseases (ILD) patterns in High-Resolution Computed Tomography (HRCT) images. The CNN consists of 3 Convolution layers, Leaky ReLU activation followed by Maximum pooling layer and dense layer. The last Fully Connected (FC) layer has 5 outputs equivalent to the classes considered such as Normal, Ground Glass (GG), Emphysema, Micro Nodules, and Fibrosis. The proposed CNN is trained and evaluated on the publicly available ILD database provided by the University Hospitals of Geneva (HUG). Experimental results are compared with the state-of-art, which shows an outstanding performance of the proposed CNN model giving 94.67% accuracy and 94.65% Favg .

Deep learning for screening of interstitial lung disease patterns in high-resolution CT images

To assess the frequency of disease subsets and the spectrum of organ involvement, particularly focusing on interstitial lung disease (ILD) patterns among patients with systemic sclerosis (SSc). Observational study. Place and Duration of the Study: Institute of Rheumatic Diseases, Central Park Teaching Hospital, and its affiliated Arthritis Care Centre, Lahore, Pakistan, from July 2022 to December 2023. Data were extracted from electronic records and gathered using a questionnaire.Patients were classified into limited cutaneous systemic sclerosis (lcSSc) and diffuse cutaneous systemic sclerosis (dcSSc) subsets based on clinical criteria. Gender, age, duration of disease, clinical features, and ILD patterns were compared between the groups. The mean age of the 68 (88.3%) female patients was 37.9 ± 11.2 years. Younger patients presented with diffuse scleroderma (36 ± 11.3 years) compared to those with limited scleroderma (40.2 ± 10.7 years). The most common clinical feature was Raynaud's phenomenon (90.9%), followed by digital ulcers (41.6%). ILD was present in 68.8%, with non-specific interstitial pneumonia (NSIP) identified in 31.2%, usual interstitial pneumonia (UIP) in 19.5%, and fibrosing NSIP in 3.9%. Systemic sclerosis predominantly affects younger females, with a higher diffuse cutaneous subtype. Raynaud's phenomenon is the most common manifestation. ILD is a significant complication, with NSIP being the most common pattern observed. Systemic sclerosis, Rheumatic diseases, Limited cutaneous systematic sclerosis, Diffuse cutaneous systematic sclerosis.

Holistically detecting interstitial lung disease (ILD) patterns from CT images is challenging yet clinically important. Unfortunately, most existing solutions rely on manually provided regions of interest, limiting their clinical usefulness. We focus on two challenges currently existing in two publicly available datasets. First of all, missed labeling of regions of interest is a common issue in existing medical image datasets due to the labor-intensive nature of the annotation task which requires high levels of clinical proficiency. Second, no work has yet focused on predicting more than one ILD from the same CT slice, despite the frequency of such occurrences. To address these limitations, we propose three algorithms based on deep convolutional neural networks (CNNs). The differences between the two main publicly available datasets are discussed as well.

Interstitial lung disease (ILD) refers to a group of various abnormal inflammations of lung tissues and early diagnosis of these disease patterns is crucial for the treatment. Yet it is difficult to make an accurate diagnosis due to the similarity among the clinical manifestations of these diseases. In order to assist the radiologists, computer-aided diagnosis systems have been developed. Besides, the potential of deep convolutional neural networks (CNNs) is also expected to exert on the medical image analysis in recent years. In this paper, we design a new deep convolutional neural network (CNN) architecture to achieve the classification task of ILD patterns. Furthermore, we also propose a novel two-stage transfer learning (TSTL) method to deal with the problem of the lack of training data, which leverages the knowledge learned from sufficient textural source data and auxiliary unlabeled lung CT data to the target domain. We adopt the unsupervised manner to learn the unlabeled data, by which the objective function composed of the prediction confidence and mutual information are optimized. The experimental results show that our proposed CNN architecture achieves desirable performance and outperforms most of the state-of-the-art ones. The comparative analysis demonstrates the promising feasibility and advantages of the proposed two-stage transfer learning strategy as well as the potential of the knowledge learning from lung CT data. Graphical Abstract The framework of the proposed two-stage transfer learning method.

Coronavirus (COVID-19) was first observed in Wuhan, China, and quickly propagated worldwide. It is considered the supreme crisis of the present era and one of the most crucial hazards threatening worldwide health. Therefore, the early detection of COVID-19 is essential. The common way to detect COVID-19 is the reverse transcription-polymerase chain reaction (RT-PCR) test, although it has several drawbacks. Computed tomography (CT) scans can enable the early detection of suspected patients, however, the overlap between patterns of COVID-19 and other types of pneumonia makes it difficult for radiologists to diagnose COVID-19 accurately. On the other hand, deep learning (DL) techniques and especially the convolutional neural network (CNN) can classify COVID-19 and non-COVID-19 cases. In addition, DL techniques that use CT images can deliver an accurate diagnosis faster than the RT-PCR test, which consequently saves time for disease control and provides an efficient computer-aided diagnosis (CAD) system. The shortage of publicly available datasets of CT images, makes the CAD system’s design a challenging task. The CAD systems in the literature are based on either individual CNN or two-fused CNNs; one used for segmentation and the other for classification and diagnosis. In this article, a novel CAD system is proposed for diagnosing COVID-19 based on the fusion of multiple CNNs. First, an end-to-end classification is performed. Afterward, the deep features are extracted from each network individually and classified using a support vector machine (SVM) classifier. Next, principal component analysis is applied to each deep feature set, extracted from each network. Such feature sets are then used to train an SVM classifier individually. Afterward, a selected number of principal components from each deep feature set are fused and compared with the fusion of the deep features extracted from each CNN. The results show that the proposed system is effective and capable of detecting COVID-19 and distinguishing it from non-COVID-19 cases with an accuracy of 94.7%, AUC of 0.98 (98%), sensitivity 95.6%, and specificity of 93.7%. Moreover, the results show that the system is efficient, as fusing a selected number of principal components has reduced the computational cost of the final model by almost 32%.

Pattern of interstitial lung disease in Southern India: A retrospective study.

BackgroundThe diagnosis of thyroid cancer and distinguishing benign from malignant thyroid nodules by junior radiologists can be challenging. This study aimed to develop a computer-aided diagnosis (CAD) system based on the Thyroid Imaging Reporting and Data System (TI-RADS) to distinguish benign from malignant thyroid nodules by analyzing ultrasound images to improve the diagnostic performance of junior radiologists.Material/MethodsA modified TI-RADS based on a convolutional neural network (CNN) was used to develop the CAD system. This retrospective study reviewed 789 thyroid nodules from 695 patients and included radiologists with different diagnostic experience. Five study groups included the CAD group, the junior radiologist group, the intermediate-level radiologist group, the senior radiologist group, and the group in which the junior radiologist used the CAD system. The ultrasound findings were reviewed and compared with the histopathology diagnosis.ResultsThe CAD system for the diagnosis of thyroid cancer showed an accuracy of 80.35%, a sensitivity of 80.64%, a specificity of 80.13%, a positive predictive value (PPV) of 76.02%, a negative predictive value (NPV) of 84.12%, and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.87. The accuracy of the junior radiologists in diagnosing thyroid cancer using CAD was similar to that of intermediate-level radiologists (79.21% vs. 77.57%; P=0.427).ConclusionsThe use of ultrasound CAD based on the TI-RADS showed potential for distinguishing between benign and malignant thyroid nodules and improved the diagnostic performance of junior radiologists.

Early and accurate diagnosis of interstitial lung diseases (ILDs) is crucial for making treatment decisions, but can be challenging even for experienced radiologists. The diagnostic procedure is based on the detection and recognition of the different ILD pathologies in thoracic CT scans, yet their manifestation often appears similar. In this study, we propose the use of a deep purely convolutional neural network for the semantic segmentation of ILD patterns, as the basic component of a computer aided diagnosis system for ILDs. The proposed CNN, which consists of convolutional layers with dilated filters, takes as input a lung CT image of arbitrary size and outputs the corresponding label map. We trained and tested the network on a data set of 172 sparsely annotated CT scans, within a cross-validation scheme. The training was performed in an end-to-end and semisupervised fashion, utilizing both labeled and nonlabeled image regions. The experimental results show significant performance improvement with respect to the state of the art.

Background. Interstitial Lung Disease (ILD) is a frequent manifestation of Sjögren’s Disease (SjD), associated with significant morbidity and mortality. However, data on the prevalence of progressive-ILD in SjD remain scarce, and biomarkers for predicting progression are lacking. Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER) is a validated CT-based software that quantifies ILD patterns such as ground-glass opacities, reticulation, honeycombing, and low attenuation areas. CALIPER-derived parameters correlate with pulmonary function tests (PFT) and outcomes in IPF and other autoimmune ILDs, but their role in SjD-ILD is unexplored. Our aim was to assess the prognostic value of CALIPER-derived parameters in SjD-ILD patients Materials and Methods. SjD patients (2016 ACR/EULAR criteria) with HRCT-confirmed ILD followed from Jan-2018 to Sep-2023 were retrospectively included if >/=1 HRCT was suitable for CALIPER analysis. Clinical, laboratory and PFT data were collected at baseline and follow-up. Progressive-fibrosing ILD (PF-ILD) was defined (ATS criteria) by >/=2 of: worsening symptoms, FVC decline >/=5% or DLCO >/=10%, or radiological progression within 1 year. CALIPER-derived ILD% (sum of ground-glass, reticular, honeycombing) and VRS% (vascular-related structures) were calculated. Visual ILD extent (Warrick score) and pattern were assessed by a thoracic radiologist Results. Twenty-three patients (F:M=18:5, mean age 66.2±9.5 yrs, mean follow-up 6.1±5 yrs) were enrolled. ILD patterns included NSIP (n=14), UIP (n=6), and NSIP+OP (n=3). Dyspnea and cough occurred in 21 and 19 patients respectively. Median baseline FVC and DLCO were 83% and 64%. Seventeen patients received immunosuppressants; none received antifibrotics. Seven required long-term oxygen (LTO2) and 7 developed PF-ILD. Baseline ILD% and VRS% demonstrated a moderate-strong correlation with FCV% and DLCO%, visual ILD quantification (Warrick score) and between them (table 1). VRS%, Reticulation%, and Honeycombing% were significantly higher in UIP (p=.021, .038, .047 respectively). On univariate regression analysis, VRS% (OR 3.2, 95%CI 1.1-9.1, p=.03) and ILD% (OR 1.13, 95%CI 1.01-1.3, p=.05) were associated with LTO2. According to ROC analysis, VRS% had an AUC of 0.813 (p=.019) with an optimal cut-off of 3.8% yielding a sensitivity of 71.4% and a specificity of 87.5% in predicting LTO2. ILD% had an AUC of 0.777 (p=.038) with a cut-off of 11.6% resulting in a 71.4% sensitivity and a 75% specificity in predicting LTO2. On univariate analysis VRS% (OR 2.8, 95%CI 1-8, p=.05) was associated with a PF-ILD behavior in the next year, with an AUC of 0.85 (p=.023) and an optimal cut-off of 3.8% resulting in a 83.3% sensitivity and 80% specificity. Conclusions. CALIPER-derived parameters correlate strongly with lung function and predict adverse outcomes in SjD-ILD. Automated HRCT analysis offers promising digital biomarkers for ILD assessment and risk stratification. Integrating these metrics with clinical and functional data could support early identification of progressive-ILD and guide therapy. Further validation in larger cohorts is warranted.

Deep-learning approaches with data augmentation have been widely used when developing neuroimaging-based computer-aided diagnosis (CAD) systems. To prevent the inflated diagnostic performance caused by data leakage, a correct cross-validation (CV) method should be employed, but this has been still overlooked in recent deep-learning-based CAD studies. The goal of this study was to investigate the impact of correct and incorrect CV methods on the diagnostic performance of deep-learning-based CAD systems after data augmentation. To this end, resting-state electroencephalogram (EEG) data recorded from post-traumatic stress disorder patients and healthy controls were augmented using a cropping method with different window sizes, respectively. Four different CV approaches were used to estimate the diagnostic performance of the CAD system, i.e., subject-wise CV (sCV), overlapped sCV (oSCV), trial-wise CV (tCV), and overlapped tCV (otCV). Diagnostic performances were evaluated using two deep-learning models based on convolutional neural network. Data augmentation can increase the performance with all CVs, but inflated diagnostic performances were observed when using incorrect CVs (tCV and otCV) due to data leakage. Therefore, the correct CV (sCV and osCV) should be used to develop a deep-learning-based CAD system. We expect that our investigation can provide deep-insight for researchers who plan to develop neuroimaging-based CAD systems for psychiatric disorders using deep-learning algorithms with data augmentation.

Deep learning is now widely used as an efficient tool for medical image classification and segmentation. However, conventional machine learning techniques are still more accurate than deep learning when only a small dataset is available. In this study, we present a general data augmentation strategy using Perlin noise, applying it to pixel-by-pixel image classification and quantification of various kinds of image patterns of diffuse interstitial lung disease (DILD). Using retrospectively obtained high-resolution computed tomography (HRCT) images from 106 patients, 100 regions-of-interest (ROIs) for each of six classes of image patterns (normal, ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation) were selected for deep learning classification by experienced thoracic radiologists. For extra-validation, the deep learning quantification of the six classification patterns was evaluated for 92 HRCT whole lung images for which hand-labeled segmentation masks created by two experienced radiologists were available. FusionNet, a convolutional neural network (CNN), was used for training, test, and extra-validation on classifications of DILD image patterns. The accuracy of FusionNet with data augmentation using Perlin noise (89.5%, 49.8%, and 55.0% for ROI-based classification and whole lung quantifications by two radiologists, respectively) was significantly higher than that with conventional data augmentation (82.1%, 45.7%, and 49.9%, respectively). This data augmentation strategy using Perlin noise could be widely applied to deep learning studies for image classification and segmentation, especially in cases with relatively small datasets.

Interstitial lung disease (ILD) causes pulmonary fibrosis. The correct classification of ILD plays a crucial role in the diagnosis and treatment process. In this research work, we propose a lung nodules recognition method based on a deep convolutional neural network (DCNN) and global features, which can be used for computer-aided diagnosis (CAD) of global features of lung nodules. Firstly, a DCNN is constructed based on the characteristics and complexity of lung computerized tomography (CT) images. Then we discussed the effects of different iterations on the recognition results and influence of different model structures on the global features of lung nodules. We also incorporated the improvement of convolution kernel size, feature dimension, and network depth. Thirdly, the effects of different pooling methods, activation functions and training algorithms we proposed has been analyzed to demonstrate the advantages of the new strategy. Finally, the experimental results verify the feasibility of the proposed DCNN for CAD of global features of lung nodules, and the evaluation shown that our proposed method could achieve an outstanding results compare to state-of-arts.

Our contribution presents a research progress in our long-term project that deals with spine analysis in computed tomography (CT) data. A fully automatic computer-aided diagnosis (CAD) system is presented, enabling the simultaneous segmentation and classification of metastatic tissues that can occur in the vertebrae of oncological patients. The task of the proposed CAD system is to segment metastatic lesions and classify them into two categories: osteolytic and osteoblastic. These lesions, especially osteolytic, are ill defined and it is difficult to detect them directly with only information about voxel intensity. The use of several local texture and shape features turned out to be useful for correct classification, however the exact determination of relevant image features is a difficult task. For this reason, the feature determination has been solved by automatic feature extraction provided by a deep convolutional neural network (CNN). The achieved mean sensitivity of detected lesions is greater than 92% with approximately three false positive detections per lesion for both types.

Overview of the Histologic Patterns in Interstitial Lung Disease