Automated tissue characterization is one of the most crucial components of a computer aided diagnosis (CAD) system for interstitial lung diseases (ILDs). Although much research has been conducted in this field, the problem remains challenging. Deep learning techniques have recently achieved impressive results in a variety of computer vision problems, raising expectations that they might be applied in other domains, such as medical image analysis. In this paper, we propose and evaluate a convolutional neural network (CNN), designed for the classification of ILD patterns. The proposed network consists of 5 convolutional layers with 2 × 2 kernels and LeakyReLU activations, followed by average pooling with size equal to the size of the final feature maps and three dense layers. The last dense layer has 7 outputs, equivalent to the classes considered: healthy, ground glass opacity (GGO), micronodules, consolidation, reticulation, honeycombing and a combination of GGO/reticulation. To train and evaluate the CNN, we used a dataset of 14696 image patches, derived by 120 CT scans from different scanners and hospitals. To the best of our knowledge, this is the first deep CNN designed for the specific problem. A comparative analysis proved the effectiveness of the proposed CNN against previous methods in a challenging dataset. The classification performance ( ~ 85.5%) demonstrated the potential of CNNs in analyzing lung patterns. Future work includes, extending the CNN to three-dimensional data provided by CT volume scans and integrating the proposed method into a CAD system that aims to provide differential diagnosis for ILDs as a supportive tool for radiologists.

Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis systems have been developed. These commonly rely on a fixed scale classifier that scans CT images, recognizes textural lung patterns, and generates a map of pathologies. In a previous study, we proposed a method for classifying lung tissue patterns using a deep convolutional neural network (CNN), with an architecture designed for the specific problem. In this study, we present an improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification. Six publicly available texture databases are used to pretrain networks with the proposed architecture, which are then fine-tuned on the lung tissue data. The resulting CNNs are combined in an ensemble and their fused knowledge is compressed back to a network with the original architecture. The proposed approach resulted in an absolute increase of about 2% in the performance of the proposed CNN. The results demonstrate the potential of transfer learning in the field of medical image analysis, indicate the textural nature of the problem and show that the method used for training a network can be as important as designing its architecture.

Background: Assessing functional impairment, therapeutic response and disease progression in patients with idiopathic pulmonary fibrosis (IPF) continues to be challenging. Hyperpolarized ¹²⁹Xe MRI can address this gap through its unique capability to image gas transfer three-dimensionally from airspaces to interstitial barrier tissues to red blood cells (RBCs). This must be validated by testing the degree to which it correlates with pulmonary function tests (PFTs) and CT scores, and its spatial distribution reflects known physiology and patterns of disease.Methods: 13 healthy individuals (33.6±15.7 years) and 12 patients with IPF (66.0±6.4 years) underwent ¹²⁹Xe MRI to generate three-dimensional quantitative maps depicting the ¹²⁹Xe ventilation distribution, its uptake in interstitial barrier tissues and its transfer to RBCs. For each map, mean values were correlated with PFTs and CT fibrosis scores, and their patterns were tested for the ability to depict functional gravitational gradients in healthy lung and to detect the known basal and peripheral predominance of disease in IPF.Results: ¹²⁹Xe MRI depicted functional impairment in patients with IPF, whose mean barrier uptake increased by 188% compared with the healthy reference population. ¹²⁹Xe MRI metrics correlated poorly and insignificantly with CT fibrosis scores but strongly with PFTs. Barrier uptake and RBC transfer both correlated significantly with diffusing capacity of the lungs for carbon monoxide (r=−0.75, p<0.01 and r=0.72, p<0.01), while their ratio (RBC/barrier) correlated most strongly (r=0.94, p<0.01). RBC transfer exhibited significant anterior-posterior gravitational gradients in healthy volunteers, but not in IPF, where it was significantly impaired in the basal (p=0.02) and subpleural (p<0.01) lung.Conclusions: Hyperpolarized¹²⁹Xe MRI is a rapid and well-tolerated exam that provides region-specific quantification of interstitial barrier thickness and RBC transfer efficiency. With further development, it could become a robust tool for measuring disease progression and therapeutic response in patients with IPF, sensitively and non-invasively.

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.

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 (CAD) 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 dataset of 172 sparsely annotated CT scans, within a cross-validation scheme. The training was performed in an end-to-end and semi-supervised fashion, utilizing both labeled and non-labeled image regions. The experimental results show significant performance improvement with respect to the state of the art.

OBJECTIVE. The purpose of this study was to assess the diagnostic accuracy of effective atomic number maps reconstructed from dual-energy contrast-enhanced data for discriminating between nonenhancing renal cysts and enhancing masses. MATERIALS AND METHODS. Two hundred six patients (128 men, 78 women; mean age, 64 years) underwent a CT renal mass protocol (single-energy unenhanced and dual-energy contrast-enhanced nephrographic imaging) at two different hospitals. For each set of patients, two blinded, independent observers performed measurements on effective atomic number maps from contrast-enhanced dual-energy data. Renal mass assessment on unenhanced and nephrographic images, corroborated by imaging and medical records, was the reference standard. The diagnostic accuracy of effective atomic number maps was assessed with ROC analysis. RESULTS. Significant differences in mean effective atomic numbers (Zeff) were observed between nonenhancing and enhancing masses (set A, 8.19 vs 9.59 Zeff; set B, 8.05 vs ...