International Journal of Biomedical Imaging最新文献

Brain tumor is a deadly neurological disease caused by an abnormal and uncontrollable growth of cells inside the brain or skull. The mortality ratio of patients suffering from this disease is growing gradually. Analysing Magnetic Resonance Images (MRIs) manually is inadequate for efficient and accurate brain tumor diagnosis. An early diagnosis of the disease can activate a timely treatment consequently elevating the survival ratio of the patients. Modern brain imaging methodologies have augmented the detection ratio of brain tumor. In the past few years, a lot of research has been carried out for computer-aided diagnosis of human brain tumor to achieve 100% diagnosis accuracy. The focus of this research is on early diagnosis of brain tumor via Convolution Neural Network (CNN) to enhance state-of-the-art diagnosis accuracy. The proposed CNN is trained on a benchmark dataset, BR35H, containing brain tumor MRIs. The performance and sustainability of the model is evaluated on six different datasets, i.e., BMI-I, BTI, BMI-II, BTS, BMI-III, and BD-BT. To improve the performance of the model and to make it sustainable for totally unseen data, different geometric data augmentation techniques, along with statistical standardization, are employed. The proposed CNN-based CAD system for brain tumor diagnosis performs better than other systems by achieving an average accuracy of around 98.8% and a specificity of around 0.99. It also reveals 100% correct diagnosis for two brain MRI datasets, i.e., BTS and BD-BT. The performance of the proposed system is also compared with the other existing systems, and the analysis reveals that the proposed system outperforms all of them.

[This corrects the article DOI: 10.1155/2013/205494.].

The novel coronavirus disease 2019 (COVID-19) is a contagious disease that has caused thousands of deaths and infected millions worldwide. Thus, various technologies that allow for the fast detection of COVID-19 infections with high accuracy can offer healthcare professionals much-needed help. This study is aimed at evaluating the effectiveness of the state-of-the-art pretrained Convolutional Neural Networks (CNNs) on the automatic diagnosis of COVID-19 from chest X-rays (CXRs). The dataset used in the experiments consists of 1200 CXR images from individuals with COVID-19, 1345 CXR images from individuals with viral pneumonia, and 1341 CXR images from healthy individuals. In this paper, the effectiveness of artificial intelligence (AI) in the rapid and precise identification of COVID-19 from CXR images has been explored based on different pretrained deep learning algorithms and fine-tuned to maximise detection accuracy to identify the best algorithms. The results showed that deep learning with X-ray imaging is useful in collecting critical biological markers associated with COVID-19 infections. VGG16 and MobileNet obtained the highest accuracy of 98.28%. However, VGG16 outperformed all other models in COVID-19 detection with an accuracy, F1 score, precision, specificity, and sensitivity of 98.72%, 97.59%, 96.43%, 98.70%, and 98.78%, respectively. The outstanding performance of these pretrained models can significantly improve the speed and accuracy of COVID-19 diagnosis. However, a larger dataset of COVID-19 X-ray images is required for a more accurate and reliable identification of COVID-19 infections when using deep transfer learning. This would be extremely beneficial in this pandemic when the disease burden and the need for preventive measures are in conflict with the currently available resources.

Diabetic retinopathy is one of the leading diseases affecting eyes. Lack of early detection and treatment can lead to total blindness of the diseased eyes. Recently, numerous researchers have attempted producing automatic diabetic retinopathy detection techniques to supplement diagnosis and early treatment of diabetic retinopathy symptoms. In this manuscript, a new approach has been proposed. The proposed approach utilizes the feature extracted from the fundus image using a local extrema information with quantized Haralick features. The quantized features encode not only the textural Haralick features but also exploit the multiresolution information of numerous symptoms in diabetic retinopathy. Long Short-Term Memory network together with local extrema pattern provides a probabilistic approach to analyze each segment of the image with higher precision which helps to suppress false positive occurrences. The proposed approach analyzes the retina vasculature and hard-exudate symptoms of diabetic retinopathy on two different public datasets. The experimental results evaluated using performance matrices such as specificity, accuracy, and sensitivity reveal promising indices. Similarly, comparison with the related state-of-the-art researches highlights the validity of the proposed method. The proposed approach performs better than most of the researches used for comparison.

One of the major shortcomings of Hopfield neural network (HNN) is that the network may not always converge to a fixed point. HNN, predominantly, is limited to local optimization during training to achieve network stability. In this paper, the convergence problem is addressed using two approaches: (a) by sequencing the activation of a continuous modified HNN (MHNN) based on the geometric correlation of features within various image hyperplanes via pixel gradient vectors and (b) by regulating geometric pixel gradient vectors. These are achieved by regularizing proposed MHNNs under cohomology, which enables them to act as an unconventional filter for pixel spectral sequences. It shifts the focus to both local and global optimizations in order to strengthen feature correlations within each image subspace. As a result, it enhances edges, information content, contrast, and resolution. The proposed algorithm was tested on fifteen different medical images, where evaluations were made based on entropy, visual information fidelity (VIF), weighted peak signal-to-noise ratio (WPSNR), contrast, and homogeneity. Our results confirmed superiority as compared to four existing benchmark enhancement methods.

Cardiac magnetic resonance imaging (CMR) is considered the gold standard for measuring cardiac function. Further, in a single CMR exam, information about cardiac structure, tissue composition, and blood flow could be obtained. Nevertheless, CMR is underutilized due to long scanning times, the need for multiple breath-holds, use of a contrast agent, and relatively high cost. In this work, we propose a rapid, comprehensive, contrast-free CMR exam that does not require repeated breath-holds, based on recent developments in imaging sequences. Time-consuming conventional sequences have been replaced by advanced sequences in the proposed CMR exam. Specifically, conventional 2D cine and phase-contrast (PC) sequences have been replaced by optimized 3D-cine and 4D-flow sequences, respectively. Furthermore, conventional myocardial tagging has been replaced by fast strain-encoding (SENC) imaging. Finally, T1 and T2 mapping sequences are included in the proposed exam, which allows for myocardial tissue characterization. The proposed rapid exam has been tested in vivo. The proposed exam reduced the scan time from >1 hour with conventional sequences to <20 minutes. Corresponding cardiovascular measurements from the proposed rapid CMR exam showed good agreement with those from conventional sequences and showed that they can differentiate between healthy volunteers and patients. Compared to 2D cine imaging that requires 12-16 separate breath-holds, the implemented 3D-cine sequence allows for whole heart coverage in 1-2 breath-holds. The 4D-flow sequence allows for whole-chest coverage in less than 10 minutes. Finally, SENC imaging reduces scan time to only one slice per heartbeat. In conclusion, the proposed rapid, contrast-free, and comprehensive cardiovascular exam does not require repeated breath-holds or to be supervised by a cardiac imager. These improvements make it tolerable by patients and would help improve cost effectiveness of CMR and increase its adoption in clinical practice.

Idiopathic pulmonary fibrosis is a progressive, chronic lung disease characterized by the accumulation of extracellular matrix proteins, including collagen and elastin. Imaging of extracellular matrix in fibrotic lungs is important for evaluating its pathological condition as well as the distribution of drugs to pulmonary focus sites and their therapeutic effects. In this study, we compared techniques of staining the extracellular matrix with optical tissue-clearing treatment for developing three-dimensional imaging methods for focus sites in pulmonary fibrosis. Mouse models of pulmonary fibrosis were prepared via the intrapulmonary administration of bleomycin. Fluorescent-labeled tomato lectin, collagen I antibody, and Col-F, which is a fluorescent probe for collagen and elastin, were used to compare the imaging of fibrotic foci in intact fibrotic lungs. These lung samples were cleared using the Clear^T2 tissue-clearing technique. The cleared lungs were two dimensionally observed using laser-scanning confocal microscopy, and the images were compared with those of the lung tissue sections. Moreover, three-dimensional images were reconstructed from serial two-dimensional images. Fluorescent-labeled tomato lectin did not enable the visualization of fibrotic foci in cleared fibrotic lungs. Although collagen I in fibrotic lungs could be visualized via immunofluorescence staining, collagen I was clearly visible only until 40 μm from the lung surface. Col-F staining facilitated the visualization of collagen and elastin to a depth of 120 μm in cleared lung tissues. Furthermore, we visualized the three-dimensional extracellular matrix in cleared fibrotic lungs using Col-F, and the images provided better visualization than immunofluorescence staining. These results suggest that Clear^T2 tissue-clearing treatment combined with Col-F staining represents a simple and rapid technique for imaging fibrotic foci in intact fibrotic lungs. This study provides important information for imaging various organs with extracellular matrix-related diseases.

The phase cycling method is a state-of-the-art method to reconstruct complex-valued MR image. However, when it follows practical two-dimensional (2D) subsampling Cartesian acquisition which is only enforcing random sampling in the phase-encoding direction, a number of artifacts in magnitude appear. A modified approach is proposed to remove these artifacts under practical MRI subsampling, by adding one-dimensional total variation (TV) regularization into the phase cycling method to "pre-process" the magnitude component before its update. Furthermore, an operation used in SFISTA is employed to update the magnitude and phase images for better solutions. The results of the experiments show the ability of the proposed method to eliminate the ring artifacts and improve the magnitude reconstruction.

In the study of pediatric automatic bone age assessment (BAA) in clinical practice, the extraction of the object area in hand radiographs is an important part, which directly affects the prediction accuracy of the BAA. But no perfect segmentation solution has been found yet. This work is to develop an automatic hand radiograph segmentation method with high precision and efficiency. We considered the hand segmentation task as a classification problem. The optimal segmentation threshold for each image was regarded as the prediction target. We utilized the normalized histogram, mean value, and variance of each image as input features to train the classification model, based on ensemble learning with multiple classifiers. 600 left-hand radiographs with the bone age ranging from 1 to 18 years old were included in the dataset. Compared with traditional segmentation methods and the state-of-the-art U-Net network, the proposed method performed better with a higher precision and less computational load, achieving an average PSNR of 52.43 dB, SSIM of 0.97, DSC of 0.97, and JSI of 0.91, which is more suitable in clinical application. Furthermore, the experimental results also verified that hand radiograph segmentation could bring an average improvement for BAA performance of at least 13%.

The ongoing pandemic of coronavirus disease 2019 (COVID-19) has led to global health and healthcare crisis, apart from the tremendous socioeconomic effects. One of the significant challenges in this crisis is to identify and monitor the COVID-19 patients quickly and efficiently to facilitate timely decisions for their treatment, monitoring, and management. Research efforts are on to develop less time-consuming methods to replace or to supplement RT-PCR-based methods. The present study is aimed at creating efficient deep learning models, trained with chest X-ray images, for rapid screening of COVID-19 patients. We used publicly available PA chest X-ray images of adult COVID-19 patients for the development of Artificial Intelligence (AI)-based classification models for COVID-19 and other major infectious diseases. To increase the dataset size and develop generalized models, we performed 25 different types of augmentations on the original images. Furthermore, we utilized the transfer learning approach for the training and testing of the classification models. The combination of two best-performing models (each trained on 286 images, rotated through 120° or 140° angle) displayed the highest prediction accuracy for normal, COVID-19, non-COVID-19, pneumonia, and tuberculosis images. AI-based classification models trained through the transfer learning approach can efficiently classify the chest X-ray images representing studied diseases. Our method is more efficient than previously published methods. It is one step ahead towards the implementation of AI-based methods for classification problems in biomedical imaging related to COVID-19.