Local-Entropy Based Approach for X-Ray Image Segmentation and Fracture Detection

[Study on automatic and rapid diagnosis of distal radius fracture by X-ray]

This article aims to combine deep learning with image analysis technology and propose an effective classification method for distal radius fracture types. Firstly, an extended U-Net three-layer cascaded segmentation network was used to accurately segment the most important joint surface and non joint surface areas for identifying fractures. Then, the images of the joint surface area and non joint surface area separately were classified and trained to distinguish fractures. Finally, based on the classification results of the two images, the normal or ABC fracture classification results could be comprehensively determined. The accuracy rates of normal, A-type, B-type, and C-type fracture on the test set were 0.99, 0.92, 0.91, and 0.82, respectively. For orthopedic medical experts, the average recognition accuracy rates were 0.98, 0.90, 0.87, and 0.81, respectively. The proposed automatic recognition method is generally better than experts, and can be used for preliminary auxiliary diagnosis of distal radius fractures in scenarios without expert participation.

DFR-U-Net: Dual residual and feature fusion network for ulna and radius segmentation on dual-energy X-ray absorptiometry images

BACKGROUND

Ulna and radius segmentation of dual-energy X-ray absorptiometry (DXA) images is essential for measuring bone mineral density (BMD).

OBJECTIVE

To develop and test a novel deep learning network architecture for robust and efficient ulna and radius segmentation on DXA images.

METHODS

This study used two datasets including 360 cases. The first dataset included 300 cases that were randomly divided into five groups for five-fold cross-validation. The second dataset including 60 cases was used for independent testing. A deep learning network architecture with dual residual dilated convolution module and feature fusion block based on residual U-Net (DFR-U-Net) to enhance segmentation accuracy of ulna and radius regions on DXA images was developed. The Dice similarity coefficient (DSC), Jaccard, and Hausdorff distance (HD) were used to evaluate the segmentation performance. A one-tailed paired t-test was used to assert the statistical significance of our method and the other deep learning-based methods (P < 0.05 indicates a statistical significance).

RESULTS

The results demonstrated our method achieved the promising segmentation performance, with DSC of 98.56±0.40% and 98.86±0.25%, Jaccard of 97.14±0.75% and 97.73±0.48%, and HD of 6.41±11.67 pixels and 8.23±7.82 pixels for segmentation of ulna and radius, respectively. According to statistics data analysis results, our method yielded significantly higher performance than other deep learning-based methods.

CONCLUSIONS

The proposed DFR-U-Net achieved higher segmentation performance for ulna and radius on DXA images than the previous work and other deep learning approaches. This methodology has potential to be applied to ulna and radius segmentation to help doctors measure BMD more accurately in the future.

The augmented radiologist: artificial intelligence in the practice of radiology

In medicine, particularly in radiology, there are great expectations in artificial intelligence (AI), which can "see" more than human radiologists in regard to, for example, tumor size, shape, morphology, texture and kinetics - thus enabling better care by earlier detection or more precise reports. Another point is that AI can handle large data sets in high-dimensional spaces. But it should not be forgotten that AI is only as good as the training samples available, which should ideally be numerous enough to cover all variants. On the other hand, the main feature of human intelligence is content knowledge and the ability to find near-optimal solutions. The purpose of this paper is to review the current complexity of radiology working places, to describe their advantages and shortcomings. Further, we give an AI overview of the different types and features as used so far. We also touch on the differences between AI and human intelligence in problem-solving. We present a new AI type, labeled "explainable AI," which should enable a balance/cooperation between AI and human intelligence - thus bringing both worlds in compliance with legal requirements. For support of (pediatric) radiologists, we propose the creation of an AI assistant that augments radiologists and keeps their brain free for generic tasks.

Deep learning approach for automatic segmentation of ulna and radius in dual-energy X-ray imaging

BACKGROUND

Segmentation of the ulna and radius is a crucial step for the measurement of bone mineral density (BMD) in dual-energy X-ray imaging in patients suspected of having osteoporosis.

PURPOSE

This work aimed to propose a deep learning approach for the accurate automatic segmentation of the ulna and radius in dual-energy X-ray imaging.

METHODS AND MATERIALS

We developed a deep learning model with residual block (Resblock) for the segmentation of the ulna and radius. Three hundred and sixty subjects were included in the study, and five-fold cross-validation was used to evaluate the performance of the proposed network. The Dice coefficient and Jaccard index were calculated to evaluate the results of segmentation in this study.

RESULTS

The proposed network model had a better segmentation performance than the previous deep learning-based methods with respect to the automatic segmentation of the ulna and radius. The evaluation results suggested that the average Dice coefficients of the ulna and radius were 0.9835 and 0.9874, with average Jaccard indexes of 0.9680 and 0.9751, respectively.

CONCLUSION

The deep learning-based method developed in this study improved the segmentation performance of the ulna and radius in dual-energy X-ray imaging.

Single-pass metal artifact reduction using a dual-layer flat panel detector

PURPOSE

Metal artifact remains a challenge in cone-beam CT images. Many image domain-based segmentation methods have been proposed for metal artifact reduction (MAR), which require two-pass reconstruction. Such methods first segment metal from a first-pass reconstruction and then forward-project the metal mask to identify them in projections. These methods work well in general but are limited when the metal is outside the scan field-of-view (FOV) or when the metal is moving during the scan. In the former, even reconstructing with a larger FOV does not guarantee a good estimate of metal location in the projections; and in the latter, the metal location in each projection is difficult to identify due to motion. Single-pass methods that detect metal in single-energy projections have also been developed, but often have imperfect metal detection that leads to residual artifacts. In this work, we develop a MAR method using a dual-layer (DL) flat panel detector, which improves performance for single-pass reconstruction.

METHODS

In this work, we directly detect metal objects in projections using dual-energy (DE) imaging that generates material-specific images (e.g., soft tissue and bone), where the metal stands out in bone images when nonuniform soft tissue background is removed. Metal is detected via simple thresholding, and entropy filtration is further applied to remove false-positive detections. A DL detector provides DE images with superior temporal and spatial registration and was used to perform the task. Scatter correction was first performed on DE raw projections to improve the accuracy of material decomposition. One phantom mimicking a liver biopsy setup and a cadaver head were used to evaluate the metal reduction performance of the proposed method and compared with that of a standard two-pass reconstruction, a previously published sinogram-based method using a Markov random field (MRF) model, and a single-pass projection-domain method using single-energy imaging. The phantom has a liver steering setup placed in a hollow chest phantom, with embedded metal and a biopsy needle crossing the phantom boundary. The cadaver head has dental fillings and a metal tag attached to its surface. The identified metal regions in each projection were corrected by interpolation using surrounding pixels, and the images were reconstructed using filtered backprojection.

RESULTS

Our current approach removes metal from the projections, which is robust to FOV truncation during imaging acquisition. In case of FOV truncation, the method outperformed the two-pass reconstruction method. The proposed method using DE renders better accuracy in metal segmentation than the MRF method and single-energy method, which were prone to false-positive errors that cause additional streaks. For the liver steering phantom, the average spatial nonuniformity was reduced from 0.127 in uncorrected images to 0.086 using a standard two-pass reconstruction and to 0.077 using the proposed method. For the cadaver head, the average standard deviation within selected soft tissue regions ( σ s ) was reduced from 209.1 HU in uncorrected images to 69.1 HU using a standard two-pass reconstruction and to 46.8 HU using our proposed method. The proposed method reduced the processing time by 31% as compared with the two-pass method.

CONCLUSIONS

We proposed a MAR method that directly detects metal in the projection domain using DE imaging, which is robust to truncation and superior to that of single-energy imaging. The method requires only a single-pass reconstruction that substantially reduces processing time compared with the standard two-pass metal reduction method.

Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples

The combination of hyperspectral imaging (HSI) and digital pathology may yield more accurate diagnosis. In this work, we propose the use of superpixels in HS images for combining regions of pixels that can be classified according to their spectral information to classify glioblastoma (GB) brain tumors in histologic slides. The superpixels are generated by a modified simple linear iterative clustering (SLIC) method to accommodate HS images. This work employs a dataset of H&E (Hematoxylin and Eosin) stained histology slides from 13 patients with GB and over 426,000 superpixels. A linear support vector machine (SVM) classifier was performed on independent training, validation, and testing datasets. The results of this investigation show that the proposed method can detect GB brain tumors from non-tumor samples with average sensitivity and specificity of 87% and 81%, respectively. The overall accuracy of this method is 83%. The study demonstrates that hyperspectral digital pathology can be useful for detecting GB brain tumors by exploiting spectral information alone on a superpixel level.

Ultrasound Image-Based Diagnosis of Malignant Thyroid Nodule Using Artificial Intelligence

Computer-aided diagnosis systems have been developed to assist doctors in diagnosing thyroid nodules to reduce errors made by traditional diagnosis methods, which are mainly based on the experiences of doctors. Therefore, the performance of such systems plays an important role in enhancing the quality of a diagnosing task. Although there have been the state-of-the art studies regarding this problem, which are based on handcrafted features, deep features, or the combination of the two, their performances are still limited. To overcome these problems, we propose an ultrasound image-based diagnosis of the malignant thyroid nodule method using artificial intelligence based on the analysis in both spatial and frequency domains. Additionally, we propose the use of weighted binary cross-entropy loss function for the training of deep convolutional neural networks to reduce the effects of unbalanced training samples of the target classes in the training data. Through our experiments with a popular open dataset, namely the thyroid digital image database (TDID), we confirm the superiority of our method compared to the state-of-the-art methods.

Hybrid Filter Based on Fuzzy Techniques for Mixed Noise Reduction in Color Images

To decrease contamination from a mixed combination of impulse and Gaussian noise on color digital images, a novel hybrid filter is proposed. The new technique is composed of two stages. A filter based on a fuzzy metric is used for the reduction of impulse noise at the first stage. At the second stage, to remove Gaussian noise, a fuzzy peer group method is applied on the image generated from the previous stage. The performance of the introduced algorithm was evaluated on standard test images employing widely used objective quality metrics. The new approach can efficiently reduce both impulse and Gaussian noise, as much as mixed noise. The proposed filtering method was compared to the state-of-the-art methodologies: adaptive nearest neighbor filter, alternating projections filter, color block-matching 3D filter, fuzzy peer group averaging filter, partition-based trimmed vector median filter, trilateral filter, fuzzy wavelet shrinkage denoising filter, graph regularization filter, iterative peer group switching vector filter, peer group method, and the fuzzy vector median method. The experiments demonstrated that the introduced noise reduction technique outperforms those state-of-the-art filters with respect to the metrics peak signal to noise ratio (PSNR), the mean absolute error (MAE), and the normalized color difference (NCD).

A Novel Residual Dense Pyramid Network for Image Dehazing

Recently, convolutional neural network (CNN) based on the encoder-decoder structure have been successfully applied to image dehazing. However, these CNN based dehazing methods have two limitations: First, these dehazing models are large in size with enormous parameters, which not only consumes much GPU memory, but also is hard to train from scratch. Second, these models, which ignore the structural information at different resolutions of intermediate layers, cannot capture informative texture and edge information for dehazing by stacking more layers. In this paper, we propose a light-weight end-to-end network named the residual dense pyramid network (RDPN) to address the above problems. To exploit the structural information at different resolutions of intermediate layers fully, a new residual dense pyramid (RDP) is proposed as a building block. By introducing a dense information fusion layer and the residual learning module, the RDP can maximize the information flow and extract local features. Furthermore, the RDP further learns the structural information from intermediate layers via a multiscale pyramid fusion mechanism. To reduce the number of network parameters and to ease the training process, we use one RDP in the encoder and two RDPs in the decoder, following a multilevel pyramid pooling layer for incorporating global context features before estimating the final result. The extensive experimental results on a synthetic dataset and real-world images demonstrate that the new RDPN achieves favourable performance compared with some state-of-the-art methods, e.g., the recent densely connected pyramid dehazing network, the all-in-one dehazing network, the enhanced pix2pix dehazing network, pixel-based alpha blending, artificial multi-exposure image fusions and the genetic programming estimator, in terms of accuracy, run time and number of parameters. To be specific, RDPN outperforms all of the above methods in terms of PSNR by at least 4.25 dB. The run time of the proposed method is 0.021 s, and the number of parameters is 1,534,799, only 6% of that used by the densely connected pyramid dehazing network.

Entropy Analysis and Image Encryption Application Based on a New Chaotic System Crossing a Cylinder

Designing chaotic systems with specific features is a hot topic in nonlinear dynamics. In this study, a novel chaotic system is presented with a unique feature of crossing inside and outside of a cylinder repeatedly. This new system is thoroughly analyzed by the help of the bifurcation diagram, Lyapunov exponents’ spectrum, and entropy measurement. Bifurcation analysis of the proposed system with two initiation methods reveals its multistability. As an engineering application, the system’s efficiency is tested in image encryption. The complexity of the chaotic attractor of the proposed system makes it a proper choice for encryption. States of the chaotic attractor are used to shuffle the rows and columns of the image, and then the shuffled image is XORed with the states of chaotic attractor. The unpredictability of the chaotic attractor makes the encryption method very safe. The performance of the encryption method is analyzed using the histogram, correlation coefficient, Shannon entropy, and encryption quality. The results show that the encryption method using the proposed chaotic system has reliable performance.