Search

Crop variety identification is an essential link in seed detection, phenotype collection and scientific breeding. This paper takes peanut as an example to explore a new method for crop variety identification. Peanut is a crucial oil crop and cash crop. The yield and quality of different peanut varieties are different, so it is necessary to identify and classify different peanut varieties. The traditional image processing method of peanut variety identification needs to extract many features, which has defects such as intense subjectivity and insufficient generalization ability. Based on the deep learning technology, this paper improved the deep convolutional neural network VGG16 and applied the improved VGG16 to the identification and classification task of 12 varieties of peanuts. Firstly, the peanut pod images of 12 varieties obtained by the scanner were preprocessed with gray-scale, binarization, and ROI extraction to form a peanut pod data set with a total of 3365 images of 12 varieties. A series of improvements have been made to VGG16. Remove the F6 and F7 fully connected layers of VGG16. Add Conv6 and Global Average Pooling Layer. The three convolutional layers of conv5 have changed into Depth Concatenation and add the Batch Normalization(BN) layers to the model. Besides, fine-tuning is carried out based on the improved VGG16. We adjusted the location of the BN layers. Adjust the number of filters for Conv6. Finally, the improved VGG16 model's training test results were compared with the other classic models, AlexNet, VGG16, GoogLeNet, ResNet18, ResNet50, SqueezeNet, DenseNet201 and MobileNetv2 verify its superiority. The average accuracy of the improved VGG16 model on the peanut pods test set was 96.7%, which was 8.9% higher than that of VGG16, and 1.6–12.3% higher than that of other classical models. Besides, supplementary experiments were carried out to prove the robustness and generality of the improved VGG16. The improved VGG16 was applied to the identification and classification of seven corn grain varieties with the same method and an average accuracy of 90.1% was achieved. The experimental results show that the improved VGG16 proposed in this paper can identify and classify peanut pods of different varieties, proving the feasibility of a convolutional neural network in variety identification and classification. The model proposed in this experiment has a positive significance for exploring other Crop variety identification and classification.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Coronavirus 2019 (COVID-19) is a new acute respiratory disease that has spread rapidly throughout the world. In this paper, a lightweight convolutional neural network (CNN) model named multi-scale gated multi-head attention depthwise separable CNN (MGMADS-CNN) is proposed, which is based on attention mechanism and depthwise separable convolution. A multi-scale gated multi-head attention mechanism is designed to extract effective feature information from the COVID-19 X-ray and CT images for classification. Moreover, the depthwise separable convolution layers are adopted as MGMADS-CNN’s backbone to reduce the model size and parameters. The LeNet-5, AlexNet, GoogLeNet, ResNet, VGGNet-16, and three MGMADS-CNN models are trained, validated and tested with tenfold cross-validation on X-ray and CT images. The results show that MGMADS-CNN with three attention layers (MGMADS-3) has achieved accuracy of 96.75% on X-ray images and 98.25% on CT images. The specificity and sensitivity are 98.06% and 96.6% on X-ray images, and 98.17% and 98.05% on CT images. The size of MGMADS-3 model is only 43.6 M bytes. In addition, the detection speed of MGMADS-3 on X-ray images and CT images are 6.09 ms and 4.23 ms for per image, respectively. It is proved that the MGMADS-3 can detect and classify COVID-19 faster with higher accuracy and efficiency.

This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). This paper proposed a novel model based on convolutional neural networks (CNN) which aimed at accurate and fast grading of apple quality. Specific, complex, and useful image characteristics for detection and classification were captured by the proposed model. Compared with existing methods, the proposed model could better learn high-order features of two adjacent layers that were not in the same channel but were very related. The proposed model was trained and validated, with best training and validation accuracy of 99% and 98.98% at 2590th and 3000th step, respectively. The overall accuracy of the proposed model tested using an independent 300 apple dataset was 95.33%. The results showed that the training accuracy, overall test accuracy and training time of the proposed model were better than Google Inception v3 model and traditional imaging process method based on histogram of oriented gradient (HOG), gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. The proposed model has great potential in Apple’s quality detection and classification.

This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models.

In this work a novel architecture, named pseudo-softmax, to compute an approximated form of the softmax function is presented. This architecture can be fruitfully used in the last layer of Neural Networks and Convolutional Neural Networks for classification tasks, and in Reinforcement Learning hardware accelerators to compute the Boltzmann action-selection policy. The proposed pseudo-softmax design, intended for efficient hardware implementation, exploits the typical integer quantization of hardware-based Neural Networks obtaining an accurate approximation of the result. In the paper, a detailed description of the architecture is given and an extensive analysis of the approximation error is performed by using both custom stimuli and real-world Convolutional Neural Networks inputs. The implementation results, based on CMOS standard-cell technology, compared to state-of-the-art architectures show reduced approximation errors.

COVID-19 has crippled the world’s healthcare systems, setting back the economy and taking the lives of several people. Although potential vaccines are being tested and supplied around the world, it will take a long time to reach every human being, more so with new variants of the virus emerging, enforcing a lockdown-like situation on parts of the world. Thus, there is a dire need for early and accurate detection of COVID-19 to prevent the spread of the disease, even more. The current gold-standard RT-PCR test is only 71% sensitive and is a laborious test to perform, leading to the incapability of conducting the population-wide screening. To this end, in this paper, we propose an automated COVID-19 detection system that uses CT-scan images of the lungs for classifying the same into COVID and Non-COVID cases. The proposed method applies an ensemble strategy that generates fuzzy ranks of the base classification models using the Gompertz function and fuses the decision scores of the base models adaptively to make the final predictions on the test cases. Three transfer learning-based convolutional neural network models are used, namely VGG-11, Wide ResNet-50-2, and Inception v3, to generate the decision scores to be fused by the proposed ensemble model. The framework has been evaluated on two publicly available chest CT scan datasets achieving state-of-the-art performance, justifying the reliability of the model. The relevant source codes related to the present work is available in: GitHub.

Triple negative (TN) breast cancer is a subtype of breast cancer which is difficult for early detection and the prognosis is poor. In this paper, 910 benign and 934 malignant (110 TN and 824 NTN) B-mode breast ultrasound images were collected. A Resnet50 deep convolutional neural network was fine-tuned. The results showed that the averaged area under the receiver operating characteristic curve (AUC) of discriminating malignant from benign ones were 0.9789 (benign vs. TN), 0.9689 (benign vs. NTN). To discriminate TN from NTN breast cancer, the AUC was 0.9000, the accuracy was 88.89%, the sensitivity was 87.5%, and the specificity was 90.00%. It showed that the computer-aided system based on DCNN is expected to be a promising noninvasive clinical tool for ultrasound diagnosis of TN breast cancer.

This paper proposes a fully automatic method to segment the inner boundary of the bony orbit in two different image modalities: magnetic resonance imaging (MRI) and computed tomography (CT). The method, based on a deep learning architecture, uses two fully convolutional neural networks in series followed by a graph-search method to generate a boundary for the orbit. When compared to human performance for segmentation of both CT and MRI data, the proposed method achieves high Dice coefficients on both orbit and background, with scores of 0.813 and 0.975 in CT images and 0.930 and 0.995 in MRI images, showing a high degree of agreement with a manual segmentation by a human expert. Given the volumetric characteristics of these imaging modalities and the complexity and time-consuming nature of the segmentation of the orbital region in the human skull, it is often impractical to manually segment these images. Thus, the proposed method provides a valid clinical and research tool that performs similarly to the human observer.

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of Pancreatic Ductal Adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and LBP descriptors into the attention U-Net. An ensemble model is then used to cumulate the advantages of both networks using a 3D-CNN. In addition, to reduce the effects of imbalanced data, a new loss function is proposed as a weighted combination of three classic losses including Generalized Dice Loss (GDL), Weighted Pixel-Wise Cross Entropy loss (WPCE) and boundary loss. Due to insufficient sample size for vessel segmentation, we used the above-mentioned pre-trained networks and fin-tuned them. Experimental results show that the proposed method improves the Dice score for PDAC mass segmentation in portal-venous phase by 7.52% compared to state-of-the-art methods (from 53.08% to 60.6%) in term of DSC. Besides, three dimensional visualization of the tumor and surrounding vessels can facilitate the evaluation of PDAC treatment response.

Synchrotron X-ray tomography enables the examination of the internal structure of materials at submicron spatial resolution and subsecond temporal resolution. Unavoidable experimental constraints can impose dose and time limits on the measurements, introducing noise in the reconstructed images. Convolutional neural networks (CNNs) have emerged as a powerful tool to remove noise from reconstructed images. However, their training typically requires collecting a dataset of paired noisy and high-quality measurements, which is a major obstacle to their use in practice. To circumvent this problem, methods for CNN-based denoising have recently been proposed that require no separate training data beyond the already available noisy reconstructions. Among these, the Noise2Inverse method is specifically designed for tomography and related inverse problems. To date, applications of Noise2Inverse have only taken into account 2D spatial information. In this paper, we expand the application of Noise2Inverse in space, time, and spectrum-like domains. This development enhances applications to static and dynamic micro-tomography as well as X-ray diffraction tomography. Results on real-world datasets establish that Noise2Inverse is capable of accurate denoising and enables a substantial reduction in acquisition time while maintaining image quality., Scientific Reports, 11 (1), ISSN:2045-2322

An artificial neural network consists of neurons and synapses. Neuron gives output based on its input according to non-linear activation functions such as the Sigmoid, Hyperbolic Tangent (Tanh), or Rectified Linear Unit (ReLU) functions, etc.. Synapses connect the neuron outputs to their inputs with tunable real-valued weights. The most resource-demanding operations in realizing such neural networks are the multiplication and accumulate (MAC) operations that compute the dot product between real-valued outputs from neurons and the synapses weights. The efficiency of neural networks can be drastically enhanced if the neuron outputs and/or the weights can be trained to take binary values $$\pm 1$$ ± 1 only, for which the MAC can be replaced by the simple XNOR operations. In this paper, we demonstrate an adiabatic training method that can binarize the fully-connected neural networks and the convolutional neural networks without modifying the network structure and size. This adiabatic training method only requires very minimal changes in training algorithms, and is tested in the following four tasks: the recognition of hand-writing numbers using a usual fully-connected network, the cat-dog recognition and the audio recognition using convolutional neural networks, the image recognition with 10 classes (CIFAR-10) using ResNet-20 and VGG-Small networks. In all tasks, the performance of the binary neural networks trained by the adiabatic method are almost identical to the networks trained using the conventional ReLU or Sigmoid activations with real-valued activations and weights. This adiabatic method can be easily applied to binarize different types of networks, and will increase the computational efficiency considerably and greatly simplify the deployment of neural networks.

Accurately mapping individual tree species in densely forested environments is crucial to forest inventory. When considering only RGB images, this is a challenging task for many automatic photogrammetry processes. The main reason for that is the spectral similarity between species in RGB scenes, which can be a hindrance for most automatic methods. This paper presents a deep learning-based approach to detect an important multi-use species of palm trees (Mauritia flexuosa; i.e., Buriti) on aerial RGB imagery. In South-America, this palm tree is essential for many indigenous and local communities because of its characteristics. The species is also a valuable indicator of water resources, which comes as a benefit for mapping its location. The method is based on a Convolutional Neural Network (CNN) to identify and geolocate singular tree species in a high-complexity forest environment. The results returned a mean absolute error (MAE) of 0.75 trees and an F1-measure of 86.9%. These results are better than Faster R-CNN and RetinaNet methods considering equal experiment conditions. In conclusion, the method presented is efficient to deal with a high-density forest scenario and can accurately map the location of single species like the M. flexuosa palm tree and may be useful for future frameworks.

SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the convolutional neural networks, has been widely applied to the classification of medical images. In order to reliably classify SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses, in this paper, we present several deep classifiers based on the deep networks. Specifically, original SPECT images are cropped to extract the thoracic region, followed by a geometric transformation that contributes to augment the original data. We then construct deep classifiers based on the widely used deep networks including VGG, ResNet and DenseNet by fine-tuning their parameters and structures or self-defining new network structures. Experiments on a set of real-world SPECT bone images show that the proposed classifiers perform well in identifying bone metastasis with SPECT imaging. It achieves 0.9807, 0.9900, 0.9830, 0.9890, 0.9802 and 0.9933 for accuracy, precision, recall, specificity, F-1 score and AUC, respectively, on the test samples from the augmented dataset without normalization.

Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient and for large datasets implies a massive redundancy of features detectors. Even though capsules networks are still in their infancy, they constitute a promising solution to extend current convolutional networks and endow artificial visual perception with a process to encode more efficiently all feature affine transformations. Indeed, a properly working capsule network should theoretically achieve higher results with a considerably lower number of parameters count due to intrinsic capability to generalize to novel viewpoints. Nevertheless, little attention has been given to this relevant aspect. In this paper, we investigate the efficiency of capsule networks and, pushing their capacity to the limits with an extreme architecture with barely 160K parameters, we prove that the proposed architecture is still able to achieve state-of-the-art results on three different datasets with only 2% of the original CapsNet parameters. Moreover, we replace dynamic routing with a novel non-iterative, highly parallelizable routing algorithm that can easily cope with a reduced number of capsules. Extensive experimentation with other capsule implementations has proved the effectiveness of our methodology and the capability of capsule networks to efficiently embed visual representations more prone to generalization., Accepted by Scientific Reports

Identifying novel drug–target interactions (DTIs) plays an important role in drug discovery. Most of the computational methods developed for predicting DTIs use binary classification, whose goal is to determine whether or not a drug–target (DT) pair interacts. However, it is more meaningful but also more challenging to predict the binding affinity that describes the strength of the interaction between a DT pair. If the binding affinity is not sufficiently large, such drug may not be useful. Therefore, the methods for predicting DT binding affinities are very valuable. The increase in novel public affinity data available in the DT-related databases enables advanced deep learning techniques to be used to predict binding affinities. In this paper, we propose a similarity-based model that applies 2-dimensional (2D) convolutional neural network (CNN) to the outer products between column vectors of two similarity matrices for the drugs and targets to predict DT binding affinities. To our best knowledge, this is the first application of 2D CNN in similarity-based DT binding affinity prediction. The validation results on multiple public datasets show that the proposed model is an effective approach for DT binding affinity prediction and can be quite helpful in drug development process.

Adaptive optics flood illumination ophthalmoscopy (AO-FIO) is an established imaging tool in the investigation of retinal diseases. However, the clinical interpretation of AO-FIO images can be challenging due to varied image quality. Therefore, image quality assessment is essential before interpretation. An image assessment tool will also assist further work on improving the image quality, either during acquisition or post processing. In this paper, we describe, validate and compare two automated image quality assessment methods; the energy of Laplacian focus operator (LAPE; not commonly used but easily implemented) and convolutional neural network (CNN; effective but more complex approach). We also evaluate the effects of subject age, axial length, refractive error, fixation stability, disease status and retinal location on AO-FIO image quality. Based on analysis of 10,250 images of 50 × 50 μm size, at 41 retinal locations, from 50 subjects we demonstrate that CNN slightly outperforms LAPE in image quality assessment. CNN achieves accuracy of 89%, whereas LAPE metric achieves 73% and 80% (for a linear regression and random forest multiclass classifier methods, respectively) compared to ground truth. Furthermore, the retinal location, age and disease are factors that can influence the likelihood of poor image quality.

Temporal bone CT-scan is a prerequisite in most surgical procedures concerning the ear such as cochlear implants. The 3D vision of inner ear structures is crucial for diagnostic and surgical preplanning purposes. Since clinical CT-scans are acquired at relatively low resolutions, improved performance can be achieved by registering patient-specific CT images to a high-resolution inner ear model built from accurate 3D segmentations based on micro-CT of human temporal bone specimens. This paper presents a framework based on convolutional neural network for human inner ear segmentation from micro-CT images which can be used to build such a model from an extensive database. The proposed approach employs an auto-context based cascaded 2D U-net architecture with 3D connected component refinement to segment the cochlear scalae, semicircular canals, and the vestibule. The system was formulated on a data set composed of 17 micro-CT from public Hear-EU dataset. A Dice coefficient of 0.90 and Hausdorff distance of 0.74 mm were obtained. The system yielded precise and fast automatic inner-ear segmentations.

In this paper, we propose a real-time prediction model that can respond to particulate matters (PM) in the air, which are an indication of poor air quality. The model applies interpolation to air quality and weather data and then uses a Convolutional Neural Network (CNN) to predict PM concentrations. The interpolation transforms the irregular spatial data into an equally spaced grid, which the model requires. This combination creates the interpolated CNN (ICNN) model that we use to predict PM10 and PM2.5 concentrations. The PM10 and PM2.5 evaluation results show an effective prediction performance with an R-squared higher than 0.97 and a root mean square error (RMSE) of approximately 16% of the standard deviation. Furthermore, both PM10 and PM2.5 prediction models forecast high concentrations with high reliability, with a probability of detection higher than 0.90 and a critical success index exceeding 0.85. The proposed ICNN prediction model achieves a high prediction performance using spatio-temporal information and presents a new direction in the prediction field.

Diabetic macular edema (DME) and retina vein occlusion (RVO) are macular diseases in which central photoreceptors are affected due to pathological accumulation of fluid. Optical coherence tomography allows to visually assess and evaluate photoreceptor integrity, whose alteration has been observed as an important biomarker of both diseases. However, the manual quantification of this layered structure is challenging, tedious and time-consuming. In this paper we introduce a deep learning approach for automatically segmenting and characterising photoreceptor alteration. The photoreceptor layer is segmented using an ensemble of four different convolutional neural networks. En-face representations of the layer thickness are produced to characterize the photoreceptors. The pixel-wise standard deviation of the score maps produced by the individual models is also taken to indicate areas of photoreceptor abnormality or ambiguous results. Experimental results showed that our ensemble is able to produce results in pair with a human expert, outperforming each of its constitutive models. No statistically significant differences were observed between mean thickness estimates obtained from automated and manually generated annotations. Therefore, our model is able to reliable quantify photoreceptors, which can be used to improve prognosis and managment of macular diseases.

The retention of a capsule endoscope (CE) in the stomach and the duodenal bulb during the examination is a troublesome problem, which can make the medical staff spend several hours observing whether the CE enters the descending segment of the duodenum (DSD). This paper investigated and evaluated the Convolution Neural Network (CNN) for automatic retention-monitoring of the CE in the stomach or the duodenal bulb. A trained CNN system based on 180,000 CE images of the DSD, stomach, and duodenal bulb was used to assess its recognition of the accuracy by calculating the area under the receiver operating characteristic curve (ROC-AUC), sensitivity and specificity. The AUC for distinguishing the DSD was 0.984. The sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 97.8%, 96.0%, 96.1% and 97.8%, respectively, at a cut-off value of 0.42 for the probability score. The deviated rate of the time into the DSD marked by the CNN at less than ±8 min was 95.7% (P 0.01). These results indicate that the CNN for automatic retention-monitoring of the CE in the stomach or the duodenal bulb can be used as an efficient auxiliary measure in the clinical practice.

This paper proposed a non-segmentation radiological method for classification of benign and malignant thyroid tumors using B mode ultrasound data. This method aimed to combine the advantages of morphological information provided by ultrasound and convolutional neural networks in automatic feature extraction and accurate classification. Compared with the traditional feature extraction method, this method directly extracted features from the data set without the need for segmentation and manual operations. 861 benign nodule images and 740 malignant nodule images were collected for training data. A deep convolution neural network VGG-16 was constructed to analyze test data including 100 malignant nodule images and 109 benign nodule images. A nine fold cross validation was performed for training and testing of the classifier. The results showed that the method had an accuracy of 86.12%, a sensitivity of 87%, and a specificity of 85.32%. This computer-aided method demonstrated comparable diagnostic performance with the result reported by an experienced radiologist based on American college of radiology thyroid imaging reporting and data system (ACR TI-RADS) (accuracy: 87.56%, sensitivity: 92%, and specificity: 83.49%). The automation advantage of this method suggested application potential in computer-aided diagnosis of thyroid cancer.

The identification of suspicious microseismic events is the first crucial step in microseismic data processing. Existing automatic classification methods are based on the training of a large data set, which is challenging to apply in mines without a long-term manual data processing. In this paper, we present a method to automatically classify microseismic records with limited samples in underground mines based on capsule networks (CapsNet). We divide each microseismic record into 33 frames, then extract 21 commonly used features in time and frequency from each frame. Consequently, a 21 × 33 feature matrix is utilized as the input of CapsNet. On this basis, we use different sizes of training sets to train the classification models separately. The trained model is tested using the same test set containing 3,200 microseismic records and compared to convolutional neural networks (CNN) and traditional machine learning methods. Results show that the accuracy of our proposed method is 99.2% with limited training samples. It is superior to CNN and traditional machine learning methods in terms of Accuracy, Precision, Recall, F1-Measure, and reliability.

The Myxococcales order consist of eleven families comprising30 genera, and are featured by the formation of the highest level of differential structure aggregations called fruiting bodies. These multicellular structures are essential for their resistance in ecosystems and is used in the primitive identification of these bacteria while their accurate taxonomic position is confirmed by the nucleotide sequence of 16SrRNA gene. Phenotypic classification of these structures is currently performed based on the stereomicroscopic observations that demand personal experience. The detailed phenotypic features of the genera with similar fruiting bodies are not readily distinctive by not particularly experienced researchers. The human examination of the fruiting bodies requires high skill and is error-prone. An image pattern analysis of schematic images of these structures conducted us to the construction of a database, which led to an extractable recognition of the unknown fruiting bodies. In this paper, Convolutional Neural Network (CNN) was considered as a baseline for recognition of fruiting bodies. In addition, to enhance the result the classifier, part of CNN is replaced with other classifiers. By employing the introduced model, all 30 genera of this order could be recognized based on stereomicroscopic images of the fruiting bodies at the genus level that not only does not urge us to amplify and sequence gene but also can be attained without preparation of microscopic slides of the vegetative cells or myxospores. The accuracy of 77.24% in recognition of genera and accuracy of 88.92% in recognition of suborders illustrate the applicability property of the proposed machine learning model.

This paper introduces a deep-learning based computer-aided diagnostic (CAD) system for the early detection of acute renal transplant rejection. For noninvasive detection of kidney rejection at an early stage, the proposed CAD system is based on the fusion of both imaging markers and clinical biomarkers. The former are derived from diffusion-weighted magnetic resonance imaging (DW-MRI) by estimating the apparent diffusion coefficients (ADC) representing the perfusion of the blood and the diffusion of the water inside the transplanted kidney. The clinical biomarkers, namely: creatinine clearance (CrCl) and serum plasma creatinine (SPCr), are integrated into the proposed CAD system as kidney functionality indexes to enhance its diagnostic performance. The ADC maps are estimated for a user-defined region of interest (ROI) that encompasses the whole kidney. The estimated ADCs are fused with the clinical biomarkers and the fused data is then used as an input to train and test a convolutional neural network (CNN) based classifier. The CAD system is tested on DW-MRI scans collected from 56 subjects from geographically diverse populations and different scanner types/image collection protocols. The overall accuracy of the proposed system is 92.9% with 93.3% sensitivity and 92.3% specificity in distinguishing non-rejected kidney transplants from rejected ones. These results demonstrate the potential of the proposed system for a reliable non-invasive diagnosis of renal transplant status for any DW-MRI scans, regardless of the geographical differences and/or imaging protocol.

Rice disease recognition is crucial in automated rice disease diagnosis systems. At present, deep convolutional neural network (CNN) is generally considered the state-of-the-art solution in image recognition. In this paper, we propose a novel rice blast recognition method based on CNN. A dataset of 2906 positive samples and 2902 negative samples is established for training and testing the CNN model. In addition, we conduct comparative experiments for qualitative and quantitatively analysis in our evaluation of the effectiveness of the proposed method. The evaluation results show that the high-level features extracted by CNN are more discriminative and effective than traditional hand-crafted features including local binary patterns histograms (LBPH) and Haar-WT (Wavelet Transform). Moreover, quantitative evaluation results indicate that CNN with Softmax and CNN with support vector machine (SVM) have similar performances, with higher accuracy, larger area under curve (AUC), and better receiver operating characteristic (ROC) curves than both LBPH plus an SVM as the classifier and Haar-WT plus an SVM as the classifier. Therefore, our CNN model is a top performing method for rice blast disease recognition and can be potentially employed in practical applications.

Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subject were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps and layers, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur achieved a high dice similarity score of 0.94$\pm$0.05 with precision = 0.95$\pm$0.02, and recall = 0.94$\pm$0.08 using a CNN architecture based on 3D convolution exceeding the performance of 2D CNNs. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis., This is a pre-print of an article published in Scientific Reports. The final authenticated version is available online at: https://doi.org/10.1038/s41598-018-34817-6

Machine learning has considerably improved medical image analysis in the past years. Although data-driven approaches are intrinsically adaptive and thus, generic, they often do not perform the same way on data from different imaging modalities. In particular computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs), mostly due to the broad dynamic range of intensities and the varying number of recorded slices of CT volumes. In this paper, we address these issues with a framework that adds domain-specific data preprocessing and augmentation to state-of-the-art CNN architectures. Our major focus is to stabilise the prediction performance over samples as a mandatory requirement for use in automated and semi-automated workflows in the clinical environment. To validate the architecture-independent effects of our approach we compare a neural architecture based on dilated convolutions for parallel multi-scale processing (a modified Mixed-Scale Dense Network: MS-D Net) to traditional scaling operations (a modified U-Net). Finally, we show that an ensemble model combines the strengths across different individual methods. Our framework is simple to implement into existing deep learning pipelines for CT analysis. It performs well on a range of tasks such as liver and kidney segmentation, without significant differences in prediction performance on strongly differing volume sizes and varying slice thickness. Thus our framework is an essential step towards performing robust segmentation of unknown real-world samples.