scholarly journals dSPIC: a deep SPECT image classification network for automated multi-disease, multi-lesion diagnosis

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Qiang Lin ◽  
Chuangui Cao ◽  
Tongtong Li ◽  
Zhengxing Man ◽  
Yongchun Cao ◽  
...  
Keyword(s):  
Image Classification ◽  
Bone Scintigraphy ◽  
Data Augmentation ◽  
Spect Imaging ◽  
Whole Body ◽  
Geometric Transformation ◽  
Imaging Data ◽  
Generative Adversarial Network ◽  
Spect Image ◽  
Spect Images

Abstract Background Functional imaging especially the SPECT bone scintigraphy has been accepted as the effective clinical tool for diagnosis, treatment, evaluation, and prevention of various diseases including metastasis. However, SPECT imaging is brightly characterized by poor resolution, low signal-to-noise ratio, as well as the high sensitivity and low specificity because of the visually similar characteristics of lesions between diseases on imaging findings. Methods Focusing on the automated diagnosis of diseases with whole-body SPECT scintigraphic images, in this work, a self-defined convolutional neural network is developed to survey the presence or absence of diseases of concern. The data preprocessing mainly including data augmentation is first conducted to cope with the problem of limited samples of SPECT images by applying the geometric transformation operations and generative adversarial network techniques on the original SPECT imaging data. An end-to-end deep SPECT image classification network named dSPIC is developed to extract the optimal features from images and then to classify these images into classes, including metastasis, arthritis, and normal, where there may be multiple diseases existing in a single image. Results A group of real-world data of whole-body SPECT images is used to evaluate the self-defined network, obtaining a best (worst) value of 0.7747 (0.6910), 0.7883 (0.7407), 0.7863 (0.6956), 0.8820 (0.8273) and 0.7860 (0.7230) for accuracy, precision, sensitivity, specificity, and F-1 score, respectively, on the testing samples from the original and augmented datasets. Conclusions The prominent classification performance in contrast to other related deep classifiers including the classical AlexNet network demonstrates that the built deep network dSPIC is workable and promising for the multi-disease, multi-lesion classification task of whole-body SPECT bone scintigraphy images.

scholarly journals An Imbalanced Image Classification Method for the Cell Cycle Phase

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 249
Author(s):  
Xin Jin ◽  
Yuanwen Zou ◽  
Zhongbing Huang
Keyword(s):  
Cell Cycle ◽  
Deep Learning ◽  
Image Classification ◽  
Classification Accuracy ◽  
Data Augmentation ◽  
Cycle Phase ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cellular Life

The cell cycle is an important process in cellular life. In recent years, some image processing methods have been developed to determine the cell cycle stages of individual cells. However, in most of these methods, cells have to be segmented, and their features need to be extracted. During feature extraction, some important information may be lost, resulting in lower classification accuracy. Thus, we used a deep learning method to retain all cell features. In order to solve the problems surrounding insufficient numbers of original images and the imbalanced distribution of original images, we used the Wasserstein generative adversarial network-gradient penalty (WGAN-GP) for data augmentation. At the same time, a residual network (ResNet) was used for image classification. ResNet is one of the most used deep learning classification networks. The classification accuracy of cell cycle images was achieved more effectively with our method, reaching 83.88%. Compared with an accuracy of 79.40% in previous experiments, our accuracy increased by 4.48%. Another dataset was used to verify the effect of our model and, compared with the accuracy from previous results, our accuracy increased by 12.52%. The results showed that our new cell cycle image classification system based on WGAN-GP and ResNet is useful for the classification of imbalanced images. Moreover, our method could potentially solve the low classification accuracy in biomedical images caused by insufficient numbers of original images and the imbalanced distribution of original images.

scholarly journals The usefulness of SwiftScan technology for bone scintigraphy using a novel anthropomorphic phantom

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Takayuki Shibutani ◽  
Masahisa Onoguchi ◽  
Yuka Naoi ◽  
Hiroto Yoneyama ◽  
Takahiro Konishi ◽  
...  
Keyword(s):  
High Resolution ◽  
Bone Scintigraphy ◽  
Low Energy ◽  
Acquisition Time ◽  
Emission Computed Tomography ◽  
Blend Ratio ◽  
Planar Image ◽  
Spect Image ◽  
Step And Shoot ◽  
Spect Images

AbstractThe aim of this study was to demonstrate the usefulness of SwiftScan with a low-energy high-resolution and sensitivity (LEHRS) collimator for bone scintigraphy using a novel bone phantom simulating the human body. SwiftScan planar image of lateral view was acquired in clinical condition; thereafter, each planar image of different blend ratio (0–80%) of Crality 2D processing were created. SwiftScan planar images with reduced acquisition time by 25–75% were created by Poisson’s resampling processing. SwiftScan single photon emission computed tomography (SPECT) was acquired with step-and-shoot and continuous mode, and SPECT images were reconstructed using a three-dimensional ordered subset expectation maximization incorporating attenuation, scatter and spatial resolution corrections. SwiftScan planar image showed a high contrast to noise ratio (CNR) and low percent of the coefficient of variance (%CV) compared with conventional planar image. The CNR of the tumor parts in SwiftScan SPECT was higher than that of the conventional SPECT image of step and shoot acquisition, while the %CV showed the lowest value in all systems. In conclusion, SwiftScan planar and SPECT images were able to reduce the image noise compared with planar and SPECT image with a low-energy high-resolution collimator, so that SwiftScan planar and SPECT images could be obtained a high CNR. Furthermore, the SwiftScan planar image was able to reduce the acquisition time by 25% when the blend ratio of Clarity 2D processing set to more than 40%.

scholarly journals Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4485 ◽  
Author(s):  
Kai Zhang ◽  
Guanghua Xu ◽  
Zezhen Han ◽  
Kaiquan Ma ◽  
Xiaowei Zheng ◽  
...  
Keyword(s):  
Neural Network ◽  
Motor Imagery ◽  
Large Scale ◽  
Data Augmentation ◽  
Classification Performance ◽  
Hybrid Network ◽  
Geometric Transformation ◽  
Generative Adversarial Network ◽  
Performance Improvements ◽  
Adversarial Network

As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.

Scintigraphy with 99m Tc-Phosphonate and 67Gallium in Patients Suspected of Primary Bone Tumors

1982 ◽  
Vol 21 (04) ◽  
pp. 136-139 ◽  
Author(s):  
C.-J. Edeling
Keyword(s):  
Soft Tissue ◽  
Bone Scintigraphy ◽  
Primary Tumor ◽  
Bone Tumors ◽  
Whole Body ◽  
Skeletal Metastases ◽  
Malignant Bone Tumors ◽  
67Ga Scintigraphy ◽  
Primary Bone Tumors ◽  
Primary Bone

Whole-body scintigraphy with both 99mTc-phosphonate and 67Ga was performed on 92 patients suspected of primary bone tumors. In 46 patients with primary malignant bone tumors, scintigraphy with 99mTc-phosphonate disclosed the primary tumor in 44 cases and skeletal metastases in 11, and 67Ga scintigraphy detected the primary tumor in 43 cases, skeletal metastases in 6 cases and soft-tissue metastases in 8 cases. In 25 patients with secondary malignant bone tumors, bone scintigraphy visualized a single lesion in 10 cases and several lesions in 15 cases, and 67Ga scintigraphy detected the primary tumor in 17 cases, skeletal metastases in 17 cases and soft-tissue metastases in 9 cases. In 21 patients with benign bone disease positive uptake of 99mTc-phosphonate was recognized in 19 cases and uptake of 67Ga in 17 cases. It is concluded that bone scintigraphy should be used in patients suspected of primary bone tumors. If malignancy is suspected, 67Ga scintigraphy should be performed in addition.

scholarly journals GPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1269
Author(s):  
Jiabin Luo ◽  
Wentai Lei ◽  
Feifei Hou ◽  
Chenghao Wang ◽  
Qiang Ren ◽  
...  
Keyword(s):  
Image Denoising ◽  
Data Augmentation ◽  
Noise Suppression ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Training Dataset ◽  
Generative Adversarial Network ◽  
Multi Scale ◽  
Convolutional Autoencoder

Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).

scholarly journals Quality and utility of [123I]I-metaiodobenzylguanidine cardiac SPECT imaging in nondiabetic postinfarction heart failure patients qualified for implantable cardioverter defibrillator

2021 ◽  
Author(s):  
Anna Teresińska ◽  
Olgierd Woźniak ◽  
Aleksander Maciąg ◽  
Jacek Wnuk ◽  
Jarosław Jezierski ◽  
...  
Keyword(s):  
Heart Failure ◽  
Implantable Cardioverter Defibrillator ◽  
Left Lung ◽  
Spect Imaging ◽  
Cardiac Innervation ◽  
Cardiac Spect ◽  
Cardioverter Defibrillator ◽  
Planar Images ◽  
Spect Images

Abstract Objective Impaired cardiac adrenergic activity has been demonstrated in heart failure (HF) and in diabetes mellitus (DM). [123I]I-metaiodobenzylguanidine (MIBG) enables assessment of the cardiac adrenergic nervous system. Tomographic imaging of the heart is expected to be superior to planar imaging. This study aimed to determine the quality and utility of MIBG SPECT in the assessment of cardiac innervation in postinfarction HF patients without DM, qualified for implantable cardioverter defibrillator (ICD) in primary prevention of sudden cardiac death. Methods Consecutive patients receiving an ICD on the basis of contemporary guidelines were prospectively included. Planar MIBG studies were followed by SPECT. The essential analysis was based on visual assessment of the quality of SPECT images (“high”, “low” or “unacceptable”). The variables used in the further analysis were late summed defect score for SPECT images and heart-to-mediastinum rate for planar images. MIBG images were assessed independently by two experienced readers. Results Fifty postinfarction nondiabetic HF subjects were enrolled. In 13 patients (26%), the assessment of SPECT studies was impossible. In addition, in 13 of 37 patients who underwent semiquantitative SPECT evaluation, the assessment was equivocal. Altogether, in 26/50 patients (52%, 95% confidence interval 38–65%), the quality of SPECT images was unacceptable or low and was limited by low MIBG cardiac uptake and by comparatively high, interfering MIBG uptake in the neighboring structures (primarily, in the lungs). Conclusions The utility of MIBG SPECT imaging, at least with conventional imaging protocols, in the qualification of postinfarction HF patients for ICD, is limited. In approximately half of the postinfarction HF patients, SPECT assessment of cardiac innervation can be impossible or equivocal, even without additional damage from diabetic cardiac neuropathy. The criteria predisposing the patient to good-quality MIBG SPECT are: high values of LVEF from the range characterizing the patients qualified to ICD (i.e., close to 35%) and left lung uptake intensity in planar images comparable to or lower than heart uptake.

Sign in / Sign up

Export Citation Format

Share Document