Query:
学者姓名:冯金超
Refining:
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract :
Brain tumors, which are uncontrolled growths of brain cells, pose a threat to people worldwide. However, accurately classifying brain tumors through computerized methods has been difficult due to differences in size, shape, and location of the tumors and limitations in the medical field. Improved precision is critical in detecting brain tumors, as small errors in human judgments can result in increased mortality rates. This paper proposes a new method for improving early detection and decision-making in brain tumor severity using learning methodologies. Clinical data -sets are used to obtain benchmark images of brain tumors, which undergo pre-processing, data aug-mentation with a Generative Adversarial Network, and classification with an Adaptive Layer Cascaded ResNet (ALCResNet) optimized with Improved Border Collie Optimization (IBCO). The abnormal images are then segmented using the DeepLabV3 model and fed into the ALCRes-Net for final classification into Meningioma, Glioma, or Pituitary. The IBCO algorithm-based ALCResNet model outperforms other heuristic classifiers for brain tumor classification and severity estimation, with improvements ranging from 1.3% to 4.4% over COA-ALCResNet, DHOA-ALCResNet, MVO-ALCResNet, and BCO-ALCResNet. The IBCO algorithm-based ALCResNet model also achieves higher accuracy than non-heuristic classifiers such as CNN, DNN, SVM, and ResNet, with improvements ranging from 2.4% to 3.6% for brain tumor classification and 0.9% to 3.8% for severity estimation. The proposed method offers an automated classification and grading system for brain tumors and improves the accuracy of brain tumor classification and severity estimation, promoting more precise decision-making regarding diagnosis and treatment.& COPY; 2023 The Authors. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).
Keyword :
Adaptive Layer Cascaded ResNet Adaptive Layer Cascaded ResNet Generative Adversarial Net-work Generative Adversarial Net-work Brain Tumor Grading Sys-tem Brain Tumor Grading Sys-tem DeepLabV3 DeepLabV3 Brain Tumor Classification System Brain Tumor Classification System Improved Border Collie Optimization Improved Border Collie Optimization
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Yaqub, Muhammad , Jinchao, Feng , Ahmed, Shahzad et al. DeepLabV3, IBCO-based ALCResNet: A fully automated classification, and grading system for brain tumor [J]. | ALEXANDRIA ENGINEERING JOURNAL , 2023 , 76 : 609-627 . |
MLA | Yaqub, Muhammad et al. "DeepLabV3, IBCO-based ALCResNet: A fully automated classification, and grading system for brain tumor" . | ALEXANDRIA ENGINEERING JOURNAL 76 (2023) : 609-627 . |
APA | Yaqub, Muhammad , Jinchao, Feng , Ahmed, Shahzad , Mehmood, Atif , Chuhan, Imran Shabir , Manan, Malik Abdul et al. DeepLabV3, IBCO-based ALCResNet: A fully automated classification, and grading system for brain tumor . | ALEXANDRIA ENGINEERING JOURNAL , 2023 , 76 , 609-627 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time-consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer-assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E-ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively.
Keyword :
data augmentation data augmentation semantic segmentation semantic segmentation residual network residual network diabetic retinopathy diabetic retinopathy retinal image retinal image convolution neural network convolution neural network exudates exudates
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Manan, Malik Abdul , Jinchao, Feng , Khan, Tariq M. M. et al. Semantic segmentation of retinal exudates using a residual encoder-decoder architecture in diabetic retinopathy [J]. | MICROSCOPY RESEARCH AND TECHNIQUE , 2023 , 86 (11) : 1443-1460 . |
MLA | Manan, Malik Abdul et al. "Semantic segmentation of retinal exudates using a residual encoder-decoder architecture in diabetic retinopathy" . | MICROSCOPY RESEARCH AND TECHNIQUE 86 . 11 (2023) : 1443-1460 . |
APA | Manan, Malik Abdul , Jinchao, Feng , Khan, Tariq M. M. , Yaqub, Muhammad , Ahmed, Shahzad , Chuhan, Imran Shabir . Semantic segmentation of retinal exudates using a residual encoder-decoder architecture in diabetic retinopathy . | MICROSCOPY RESEARCH AND TECHNIQUE , 2023 , 86 (11) , 1443-1460 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Generative adversarial networks (GAN), which are fueled by deep learning, are an efficient technique for image reconstruction using under-sampled MR data. In most cases, the performance of a particular model's reconstruction must be improved by using a substantial proportion of the training data. However, gathering tens of thousands of raw patient data for training the model in actual clinical applications is difficult because retaining k-space data is not customary in the clinical process. Therefore, it is imperative to increase the generalizability of a network that was created using a small number of samples as quickly as possible. This research explored two unique applications based on deep learning-based GAN and transfer learning. Seeing as MRI reconstruction procedures go for brain and knee imaging, the proposed method outperforms current techniques in terms of signal-to-noise ratio (PSNR) and structural similarity index (SSIM). As compared to the results of transfer learning for the brain and knee, using a smaller number of training cases produced superior results, with acceleration factor (AF) 2 (for brain PSNR (39.33); SSIM (0.97), for knee PSNR (35.48); SSIM (0.90)) and AF 4 (for brain PSNR (38.13); SSIM (0.95), for knee PSNR (33.95); SSIM (0.86)). The approach that has been described would make it easier to apply future models for MRI reconstruction without necessitating the acquisition of vast imaging datasets.
Keyword :
MRI MRI image reconstruction image reconstruction deep learning deep learning transfer learning transfer learning GANs GANs
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Yaqub, Muhammad , Feng Jinchao , Ahmed, Shahzad et al. GAN-TL: Generative Adversarial Networks with Transfer Learning for MRI Reconstruction [J]. | APPLIED SCIENCES-BASEL , 2022 , 12 (17) . |
MLA | Yaqub, Muhammad et al. "GAN-TL: Generative Adversarial Networks with Transfer Learning for MRI Reconstruction" . | APPLIED SCIENCES-BASEL 12 . 17 (2022) . |
APA | Yaqub, Muhammad , Feng Jinchao , Ahmed, Shahzad , Arshid, Kaleem , Bilal, Muhammad Atif , Akhter, Muhammad Pervez et al. GAN-TL: Generative Adversarial Networks with Transfer Learning for MRI Reconstruction . | APPLIED SCIENCES-BASEL , 2022 , 12 (17) . |
Export to | NoteExpress RIS BibTex |
Abstract :
Image reconstruction in magnetic resonance imaging (MRI) and computed tomography (CT) is a mathematical process that generates images at many different angles around the patient. Image reconstruction has a fundamental impact on image quality. In recent years, the literature has focused on deep learning and its applications in medical imaging, particularly image reconstruction. Due to the performance of deep learning models in a wide variety of vision applications, a considerable amount of work has recently been carried out using image reconstruction in medical images. MRI and CT appear as the ultimate scientifically appropriate imaging mode for identifying and diagnosing different diseases in this ascension age of technology. This study demonstrates a number of deep learning image reconstruction approaches and a comprehensive review of the most widely used different databases. We also give the challenges and promising future directions for medical image reconstruction.
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Yaqub, Muhammad , Jinchao, Feng , Arshid, Kaleem et al. Deep Learning-Based Image Reconstruction for Different Medical Imaging Modalities [J]. | COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE , 2022 , 2022 . |
MLA | Yaqub, Muhammad et al. "Deep Learning-Based Image Reconstruction for Different Medical Imaging Modalities" . | COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022 (2022) . |
APA | Yaqub, Muhammad , Jinchao, Feng , Arshid, Kaleem , Ahmed, Shahzad , Zhang, Wenqian , Nawaz, Muhammad Zubair et al. Deep Learning-Based Image Reconstruction for Different Medical Imaging Modalities . | COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE , 2022 , 2022 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Cherenkov-excited luminescence scanned imaging (CELSI) is a new emerging imaging modality, which uses linear accelerator (LINAC) to induce Cherenkov radiation, and then secondary excite molecular probes to produce luminescence. The tomographic distribution of the molecular probes can be recovered by a reconstruction algorithm. However, the reconstruction images usually suffer from many artifacts. To improve the image quality for tomographic reconstruction, we propose a reconstruction method based on learned KSVD. Numerical simulation experiments reveal that the proposed algorithm can reduce the artifacts in the reconstructed image. The quantitative results show that the structured similarity (SSIM) is improved more than 8.8% compared to the existing algorithms. In addition, our results also demonstrate that the proposed algorithm has the best performance under different noise levels (0.5%, 1%, 2%, and 4%).
Keyword :
artifacts removal artifacts removal image reconstruction image reconstruction Cherenkov-excited luminescence scanned imaging Cherenkov-excited luminescence scanned imaging learned KSVD learned KSVD
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Zhang, Hu , Li, Zhe , Sun, Zhonghua et al. Improved image quality for Cherenkov-Excited Luminescence Scanned Tomography based on learned KSVD [J]. | MOLECULAR-GUIDED SURGERY: MOLECULES, DEVICES, AND APPLICATIONS VIII , 2022 , 11943 . |
MLA | Zhang, Hu et al. "Improved image quality for Cherenkov-Excited Luminescence Scanned Tomography based on learned KSVD" . | MOLECULAR-GUIDED SURGERY: MOLECULES, DEVICES, AND APPLICATIONS VIII 11943 (2022) . |
APA | Zhang, Hu , Li, Zhe , Sun, Zhonghua , Geng, Mengfan , Jia, Kebin , Feng, Jinchao . Improved image quality for Cherenkov-Excited Luminescence Scanned Tomography based on learned KSVD . | MOLECULAR-GUIDED SURGERY: MOLECULES, DEVICES, AND APPLICATIONS VIII , 2022 , 11943 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Cherenkov-excited luminescence scanned tomography (CELST) is an emerging tomographic optical imaging modality. However, recovering spatial distribution of luminescent source from boundary measurements is a typically ill-posed problem. To improve the performance of CELST reconstruction, an end-to-end reconstruction algorithm is developed by combining dilated convolution and attention mechanism based on Unet (DA-Unet). Its performance is validated with numerical simulations. The results reveal that DA-Unet has superior reconstruction performance with high spatial resolution. It achieves image quality with PSNR of more than 35 dB and SSIM of larger than 0.95. Furthermore, the DA-Unet can reconstruct luminescent source even with less boundary measurements.
Keyword :
attention mechanism attention mechanism Cherenkov-excited luminescence scanned tomography Cherenkov-excited luminescence scanned tomography dilated convolution dilated convolution U-Net U-Net
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Zhang, Wenqian , Li, Zhe , Sun, Zhonghua et al. Cherenkov-excited luminescence scanned tomography reconstruction based on Unet [J]. | MOLECULAR-GUIDED SURGERY: MOLECULES, DEVICES, AND APPLICATIONS VIII , 2022 , 11943 . |
MLA | Zhang, Wenqian et al. "Cherenkov-excited luminescence scanned tomography reconstruction based on Unet" . | MOLECULAR-GUIDED SURGERY: MOLECULES, DEVICES, AND APPLICATIONS VIII 11943 (2022) . |
APA | Zhang, Wenqian , Li, Zhe , Sun, Zhonghua , Jia, Kebin , Feng, Jinchao . Cherenkov-excited luminescence scanned tomography reconstruction based on Unet . | MOLECULAR-GUIDED SURGERY: MOLECULES, DEVICES, AND APPLICATIONS VIII , 2022 , 11943 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Diffuse Optical Tomography ( DOT) is a promising non-invasive and relatively low-cost biomedical image technology. The aim of DOT is to reconstruct optical properties of the tissue from boundary measurements. However, the DOT reconstruction is a severely ill-posed problem. To reduce the ill-posedness of DOT and to improve image quality, image-guided DOT has attracted more attention. In this paper, a reconstruction algorithm for DOT is proposed based on the convolutional neural network (CNN). It uses both optical measurements and magnetic resonance imaging (MRI) images as the input of the CNN, and directly reconstructs the distribution of absorption coefficient. The merits of the proposed algorithm are without segmenting MRI images and modeling light propagation. The performance of the proposed algorithm is evaluated using numerical simulation experiments. Our results reveal that the proposed method can achieve superior performance compared with conventional reconstruction algorithms and other deep learning methods. Our result shows that the average SSIM of reconstructed images is above 0.88, and the average PSNR is more than 35 dB.
Keyword :
image-guided reconstruction image-guided reconstruction Diffuse optical tomography Diffuse optical tomography convolutional neural network convolutional neural network deep learning deep learning
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Zhang, Wanlong , Li, Zhe , Sun, Zhonghua et al. A novelty Convolutional Neural Network Based Direct Reconstruction for MRI Guided Diffuse Optical Tomography [J]. | MULTIMODAL BIOMEDICAL IMAGING XVII , 2022 , 11952 . |
MLA | Zhang, Wanlong et al. "A novelty Convolutional Neural Network Based Direct Reconstruction for MRI Guided Diffuse Optical Tomography" . | MULTIMODAL BIOMEDICAL IMAGING XVII 11952 (2022) . |
APA | Zhang, Wanlong , Li, Zhe , Sun, Zhonghua , Jia, Kebin , Feng, Jinchao . A novelty Convolutional Neural Network Based Direct Reconstruction for MRI Guided Diffuse Optical Tomography . | MULTIMODAL BIOMEDICAL IMAGING XVII , 2022 , 11952 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Diffusion correlation spectroscopy (DCS) is a relatively new methodology that has been extensively used for the noninvasive monitoring of tissue blood flow. This technology irradiates the tissue surface with near-infrared light, calculates the light intensity autocorrelation function of the scattered spot on the tissue surface, and computes the movement of red blood cells to realize the quantitative detection of blood flow changes in tissues. DCS measurements show more promise for the noninvasive, radiation-free, continuous and real-time monitoring, wide application range, and low detection requirements of tissue blood flow than the other blood flow monitoring methods such as laser Doppler flowmetry (LDF), magnetic resonance imaging (MRI), and positron emission tomography (PET). Moreover, DCS technology can be utilized for the bedside monitoring of tissue blood flow. The DCS technique is mainly introduced in which its theoretical background, instrumentation, progress, and clinical applications are included, as well as its future development prospects are discussed.
Keyword :
near-infrared spectroscopy near-infrared spectroscopy tissue blood flow tissue blood flow cardiovascular and cerebrovascular disease cardiovascular and cerebrovascular disease biotechnology biotechnology cancer cancer diffusion correlation spectroscopy diffusion correlation spectroscopy
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Li Zhe , Feng Jinchao , Jia Kebin . Diffusion Correlation Spectroscopy for Tissue Blood Flow Monitoring and Its Clinical Applications [J]. | LASER & OPTOELECTRONICS PROGRESS , 2022 , 59 (6) . |
MLA | Li Zhe et al. "Diffusion Correlation Spectroscopy for Tissue Blood Flow Monitoring and Its Clinical Applications" . | LASER & OPTOELECTRONICS PROGRESS 59 . 6 (2022) . |
APA | Li Zhe , Feng Jinchao , Jia Kebin . Diffusion Correlation Spectroscopy for Tissue Blood Flow Monitoring and Its Clinical Applications . | LASER & OPTOELECTRONICS PROGRESS , 2022 , 59 (6) . |
Export to | NoteExpress RIS BibTex |
Abstract :
Diffuse optical tomography (DOT) is a promising non-invasive optical imaging technique that can provide functional information of biological tissues. Since diffuse light undergoes multiple scattering in biological tissues and boundary measurements are limited, DOT reconstruction is ill-posedness and ill-conditioned. To overcome these limitations, Tikhonov regularization is the most popular algorithm. Recently, deep learning based reconstruction methods have attracted increasing attention, and promising results have been reported. However, they lack generalization for unstructured physical model. Therefore, a model-base convolution neural network framework (Model-CNN) is developed. It composes of two layers: data consistency layer and depth layer, which increases the interpretability of the model. Its performance is evaluated with numerical simulations. Our results demonstrate that Model-CNN can get better reconstructed results than those obtained by Tikhonov Regularization in terms of ABE, MSE, and PSNR.
Keyword :
Convolutional neural network Convolutional neural network diffuse optical tomography diffuse optical tomography model-engine model-engine
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Wei, Chengpu , Li, Zhe , Sun, Zhonghua et al. Diffusion equation engine deep learning for diffuse optical tomography [J]. | MULTIMODAL BIOMEDICAL IMAGING XVII , 2022 , 11952 . |
MLA | Wei, Chengpu et al. "Diffusion equation engine deep learning for diffuse optical tomography" . | MULTIMODAL BIOMEDICAL IMAGING XVII 11952 (2022) . |
APA | Wei, Chengpu , Li, Zhe , Sun, Zhonghua , Jia, Kebin , Feng, Jinchao . Diffusion equation engine deep learning for diffuse optical tomography . | MULTIMODAL BIOMEDICAL IMAGING XVII , 2022 , 11952 . |
Export to | NoteExpress RIS BibTex |
Keyword :
cancer therapy cancer therapy pharmacological research pharmacological research imaging technology imaging technology oncology oncology small molecule drugs small molecule drugs
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Zeng, Qi , Cao, Xu , Feng, Jinchao et al. Editorial: Imaging Technology in Oncology Pharmacological Research [J]. | FRONTIERS IN PHARMACOLOGY , 2021 , 12 . |
MLA | Zeng, Qi et al. "Editorial: Imaging Technology in Oncology Pharmacological Research" . | FRONTIERS IN PHARMACOLOGY 12 (2021) . |
APA | Zeng, Qi , Cao, Xu , Feng, Jinchao , Shan, Hong , Chen, Xueli . Editorial: Imaging Technology in Oncology Pharmacological Research . | FRONTIERS IN PHARMACOLOGY , 2021 , 12 . |
Export to | NoteExpress RIS BibTex |
Export
Results: |
Selected to |
Format: |