TPUAR-Net: Two Parallel U-Net with Asymmetric Residual-Based Deep Convolutional Neural Network for Brain Tumor Segmentation

Abd-Ellah, Mahmoud Khaled; Khalaf, Ashraf A. M.; Awad, Ali Ismail; Hamed, Hesham F. A.

doi:10.1007/978-3-030-27272-2_9

Cited by 16 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brain tumor [106], [107], [110]- [112], [114]- [118] Base U-net [18], [109], [120] 3D U-net [81] Adversarial net; GAN [59], [108] Residual block [113] Dense block [87] Cascaded U-net [92] Residual block; Parallel U-net [44] Inception block; Up skip connections [45] Dense block; Inception block [119] 3D U-net; Residual block [19] 3D U-net, Inception block, Residual block Brain tissue [103], [121]- [124] Base U-net [28], [160] 3D U-net [161] 2.5D U-net [54] Residual block [101] Parallel U-net [41] Attention gate; Residual block White matter tracts [126], [127] U-net with modified skip connections [125] Base U-net [89] Cascaded U-net Fetal brain [128]- [130] Base U-net [131] Base U-net; 3D U-net Stroke lesion/thrombus [133]- [136] Base U-net [132] 3D U-net [69] Dense block; Inception block Cardiovascular structures [138], [140]- [142], [144], …”

Section: Reference Model/methods Usedmentioning

confidence: 99%

“…Yet another arrangement of the overall architecture can be found in the form of a parallel arrangement of part or the entirety of a U-net network. Abd-Ellah et al [92] arranged two parallel U-nets and aggregated the results for improved segmentation accuracy. Soltanpour et al [93] implemented four parallel U-nets with each segmenting a different CT map and then merging the results.…”

Section: Parallel Arrangementmentioning

confidence: 99%

“…U-net has been used extensively in this regard for the segmentation of brain structures. Various U-net models have been applied on MR images for brain tumor diagnosis [18], [19], [59], [45], [81], [106], [107], [87], [108]- [111], [92], [112]- [119], [44], [120]. U-net has also been applied on brain tissue for investigation of neurological conditions [54], [101], [103], [121]- [124], analysis of white matter tissue [125]- [127], [89], fetal brain development [128]- [131], and stroke lesions [69], [132]- [136].…”

Section: Magnetic Resonance Imaging (Mri)mentioning

confidence: 99%

See 2 more Smart Citations

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

U-net is an image segmentation technique developed primarily for image segmentation tasks. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities, from CT scans and MRI to Xrays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net's potential is still increasing, this narrative literature review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.

show abstract

Section: Reference Model/methods Usedmentioning

confidence: 99%

Section: Parallel Arrangementmentioning

confidence: 99%

Section: Magnetic Resonance Imaging (Mri)mentioning

confidence: 99%

See 1 more Smart Citation

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The final layer is the classification layer that returns the classification output of the neural network. The categorical cross-entropy loss (error) is applied for multi-class classification [23].…”

Section: Softmaxmentioning

confidence: 99%

Deep Neural Network for Breast Tumor Classification Through Histopathological Image

Ibraheem

Rahouma

Hamed

2022

Journal of Advanced Engineering Trends

View full text Add to dashboard Cite

Most oncologists differ in their opinions about the diagnosis using histopathological images, so the manual diagnosis of breast cancer is difficult, and it also needs high experience. Building a model of breast tumor classification is an essential task. Computer-aided diagnosis (CAD) enables efficient and accurate diagnosis of this type of imaging. Moreover, it helps early diagnosis of breast tumors. Deep learning has begun to evolve in the last decades, so convolutional neural networks (CNN) are used to classify breast tumors. We introduced the automatic breast cancer classification methods to help doctors in examination and treatment, which can automatically classify the histopathological images as benign or malignant. This study's theoretical basis is developing a deep learning tumor classification system. It uses a deep learning approach, i.e., the proposed CNN Network consists of three stages. The first stage is preprocessing. The second stage is the feature extraction stage that takes input as augmented preprocessed images. This stage has 2 phases. The first phase consists of three parallel CNN branches with different filter sizes to extract different feature levels. We merged the three parallel branches in the second phase, which produced a feature fusion path that reduced the time complexity and enhanced the designed method's performance. The third stage classifies the fused features as benign or malignant. The BreakHis database is used and implemented and contains 7909 images of breast tumor tissue for 82 patients. The dataset was divided into 60%, 20%, 20% for training, validation, and testing. Several tests were performed to achieve the best diagnostic accuracy of 91.37 %. The results are compared to the results of different techniques in the literature. The introduced advantages of our method make it help in the shortest treatment time, especially in the case of the large-scale histopathological images of the breast cancer dataset where the average testing time per image for the proposed method was 0.08s.

show abstract

“…Brain tumor is proven to be a life-threatening and fatal disease [4]. In 2018, The American Cancer Society declared that there are 23,880 new instances with a brain tumor and 16,830 deaths in the United States alone [6]. Moreover, in recent decades, the number of died instances from brain tumors has increased in advanced nations by 300% as declared by the National Brain Tumor Foundation (NBTF) [7].…”

Section: Introductionmentioning

confidence: 99%

Brain Tumor Automatic Detection from MRI Images Using Transfer Learning Model with Deep Convolutional Neural Network

Bayoumi¹,

Abd-Ellah

Khalaf

et al. 2021

Journal of Advanced Engineering Trends

Self Cite

View full text Add to dashboard Cite

Brain tumor detection successfully in early-stage plays important role in improving patient treatment and survival. Evaluating magnetic resonance imaging (MRI) images manually is a very difficult task due to the numerous numbers of images produced in the clinic routinely. So, there is a need for using a computer-aided diagnosis (CAD) system for early detection and classification of brain tumors as normal and abnormal. The paper aims to design and evaluate the convolution neural network (CNN) Transfer Learning state-of-the-art performance proposed for image classification over the recent years. Five different modifications have been applied to five different famous CNN to know the most effective modification. Five-layer modifications with parameter tuning are applied for each architecture providing a new CNN architecture for brain tumor detection. Most brain tumor datasets have a small number of images to train the deep learning structure. Therefore, two datasets are used in the evaluation to ensure the effectiveness of the proposed structures. Firstly, a standard dataset from the RIDER Neuro MRI database including 349 brain MRI images with 109 normal images and 240 abnormal images. Secondly, a collection of 120 brain MRI images including 60 abnormal images and 60 normal images. The results show that the proposed CNN Transfer Learning with MRI's can learn significant biomarkers of brain tumor, however, the best accuracy, specificity, and sensitivity gained is 100% for all of them.

show abstract

TPUAR-Net: Two Parallel U-Net with Asymmetric Residual-Based Deep Convolutional Neural Network for Brain Tumor Segmentation

Cited by 16 publications

References 18 publications

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

Deep Neural Network for Breast Tumor Classification Through Histopathological Image

Brain Tumor Automatic Detection from MRI Images Using Transfer Learning Model with Deep Convolutional Neural Network

Contact Info

Product

Resources

About