首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 15 毫秒
1.
    
The brain tumour is the mass where some tissues become old or damaged, but they do not die or not leave their space. Mainly brain tumour masses occur due to malignant masses. These tissues must die so that new tissues are allowed to be born and take their place. Tumour segmentation is a complex and time-taking problem due to the tumour’s size, shape, and appearance variation. Manually finding such masses in the brain by analyzing Magnetic Resonance Images (MRI) is a crucial task for experts and radiologists. Radiologists could not work for large volume images simultaneously, and many errors occurred due to overwhelming image analysis. The main objective of this research study is the segmentation of tumors in brain MRI images with the help of digital image processing and deep learning approaches. This research study proposed an automatic model for tumor segmentation in MRI images. The proposed model has a few significant steps, which first apply the pre-processing method for the whole dataset to convert Neuroimaging Informatics Technology Initiative (NIFTI) volumes into the 3D NumPy array. In the second step, the proposed model adopts U-Net deep learning segmentation algorithm with an improved layered structure and sets the updated parameters. In the third step, the proposed model uses state-of-the-art Medical Image Computing and Computer-Assisted Intervention (MICCAI) BRATS 2018 dataset with MRI modalities such as T1, T1Gd, T2, and Fluid-attenuated inversion recovery (FLAIR). Tumour types in MRI images are classified according to the tumour masses. Labelling of these masses carried by state-of-the-art approaches such that the first is enhancing tumour (label 4), edema (label 2), necrotic and non-enhancing tumour core (label 1), and the remaining region is label 0 such that edema (whole tumour), necrosis and active. The proposed model is evaluated and gets the Dice Coefficient (DSC) value for High-grade glioma (HGG) volumes for their test set-a, test set-b, and test set-c 0.9795, 0.9855 and 0.9793, respectively. DSC value for the Low-grade glioma (LGG) volumes for the test set is 0.9950, which shows the proposed model has achieved significant results in segmenting the tumour in MRI using deep learning approaches. The proposed model is fully automatic that can implement in clinics where human experts consume maximum time to identify the tumorous region of the brain MRI. The proposed model can help in a way it can proceed rapidly by treating the tumor segmentation in MRI.  相似文献   

2.
    
Skin lesion segmentation is a crucial step for skin lesion analysis and subsequent treatment. However, it is still a challenging task due to the irregular and fuzzy lesion borders, and the diversity of skin lesions. In this article, we propose Triple-UNet, an organic combination of three UNet architectures with suitable modules, to automatically segment skin lesions. To enhance the target object region of the image, we design a region of interest enhancement module (ROIE) that uses the predicted score map of the first UNet. The enhanced image and the features learned by the first UNet help the second UNet obtain a better score map. Finally, the results are fine-tuned by the third UNet. We evaluate our algorithm on a publicly available dataset of skin lesion segmentation. Experiments have shown that TripleUNet achieves an accuracy of 92.5% on the ISIC-2018 skin lesion segmentation benchmark, with Dice and mIoU of 0.909 and 0.836, respectively, which outperforms the state-of-the-art algorithms.  相似文献   

3.
    
One of the most difficult problems that develop when brain cells start to grow out of control is a brain tumor, which is regarded as the most lethal disease of the century. Finding and identifying malignant brain magnetic resonance imaging (MRI) images is the major challenge before therapy. Researchers have been putting a lot of effort into creating the best method for more accurate real-world medical image recognition. For manual categorization, it is quite time-consuming to segment large quantities of MRI data. To mitigate these issues, this paper suggests the information exchange gateway-based residual UNet (IEGResUNet) model, which uses the ResUNet model as a base model. Additionally, including principal component analysis (PCA) data augmentation will increase the model's efficiency while also enhancing its speed. The IEGResUNet model shows an ablation investigation on three Brats datasets, with and without PCA augmentation. The results demonstrate that IEGResUNet will improve segmentation effectiveness and can also manage the imbalance in input data when PCA data augmentation models are included. The dice score on BraTS 2019 for whole tumor, region of core tumor, and region of enhancing tumor were 0.9083, 0.883, and 0.8106 respectively. Also, on BraTS 2020, the dice score for WT, CT, and ET 0.9083, 0.883, and 0.8106 was respectively. Similarly, on BraTS 2021, the dice score for WT, CT, and ET was 0.8737, 0.8866, and 0.7963 respectively. Comparing against baseline models, the IEGResUNet scored well in terms of dice score and intersection over union.  相似文献   

4.
    
Breast cancer is one of the deadly diseases in women that have raised the mortality rate of women. An accurate and early detection of breast cancer using mammogram images is still a complex task. Hence, this article proposes a novel breast cancer detection model, which included five major phases: (a) preprocessing, (b) segmentation, (c) feature extraction, (d) feature selection, and (e) classification. The input mammogram image is initially preprocessed using contrast limited adaptive histogram equalization (CLAHE) and median filtering. The preprocessed image is then subjected to segmentation via the region growing algorithm. Subsequently, geometric features, texture features and gradient features are extracted from the segmented image. Since the length of the feature vector is large, it is essential to select the optimal features. Here, the selection of optimal features is done by a hybrid optimization algorithm. Once the optimal features are selected, they are subjected to the classification process involving the neural network (NN) classifier. As a novelty, the weight of NN is selected optimally to enhance the accuracy of diagnosis (benign and malignant). The optimal feature selection as well as the weight optimization of NN is accomplished by merging the Lion algorithm (LA) and particle swarm optimization (PSO), named as velocity updated lion algorithm (VU‐LA). Finally, a performance‐based evaluation is carried out between VU‐LA and the existing models like, whale optimization algorithm (WOA), gray wolf optimization (GWO), firefly (FF), PSO, and LA.  相似文献   

5.
    
Biopsy is one of the most commonly used modality to identify breast cancer in women, where tissue is removed and studied by the pathologist under the microscope to look for abnormalities in tissue. This technique can be time-consuming, error-prone, and provides variable results depending on the expertise level of the pathologist. An automated and efficient approach not only aids in the diagnosis of breast cancer but also reduces human effort. In this paper, we develop an automated approach for the diagnosis of breast cancer tumors using histopathological images. In the proposed approach, we design a residual learning-based 152-layered convolutional neural network, named as ResHist for breast cancer histopathological image classification. ResHist model learns rich and discriminative features from the histopathological images and classifies histopathological images into benign and malignant classes. In addition, to enhance the performance of the developed model, we design a data augmentation technique, which is based on stain normalization, image patches generation, and affine transformation. The performance of the proposed approach is evaluated on publicly available BreaKHis dataset. The proposed ResHist model achieves an accuracy of 84.34% and an F1-score of 90.49% for the classification of histopathological images. Also, this approach achieves an accuracy of 92.52% and F1-score of 93.45% when data augmentation is employed. The proposed approach outperforms the existing methodologies in the classification of benign and malignant histopathological images. Furthermore, our experimental results demonstrate the superiority of our approach over the pre-trained networks, namely AlexNet, VGG16, VGG19, GoogleNet, Inception-v3, ResNet50, and ResNet152 for the classification of histopathological images.  相似文献   

6.
    
The task of segmentation of brain regions affected by ischemic stroke is help to tackle important challenges of modern stroke imaging analysis. Unfortunately, at the moment, the models for solving this problem using machine learning methods are far from ideal. In this paper, we consider a modified 3D UNet architecture to improve the quality of stroke segmentation based on 3D computed tomography images. We use the ISLES 2018 (Ischemic Stroke Lesion Segmentation Challenge 2018) open dataset to train and test the proposed model. Interpretation of the obtained results, as well as the ideas for further experiments are included in the paper. Our evaluation is performed using the Dice or f1 score coefficient and the Jaccard index. Our architecture may simply be extended to ischemia segmentation and computed tomography image identification by selecting relevant hyperparameters. The Dice/f1 score similarity coefficient of our model shown 58% and results close to ground truth which is higher than the standard 3D UNet model, demonstrating that our model can accurately segment ischemic stroke. The modified 3D UNet model proposed by us uses an efficient averaging method inside a neural network. Since this set of ISLES is limited in number, using the data augmentation method and neural network regularization methods to prevent overfitting gave the best result. In addition, one of the advantages is the use of the Intersection over Union loss function, which is based on the assessment of the coincidence of the shapes of the recognized zones.  相似文献   

7.
    
An unusual condition of the eye called diabetic retinopathy affects the human retina and is brought on by the blood's constant rise in insulin levels. Loss of vision is the result. Diabetic retinopathy can be improved by receiving an early diagnosis to prevent further damage. A cost-effective method of accumulating medical treatments is through appropriate DR screening. In this work, deep learning framework is introduced for the accurate classification of retinal diseases. The proposed method processes retinal fundus images obtained from databases, addressing noise and artifacts through an improved median filter (ImMF). It leverages the UNet++ model for precise segmentation of the disease-affected regions. UNet++ enhances feature extraction through cross-stage connections, improving segmentation results. The segmented images are then fed as input to the improved gannet optimization-based capsule DenseNet (IG-CDNet) for retinal disease classification. The hybrid capsule DenseNet (CDNet) classifies disease and is optimized using the improved gannet optimization algorithm to boost classification accuracy. Finally, the accuracy and dice score values achieved are 0.9917 and 0.9652 on the APTOS-2019 dataset.  相似文献   

8.
    
To propose and implement an automated machine learning (ML) based methodology to predict the overall survival of glioblastoma multiforme (GBM) patients. In the proposed methodology, we used deep learning (DL) based 3D U-shaped Convolutional Neural Network inspired encoder-decoder architecture to segment the brain tumor. Further, feature extraction was performed on these segmented and raw magnetic resonance imaging (MRI) scans using a pre-trained 2D residual neural network. The dimension-reduced principal components were integrated with clinical data and the handcrafted features of tumor subregions to compare the performance of regression-based automated ML techniques. Through the proposed methodology, we achieved the mean squared error (MSE) of 87 067.328, median squared error of 30 915.66, and a SpearmanR correlation of 0.326 for survival prediction (SP) with the validation set of Multimodal Brain Tumor Segmentation 2020 dataset. These results made the MSE far better than the existing automated techniques for the same patients. Automated SP of GBM patients is a crucial topic with its relevance in clinical use. The results proved that DL-based feature extraction using 2D pre-trained networks is better than many heavily trained 3D and 2D prediction models from scratch. The ensembled approach has produced better results than single models. The most crucial feature affecting GBM patients' survival is the patient's age, as per the feature importance plots presented in this work. The most critical MRI modality for SP of GBM patients is the T2 fluid attenuated inversion recovery, as evident from the feature importance plots.  相似文献   

9.
    
Intelligent straw coverage detection plays an important role in agricultural production and the ecological environment. Traditional pattern recognitionhas some problems, such as low precision and a long processing time, when segmenting complex farmland, which cannot meet the conditions of embeddedequipment deployment. Based on these problems, we proposed a novel deeplearning model with high accuracy, small model size and fast running speednamed Residual Unet with Attention mechanism using depthwise convolution(RADw–UNet). This algorithm is based on the UNet symmetric codec model.All the feature extraction modules of the network adopt the residual structure,and the whole network only adopts 8 times the downsampling rate to reducethe redundant parameters. To better extract the semantic information of the spatialand channel dimensions, the depthwise convolutional residual block is designedto be used in feature maps with larger depths to reduce the number of parameterswhile improving the model accuracy. Meanwhile, the multi–level attentionmechanism is introduced in the skip connection to effectively integrate the information of the low–level and high–level feature maps. The experimental resultsshowed that the segmentation performance of RADw–UNet outperformed traditional methods and the UNet algorithm. The algorithm achieved an mIoU of94.9%, the number of trainable parameters was only approximately 0.26 M,and the running time for a single picture was less than 0.03 s.  相似文献   

10.
    
Several researchers are trying to develop different computer-aided diagnosis system for breast cancer employing machine learning (ML) methods. The inputs to these ML algorithms are labeled histopathological images which have complex visual patterns. So, it is difficult to identify quality features for cancer diagnosis. The pre-trained Convolutional Neural Networks (CNNs) have recently emerged as an unsupervised feature extractor. However, a limited investigation has been done for breast cancer recognition using histopathology images with CNN as a feature extractor. This work investigates ten different pre-trained CNNs for extracting the features from breast cancer histopathology images. The breast cancer histopathological images are obtained from publicly available BreakHis dataset. The classification models for the different feature sets, which are obtained using different pre-trained CNNs in consideration, are developed using a linear support vector machine. The proposed method outperforms the other state of art methods for cancer detection, which can be observed from the results obtained.  相似文献   

11.
    
Breast cancer is the second deadliest type of cancer. Early detection of breast cancer can considerably improve the effectiveness of treatment. A significant early sign of breast cancer is the mass. However, separating the cancerous masses from the normal portions of the breast tissue is usually a challenge for radiologists. Recently, because of the availability of high‐accuracy computing, computer‐aided detection systems based on image processing have become capable of accurately diagnosing the various types of cancers. The main purpose of this study is to utilize a powerful image segmentation method for the diagnosis of cancerous regions through mammography, based on a new configuration of the multilayer perceptron (MLP) neural network. The most popular method for minimizing the errors in an MLP neural network is backpropagation. However, this method has certain drawbacks, such as a low convergence speed and becoming trapped at the local minimum. In this study, a new training algorithm based on the whale optimization algorithm is proposed for the MLP network. This algorithm is capable of solving various problems toward the current algorithms for the analyzed systems. The proposed method is validated on the Mammographic Image Analysis Society database, which contains 322 digitized mammography images, and the Digital Database for Screening Mammography, which contains approximately 2500 digitized mammography images. To assess the detection performance of the proposed system, the correct detection rate, percentage of identification with false acceptance, and percentage of identification with false rejection were evaluated and compared using various methods. The results indicate that the proposed method is highly efficient and yields significantly better accuracy compared with other methods.  相似文献   

12.
    
It has been shown that the combination of multimodal magnetic resonance imaging (MRI) images can improve the discrimination of diseased tissue. The fusion of dissimilar imaging data for classification and segmentation purposes, however, is not a trivial task, as there is an inherent difference in information domains, dimensionality, and scales. This work proposed a multiview consensus clustering methodology for the integration of multimodal MR images into a unified segmentation aiming at heterogeneity assessment in tumoral lesions. Using a variety of metrics and distance functions this multiview imaging approach calculated multiple vectorial dissimilarity‐spaces for each MRI modality and it maked use of cluster ensembles to combine a set of unsupervised base segmentations into an unified partition of the voxel‐based data. The methodology was demonstrated with simulated data in application to dynamic contrast enhanced MRI and diffusion tensor imaging MR, for which a manifold learning step was implemented in order to account for the geometric constrains of the high dimensional diffusion information. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 56–67, 2015  相似文献   

13.
    
Medical image segmentation is a preliminary stage of inclusion in identification tools. The correct segmentation of brain Magnetic Resonance Imaging (MRI) images is crucial for an accurate detection of the disease diagnosis. Due to in‐homogeneity, low distinction and noise the segmentation of the brain MRI images is treated as the most challenging task. In this article, we proposed hybrid segmentation, by combining the clustering methods with Hidden Markov Random Field (HMRF) technique. This aims to decrease the computational load and improves the runtime of segmentation method, as MRF methodology is used in post‐processing the images. Its evaluation has performed on real imaging data, resulting in the classification of brain tissues with dice similarity metric. These results indicate the improvement in performance of the proposed method with various noise levels, compared with existing algorithms. In implementation, selection of clustering method provides better results in the segmentation of MRI brain images.  相似文献   

14.
    
Histopathology is considered as the gold standard for diagnosing breast cancer. Traditional machine learning (ML) algorithm provides a promising performance for cancer diagnosis if the training dataset is balanced. Nevertheless, if the training dataset is imbalanced the performance of the ML model is skewed toward the majority class. It may pose a problem for the pathologist because if the benign sample is misclassified as malignant, then a pathologist could make a misjudgment about the diagnosis. A limited investigation has been done in literature for solving the class imbalance problem in computer‐aided diagnosis (CAD) of breast cancer using histopathology. This work proposes a hybrid ML model to solve the class imbalance problem. The proposed model employs pretrained ResNet50 and the kernelized weighted extreme learning machine for CAD of breast cancer using histopathology. The breast cancer histopathological images are obtained from publicly available BreakHis and BisQue datasets. The proposed method achieved a reasonable performance for the classification of the minority as well as the majority class instances. In comparison, the proposed approach outperforms the state‐of‐the‐art ML models implemented in previous studies using the same training‐testing folds of the publicly accessible BreakHis dataset.  相似文献   

15.
    
We propose in this article an approach to optimize the processing time and to improve the quality of brain magnetic resonance images segmentation. Level set method (LSM) was adopted with a periodic reinitialization process to prevent the LS function from being too steep or too flat near the interface. Although it is used to maintain the stability of the interface evolution and gives interesting results, it requires a longer processing time. To overcome this disadvantage and reduce the processing time, we propose a hybridization with a regular Gaussian pyramid, which reduces the resolution of the initial image and prevents the possibility of local minima. To compare the different segmentation algorithms, we used six types of quality measurements: specificity, sensitivity, Dice similarity, the Jaccard index, and the correctly and incorrectly marked pixels. A comparison between the results obtained by LSM, LSM with reinitialization, the approach of Barman et al., An International Journal 1 (2011), particle swarm optimization based on the Chan and Vese model (Mandal et al., Engineering Applications of Artificial Intelligence 35 (2014), 199‐214) and by our hybrid approach reveals a clear efficiency of our hybridization strategy. The processing time was significantly reduced, and the quality of segmentation was improved. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 243–253, 2016  相似文献   

16.
    
Denoizing of magnetic resonance (MR) brain images has been focus of numerous studies in the past. The performance of subsequent stages of image processing, in automated image analysis, is substantially improved by explicit consideration of noise. Nonlocal means (NLM) is a popular denoizing method which exploits usual redundancy present in an image to restore noise free image. It computes restored value of a pixel as weighted average of candidate pixels in a search window. In this article, we propose an improved version of the NLM algorithm which is modified in two ways. First, a robust threshold criterion is introduced, which helps selecting suitable pixels for participation in the restoration process. Second, the search window size is made adaptive using a window adaptation test based on the proposed threshold criterion. The modified NLM algorithm is named as improved adaptive nonlocal means (IANLM). An alternate implementation of IANLM is also proposed which exploits the image smoothness property to yield better denoizing performance. The computational burden is reduced significantly due to proposed modifications. Experiments are performed on simulated and real brain MR images at various noise levels. Results indicate that the proposed algorithm produces not only better denoizing results (quantitatively and qualitatively), but is also computationally more efficient. Moreover, the proposed technique is incorporated in an already proposed segmentation framework to check its validity in the practical scenario of segmentation. Improved segmentation results (quantitative and qualitative) verify the practical usefulness of the proposed algorithm in real world medical applications. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 235–248, 2013  相似文献   

17.
    
In this study, we investigated the changes of quantitative dynamic contrast‐enhanced (DCE)‐MRI parameters using a reference region (RR) model for the breast invasive ductal carcinoma (IDC). We retrospectively analyzed 80 cases with pathologically confirmed IDC using quantitative DCE‐MRI with a RR model. The pharmacokinetic quantitative parameters and prognostic factors of IDC were measured, and the relationship between them was examined. The volume transfer constant (RRKtrans) and rate constant (Kep) were significantly higher in patients with level 3 histological grading compared to patients with level 1 & 2 histological grading (p < 0.05), and patients with negative estrogen receptor (ER‐negative) and/or negative progesterone receptor (PR‐negative) compared to patients with ER‐positive (p < 0.05) and/or PR‐positive (p < 0.05), and Triple‐Negative Breast Cancer (TNBC) type compared to luminal type breast cancer, respectively. Our results demonstrated that high RRKtrans and Kep values were associated with TNBC type. In addition, RRKtrans and Kep parameters can differentiate luminal type and TNBC type breast cancer.  相似文献   

18.
    
The diagnosis' treatment planning, follow-up and prognostication of Gliomas is significantly enhanced on Magnetic Resonance Imaging. In the present research, deep learning-based variant of convolutional neural network methodology is proposed for glioma segmentation where pretrained autoencoder acts as backbone to the 3D-Unet which performs the segmentation task as well as image restoration. Further, Unet accepts input as the combination of three non-native MR images (T2, T1CE, and FLAIR) to extract maximum and superior features for segmenting tumor regions. Further, weighted dice loss employed, focusses on segregating tumor region into three regions of interest namely whole tumor with oedema (WT), enhancing tumor (ET), and tumor core (TC). The optimizer preferred in the proposed methodology is Adam and the learning rate is initially set to 1⁢e−4, progressively reduced by a cosine decay after 50 epochs. The learning parameters are reduced to a larger extent (up to 9.8 M as compared to 27 M). The experimental results show that the proposed model achieved Dice similarity coefficients: 0.77, 0.92, and 0.84; sensitivity: 0.90, 0.95, and 0.89; specificity: 0.97, 0.99, and 0.99; Hausdorff95: 5.74, 4.89, and 6.00, in the three regions including ET, WT, TC. This proposed Glioma segmentation method is efficient for segregation of tumors.  相似文献   

19.
    
Breast cancer remains one of the most significant health threats to women, making precise segmentation of target tumors critical for early clinical intervention and postoperative monitoring. While numerous convolutional neural networks (CNNs) and vision transformers have been developed to segment breast tumors from ultrasound images, both architectures encounter difficulties in effectively modeling long-range dependencies, which are essential for accurate segmentation. Drawing inspiration from the Mamba architecture, we introduce the Vision Mamba-CNN U-Net (VMC-UNet) for breast tumor segmentation. This innovative hybrid framework merges the long-range dependency modeling capabilities of Mamba with the detailed local representation power of CNNs. A key feature of our approach is the implementation of a residual connection method within the U-Net architecture, utilizing the visual state space (VSS) module to extract long-range dependency features from convolutional feature maps effectively. Additionally, to better integrate texture and structural features, we have designed a bilinear multi-scale attention module (BMSA), which significantly enhances the network's ability to capture and utilize intricate feature details across multiple scales. Extensive experiments conducted on three public datasets demonstrate that the proposed VMC-UNet surpasses other state-of-the-art methods in breast tumor segmentation, achieving Dice coefficients of 81.52% for BUSI, 88.00% for BUS, and 88.96% for STU. The source code is accessible at https://github.com/windywindyw/VMC-UNet.  相似文献   

20.
    
Cervical cancer is one of the most common gynecological malignancies, and when detected and treated at an early stage, the cure rate is almost 100%. Colposcopy can be used to diagnose cervical lesions by direct observation of the surface of the cervix using microscopic biopsy and pathological examination, which can improve the diagnosis rate and ensure that patients receive fast and effective treatment. Digital colposcopy and automatic image analysis can reduce the work burden on doctors, improve work efficiency, and help healthcare institutions to make better treatment decisions in underdeveloped areas. The present study used a deep-learning model to classify the images of cervical lesions. Clinicians could determine patient treatment based on the type of cervix, which greatly improved the diagnostic efficiency and accuracy. The present study was divided into two parts. First, convolutional neural networks were used to segment the lesions in the cervical images; and second, a neural network model similar to CapsNet was used to identify and classify the cervical images. Finally, the training set accuracy of our model was 99%, the test set accuracy was 80.1%, it obtained better results than other classification methods, and it realized rapid classification and prediction of mass image data.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号