Search

The variations among shapes, sizes, and locations of tumors are obstacles for accurate automatic segmentation. U-Net is a simplified approach for automatic segmentation. Generally, the convolutional or the dilated convolutional layers are used for brain tumor segmentation. However, existing segmentation methods of the significant dilation rates degrade the final accuracy. Moreover, tuning parameters and imbalance ratio between the different tumor classes are the issues for segmentation. The proposed model, known as Residual-Dilated Dense Atrous-Spatial Pyramid Pooling (RD2A) 3D U-Net, is found adequate to solve these issues. The RD2A is the combination of the residual connections, dilation, and dense ASPP to preserve more contextual information of small sizes of tumors at each level encoder path. The multi-scale contextual information minimizes the ambiguities among the tissues of the white matter (WM) and gray matter (GM) of the infant’s brain MRI. The BRATS 2018, BRATS 2019, and iSeg-2019 datasets are used on different evaluation metrics to validate the RD2A. In the BRATS 2018 validation dataset, the proposed model achieves the average dice scores of 90.88, 84.46, and 78.18 for the whole tumor, the tumor core, and the enhancing tumor, respectively. We also evaluated on iSeg-2019 testing set, where the proposed approach achieves the average dice scores of 79.804, 77.925, and 80.569 for the cerebrospinal fluid (CSF), the gray matter (GM), and the white matter (WM), respectively. Furthermore, the presented work also obtains the mean dice scores of 90.35, 82.34, and 71.93 for the whole tumor, the tumor core, and the enhancing tumor, respectively on the BRATS 2019 validation dataset. Experimentally, it is found that the proposed approach is ideal for exploiting the full contextual information of the 3D brain MRI datasets.

Melanoma is one kind of dangerous cancer that has been increasing rapidly in the world. Initial diagnosis is essential to survival, but often the disease is diagnosed in the fatal stage. The rapid growth of skin cancers raises a huge demand for accurate automatic skin lesion segmentation. While deep learning techniques, i.e., convolutional neural network (CNN), have been widely used for precise segmentation, the existing densely connected network (DenseNet) and residual network (ResNet)–based encoder-decoder architectures used non-biomedical features for skin lesion tasks. The complexity of tuned parameters, small information in the pre-trained features, and the lack of multi-scale information degrade the performance of skin lesion segmentation. To address these issues, we present encoder-decoder–based CNN for skin lesion segmentation, based on the widely used UNet architecture. We exploit the benefit of combining DenseNet and ResNet to improve the performance of skin lesion segmentation. In the encoder path, atrous spatial pyramid pooling (ASPP) is used to generate multi-scale features from different dilation rates. We used dense skip connection to combine the feature maps of both encoder and decoder paths. We evaluate our approach on ISIC 2018 dataset and achieve competitive performance as compared to other state-of-the-art approaches. Compared to the previous UNet approaches, our method gains a high Jaccard index, Dice, accuracy, and sensitivity. We think that this progress is mainly due to the combined architecture of DenseNet, ResNet, ASPP, and dense skip connection that preserve the contextual information in the encoder-decoder paths. We utilized the combined benefits of both recent DenseNet and ResNet architectures. We used ASPP to exploit multi-scale contextual information by adopting multiple dilation rates. We also implemented dense skip connections for better recovery of fine-grained information of target objects. In the future, we believe that this approach will be helpful to other medical image segmentation tasks.

UNet and its variations achieve state-of-the-art performances in medical image segmentation. In end-to-end learning, the training with high-resolution medical images achieves higher accuracy for medical image segmentation. However, the network depth, a massive number of parameters, and low receptive fields are issues in developing deep architecture. Moreover, the lack of multi-scale contextual information degrades the segmentation performance due to the different sizes and shapes of regions of interest. The extraction and aggregation of multi-scale features play an important role in improving medical image segmentation performance. This paper introduces the MH UNet, a multi-scale hierarchical-based architecture for medical image segmentation that addresses the challenges of heterogeneous organ segmentation. To reduce the training parameters and increase efficient gradient flow, we implement densely connected blocks. Residual-Inception blocks are used to obtain full contextual information. A hierarchical block is introduced between the encoder-decoder for acquiring and merging features to extract multi-scale information in the proposed architecture. We implement and validate our proposed architecture on four challenging MICCAI datasets. Our proposed approach achieves state-of-the-art performance on the BraTS 2018, 2019, and 2020 Magnetic Resonance Imaging (MRI) validation datasets. Our approach is 14.05 times lighter than the best method of BraTS 2018. In the meantime, our proposed approach has 2.2 times fewer training parameters than the top 3D approach on the ISLES 2018 Computed Tomographic Perfusion (CTP) testing dataset. MH UNet is available at https://github.com/parvezamu/MHUnet.

Magnetic Resonance Imaging (MRI) is dominant modality for infant brain analysis. Segmenting the whole infant MRI brain into number of tissues such as Cerebrospinal fluid (CSF), White matter (WM), and Gray Matter (GM) are highly desirable in the clinical environment. However, traditional methods tend to be degrading due to low contrast between GM and WM in isointense phase (about 6–8 months of early life). Recently, Convolutional Neural Network (CNN) emerged as a robust intelligent approach to examine medical image. The UNet model is among the preferred CNN models that have been widely used for medical imaging applications and achieved excellent results. The UNet architecture is a combination of convolutional, pooling, and up-sampling layers. Recently, 3D-UNet architecture used to exploit 3D-contextual information of volumetric data in many applications. However, CNN faces challenge to distinguish the similar brain tissues. In this paper, we present a variant of 3D-UNet to extract the volumetric contextual information of medical data. We propose a novel combined architecture of dense connection, residual connection, and inception module. The proposed architecture contains three stages, namely the densely connected stage, a residual inception stage, and an up-sampling stage. Our proposed approach provides state-of-art results in comparison to other existing approaches. This suggested approach achieves dice scores of 0.95, 0.905, and 0.92 in CSF, WM, and GM tissues respectively.

Automatic accurate segmentation of medical images has significant role in computer-aided diagnosis and disease treatment. The segmentation of cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM) tissues plays an important role in infant brain structure for studying early brain development. However, this task is very challenging due to low contrast between GM and WM in isointense phase (approximately 6-8 months of age). In this study, we develop a hyper-densely connected convolutional neural network (CNN) for segmentation of volumetric infant brain. The proposed model provides dense connection between layers to improve the performance of flow information in the network. It also allows the multiscale contextual information by concatenating the feature maps of early, intermediate, and later layers. This architecture employs MR-T1 and T2 as input, which are processed in two separate independent paths, and then their low, intermediate, and high layer features are fused for final segmentation. An important change relative to earlier densely connected networks is the application of direct layer connections from the same and different paths. In this scenario, each modality is processed in an independent path, and dense connections occur not only between layers within the same path, but also between layers in different paths. Adopting such dense connectivity leads to benefits of deep supervision and improved gradient flow. Furthermore, by combining the feature maps of early, intermediate, and late convolutional layers, our architecture injects multiscale information into the final segmentation. This suggested approach is examined in the MICCAI Grand Challenge iSEG and obtains significant advantages over existing approaches in terms of parameter efficiency and segmentation accuracy on 6-month infant brain MRI segmentation.

Deep convolutional neural network (CNN) achieves remarkable performance for medical image analysis. UNet is the primary source in the performance of 3D CNN architectures for medical imaging tasks, including brain tumor segmentation. The skip connection in the UNet architecture concatenates features from both encoder and decoder paths to extract multi-contextual information from image data. The multi-scaled features play an essential role in brain tumor segmentation. However, the limited use of features can degrade the performance of the UNet approach for segmentation. In this paper, we propose a modified UNet architecture for brain tumor segmentation. In the proposed architecture, we used densely connected blocks in both encoder and decoder paths to extract multi-contextual information from the concept of feature reusability. In addition, residual-inception blocks (RIB) are used to extract the local and global information by merging features of different kernel sizes. We validate the proposed architecture on the multi-modal brain tumor segmentation challenge (BRATS) 2020 testing dataset. The dice (DSC) scores of the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) are 89.12%, 84.74%, and 79.12%, respectively.

The brain tumor segmentation task aims to classify tissue into the whole tumor (WT), tumor core (TC) and enhancing tumor (ET) classes using multimodel MRI images. Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time-consuming, and subjective, this task is at the same time very challenging to automatic segmentation methods. Thanks to the powerful learning ability, convolutional neural networks (CNNs), mainly fully convolutional networks, have shown promising brain tumor segmentation. This paper further boosts the performance of brain tumor segmentation by proposing hyperdense inception 3D UNet (HI-Net), which captures multi-scale information by stacking factorization of 3D weighted convolutional layers in the residual inception block. We use hyper dense connections among factorized convolutional layers to extract more contexual information, with the help of features reusability. We use a dice loss function to cope with class imbalances. We validate the proposed architecture on the multi-modal brain tumor segmentation challenges (BRATS) 2020 testing dataset. Preliminary results on the BRATS 2020 testing set show that achieved by our proposed approach, the dice (DSC) scores of ET, WT, and TC are 0.79457, 0.87494, and 0.83712, respectively.

A residual 3D U-Net enables multi-scaling with the concatenation of feature maps from different scales. The connectors between different sub-networks assist in fusion of feature maps. A multi-path architecture enables the fusion of feature maps from different scales. In this paper, the combination of two different architectures is proposed to effectively combine the advantages of both the models to solve the problem of complex brain MRIs. To validate our statement, we build a 3D variation of U-Net with residual, inception, and dense connections. After each upsampling process, the early, middle, and late fusion methods are employed to introduce the information from the multi-path model with the residual 3D U-Net. In the proposed work, we use multiple atrous rates on various paths to solve the problem of small receptive field size. To test our algorithm, a publicly available benchmark dataset is used during training and validation. To handle the over-fitting issue, we used the data augmentation techniques. The multi-label dice loss function reduces the chance of class imbalance problem between healthy and unhealthy tissues. The balance between the severely unbalanced classes during training enabling our algorithm to learn efficient features. Our proposed approach gives competitive scores on different evaluations and provides a meaningful solution to understand the problem of sophisticated brain tumor segmentation.

The accurate automatic segmentation of brain tumors enhances the probability of survival rate. Convolutional Neural Network (CNN) is a popular automatic approach for image evaluations. CNN provides excellent results against classical machine learning algorithms. In this paper, we present a unique approach to incorporate contexual information from multiple brain MRI labels. To address the problems of brain tumor segmentation, we implement combined strategies of residual-dense connections, multiple rates of an atrous convolutional layer on popular 3D U-Net architecture. To train and validate our proposed algorithm, we used BRATS 2019 different datasets. The results are promising on the different evaluation metrics.

The exact position of dead tissue in ischemic stroke lesions plays an important role to cure the life-threatening condition. However, this issue stays difficult caused by variation of ischemic strokes such as shape and location. Fully convolutional neural networks (FCN) have great potential for semantic image segmentation. Recently, UNet based CNN architectures have secured outstanding performance in the application of medical imaging. The primary problem is data imbalanced in the application of such networks which are very common in medical data application such as lesion applications where non-lesion voxels are higher than lesion voxels. Data imbalance generates low recall and high precision on the prediction of trained networks. Biases towards the particular class are not suitable for many medical works where false positives are less than false negatives. A lot of approaches are developed to tackle this issue including balanced sampling, sample re-weighting, and recently focal loss and similarity loss functions. In this paper, we proposed hyper densely connected network along with hybrid loss functions for ischemic stroke lesions segmentation. The densely connected network exploits the contextual information of multi-modalities, and hybrid loss function uses to overcome the data imbalance. We evaluate our performance on ISLES dataset. Our approach performs well as compared to other existing methods.

In the medical domain, 3D convolutional neural network has accomplished excellent results in analysing brain MRI. Inspired by the dense connection, dilation, types of feature fusion methods and availability of essential standards of information presented in multi-modalities and hierarchical knowledge transfers, we present a unique solution for automatically segmenting high-grade glioblastoma, which is a critical type of brain tumor leading to a large number of deaths in the world. The improved survival rates during early detection of this tumor encourage us to provide our contribution using popular machine learning techniques, such as deep learning. In such contribution, the convolutional layer automatically handles the learning feature with a vital concept of receptive field. The deep network allows increased receptive field for learning excellent information. However, this method can be halted by limited memory, especially in building a deep hierarchical architecture. Our model provides a solution towards the path of building a deep, dense architecture by implementing the dilation layer with dense pattern. The receptive field can be increased exponentially and the excessive use of convolution layers can be reduced to reduce parameters and allow the efficient utilisation of GPU memory. Effectively combining local and global contextual information in our model helps in further understanding of different tumor types. We propose to segment the entire tumor hierarchically and use its information to segment its sub-regions, thereby enhancing the tumor and tumor core. The network trained and validated with Brats 2018 data set can achieve dice scores of 0.8480, 0.8574 and 0.8219. Results verify the utilisation of dense connectivity with mixed dilated and conventional convolutional layers. To learn the global contextual information, we initially increase and then decrease the dilation rated with dense connections to minimise the possible loss of information due to the successive dilated rates. Our experimental results verify our innovative work for utilising this type of connectivity in medical image segmentation.

Glioma is one of the most widespread and intense forms of primary brain tumors. Accurate subcortical brain segmentation is essential in the evaluation of gliomas which helps to monitor the growth of gliomas and assists in the assessment of medication effects. Manual segmentation is needed a lot of human resources on Magnetic Resonance Imaging (MRI) data. Deep learning methods have become a powerful tool to learn features automatically in medical imaging applications including brain tissue segmentation, liver segmentation, and brain tumor segmentation. The shape of gliomas, structure, and location are different among individual patients, and it is a challenge to developing a model. In this paper, 3D hyper-dense Convolutional Neural Network(Cnn)is developed to segment tumors, in which it captures the global and local contextual information from two scales of global and local patches along with the two scales of receptive field. Densely connected blocks are used to exploit the benefit of a CNN to boost the model segmentation performance in Enhancing Tumor (ET), Non-Enhancing Tumor (NET), and Peritumoral Edema (PE). This dense architecture adopts 3D Fully Convolutional Network (FCN) architecture that is used for end-to-end volumetric prediction. The dense connectivity can offer a chance of deep supervision and improve gradient flow information in the learning process. The network is trained hierarchically based on global and local patches. In this scenario, the both patches are processed in their separate path, and dense connections happen not only between same path layers but also between different path layers. Our approach is validated on the BraTS 2018 dataset with the dice-score of 0.87, 0.81 and 0.84 for the complete tumor, enhancing tumor, and tumor core respectively. These outcomes are very close to the reported state-of-the-art results, and our approach is preferable to present 3D-based approaches when it comes to compactness, time and parameter efficiency on MRI brain tumor segmentation.

In this paper we propose to use fuzzy logic in detecting emotional content from text. Fuzzy logic was developed to deal with concepts that do not have well-defined, sharp boundaries, which theoretically is ideal for emotion as no well-defined boundaries are defined for emotion categories (e.g., happiness, sadness, surprise, fear, disgust, and anger).The transition from one physiological state of emotion to another is also gradual and could easily be modeled by fuzzy logic approach.

Data mining is gaining popularity in disparate research fields due to its boundless applications and approaches to mine the data in an appropriate manner. Owing to the changes, the current world acquiring, it is one of the optimal approach for approximating the nearby future consequences. Along with advanced researches in healthcare monstrous of data are available, but the main difficulty is how to cultivate the existing information into a useful practices. To unfold this hurdle the concept of data mining is the best suited. Data mining have a great potential to enable healthcare systems to use data more efficiently and effectively. Hence, it improves care and reduces costs. This paper reviews various Data Mining techniques such as classification, clustering, association, regression in health domain. It also highlights applications, challenges and future work of Data Mining in healthcare.