A coronary artery CTA segmentation approach based on deep learning

Presence of plaque and coronary artery stenosis are the main causes of coronary heart disease. Detection of plaque and coronary artery segmentation have become the first choice in detecting coronary artery disease. The purpose of this study is to investigate a new method for plaque detection and automatic segmentation and diagnosis of coronary arteries and to test its feasibility of applying to clinical medical image diagnosis. A multi-model fusion coronary CT angiography (CTA) vessel segmentation method is proposed based on deep learning. The method includes three network layer models namely, an original 3-dimensional full convolutional network (3D FCN) and two networks that embed the attention gating (AG) model in the original 3D FCN. Then, the prediction results of the three networks are merged by using the majority voting algorithm and thus the final prediction result of the networks is obtained. In the post-processing stage, the level set function is used to further iteratively optimize the results of network fusion prediction. The JI (Jaccard index) and DSC (Dice similarity coefficient) scores are calculated to evaluate accuracy of blood vessel segmentations. Applying to a CTA dataset of 20 patients, accuracy of coronary blood vessel segmentation using FCN, FCN-AG1, FCN-AG2 network and the fusion method are tested. The average values of JI and DSC of using the first three networks are (0.7962, 0.8843), (0.8154, 0.8966) and (0.8119, 0.8936), respectively. When using new fusion method, average JI and DSC of segmentation results increase to (0.8214, 0.9005), which are better than the best result of using FCN, FCN-AG1 and FCN-AG2 model independently.

Medical Image Segmentation by Fish Schooling Algorithm and Neural Network

Medical image diagnosis by machine decrease the doctor load and increases the efficiency of treatment as well. Many of diagnosis process depends on chemical data and some are depend on digital images. This work focus on brain tumor medical image diagnosis by segmenting the tumor region in the image. For tumor detection neural network was trained by the model. Selected features extract from the image by fish schooling genetic algorithm for training of neural network It was obtained that fish schooling based genetic feature selection has increases the detection accuracy of trained model. Experiment was done on real dataset and results compared with existing techniques of tumor detection from MRI images.

Interpretable Diagnosis for Whole-Slide Melanoma Histology Images Using Convolutional Neural Network

At present, deep learning-based medical image diagnosis had achieved high performance in several diseases. However, the black-box nature of the convolutional neural network (CNN) limits their role in diagnosis. In this study, a novel interpretable diagnosis pipeline using the CNN model was proposed. Furthermore, a sizeable melanoma database that contains 841 digital whole-slide images (WSIs) was built to train and evaluate the model. The model achieved strong melanoma classification ability (0.962 areas under the receiver operating characteristic, 0.887 sensitivity, and 0.925 specificity). Moreover, the proposed model outperformed the existing schemes in terms of accuracy that is 20 pathologists (0.933 vs 0.732 accuracy). Finally, the gradient-weighted class activation mapping (Grad-CAM) method was used to show the inner logic of the proposed model and its feasibility to improve diagnosis process in healthcare. The mechanism of feature heat maps which is visualized through a saliency mapping has demonstrated that features learned or extracted by the proposed model are compatible with the accepted pathological features. Conclusively, the proposed model provides a rapid and accurate diagnosis by locating the distinctive features of melanoma to build doctors’ trust in the CNNs’ diagnosis results.

Performance Analysis on the Effect of Noise in Inverse Surface Adaptive Thresholding (ISAT)

Thresholding is one of the powerful methods in segmentation phase. Numerous methods were proposed to segment the foreground from the background but there is limited number of studies that analyse the effect of noise since the present of noise will affect the performance of the thresholding method. In this paper, the main idea is to analyse the effect of noise in Inverse Surface Adaptive Thresholding (ISAT) method. ISAT method is known as an excellent method to segment the image with the present of noise. The result of this analysis can be a guideline to researcher when implementing ISAT method especially in medical image diagnosis. Initially, several images with different noise variations were prepared and underwent ISAT method. In ISAT method, several image processing methods were incorporated namely edge detection, Otsu thresholding and inverse surface construction. The resulting images were evaluated using Misclassification Error (ME) to evaluate the performance of the segmentation result. Based on the obtained results, ISAT performance is consistent although the noise percentage increases from 5% to 25%.

Review of Breast Cancer Pathologigcal Image Processing

Breast cancer is one of the most common malignancies. Pathological image processing of breast has become an important means for early diagnosis of breast cancer. Using medical image processing to assist doctors to detect potential breast cancer as early as possible has always been a hot topic in the field of medical image diagnosis. In this paper, a breast cancer recognition method based on image processing is systematically expounded from four aspects: breast cancer detection, image segmentation, image registration, and image fusion. The achievements and application scope of supervised learning, unsupervised learning, deep learning, CNN, and so on in breast cancer examination are expounded. The prospect of unsupervised learning and transfer learning for breast cancer diagnosis is prospected. Finally, the privacy protection of breast cancer patients is put forward.

On the use of CNNs with patterned stride for medical image analysis

The use of deep learning techniques for early and accurate medical image diagnosis has grown significantly in recent years, with some encouraging results across many medical specialties, pathologies, and image types. One of the most popular deep neural network architectures is the convolutional neural network (CNN), widely used for medical image classification and segmentation, among other tasks. One of the configuration parameters of a CNN is called stride and it regulates how sparsely the image is sampled during the convolutional process. This paper explores the idea of applying a patterned stride strategy: pixels closer to the center are processed with a smaller stride concentrating the amount of information sampled, and pixels away from the center are processed with larger strides consequently making those areas to be sampled more sparsely. We apply this method to different medical image classification tasks and demonstrate experimentally how the proposed patterned stride mechanism outperforms a baseline solution with the same computational cost (processing and memory). We also discuss the relevance and potential future extensions of the proposed method.

Denoising of magnetic resonance images using discriminative learning-based deep convolutional neural network

BACKGROUND: The noise in magnetic resonance (MR) images causes severe issues for medical diagnosis purposes. OBJECTIVE: In this paper, we propose a discriminative learning based convolutional neural network denoiser to denoise the MR image data contaminated with noise. METHODS: The proposed method incorporates the use of depthwise separable convolution along with local response normalization with modified hyperparameters and internal skip connections to denoise the contaminated MR images. Moreover, the addition of parametric RELU instead of normal conventional RELU in our proposed architecture gives more stable and fine results. The denoised images were further segmented to test the appropriateness of the results. The network is trained on one dataset and tested on other dataset produces remarkably good results. RESULTS: Our proposed network was used to denoise the images of different noise levels, and it yields better performance as compared with various networks. The SSIM and PSNR showed an average improvement of (7.2 ± 0.002) % and (8.5 ± 0.25) % respectively when tested on different datasets without retaining the network. An improvement of 5% and 6% was achieved in the values of mean intersection over union (mIoU) and BF score when the denoised images were segmented for testing the relevancy in biomedical imaging applications. The statistical test suggests that the obtained results are statistically significant as p< 0.05. CONCLUSION: The denoised images obtained are more clinically suitable for medical image diagnosis purposes, as depicted by the evaluation parameters. Further, external clinical validation was performed by an experienced radiologist for testing the validation of the resulting images.

MLAF-CapsNet: Multi-lane atrous feature fusion capsule network with contrast limited adaptive histogram equalization for brain tumor classification from MRI images

Convolutional neural networks (CNNs) for automatic classification and medical image diagnosis have recently displayed a remarkable performance. However, the CNNs fail to recognize original images rotated and oriented differently, limiting their performance. This paper presents a new capsule network (CapsNet) based framework known as the multi-lane atrous feature fusion capsule network (MLAF-CapsNet) for brain tumor type classification. The MLAF-CapsNet consists of atrous and CLAHE, where the atrous increases receptive fields and maintains spatial representation, whereas the CLAHE is used as a base layer that uses an improved adaptive histogram equalization (AHE) to enhance the input images. The proposed method is evaluated using whole-brain tumor and segmented tumor datasets. The efficiency performance of the two datasets is explored and compared. The experimental results of the MLAF-CapsNet show better accuracies (93.40% and 96.60%) and precisions (94.21% and 96.55%) in feature extraction based on the original images from the two datasets than the traditional CapsNet (78.93% and 97.30%). Based on the two datasets’ augmentation, the proposed method achieved the best accuracy (98.48% and 98.82%) and precisions (98.88% and 98.58%) in extracting features compared to the traditional CapsNet. Our results indicate that the proposed method can successfully improve brain tumor classification problems and support radiologists in medical diagnostics.

Using Transfer Learning and Hierarchical Classifier to Diagnose Melanoma From Dermoscopic Images

The deadliest form of skin cancer is melanoma, and if detected in time, it is curable. Detection of melanoma using biopsy is a painful and time-consuming task. Alternate means are being used by medical experts to diagnose melanoma by extracting features from skin lesion images. Medical image diagnosis requires intelligent systems. Many intelligent systems based on image processing and machine learning have been proposed by researchers in the past to detect different kinds of diseases that are successfully used by healthcare organisations worldwide. Intelligent systems to detect melanoma from skin lesion images are also evolving with the aim of improving the accuracy of melanoma detection. Feature extraction plays a critical role. In this paper, a model is proposed in which features are extracted using convolutional neural network (CNN) with transfer learning and a hierarchical classifier consisting of random forest (RF), k-nearest neighbor (KNN), and adaboost is used to detect melanoma using the extracted features. Experimental results show the effectiveness of the proposed model.