Model For Medical Image Segmentation Research Articles

A Multi-Scale Context Aware Attention Model for Medical Image Segmentation.

Medical image segmentation is critical for efficient diagnosis of diseases and treatment planning. In recent years, convolutional neural networks (CNN)-based methods, particularly U-Net and its variants, have achieved remarkable results on medical image segmentation tasks. However, they do not always work consistently on images with complex structures and large variations in regions of interest (ROI). This could be due to the fixed geometric structure of the receptive fields used for feature extraction and repetitive down-sampling operations that lead to information loss. To overcome these problems, the standard U-Net architecture is modified in this work by replacing the convolution block with a dilated convolution block to extract multi-scale context features with varying sizes of receptive fields, and adding a dilated inception block between the encoder and decoder paths to alleviate the problem of information recession and the semantic gap between features. Furthermore, the input of each dilated convolution block is added to the output through a squeeze and excitation unit, which alleviates the vanishing gradient problem and improves overall feature representation by re-weighting the channel-wise feature responses. The original inception block is modified by reducing the size of the spatial filter and introducing dilated convolution to obtain a larger receptive field. The proposed network was validated on three challenging medical image segmentation tasks with varying size ROIs: lung segmentation on chest X-ray (CXR) images, skin lesion segmentation on dermoscopy images and nucleus segmentation on microscopy cell images. Improved performance compared to state-of-the-art techniques demonstrates the effectiveness and generalisability of the proposed Dilated Convolution and Inception blocks-based U-Net (DCI-UNet).

Design of Machine Learning based Evolutionary Model for Medical Image Segmentation

Design of Machine Learning based Evolutionary Model for Medical Image Segmentation

Improving Calibration and Out-of-Distribution Detection in Deep Models for Medical Image Segmentation.

Convolutional Neural Networks (CNNs) have proved to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical image datasets is still challenging, with many studies promoting techniques such as transfer learning. Moreover, these models are infamous for producing over-confident predictions and for failing silently when presented with out-of-distribution (OOD) test data. In this paper, for improving prediction calibration we advocate for multi-task learning, i.e., training a single model on several different datasets, spanning different organs of interest and different imaging modalities. We show that multi-task learning can significantly improve model confidence calibration. For OOD detection, we propose a novel method based on spectral analysis of CNN feature maps. We show that different datasets, representing different imaging modalities and/or different organs of interest, have distinct spectral signatures, which can be used to identify whether or not a test image is similar to the images used for training. We show that our proposed method is more accurate than several competing methods, including methods based on prediction uncertainty and image classification.

FSOU-Net: Feature supplement and optimization U-Net for 2D medical image segmentation.

The results of medical image segmentation can provide reliable evidence for clinical diagnosis and treatment. The U-Net proposed previously has been widely used in the field of medical image segmentation. Its encoder extracts semantic features of different scales at different stages, but does not carry out special processing for semantic features of each scale. To improve the feature expression ability and segmentation performance of U-Net, we proposed a feature supplement and optimization U-Net (FSOU-Net). First, we put forward the view that semantic features of different scales should be treated differently. Based on this view, we classify the semantic features automatically extracted by encoders into two categories: shallow semantic features and deep semantic features. Then, we propose the shallow feature supplement module (SFSM), which obtains fine-grained semantic features through up-sampling to supplement the shallow semantic information. Finally, we propose the deep feature optimization module (DFOM), which uses the expansive convolution of different receptive fields to obtain multi-scale features and then performs multi-scale feature fusion to optimize the deep semantic information. The proposed model is experimented on three medical image segmentation public datasets, and the experimental results prove the correctness of the proposed idea. The segmentation performance of the model is higher than the advanced models for medical image segmentation. Compared with baseline network U-NET, the main index of Dice index is 0.75% higher on the RITE dataset, 2.3% higher on the Kvasir-SEG dataset, and 0.24% higher on the GlaS dataset. The proposed method can greatly improve the feature representation ability and segmentation performance of the model.

Dual-Branch-UNet: A Dual-Branch Convolutional Neural Network for Medical Image Segmentation

In intelligent perception and diagnosis of medical equipment, the visual and morphological changes in retinal vessels are closely related to the severity of cardiovascular diseases (e.g., diabetes and hypertension). Intelligent auxiliary diagnosis of these diseases depends on the accuracy of the retinal vascular segmentation results. To address this challenge, we design a Dual-Branch-UNet framework, which comprises a Dual-Branch encoder structure for feature extraction based on the traditional U-Net model for medical image segmentation. To be more explicit, we utilize a novel parallel encoder made up of various convolutional modules to enhance the encoder portion of the original U-Net. Then, image features are combined at each layer to produce richer semantic data and the model’s capacity is adjusted to various input images. Meanwhile, in the lower sampling section, we give up pooling and conduct the lower sampling by convolution operation to control step size for information fusion. We also employ an attention module in the decoder stage to filter the image noises so as to lessen the response of irrelevant features. Experiments are verified and compared on the DRIVE and ARIA datasets for retinal vessels segmentation. The proposed Dual-Branch-UNet has proved to be superior to other five typical state-of-the-art methods.

An efficient deep equilibrium model for medical image segmentation

In this paper, we propose an effective method that takes the advantages of classical methods and deep learning technology for medical image segmentation through modeling the neural network as a fixed point iteration seeking for system equilibrium by adding a feedback loop. In particular, the nuclear segmentation of medical image is used as an example to demonstrate the proposed method where it can successfully complete the challenge of segmenting nuclei from cells in different histopathological images. Specifically, the nuclei segmentation is formulated as a dynamic process to search for the system equilibrium. Starting from an initial segmentation generated either by a classic algorithm or pre-trained deep learning model, a sequence of segmentation output is created and combined with the original image to dynamically drive the segmentation towards the expected value. This dynamical extension to neural networks requires little extra change on the backbone deep neural network while it significantly increased model accuracy, generalizability, and stability as demonstrated by intensive experimental results from pathological images of different tissue types across different open datasets.

Thrifty Neural Architecture Search for Medical Image Segmentation (Student Abstract)

Convolutional neural network (CNN) based image segmentation has been widely used in analyzing medical images and benefited many real-world disease diagnosis applications. However, existing advanced CNN-based medical image segmentation models usually contain numerous parameters that require massive computation and memory, limiting the applicability of these models in the data-constrained or hardware-constrained environments. By leveraging the recently proposed neural architecture search (NAS), this paper presents a novel approach, dubbed Thrifty NAS, to design computation and memory-efficient models for medical image segmentation automatically. The searched models by Thrifty NAS are with much fewer parameters while retaining competitive performance. More specifically, we design a micro level space for cell structure search and a macro level cell path for better network structure modeling. Extensive experimental results in different medical image datasets verify the effectiveness of the proposed method with competitive segmentation performance, especially with minuscule neural architecture model size, i.e., 0.61M that is superior to U-Net (7.76 M) and UNet++ (9.04 M).

SEGMENTATION OF MEDICAL IMAGES BY CONVOLUTIONAL NEURAL NETWORKS

Our study briefly discusses the architectures of convolutional neural networks (CNN), their advantages and disadvantages. The features of the architecture of the convolutional neural network U-net are described. An analysis of the CNN U-net was carried out, based on the analysis, a rationale was given for choosing the CNN U-net as the main architecture for using and building subsequent created and analyzed models of cert neural networks to solve the problem of segmentation of medical images. The analysis of architectures of convolutional neural networks, which can be used as convolutional layers in CNN U-net, has been carried out. Based on the analysis, three architectures of convolutional neural networks were selected and described suitable for use as convolutional layers in CNN U-net. Using CNN U-net and three selected convolutional neural networks (“resnet34”, “inceptionv3” and “vgg16”), three neural network models for medical image segmentation were created. The training and testing of the created models of neural networks was carried out. Based on the results of training and testing, an analysis of the obtained indicators was carried out. Experiments were carried out with each of the three constructed models (segmentation of images from the validation set was performed and segmented images were presented). Based on the testing indicators and empirical data obtained from the results of the experiments, the most suitable neural network model created for solving the problem of medical image segmentation was determined. The algorithm for segmentation of medical images has been improved. An algorithm is described that uses the predictions of all created models of neural networks, which demonstrated a more accurate result than each of the considered models separately.

FLeak-Seg: Automated Fundus Fluorescein Leakage Segmentation via Cross-Modal Attention Learning

Despite the recent success of deep learning-based models for medical image segmentation and the importance of automated fluorescein leakage segmentation for the diagnosis of advanced diabetic retinopathy, segmentation of fluorescein leakage has been neglected because 1) there are no publicly available databases with sufficient annotations to train segmentation models and 2) supervised models struggle to accurately distinguish between different types of fluorescein leakage and localize leakages at different imaging angles. To tackle these challenges, this work presents FLeak-Seg, a cross-modal dual attention learning method to jointly capture visual and language information, for end-to-end fluorescein leakage segmentation in fundus fluorescein angiography. Specifically, both image and text data are used as input, where visual and linguistic features are captured by a cross-modal attention learning module to compensate for the lack of annotations. A keyword classification module is also employed to identify meaningful expressions related to the type and location of fluorescein leakages to further facilitate the segmentation. Experimental results obtained in an in-house fundus fluorescein angiography database demonstrate the superiority of our method. We show how erroneous segmentation masks can be improved using FLeak-Seg, its advantages in the context of limited samples, and its behavior on segmenting different types of fluorescein leakages.

U-Net-ASPP: U-Net based on atrous spatial pyramid pooling model for medical image segmentation in COVID-19

U-Net-ASPP: U-Net based on atrous spatial pyramid pooling model for medical image segmentation in COVID-19

A porosity model for medical image segmentation of vessels.

A physics‐based medical image segmentation method is developed. Specifically, the image greyscale intensity is used to infer the voxel partial volumes and subsequently formulate a porous medium analogy. The method involves first translating the medical image volumetric data into a three‐dimensional computational domain of a porous material. A velocity field is then obtained from numerical simulations of incompressible fluid flow in the porous material, and finally a velocity iso‐surface provides the surface description of the target object. The approach is tested on CT images of eight patient‐specific cases, where cerebral aneurysms, nasal cavities (NC), and an aortic arch (AA) are the objects of interest. In the aneurysm cases, the results are compared against constant greyscale thresholding and manual segmentation. The manual segmentations of the aneurysms are validated by a clinical practitioner. Only a qualitative comparison is available for the NC, and the AA geometries. The results show that the proposed method is effective and capable of extracting the target object in a noisy domain. A sensitivity study is carried out to verify the method's performance with respect to modelling or user choices. The segmentation by the proposed method is also evaluated by performing computational fluid dynamics simulation, including a near‐wall flow analysis, to ensure that the segmented geometry and the resulting computed solution are representative and meaningful.

Shape and boundary-aware multi-branch model for semi-supervised medical image segmentation

Supervised learning-based medical image segmentation solutions usually require sufficient labeled training data. Insufficient available labeled training data often leads to the limitations of model performances, such as over-fitting, low accuracy, and poor generalization ability. However, this dilemma may worsen in the field of medical image analysis. Medical image annotation is usually labor-intensive and professional work. In this work, we propose a novel shape and boundary-aware deep learning model for medical image segmentation based on semi-supervised learning. The model makes good use of labeled data and also enables unlabeled data to be well applied by using task consistency loss. Firstly, we adopt V-Net for Pixel-wise Segmentation Map (PSM) prediction and Signed Distance Map (SDM) regression. In addition, we multiply multi-scale features, extracted by Pyramid Pooling Module (PPM) from input X, with 2 − |SDM| to enhance the features around the boundary of the segmented target, and then feed them into the Feature Fusion Module (FFM) for fine segmentation. Besides boundary loss, the high-level semantics implied in SDM facilitate the accurate segmentation of boundary regions. Finally, we get the ultimate result by fusing coarse and boundary-enhanced features. Last but not least, to mine unlabeled training data, we impose consistency constraints on the three core outputs of the model, namely PSM1, SDM, and PSM3. Through extensive experiments over three representative but challenging medical image datasets (LA2018, BraTS2019, and ISIC2018) and comparisons with the existing representative methods, we validate the practicability and superiority of our model.

Efficient active contour model for medical image segmentation and correction based on edge and region information

The inhomogeneity of images is always a challenge in the field of image segmentation. Aiming at the problem of segmentation and correction of inhomogeneous images, this paper proposes an improved active contour model based on previous models. Our model inherits the advantage of that, which is robust to images with irregular intensity distribution. Meanwhile, our model can segment and correct images with inhomogeneous intensity at the same time, performing better when segmenting images with inhomogeneous intensity. Moreover, it saves a lot of time because our model has fewer parameters to be tuned. We extend our two-phase model to the multi-phase model and the vector-valued model and prove the convergence of our algorithm. Through a lot of qualitative analysis and quantitative comparison, we find that our model can accurately segment medical images and get homogeneous corrected images. In addition, compared to other models, our model has higher accuracy with fewer iterations.

BrainSec: Automated Brain Tissue Segmentation Pipeline for Scalable Neuropathological Analysis.

As neurodegenerative disease pathological hallmarks have been reported in both grey matter (GM) and white matter (WM) with different density distributions, automating the segmentation process of GM/WM would be extremely advantageous for aiding in neuropathologic deep phenotyping. Standard segmentation methods typically involve manual annotations, where a trained researcher traces the delineation of GM/WM in ultra-high-resolution Whole Slide Images (WSIs). This method can be time-consuming and subjective, preventing a scalable analysis on pathology images. This paper proposes an automated segmentation pipeline (BrainSec) combining a Convolutional Neural Network (CNN) module for segmenting GM/WM regions and a post-processing module to remove artifacts/residues of tissues. The final output generates XML annotations that can be visualized via Aperio ImageScope. First, we investigate two baseline models for medical image segmentation: FCN, and U-Net. Then we propose a patch-based approach, BrainSec, to classify the GM/WM/background regions. We demonstrate BrainSec is robust and has reliable performance by testing it on over 180 WSIs that incorporate numerous unique cases as well as distinct neuroanatomic brain regions. We also apply gradient-weighted class activation mapping (Grad-CAM) to interpret the segmentation masks and provide relevant explanations and insights. In addition, we have integrated BrainSec with an existing Amyloid-β pathology classification model into a unified framework (without incurring significant computation complexity) to identify pathologies, visualize their distributions, and quantify each type of pathologies in segmented GM/WM regions, respectively.

Connected-UNets: a deep learning architecture for breast mass segmentation

Breast cancer analysis implies that radiologists inspect mammograms to detect suspicious breast lesions and identify mass tumors. Artificial intelligence techniques offer automatic systems for breast mass segmentation to assist radiologists in their diagnosis. With the rapid development of deep learning and its application to medical imaging challenges, UNet and its variations is one of the state-of-the-art models for medical image segmentation that showed promising performance on mammography. In this paper, we propose an architecture, called Connected-UNets, which connects two UNets using additional modified skip connections. We integrate Atrous Spatial Pyramid Pooling (ASPP) in the two standard UNets to emphasize the contextual information within the encoder–decoder network architecture. We also apply the proposed architecture on the Attention UNet (AUNet) and the Residual UNet (ResUNet). We evaluated the proposed architectures on two publically available datasets, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, and additionally on a private dataset. Experiments were also conducted using additional synthetic data using the cycle-consistent Generative Adversarial Network (CycleGAN) model between two unpaired datasets to augment and enhance the images. Qualitative and quantitative results show that the proposed architecture can achieve better automatic mass segmentation with a high Dice score of 89.52%, 95.28%, and 95.88% and Intersection over Union (IoU) score of 80.02%, 91.03%, and 92.27%, respectively, on CBIS-DDSM, INbreast, and the private dataset.

3D spatial priors for semi-supervised organ segmentation with deep convolutional neural networks

Fully Convolutional neural Networks (FCNs) are the most popular models for medical image segmentation. However, they do not explicitly integrate spatial organ positions, which can be crucial for proper labeling in challenging contexts. In this work, we propose a method that combines a model representing prior probabilities of an organ position in 3D with visual FCN predictions by means of a generalized prior-driven prediction function. The prior is also used in a self-labeling process to handle low-data regimes, in order to improve the quality of the pseudo-label selection. Experiments carried out on CT scans from the public TCIA pancreas segmentation dataset reveal that the resulting STIPPLE model can significantly increase performances compared to the FCN baseline, especially with few training images. We also show that STIPPLE outperforms state-of-the-art semi-supervised segmentation methods by leveraging the spatial prior information. STIPPLE provides a segmentation method effective with few labeled examples, which is crucial in the medical domain. It offers an intuitive way to incorporate absolute position information by mimicking expert annotators.

Skin Cancer Segmentation Using U-Net

Abstract: Melanoma is one of the most prevalent and severe types of skin cancer, accounting for 75 percent of all skin cancer deaths. Early detection of melanoma can greatly improve the chances of survival. Melanoma segmentation is a critical and necessary stage in the correct detection of melanoma. For high-resolution dermoscopy images, many previous works based on standard segmentation algorithms and deep learning methods have been offered. Automatic melanoma segmentation remains a difficult task for present algorithms due to the inherent visual complexity and ambiguity among different skin states. Among these methods, the deep learning methods have obtained more attention recently due to its high performance by training an endto-end framework, which needs no human interaction. U-net is a very popular deep learning model for medical image segmentation We present an efficient skin lesion segmentation based on an improved U-net model in this research. Experiments using the 2017 ISIC Challenge melanoma dataset reveal that the suggested technique can achieve state-of-the-art performance on the skin lesion segmentation problem. Keywords: Melanoma, Convolution neural Network, U-net, Relu, Binary_threshold, Model File

Dynamic-weighting hierarchical segmentation network for medical images

Automatic medical image segmentation plays a crucial role in many medical image analysis applications, such as disease diagnosis and prognosis. Despite the extensive progress of existing deep learning based models for medical image segmentation, they focus on extracting accurate features by designing novel network structures and solely utilize fully connected (FC) layer for pixel-level classification. Considering the insufficient capability of FC layer to encode the extracted diverse feature representations, we propose a Hierarchical Segmentation (HieraSeg) Network for medical image segmentation and devise a Hierarchical Fully Connected (HFC) layer. Specifically, it consists of three classifiers and decouples each category into several subcategories by introducing multiple weight vectors to denote the diverse characteristics in each category. A subcategory-level and a category-level learning schemes are then designed to explicitly enforce the discrepant subcategories and automatically capture the most representative characteristics. Hence, the HFC layer can fit the variant characteristics so as to derive an accurate decision boundary. To enhance the robustness of HieraSeg Network with the variability of lesions, we further propose a Dynamic-Weighting HieraSeg (DW-HieraSeg) Network, which introduces an Image-level Weight Net (IWN) and a Pixel-level Weight Net (PWN) to learn data-driven curriculum. Through progressively incorporating informative images and pixels in an easy-to-hard manner, DW-HieraSeg Network is able to eliminate local optimums and accelerate the training process. Additionally, a class balanced loss is proposed to constrain the PWN for preventing the overfitting problem in minority category. Comprehensive experiments on three benchmark datasets, EndoScene, ISIC and Decathlon, show our newly proposed HieraSeg and DW-HieraSeg Networks achieve state-of-the-art performance, which clearly demonstrates the effectiveness of the proposed approaches for medical image segmentation.

Multichannel convolutional neural network-based fuzzy active contour model for medical image segmentation

Multichannel convolutional neural network-based fuzzy active contour model for medical image segmentation

AEDCN-Net: Accurate and Efficient Deep Convolutional Neural Network Model for Medical Image Segmentation

Image segmentation was significantly enhanced after the emergence of deep learning (DL) methods. In particular, deep convolutional neural networks (DCNNs) have assisted DL-based segmentation models to achieve state-of-the-art performance in fields critical to human beings, such as medicine. However, the existing state-of-the-art methods often use computationally expensive operations to achieve high accuracy and lightweight networks often lack a precise medical image segmentation. Therefore, this study proposes an accurate and efficient DCNN model (AEDCN-Net) based on an elaborate preprocessing step and a resourceful model architecture. The AEDCN-Net exploits bottleneck, atrous, and asymmetric convolution-based residual skip connections in the encoding path that reduce the number of trainable parameters and floating point operations (FLOPs) to learn feature representations with a larger receptive field. The decoding path employs the nearest-neighbor based upsampling method instead of a computationally resourceful transpose convolution operation that requires an extensive number of trainable parameters. The proposed method attains a superior performance in both computational time and accuracy compared to the existing state-of-the-art methods. The results of benchmarking using four real-life medical image datasets specifically illustrate that the AEDCN-Net has a faster convergence compared to the computationally expensive state-of-the-art models while using significantly fewer trainable parameters and FLOPs that result in a considerable speed-up during inference. Moreover, the proposed method obtains a better accuracy in several evaluation metrics compared with the existing lightweight and efficient methods.