CT Image Segmentation Research Articles

A Hybrid Optimization Approach for Pulmonary Nodules Segmentation and Classification using Deep CNN

Lung Cancer, due to a lower survival rate, is a deadly disease as compared to other cancers. The prior determination of the lung cancer tends to increase the survival rate. Though there are numerous lung cancer detection techniques, they are all insufficient to detect accurate cancer due to variations in the intensity of the CT scan image. For more accuracy in segmentation of CT images, the proposed Elephant-Based Bald Eagle Optimization (EBEO) algorithm is used. This proposed research concentrates on developing a lung nodule detection technique based on Deep learning. To obtain an effective result, the segmentation process will be carried out using the proposed algorithm. Further, the proposed algorithm will be utilized to tune the hyper parameter of the deep learning classifier to increase detection accuracy. It is expected that the proposed state-of-art method will exceed all conventional methods in terms of detection accuracy due to the effectiveness of the proposed algorithm. This survey will be helpful for the healthcare research communities with sufficient knowledge to understand the concepts of the EBEO algorithm and the Deep Convolutional Neural Network for improving the overall human healthcare system.

Research on Lightweight Network Segmentation of Lung Parenchyma CT Image Based on FPGA Platform

Image segmentation algorithms for medical embedded vision devices usually require a light and low latency model. In this study, a novel lightweight DepthWise U-shape network (DWU-net) is proposed to address this issue, which implements the task of lung parenchyma image segmentation. In the contracting path and expanding path of segmentation network, we introduce a separable convolution unit to replace standard convolution for image feature extraction, which can learn the unique features of each layer of the image from multiple perspectives, and has more advantages in feature expression. Our algorithm has better flexibility, comparing to the original model, the model parameters’ number has been greatly reduced and the time efficiency is fully improved. The proposed architecture achieves good performance in FPGA implementation.

Comparison of biomechanical effects of polyetheretherketone (PEEK) rods and titanium rods in lumbar long-segment instrumentation: a finite element study.

Polyetheretherketone (PEEK) lumbar fusion rods have been successfully used in short-segment posterior instrumentation to prevent adjacent segment degeneration. However, limited studies have reported their application in lumbar long-segment instrumentation. This study aimed to compare the biomechanical performances of PEEK rods and titanium rods in lumbar long-segment instrumentation using finite element (FE) models, with the expectation of providing clinical guidance. A lumbar FE model (A) and four lumbar fixation FE models (BI, CI, BII, CII) of the L1-S1 vertebral body were developed using CT image segmentation (A: intact model; BI: intact model with L2-S1 PEEK rod internal fixation; CI: intact model with L2-S1 titanium rod internal fixation; BII: intact model with L3-S1 PEEK rod internal fixation; CII: intact model with L3-S1 titanium rod internal fixation). A 150-N preload was applied to the top surface of L1, similar to the intact model. The stresses on the lumbar intervertebral disc, facet joint, pedicle screws, and rods were calculated to evaluate the biomechanical effect of the different fixation procedures in lumbar long-segment instrumented surgery. Under the four physiological motion states, the average stresses on the adjacent segment intervertebral disc and facet joint in all fixation models were greater than those in the intact model. Furthermore, the average stresses on the adjacent segment intervertebral disc and facet joint were greater in models CI and CII than in models BI and BII, respectively. The average stresses on the pedicle screws and rods were decreased in models BI and BII compared with models CI and CII under the four physiological motion states, respectively. The PEEK rod internal fixation system may have better biomechanical properties than the titanium rod internal fixation system in delaying adjacent segment degeneration, improving the lumbar function of postoperative patients, and reducing the risk of screw loosening and breakage in lumbar long-segment instrumentation.

CT image segmentation as a tool for volumetric measurement of external inflammatory root resorption

CT image segmentation as a tool for volumetric measurement of external inflammatory root resorption

Segmentation of abdominal CT and cardiac MR images with multi scale visual attention

Segmentation of abdominal CT and cardiac MR images with multi scale visual attention

Microcrack Segmentation of 3D CT Images Based on Multi-Task Learning

Microcrack Segmentation of 3D CT Images Based on Multi-Task Learning

Superiorized iteration algorithm for CT image simultaneous reconstruction and segmentation

Superiorized iteration algorithm for CT image simultaneous reconstruction and segmentation

Design of compensation algorithms for zero padding and its application to a patch based deep neural network.

In this article, compensation algorithms for zero padding are suggested to enhance the performance of deep convolutional neural networks. By considering the characteristics of convolving filters, the proposed methods efficiently compensate convolutional output errors due to zero padded inputs in a convolutional neural network. Primarily the algorithms are developed for patch based SRResNet for Single Image Super Resolution and the performance comparison is carried out using the SRResNet model but due to generalized nature of the padding algorithms its efficacy is tested in U-Net for Lung CT Image Segmentation. The proposed algorithms show better performance than the existing algorithm called partial convolution based padding (PCP), developed recently.

HMSAM-UNet: A Hierarchical Multi-Scale Attention Module-Based Convolutional Neural Network for Improved CT Image Segmentation

HMSAM-UNet: A Hierarchical Multi-Scale Attention Module-Based Convolutional Neural Network for Improved CT Image Segmentation

MIS-Net: A deep learning-based multi-class segmentation model for CT images.

The accuracy of traditional CT image segmentation algorithms is hindered by issues such as low contrast and high noise in the images. While numerous scholars have introduced deep learning-based CT image segmentation algorithms, they still face challenges, particularly in achieving high edge accuracy and addressing pixel classification errors. To tackle these issues, this study proposes the MIS-Net (Medical Images Segment Net) model, a deep learning-based approach. The MIS-Net model incorporates multi-scale atrous convolution into the encoding and decoding structure with symmetry, enabling the comprehensive extraction of multi-scale features from CT images. This enhancement aims to improve the accuracy of lung and liver edge segmentation. In the evaluation using the COVID-19 CT Lung and Infection Segmentation dataset, the left and right lung segmentation results demonstrate that MIS-Net achieves a Dice Similarity Coefficient (DSC) of 97.61. Similarly, in the Liver Tumor Segmentation Challenge 2017 public dataset, the DSC of MIS-Net reaches 98.78.

Lung image segmentation via generative adversarial networks.

Lung image segmentation plays an important role in computer-aid pulmonary disease diagnosis and treatment. This paper explores the lung CT image segmentation method by generative adversarial networks. We employ a variety of generative adversarial networks and used their capability of image translation to perform image segmentation. The generative adversarial network is employed to translate the original lung image into the segmented image. The generative adversarial networks-based segmentation method is tested on real lung image data set. Experimental results show that the proposed method outperforms the state-of-the-art method. The generative adversarial networks-based method is effective for lung image segmentation.

Influence of compaction and curing in the Automated Fiber Placement Process on the mechanical performance of composite laminates

This paper investigates the effect of compaction and curing states on the mechanical properties and void content of AFP-manufactured laminates. For the mechanical characterization, tensile tests, 4-point-bending tests and interlaminar shear strength (ILSS) tests were applied. The internal structure was evaluated via micro CT. For the surface structure evaluation, an optical profilometer was used. The void content was determined via segmentation of the micro CT images. The paper is subdivided into the description of the applied materials and methods, the results and their discussion and a conclusion. The study showcases the potential of AFP-manufactured aerospace composites to attain high-quality results even without the need for an autoclave, making them well-suited for unmanned applications.

Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models.

Imaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COVID-19, which are crucial to be detected and quantified in order to obtain an accurate disease stratification and prognosis. However, visual assessment and quantification represent a time-consuming task for radiologists. In this regard, tools for semi-automatic segmentation, such as those based on Convolutional Neural Networks, can facilitate the detection of pathological lesions by delineating their contour. In this work, we compared four state-of-the-art Convolutional Neural Networks based on the encoder-decoder paradigm for the binary segmentation of COVID-19 infections after training and testing them on 90 HRCT volumetric scans of patients diagnosed with COVID-19 collected from the database of the Pisa University Hospital. More precisely, we started from a basic model, the well-known UNet, then we added an attention mechanism to obtain an Attention-UNet, and finally we employed a recurrence paradigm to create a Recurrent-Residual UNet (R2-UNet). In the latter case, we also added attention gates to the decoding path of an R2-UNet, thus designing an R2-Attention UNet so as to make the feature representation and accumulation more effective. We compared them to gain understanding of both the cognitive mechanism that can lead a neural model to the best performance for this task and the good compromise between the amount of data, time, and computational resources required. We set up a five-fold cross-validation and assessed the strengths and limitations of these models by evaluating the performances in terms of Dice score, Precision, and Recall defined both on 2D images and on the entire 3D volume. From the results of the analysis, it can be concluded that Attention-UNet outperforms the other models by achieving the best performance of 81.93%, in terms of 2D Dice score, on the test set. Additionally, we conducted statistical analysis to assess the performance differences among the models. Our findings suggest that integrating the recurrence mechanism within the UNet architecture leads to a decline in the model's effectiveness for our particular application.

Attention UNet3+: a full-scale connected attention-aware UNet for CT image segmentation of liver

Attention UNet3+: a full-scale connected attention-aware UNet for CT image segmentation of liver

A combined encoder–transformer–decoder network for volumetric segmentation of adrenal tumors

BackgroundThe morphology of the adrenal tumor and the clinical statistics of the adrenal tumor area are two crucial diagnostic and differential diagnostic features, indicating precise tumor segmentation is essential. Therefore, we build a CT image segmentation method based on an encoder–decoder structure combined with a Transformer for volumetric segmentation of adrenal tumors.MethodsThis study included a total of 182 patients with adrenal metastases, and an adrenal tumor volumetric segmentation method combining encoder–decoder structure and Transformer was constructed. The Dice Score coefficient (DSC), Hausdorff distance, Intersection over union (IOU), Average surface distance (ASD) and Mean average error (MAE) were calculated to evaluate the performance of the segmentation method.ResultsAnalyses were made among our proposed method and other CNN-based and transformer-based methods. The results showed excellent segmentation performance, with a mean DSC of 0.858, a mean Hausdorff distance of 10.996, a mean IOU of 0.814, a mean MAE of 0.0005, and a mean ASD of 0.509. The boxplot of all test samples' segmentation performance implies that the proposed method has the lowest skewness and the highest average prediction performance.ConclusionsOur proposed method can directly generate 3D lesion maps and showed excellent segmentation performance. The comparison of segmentation metrics and visualization results showed that our proposed method performed very well in the segmentation.

RCNN with Swallow Swarm Optimization for Liver Disease Detection and Classification

One of the most serious medical conditions that can endanger a person's life and health is liver disease. The second-leading cause of death for men and sixth-leading cause of death for women, respectively, is liver cancer. In 2008, liver cancer claimed the lives of almost 750,000 people, killing 960,000 of them. The segmentation and identification of CT images produced by computer tomography has emerged as a major topic in medical image processing. There are few choices for liver segmentation due to the enormous amount of time and resources necessary to train a deep learning model. As part of this research, we created the Region utilizing Convolutional Neural Network, a novel way of extracting the liver from CT scan images (RCNN). The suggested CNN approach, which employs softmax to isolate the liver from the background, contains of three convolutional layers and two entirely associated layers. In the CapsNet and CAL layers, there are class dependencies and an efficient mechanism to connect CAL and subsequent CapsNet processing. Finally, the classification is carried out using the SSO-CSAE model, an approach known as the swallow swarm optimization that is based on the Convolutional Sparse Autoencoder (CSAE) The MICCAI SLiver '07, 3Dircadb01, and LiTS17 benchmark datasets were used to validate the proposed RCNN-SSO approach. When compared to other frameworks, the proposed framework performed well in numerous categories.

Body composition analysis using convolutional neural network in predicting postoperative pancreatic fistula and survival after pancreatoduodenectomy for pancreatic cancer

PurposeTo evaluate whether body composition measurements acquired using convolutional neural networks (CNNs) from preoperative CT images could predict postoperative pancreatic fistula (POPF) and overall survival (OS) after pancreaticoduodenectomy in patients with pancreatic ductal adenocarcinoma (PDAC). Methods257 patients (160 men; median age [interquartile range], 67 [60–74]) who underwent pancreaticoduodenectomy for PDAC between January 2013 and December 2017 were included in this retrospective study. Body composition measurements were based on a CNN trained to segment CT images into skeletal muscle area, visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT). Skeletal muscle area, VAT, and SAT were normalized to height square and labeled as skeletal muscle, VAT, and SAT indices, respectively. The independent risk factors for clinically relevant POPF (grade B or C) were determined using a multivariate logistic regression model, and prognostic factors for OS were assessed using Cox proportional hazards regression analyses. ResultsAfter pancreatioduodenectomy, 27 patients developed POPF grade B or C (10.5 %, 27/257). The VAT index (odds ratio [OR] = 7.43, p < 0.001) was the only independent prognostic factor for POPF grade B or C. During the median follow-up period of 23 months, 205 (79.8 % [205/257]) patients died. For prediction of OS, skeletal muscle index (hazard ratio [HR] = 0.58, p = 0.018) was a significant factor, along with vascular invasion (HR = 1.85, p < 0.001) and neoadjuvant therapy (HR = 0.58, p = 0.011). ConclusionsA high VAT index and a low skeletal muscle index can be utilized in predicting the occurrence of POPF grade B or C and poor OS, respectively.

Improving Kidney Tumor Detection Accuracy Using Hybrid U-Net Segmentation

Kidney cancer stands as a significant factor in cancer-related mortality, highlighting the critical importance of early and precise tumor detection This study introduces a computer-aided approach using the KiTS19 dataset and a hybrid U-Net architecture. Manual tumor segmentation is resource-intensive and prone to errors. Leveraging the hybrid U-Net, known for its proficiency in medical image analysis, we achieve precise tumor identification. Our method involves initial kidney and tumor segmentation in high-resolution CT images, followed by region of interest (ROI) generation and benign/malignant tumor classification. The assessment conducted on the KiTS19 dataset demonstrates encouraging outcomes, with Dice coefficients of 0.974 for kidney segmentation and 0.818 for tumor segmentation, accompanied by a tumor classification accuracy rate of 94.3%.The hybrid U-Net’s advanced feature extraction and spatial context awareness contribute to these outcomes. By streamlining diagnosis, our approach has the potential to significantly improve patient outcomes. The use of the KiTS19 dataset ensures robustness across various clinical cases and imaging modalities. This method represents a valuable advancement in computer-aided kidney tumor detection, promising to enhance patient care.

CT image segmentation of meat sheep Loin based on deep learning.

There are no clear boundaries between internal tissues in sheep Computerized Tomography images, and it is difficult for traditional methods to meet the requirements of image segmentation in application. Deep learning has shown excellent performance in image analysis. In this context, we investigated the Loin CT image segmentation of sheep based on deep learning models. The Fully Convolutional Neural Network (FCN) and 5 different UNet models were applied in image segmentation on the data set of 1471 CT images including the Loin part from 25 Australian White rams and Dolper rams using the method of 5-fold cross validation. After 10 independent runs, different evaluation metrics were applied to assess the performances of the models. All models showed excellent results in terms evaluation metrics. There were slight differences among the results from the six models, and Attention-UNet outperformed others methods with 0.998±0.009 in accuracy, 4.391±0.338 in AVER_HD, 0.90±0.012 in MIOU and 0.95±0.007 in DICE, respectively, while the optimal value of LOSS was 0.029±0.018 from Channel-UNet, and the running time of ResNet34-UNet is the shortest.

A Method of Lung Organ Segmentation in CT Images Based on Multiple Residual Structures and an Enhanced Spatial Attention Mechanism

Accurate organ segmentation is a fundamental step in disease-assisting diagnostic systems, and the precise segmentation of lung is crucial for subsequent lesion detection. Prior to this, lung segmentation algorithms had typically segmented the entire lung tissue. However, the trachea is also essential for diagnosing lung diseases. Challenges in lung parenchyma segmentation include the limited robustness of U-Net in acquiring contextual information and the small size of the trachea being mixed up with lung, making it difficult to identify and reconstruct the lungs. To overcome these difficulties, this paper proposes three improvements to U-Net: multiple concatenation modules to enhance the network’s ability to capture context, multi-scale residual learning modules to improve the model’s multi-scale learning capabilities, and an enhanced gated attention mechanism to enhance the fusion of various hierarchical features. The experimental results demonstrate that our model has achieved a significant improvement in trachea segmentation compared to existing models.