Segmentation Of Computed Tomography Images Research Articles

SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion

Objective. Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from Computed Tomography (CT) scans to address the efficacy issue of honeycomb lung segmentation. Methods. This study proposes a sparse mapping-based graph representation segmentation network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask. Results. Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47). Significance. The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis, and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

Liver tumor segmentation method based on U-Net architecture: a review

Liver cancer is a disease with a high incidence and high probability of deterioration, and for the rapid diagnosis of liver disease, CT scans must be used to segment the liver tumors. For the past few years, with the rapid development of deep learning, many deep learning methods for liver tumor segmentation using abdominal computed tomography (CT) images have appeared, and the clinical application of these methods is of important significance for computer-aided diagnosis of liver tumors. The U-Net, with its unique U-shape network structure, exhibits excellent performance in medical image segmentation field and has been extensively utilized in various medical image segmentation applications. In this paper, we summarize the researches of U-Net and its improved networks in CT image segmentation of liver tumors by deep learning methods and classify various U-Net-based convolutional neural networks (CNNs) into 2D (two-dimensional), 3D (three-dimensional), and 2.5D (2.5-dimensional). In this paper, 2D, 3D, and 2.5D convolutional neural networks are summarized. In addition, this paper summarizes the advantages and disadvantages as well as the improvement methods of each type of network, which provides a useful reference for the studies of deep learning based on liver tumor segmentation field. Finally, this paper envisions future research trends for deep learning segmentation methods in the context of liver tumors.

NeXtResUNet: A neural network for industrial CT image denoising

Image denoising is a critical issue in industrial computed tomography (CT) inspection. Most existing noise reduction algorithms are based on synthetic data, resulting in the loss of fine details, local region distortions, and other problems that arise during application in practical scenarios. As such, a fusion network, combining ConvNeXt, ResNet, and UNet is proposed in this study to address these issues. This algorithm was applied to a self-constructed industrial CT image denoising dataset, achieving a peak signal-to-noise ratio (PSNR) of 47.20 dB, which is 6% (44.48 dB) higher than that of the benchmark DnCnn. This also represents a 0.5% improvement over the current state-of-the-art (SOTA) SCUNet (46.94 dB). More importantly, the proposed network is superior to other existing models in terms of the overall visual effects and degree of image detail preservation. The network structure is also concise yet simple to expand. As such, it can be applied not only to image denoising, but also to CT image segmentation, super resolution, and related tasks.

Development and Validation of an Artificial Intelligence Preoperative Planning and Patient-Specific Instrumentation System for Total Knee Arthroplasty.

Accurate preoperative planning for total knee arthroplasty (TKA) is crucial. Computed tomography (CT)-based preoperative planning offers more comprehensive information and can also be used to design patient-specific instrumentation (PSI), but it requires well-reconstructed and segmented images, and the process is complex and time-consuming. This study aimed to develop an artificial intelligence (AI) preoperative planning and PSI system for TKA and to validate its time savings and accuracy in clinical applications. The 3D-UNet and modified HRNet neural network structures were used to develop the AI preoperative planning and PSI system (AIJOINT). Forty-two patients who were scheduled for TKA underwent both AI and manual CT processing and planning for component sizing, 20 of whom had their PSIs designed and applied intraoperatively. The time consumed and the size and orientation of the postoperative component were recorded. The Dice similarity coefficient (DSC) and loss function indicated excellent performance of the neural network structure in CT image segmentation. AIJOINT was faster than conventional methods for CT segmentation (3.74 ± 0.82 vs. 128.88 ± 17.31 min, p < 0.05) and PSI design (35.10 ± 3.98 vs. 159.52 ± 17.14 min, p < 0.05) without increasing the time for size planning. The accuracy of AIJOINT in planning the size of both femoral and tibial components was 92.9%, while the accuracy of the conventional method in planning the size of the femoral and tibial components was 42.9% and 47.6%, respectively (p < 0.05). In addition, AI-based PSI improved the accuracy of the hip-knee-ankle angle and reduced postoperative blood loss (p < 0.05). AIJOINT significantly reduces the time needed for CT processing and PSI design without increasing the time for size planning, accurately predicts the component size, and improves the accuracy of lower limb alignment in TKA patients, providing a meaningful supplement to the application of AI in orthopaedics.

An improved Deeplab V3+ network based coconut CT image segmentation method.

Due to the unique structure of coconuts, their cultivation heavily relies on manual experience, making it difficult to accurately and timely observe their internal characteristics. This limitation severely hinders the optimization of coconut breeding. To address this issue, we propose a new model based on the improved architecture of Deeplab V3+. We replace the original ASPP(Atrous Spatial Pyramid Pooling) structure with a dense atrous spatial pyramid pooling module and introduce CBAM(Convolutional Block Attention Module). This approach resolves the issue of information loss due to sparse sampling and effectively captures global features. Additionally, we embed a RRM(residual refinement module) after the output level of the decoder to optimize boundary information between organs. Multiple model comparisons and ablation experiments are conducted, demonstrating that the improved segmentation algorithm achieves higher accuracy when dealing with diverse coconut organ CT(Computed Tomography) images. Our work provides a new solution for accurately segmenting internal coconut organs, which facilitates scientific decision-making for coconut researchers at different stages of growth.

Computed tomography and guidelines-based human-machine fusion model for predicting resectability of the pancreatic cancer.

The study aims to develop a hybrid machine learning model for predicting resectability of the pancreatic cancer, which is based on computed tomography (CT) and National Comprehensive Cancer Network (NCCN) guidelines. We retrospectively studied 349 patients. One hundred seventy-one cases from Center 1 and 92 cases from Center 2 were used as the primary training cohort, and 66 cases from Center 3 and 20 cases from Center 4 were used as the independent test dataset. Semi-automatic module of ITK-SNAP software was used to assist CT image segmentation to obtain three-dimensional (3D) imaging region of interest (ROI). There were 788 handcrafted features extracted for 3D ROI using PyRadiomics. The optimal feature subset consists of three features screened by three feature selection methods as the input of the SVM to construct the conventional radiomics-based predictive model (cRad). 3D ROI was used to unify the resolution by 3D spline interpolation method for constructing the 3D tumor imaging tensor. Using 3D tumor image tensor as input, 3D kernelled support tensor machine-based predictive model (KSTM), and 3D ResNet-based deep learning predictive model (ResNet) were constructed. Multi-classifier fusion ML model is constructed by fusing cRad, KSTM, and ResNet using multi-classifier fusion strategy. Two experts with more than 10years of clinical experience were invited to reevaluate each patient based on their CECT following the NCCN guidelines to obtain resectable, unresectable, and borderline resectable diagnoses. The three results were converted into probability values of 0.25, 0.75, and 0.50, respectively, according to the traditional empirical method. Then it is used as an independent classifier and integrated with multi-classifier fusion machine learning (ML) model to obtain the human-machine fusion ML model (HMfML). Multi-classifier fusion ML model's area under receiver operating characteristic curve (AUC; 0.8610), predictive accuracy (ACC: 80.23%), sensitivity (SEN: 78.95%), and specificity (SPE: 80.60%) is better than cRad, KSTM, and ResNet-based single-classifier models and their two-classifier fusion models. This means that three different models have mined complementary CECT feature expression from different perspectives and can be integrated through CFS-ER, so that the fusion model has better performance. HMfML's AUC (0.8845), ACC (82.56%), SEN (84.21%), SPE (82.09%). This means that ML models might learn extra information from CECT that experts cannot distinguish, thus complementing expert experience and improving the performance of hybrid ML models. HMfML can predict PC resectability with high accuracy.

Bidirectional Encoder Representations Transformers for Improving CNN-LSTM Covid-19 Disease Detection Classifier

Early identification of COVID-19 diseased persons is crucial to avoid and prevent the transmission of the SARS-CoV-2 virus. To achieve this, lung Computed Tomography (CT) scan segmentation and categorization models have been broadly developed for COVID-19 diagnosis. Amongst, Multi-Scale function learning with an Attention-based UNet and Marginal Space Deep Ambiguity-attentive Transfer Learning (MS-AUNet-MSDATL) framework is developed to concurrently segment the COVID-19 infected regions and classify their risk levels from the CT/Chest X-Ray (CXR) scans. This model utilizes Convolutional Neural Network–Long Short Term Memory (CNN-LSTM) as a classifier for proper recognition. Although CNN-LSTM efficiently learns the spatial and temporal data, but it highly ignores the pixels and their adjacent information which results in lower classification rate. So, in this paper, Bidirectional Encoder Representations from Transformers (BERT) is introduced along with CNN-LSTM in MS-AUNet-MSDATL model to resolve the above mentioned issues for efficient COVID-19 risk level classification. Initially, the segmented CT and CXR images from MS-AUNet is given as input to the BERT model. BERT structure consist of stack of transformer encoder layers which extracts fixed features from a pre-trained models to obtain the numerical representation of the given image. Then, the numerical expressions from the BERT are transformed to pre-learned CNN model for selecting the important features from the given representations. The LSTM model receives the CNN output and generates a new representation based on the data order. In addition, Fully Connected Layer (FCL) maps the CNN-LSTM results into categorization classes to learn pixels and their adjacent information for COVID-19 risk level detection and diagnosis. The complete work is termed as MS-AUNet-EMSDATL. Finally, the test findings shows that the MS-AUNet-MS-B-DATL achieves accuracy of 98.67% and 98.55% on CT and CXR images compared to the other existing frameworks.

Three-Dimensional Segmentation Assisted with Clustering Analysis for Surface and Volume Measurements of Equine Incisor in Multidetector Computed Tomography Data Sets.

Dental diagnostic imaging has progressed towards the use of advanced technologies such as 3D image processing. Since multidetector computed tomography (CT) is widely available in equine clinics, CT-based anatomical 3D models, segmentations, and measurements have become clinically applicable. This study aimed to use a 3D segmentation of CT images and volumetric measurements to investigate differences in the surface area and volume of equine incisors. The 3D Slicer was used to segment single incisors of 50 horses' heads and to extract volumetric features. Axial vertical symmetry, but not horizontal, of the incisors was evidenced. The surface area and volume differed significantly between temporary and permanent incisors, allowing for easy eruption-related clustering of the CT-based 3D images with an accuracy of >0.75. The volumetric features differed partially between center, intermediate, and corner incisors, allowing for moderate location-related clustering with an accuracy of >0.69. The volumetric features of mandibular incisors' equine odontoclastic tooth resorption and hypercementosis (EOTRH) degrees were more than those for maxillary incisors; thus, the accuracy of EOTRH degree-related clustering was >0.72 for the mandibula and >0.33 for the maxilla. The CT-based 3D images of equine incisors can be successfully segmented using the routinely achieved multidetector CT data sets and the proposed data-processing approaches.

Thresholding-accelerated convolutional neural network for aeroengine turbine blade segmentation

Turbine blades can only be detected nondestructively and precisely using industrial computed tomography (CT). The accuracy of CT image segmentation, which is a key step in CT detection, significantly affects CT detection precision. However, CT images of turbine blades cannot be segmented precisely because they contain inhomogeneity, noise, artifacts, and low-contrast areas. In addition, it is crucial to consider both efficiency and precision in industrial applications. Unfortunately, large-size networks often tend to be inefficient, while lightweight networks lack the necessary accuracy. To address these issues, we propose an innovative approach utilizing an ultra-lightweight neural network that fuses a threshold-based segmentation algorithm with a convolutional neural network for acceleration. The integrated thresholding algorithm was developed through the convolution of the Phansakar method. The convolutional neural network was designed with a simplified multichannel convolution operation to minimize computational cost. Notably, the proposed neural network utilizes only 0.11 M learnable parameters, which is significantly less than the number utilized by most classical deep neural networks. Experimental results for CFM56-7BE and Pratt & Whitney F100 aeroengine hollow turbine blade CT images demonstrate that compared to state-of-the-art algorithms, our proposed network can achieve 0.44 % mean intersection over union and 0.23 % mean Dive similarity coefficient improvements on testing datasets with significantly reduced computational cost. Therefore, the proposed method has high practical application significance and can achieve real-time detection.

Evaluation of the accuracy of cone-beam computed tomography image segmentation of isolated tooth roots based on the dynamic threshold method

ObjectiveAccurate quantification of the root surface area (RSA) plays a decisive role in the advancement of periodontal, orthodontic, and restorative treatment modalities. In this study, we aimed to develop a dynamic threshold-based computer-aided system for segmentation and calculation of the RSA of isolated teeth on cone-beam computed tomography (CBCT) and to assess the accuracy of the measured data.MethodWe selected 24 teeth to be extracted, including single-rooted and multi-rooted teeth, from 22 patients who required tooth extraction. In the experimental group, we scanned 24 isolated teeth using CBCT with a voxel size of 0.3 mm. We designed a computer-aided system based on a personalized dynamic threshold algorithm to automatically segment the roots of 24 isolated teeth in CBCT images and calculate the RSA. In the control group, we employed digital intraoral scanner devices to perform optical scanning on 24 isolated teeth and subsequently manually segmented the roots using 3-matic software to calculate the RSA. We used the paired t-test (P < 0.05) and Bland-Altman plots to analyze the consistency of the two measurement methods.ResultsThe results of the paired t-test showed that there was no significant difference in the RSAs obtained using the dynamic threshold method and the optical scanning image reconstruction (t = 1.005, P = 0.325 > 0.05). As per the Bland-Altman plot, the results were evenly distributed within the region of ± 1.96 standard deviations of the mean, with no increasing or decreasing trends and good consistency.ConclusionIn this study, we designed a computer-aided root segmentation system based on a personalized dynamic threshold algorithm to automatically segment the roots of isolated teeth in CBCT images with a voxel size of 0.3 mm. We found that the RSA calculated using this approach was highly accurate, and a voxel of 0.3 mm in size could accurately display the surface area data in CBCT images. Overall, our findings in this study provide a foundation for future work on accurate automatic segmentation of tooth roots in full-mouth CBCT images and the computation of RSA.

Liver Tumor Computed Tomography Image Segmentation Based on an Improved U-Net Model

An automated segmentation method for computed tomography (CT) images of liver tumors is an urgent clinical need. Tumor areas within liver cancer images are easily missed as they are small and have unclear borders. To address these issues, an improved liver tumor segmentation method based on U-Net is proposed. This involves incorporating attention mechanisms into the U-Net’s skip connections, giving higher weights to important regions. Through dynamically adjusting the attention recognition characteristics, the method achieves accurate localization that is focused on and discriminates target regions. Testing using the LiTS (liver tumor segmentation) public dataset resulted in a Dice similarity coefficient of 0.69. The experiments demonstrated that this method can accurately segment liver tumors.

Self-adaptive moth flame optimizer combined with crossover operator and Fibonacci search strategy for COVID-19 CT image segmentation.

The COVID-19 is one of the most significant obstacles that humanity is now facing. The use of computed tomography (CT) images is one method that can be utilized to recognize COVID-19 in early stage. In this study, an upgraded variant of Moth flame optimization algorithm (Es-MFO) is presented by considering a nonlinear self-adaptive parameter and a mathematical principle based on the Fibonacci approach method to achieve a higher level of accuracy in the classification of COVID-19 CT images. The proposed Es-MFO algorithm is evaluated using nineteen different basic benchmark functions, thirty and fifty dimensional IEEE CEC'2017 test functions, and compared the proficiency with a variety of other fundamental optimization techniques as well as MFO variants. Moreover, the suggested Es-MFO algorithm's robustness and durability has been evaluated with tests including the Friedman rank test and the Wilcoxon rank test, as well as a convergence analysis and a diversity analysis. Furthermore, the proposed Es-MFO algorithm resolves three CEC2020 engineering design problems to examine the problem-solving ability of the proposed method. The proposed Es-MFO algorithm is then used to solve the COVID-19 CT image segmentation problem using multi-level thresholding with the help of Otsu's method. Comparison results of the suggested Es-MFO with basic and MFO variants proved the superiority of the newly developed algorithm.

Automatic segmentation of large-scale CT image datasets for detailed body composition analysis

BackgroundBody composition (BC) is an important factor in determining the risk of type 2-diabetes and cardiovascular disease. Computed tomography (CT) is a useful imaging technique for studying BC, however manual segmentation of CT images is time-consuming and subjective. The purpose of this study is to develop and evaluate fully automated segmentation techniques applicable to a 3-slice CT imaging protocol, consisting of single slices at the level of the liver, abdomen, and thigh, allowing detailed analysis of numerous tissues and organs.MethodsThe study used more than 4000 CT subjects acquired from the large-scale SCAPIS and IGT cohort to train and evaluate four convolutional neural network based architectures: ResUNET, UNET++, Ghost-UNET, and the proposed Ghost-UNET++. The segmentation techniques were developed and evaluated for automated segmentation of the liver, spleen, skeletal muscle, bone marrow, cortical bone, and various adipose tissue depots, including visceral (VAT), intraperitoneal (IPAT), retroperitoneal (RPAT), subcutaneous (SAT), deep (DSAT), and superficial SAT (SSAT), as well as intermuscular adipose tissue (IMAT). The models were trained and validated for each target using tenfold cross-validation and test sets.ResultsThe Dice scores on cross validation in SCAPIS were: ResUNET 0.964 (0.909–0.996), UNET++ 0.981 (0.927–0.996), Ghost-UNET 0.961 (0.904–0.991), and Ghost-UNET++ 0.968 (0.910–0.994). All four models showed relatively strong results, however UNET++ had the best performance overall. Ghost-UNET++ performed competitively compared to UNET++ and showed a more computationally efficient approach.ConclusionFully automated segmentation techniques can be successfully applied to a 3-slice CT imaging protocol to analyze multiple tissues and organs related to BC. The overall best performance was achieved by UNET++, against which Ghost-UNET++ showed competitive results based on a more computationally efficient approach. The use of fully automated segmentation methods can reduce analysis time and provide objective results in large-scale studies of BC.

Computed Tomography Image Segmentation of Lung Corona Virus Infection Region Based on Combination of Grayscale Morphological Reconstruction and Fast Marching Method

Recently, X-ray computed tomography-imaging modality is considered as golden standard for diagnosis of coronavirus lungs infection. In worldwide, infectious patients increase rapidly that lead to weariness in health services staff, as well as instant treatment required to avoid patients’ health deterioration due to infection development. Image processing would be reinforcing health services by considering computer-based segmentation. However, a ground glass computed tomography image fashion of coronavirus lungs infection characterized by disappearance of edge region of interest and lack of object structure. In this study, these challenges addressed by introducing a new algorithm that combined both morphological reconstruction and fast marching method. The proposed algorithm applied on archived computed tomography dataset for coronavirus infected patients, results showed consistent determination of ground glass infection region compared to manual delineation of senior physician. The proposed algorithm restricted to empirical adjustment of FMM’s threshold that would be addressed in upcoming study.

FDTR: Weakening feature disparity transformer for accurate multicategory computed tomography image segmentation

Accurately segmenting object structures in computed tomography (CT) images is crucial for computer-aided surgery, diagnosis, and other interdisciplinary applications. Most state-of-the-art CT segmentation methods employ a classical jump structure to integrate shallow and deep feature information. However, the effectiveness of the current CT image segmentation and related subtasks must still be improved due to feature disparity between different layers and information transfer loss. To alleviate the problem, we propose a novel three-dimensional multicategory segmentation model, the weakening feature disparity transformer (FDTR), based on the transformer structure for CT imaging. Firstly, to effectively capture global features, we design a vision transformer-based encoder. Secondly, to enhance the model’s information representation in a lightweight manner, we devise a nested structure of dense compression connections. Lastly, to mitigate the disparity in semantic features at shallow layers, we propose supervised semantic signals. By employing the vision transformer-based encoder and the dense connection structure, we enhance the detailed information of deep features. Additionally, the semantic supervisory signal introduces deep semantic information to the shallow features, enriching the overall feature representation. We conducted extensive experiments on the KIPA2022 dataset for multiorgan segmentation and the YC2022 dataset for volumetric trait segmentation in broiler breeding. The proposed method, FDTR, effectively enhances feature transfer between shallow and deep features, achieving optimal results compared to other advanced models and demonstrating broad prospects for application.

An active learning method based on result quality evaluation for printed circuit board computed tomography image segmentation

AbstractElement detection is a key step in non‐destructive testing of printed circuit board (PCB) based on computed tomography (CT). In recent years, some image segmentation methods based on deep learning have shown great potential in the element segmentation task of PCB CT images, and greatly improved the efficiency and accuracy. However, since image segmentation is based on pixel‐level classification, the annotation of training data is difficult and costly. Aiming at this problem, the authors proposed a new active learning method based on the integration of relevant information about segmentation tasks and data variance. In this method, the Result Quality Evaluation Module (RQEM) proposed by us is used to generate task‐related information, and an adversarial network is used to generate the difference information between samples and the initial labelled data. Finally, the two parts of information are fused and used as the standard of data selecting. In the PCB CT image element segmentation task, the authors only need to select 12.7% of the whole training set with their proposed method to make Mean Intersection Over Union (MIOU) reach 79.7, which has reached 95% of the optimal performance of 83.7. The in‐depth analysis also verifies the effectiveness and stability of the authors’ method.

Evaluation of computed tomography images under deep learning in the diagnosis of severe pulmonary infection.

This work aimed to explore the diagnostic value of a deep convolutional neural network (CNN) combined with computed tomography (CT) images in patients with severe pneumonia complicated with pulmonary infection. A total of 120 patients with severe pneumonia complicated by pulmonary infection admitted to the hospital were selected as research subjects and underwent CT imaging scans. The empty convolution (EC) and U-net phase were combined to construct an EC-U-net, which was applied to process the CT images. The results showed that the learning rate of the EC-U-net model decreased substantially with increasing training times until it stabilized and reached zero after 40 training times. The segmentation result of the EC-U-net model for the CT image was very similar to that of the mask image, except for some deviations in edge segmentation. The EC-U-net model exhibited a significantly smaller cross-entropy loss function (CELF) and a higher Dice coefficient than the CNN algorithm. The diagnostic accuracy of CT images based on the EC-U-net model for severe pneumonia complicated with pulmonary infection was substantially higher than that of CT images alone, while the false negative rate (FNR) and false positive rate (FPR) were substantially lower (P < 0.05). Moreover, the true positive rates (TPRs) of CT images based on the EC-U-net model for patchy high-density shadows, diffuse ground glass density shadows, pleural effusion, and lung consolidation were obviously higher than those of the original CT images (P < 0.05). In short, the EC-U-net model was superior to the traditional algorithm regarding the overall performance of CT image segmentation, which can be clinically applied. CT images based on the EC-U-net model can clearly display pulmonary infection lesions, improve the clinical diagnosis of severe pneumonia complicated with pulmonary infection, and help to screen early pulmonary infection and carry out symptomatic treatment.

A Boundary-Enhanced Liver Segmentation Network for Multi-Phase CT Images with Unsupervised Domain Adaptation.

Multi-phase computed tomography (CT) images have gained significant popularity in the diagnosis of hepatic disease. There are several challenges in the liver segmentation of multi-phase CT images. (1) Annotation: due to the distinct contrast enhancements observed in different phases (i.e., each phase is considered a different domain), annotating all phase images in multi-phase CT images for liver or tumor segmentation is a task that consumes substantial time and labor resources. (2) Poor contrast: some phase images may have poor contrast, making it difficult to distinguish the liver boundary. In this paper, we propose a boundary-enhanced liver segmentation network for multi-phase CT images with unsupervised domain adaptation. The first contribution is that we propose DD-UDA, a dual discriminator-based unsupervised domain adaptation, for liver segmentation on multi-phase images without multi-phase annotations, effectively tackling the annotation problem. To improve accuracy by reducing distribution differences between the source and target domains, we perform domain adaptation at two levels by employing two discriminators, one at the feature level and the other at the output level. The second contribution is that we introduce an additional boundary-enhanced decoder to the encoder-decoder backbone segmentation network to effectively recognize the boundary region, thereby addressing the problem of poor contrast. In our study, we employ the public LiTS dataset as the source domain and our private MPCT-FLLs dataset as the target domain. The experimental findings validate the efficacy of our proposed methods, producing substantially improved results when tested on each phase of the multi-phase CT image even without the multi-phase annotations. As evaluated on the MPCT-FLLs dataset, the existing baseline (UDA) method achieved IoU scores of 0.785, 0.796, and 0.772 for the PV, ART, and NC phases, respectively, while our proposed approach exhibited superior performance, surpassing both the baseline and other state-of-the-art methods. Notably, our method achieved remarkable IoU scores of 0.823, 0.811, and 0.800 for the PV, ART, and NC phases, respectively, emphasizing its effectiveness in achieving accurate image segmentation.

Computed tomography image segmentation of irregular cerebral hemorrhage lesions based on improved U-Net

ObjectiveThis paper aims to improve U-Net for more accurate segmentation of irregular intracranial hemorrhage lesions in CT images. MethodsThe residual octave convolution (ResOctConv) module was introduced to overcome the semantic gap issue in U-Net, and a hybrid attention mechanism called mixed attention mechanism (MAM) was proposed to further enhance the performance of U-Net. 40 patients with irregular cerebral hemorrhage images were selected from head CT scans performed between August and December 2022. Two radiologists independently traced the edge of each selected image three times, and the final segmentation boundary was determined by consensus. The effectiveness of the lesion segmentation was measured using the Dice coefficient, Jaccard Index, and Relative volume difference. ResultsBased on the box plot of the Dice coefficient for all 40 patients, the improved U-Net demonstrated higher accuracy in segmenting irregular intracranial hemorrhage lesions in CT images compared to the original U-Net. Moreover, the comparison of Dice coefficient, Jaccard coefficient, and RVD indicates that the improved U-Net outperforms both the original U-Net and the region growing algorithm in segmenting irregular cerebral hemorrhage lesions. ConclusionsThe proposed improved U-Net outperforms both the original U-Net and the region growing algorithm in segmenting irregular cerebral hemorrhage lesions, providing an advanced toolset for radiologists to accurately identify and diagnose irregular cerebral hemorrhage lesions.

Multi-class Tissue Segmentation of CT images using an Ensemble Deep Learning method.

Microwave ablation (MWA) therapy is a well-known technique for locally destroying lung tumors with the help of computed tomography (CT) images. However, tumor recurrence occurs because of insufficient ablation of the tumor. In order to perform an accurate treatment of lung cancer, there is a demand to determine the tumor area precisely. To address the problem at hand, which involves accurately segmenting organs and tumors in CT images obtained during MWA therapy, physicians could benefit from a semantic segmentation method. However, such a method typically requires a large number of images to achieve optimal results through deep learning techniques. To overcome this challenge, our team developed four different (multiple) U-Net based semantic segmentation models that work in conjunction with one another to produce a more precise segmented image, even when working with a relatively small dataset. By combining the highest weight value of segmentation from multiple methods into a single output, we can achieve a more reliable and accurate segmentation outcome. Our approach proved successful in segmenting four different tissue structures, including lungs, lung tumors, and ablated tissues in CT medical images. The Intersection over Union (IoU) is employed to quantitatively evaluate the proposed method. The method shows the highest average IoU, with 0.99 for the background, 0.98 for the lung, 0.77 for the ablated, and 0.54 for the tumor tissue. The results show that employing multiple DL methods is superior to that of individual base-learner models for all four different tissue structures, even in the presence of the relatively small dataset.Clinical relevance- An essential issue of tumor ablation therapy is to know when the entire tumor tissue has completely been destroyed. However, as it is difficult to distinguish between destroyed and living tumor, this is hardly reliable in clinical practice during MWA therapy, especially when working with a small dataset. Improved AI segmentation methods can help to improve performance to reduce recurrence.