Computed Tomography Datasets Research Articles

Robust thoracic CT image registration with environmental adaptability using dynamic Welsch's function and hierarchical structure-awareness strategy.

Robust registration of thoracic computed tomography (CT) images is strongly impacted by motion during acquisition, high-density objects, and noise, particularly in lower-dose acquisitions. Despite the enhanced registration speed achieved by popular deep learning (DL) methods, their robustness is often neglected. This study aimed to develop a robust thoracic CT image registration algorithm to address the aforementioned issues. A novel, anatomical structure-aware hierarchical registration. By this method, employing a divide-and-conquer approach, dissimilarity metrics, and regularization terms are selected for different regions based on their distinct image features and motion patterns. These terms are then innovatively reconstructed using the Welsch's function, which allows control over the penalty distribution on the loss values. Subsequently, a novel Welsch parameter update strategy is designed for the task of thoracic CT image registration, enabling dynamic sparsity in registration from coarse to fine levels to accommodate various levels of noise and sliding motion. Moreover, the majorization-minimization (MM) algorithm is used to handle the Welsch terms by constructing surrogate functions based on the current variable values for variable update, thereby reducing the complexity of optimization. Experimental results on publicly available deformable image registration lab four-dimensional CT (DIR-Lab 4DCT) and chronic obstructive pulmonary disease (COPD) datasets with and without noise, showed that our proposed method achieves comparable performance to state-of-the-art methods in noise-free scenarios [1.14 and 1.19 mm compared to 1.14 and 1.35 mm target registration errors (TREs)], while demonstrating superior robustness in the presence of noise (1.78 and 2.38 mm compared to 2.00 and 3.31 mm TREs). Ablation studies also validated the effectiveness of each component in the method. A novel and robust algorithm for thoracic CT image registration has been proposed, which has significant potential for valuable clinical applications, including surgical quantitative imaging.

Detecting Porosity in Additively Manufactured Parts with Deep Learning and Artificial Computed Tomography Data

ABSTRACT Deep learning has recently gained significant attention in nondestructive testing tasks due to its ability to effectively analyze complex data and identify patterns. This paper proposes a methodology for defect detection on an X-ray computed tomography dataset utilizing the Mask R-CNN algorithm. The proposed approach generates artificial data from the original dataset and introduces a metric for classifying the intensity of the defects. The Mask R-CNN is trained for defect localization and classification, and the results show that the proposed approach performs competitively with, and in many cases better than, reported papers on the same dataset. This paper provides a detailed analysis of the proposed methodology, including experimental results and discussions, demonstrating its effectiveness and potential for future research.

Radiomics-guided generative adversarial network for automatic primary target volume segmentation for nasopharyngeal carcinoma using computed tomography images.

Automatic primary gross tumor volume (GTVp) segmentation for nasopharyngeal carcinoma (NPC) is a quite challenging task because of the existence of similar visual characteristics between tumors and their surroundings, especially on computed tomography (CT) images with severe low contrast resolution. Therefore, most recently proposed methods based on radiomics or deep learning (DL) is difficult to achieve good results on CT datasets. A peritumoral radiomics-guided generative adversarial network (PRG-GAN) was proposed to address this challenge. A total of 157 NPC patients with CT images was collected and divided into training, validation, and testing cohorts of 108, 9, and 30 patients, respectively. The proposed model was based on a standard GAN consisting of a generator network and a discriminator network. Morphological dilation on the initial segmentation results from GAN was first conducted to delineate annular peritumoral region, in which radiomics features were extracted as priori guide knowledge. Then, radiomics features were fused with semantic features by the discriminator's fully connected layer to achieve the voxel-level classification and segmentation. The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD) were used to evaluate the segmentation performance using a paired samples t-test with Bonferroni correction and Cohen's d (d) effect sizes. A two-sided p-value of less than 0.05 was considered statistically significant. The model-generated predictions had a high overlap ratio with the ground truth. The average DSC, HD95, and ASSD were significantly improved from 0.80±0.12, 4.65±4.71mm, and 1.35±1.15mm of GAN to 0.85±0.18 (p=0.001, d=0.71), 4.15±7.56mm (p=0.002, d=0.67), and 1.11±1.65mm (p<0.001, d=0.46) of PRG-GAN, respectively. Integrating radiomics features into GAN is promising to solve unclear border limitations and increase the delineation accuracy of GTVp for patients with NPC.

Using CT images to assist the segmentation of MR images via generalization: Segmentation of the renal parenchyma of renal carcinoma patients.

Developing deep learning models for segmenting medical images in multiple modalities with less data and annotation is an attractive and challenging task, which was previously discussed as being accomplished by complex external frameworks for bridging the gap between different modalities. Exploring the generalization ability of networks in medical images in different modalities could provide more simple and accessible methods, yet comprehensive testing could still be needed. To explore the feasibility and robustness of using computed tomography (CT) images to assist the segmentation of magnetic resonance (MR) images via the generalization, in the segmentation of renal parenchyma of renal cell carcinoma (RCC) patients. Nephrographic CT images and fat-suppressed T2-weighted (fs-T2W) images were retrospectively collected. The pure CT dataset included 116 CT images. Additionally, 240 MR images were randomly divided into subsets A and B. From subset A, three training datasets were constructed, each containing 40, 80, and 120 images, respectively. Similarly, three datasets were constructed from subset B. Subsequently, datasets with mixed modality were created by combining these pure MR datasets with the 116 CT images. The 3D-UNET models for segmenting the renal parenchyma in two steps were trained using these 13 datasets: segmenting kidneys and then the renal parenchyma. These models were evaluated in internal MR (n=120), CT (n=65) validation datasets, and an external validation dataset of CT (n=79), using the mean of the dice similarity coefficient (DSC). To demonstrate the robustness of generalization ability over different proportions of modalities, we compared the models trained with mixed modality in three different proportions and pure MR, using repeated measures analysis of variance (RM-ANOVA). We developed a renal parenchyma volume quantification tool by the trained models. The mean differences and Pearson correlation coefficients between the model segmentation volume and the ground truth segmentation volume were calculated for its evaluation. The mean DSCs of models trained with 116 data in CT in the validation of MR were 0.826, 0.842, and 0.953, respectively, for the predictions of kidney segmentation model on whole image, renal parenchymal segmentation model on kidneys with RCC and without RCC. For all models trained with mixed modality, the means of DSC were above 0.9, in all validations of CT and MR. According to the results of the comparison between models trained with mixed modality and pure MR, the means of DSC of the former were significantly greater or equal to the latter, at all three different proportions of modalities. The differences of volumes were all significantly lower than one-third of the volumetric quantification error of a previous method, and the Pearson correlation coefficients of volumes were all above 0.96 on kidneys with and without RCC of three validations. CT images could be used to assist the segmentation of MR images via the generalization, with or without the supervision of MR data. This ability showed acceptable robustness. A tool for accurately measuring renal parenchymal volume on CT and MR images was established.

AI-Assisted Detection and Localization of Spinal Metastatic Lesions.

The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96. For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. The study concludes that AI-based models can augment radiologists' capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particularly for sclerotic lesion segmentation. The annotated CT dataset produced and shared in this research serves as a valuable resource for future advancements.

Auto-contouring of cardiac substructures for Stereotactic arrhythmia radioablation (STAR): A STOPSTORM.eu consortium study

Background/PurposeHigh doses to healthy cardiac substructures (CS) in stereotactic arrhythmia radioablation (STAR) raise concerns regarding potential treatment-induced cardio-toxicity. However, CS contours are not routinely created, hindering the understanding of the CS dose–effect relationships. To address this issue, the alignment of CS contouring was initiated within the STOPSTORM consortium. In this study, we developed and evaluated auto-contouring models trained to delineate CS and major vessels in ventricular tachycardia (VT) patients. MethodsEight centres provided standard treatment planning computed tomography (CT) and/or contrast-enhanced CT datasets of 55 VT patients, each including 16 CS. Auto-contouring models were trained to contour either large structures or small structures. Dice Similarity Coefficient (DSC), 95 % Hausdorff distance (HD95) and volume ratio (VR) were used to evaluate model performance versus inter-observer variation (IOV) on seven VT patient test cases. Significant differences were tested using the Mann-Whitney U test. ResultsThe performance on the four chambers and the major vessels (median DSC: 0.88; HD95: 5.8–19.4 mm; VR: 1.09) was similar to the IOV (median DSC: 0.89; HD95: 4.8–14.0 mm; VR: 1.20).For the valves, model performance (median DSC: 0.37; HD95: 11.6 mm; VR: 1.63) was similar to the IOV (median DSC: 0.41; HD95: 12.4 mm; VR: 3.42), but slightly worse for the coronary arteries (median DSC: 0.33 vs 0.42; HD95: 24.4 mm vs 16.9 mm; VR: 1.93 vs 3.30). The IOV for these small structures remains large despite using contouring guidelines. ConclusionCS auto-contouring models trained on VT patient data perform similarly to IOV. This allows for time-efficient evaluation of CS as possible organs-at-risk.

Implementing verifiable oncological imaging by quality assurance and optimization (i‑Violin) : Protocol for aEuropean multicenter study.

Advanced imaging techniques play apivotal role in oncology. Alarge variety of computed tomography (CT) scanners, scan protocols, and acquisition techniques have led to awide range in image quality and radiation exposure. This study aims at implementing verifiable oncological imaging by quality assurance and optimization (i-Violin) through harmonizing image quality and radiation dose across Europe. The 2‑year multicenter implementation study outlined here will focus on CT imaging of lung, stomach, and colorectal cancer and include imaging for four radiological indications: diagnosis, radiation therapy planning, staging, and follow-up. Therefore, 480 anonymized CT data sets of patients will be collected by the associated university hospitals and uploaded to arepository. Radiologists will determine key abdominopelvic structures for image quality assessment by consensus and subsequently adapt apreviously developed lung CT tool for the objective evaluation of image quality. The quality metrics will be evaluated for their correlation with perceived image quality and the standardized optimization strategy will be disseminated across Europe. The results of the outlined study will be used to obtain European reference data, to build teaching programs for the developed tools, and to create aculture of optimization in oncological CT imaging. The study protocol and rationale for i‑Violin, aEuropean approach for standardization and harmonization of image quality and optimization of CT procedures in oncological imaging, is presented. Future results will be disseminated across all EU member states, and i‑Violin is thus expected to have asustained impact on CT imaging for cancer patients across Europe.

Comparison of Machine Learning Models for Brain Disease Classification Based on CT and MRI Scans

The complexity and severity of brain diseases have led to increased focus on their diagnosis and treatment. Due to the inherent drawbacks of manual medical diagnosis, such as error-prone and costly, and the recent widespread use of Artificial Intelligence (AI) in medicine, it is a worthy topic to explore machine learning in diagnosing brain diseases utilizing Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). In this paper, three brain diseases using CT or MRI datasets from Kaggle were merged and processed, and then three models of decision tree (DT), random forest (RF) and K-Nearest Neighbors (KNN) were used to make classification prediction. Furthermore, their performance was compared through classification reports and confusion matrix to analysis results. The results showed that DT performed worse than the other two models in this task, with an accuracy of 0.91, whereas RF and KNN performed similar overall, each achieving an overall accuracy of 0.96. Notably, RF exhibited less confusion, especially between some similar categories, which indicates the ability of handle complex data more effectively. Additionally, the strengths and weaknesses of the three models are discussed in the paper. These experimental results show that machine learning model, particularly RF and KNN, is a useful tool for diagnosing brain diseases with high accuracy, which could substantially assist clinical practices by providing reliable and efficient diagnostic support.

Morphologic differences in atrial and ventricular secondary tricuspid regurgitation by computed tomography

Abstract Background Differences in the mechanism behind atrial (ASTR) and ventricular (VSTR) secondary tricuspid regurgitation cause distinct remodeling in the tricuspid valve annulus (TA), right atrium (RA) and right ventricle (RV). Although these morphological changes have been described by echocardiography, computed tomography (CT) can provide better spatial resolution and detailed anatomical information particularly when planning valvular interventions. Purpose To compare the morphologic characteristics of the TA, RA and RV between ASTR and VSTR as measured by CT. Methods Patients with at least moderate secondary TR and who underwent CT were selected as follows: for the ASTR group (n=32), patients referred for atrial fibrillation (AF) ablation; for the VSTR group, patients referred for transcatheter aortic valve implantation, and which were further subdivided according to the presence of AF (with AF [n=51] and without AF [n=68]). Multiparametric echocardiographic approach was used to define TR severity. CT dataset were analyzed in diastole using a dedicated software for the following parameters: TA area, perimeter, antero-posterior (AP) and septal-lateral (SL) diameters, eccentricity index, annulus depth (to assess TA saddle shape), and RA and RV dimensions and volumes (Fig. 1). Results TR was more severe in VSTR, as 55% and 43% of patients had severe to massive TR in the VSTR group with and without AF, respectively, as compared to 12% in the ASTR group (p&amp;lt;0.001). The TA area was significantly larger in the ASTR and VSTR with AF patients (Fig.2), with a trend towards a more circular annulus by eccentricity index. Annulus depth was lower (flatter) in ASTR compared to both VSTR groups. For the RA, annulus to roof distance was larger in VSTR patients with AF, but the diameter width was wider for both ASTR and VSTR with AF. Indexed RA volume was larger in the VSTR with AF compared to both ASTR and VFTR without AF. The RV, on the other hand, showed a wide base and narrow mid in the ASTR group, both a wide base and mid in the VSTR group with AF, and slightly narrower base and wider mid in the VSTR without AF. RV base-to-mid ratio was lower for both VSTR groups compared to ASTR, but volumes did not significantly differ. RA-to-RV-volume ratio, however, was higher for the ASTR and VSTR with AF. Conclusion Remodeling of the TA and right chambers differ significantly between TR etiologies. ASTR is characterized by a larger and flatter TA, a widened RA and RV base, narrow RV mid, and almost proportional RA-to-RV volumes. VSTR remodeling differs with the presence of AF, as those without AF have a smaller and deep TA, smaller RA, a proportional dilatation of RV diameters, and a larger RV compared to RA. Differentiating these patterns may be useful to guide future interventions.

Diagnosis of COVID-19 from computed tomography slices using flower pollination algorithm, k-nearest neighbor, and support vector machine classifiers

Coronavirus disease 19 (COVID-19), caused by the severe acute respiratory syndrome-coronavirus-2 virus, is commonly diagnosed through imaging techniques such as computed tomography (CT) scans, which reveal characteristic lung lesions. In this study, we propose a computer-aided diagnosis (CAD) system to assist in the early detection of COVID-19 from CT lung slices, leveraging advanced machine-learning algorithms for precise and efficient analysis. To achieve this, we developed a CAD system that diagnoses COVID-19 from CT lung slices. An adaptive Wiener filter was applied to remove noise from the CT images. The chest tissues were then segmented using an optimal thresholding method to extract regions of interest, which represent the COVID-19 lesions under investigation. The feature vectors were divided into training and testing with an 80/20 ratio. A wrapper-based flower pollination algorithm was employed alongside the k-nearest neighbor classifier to select the optimal feature set. These selected features were subsequently used to train a support vector machine (SVM) classifier. With feature selection, the SVM achieved an accuracy of 91.30% on a real-time dataset, outperforming seven other machine learning classifiers (radial basis function-SVM, k nearest neighbor, linear discriminant analysis, random forest, na&amp;iuml;ve Bayes, AdaBoost, extreme gradient boosting) and four deep learning classifiers (convolutional neural network, recurrent neural network, long short term memory, Bidirectional long short term memory). For the publicly available COVID-19 CT dataset, an accuracy of 88.18% was achieved. In conclusion, our COVID-19 CAD system improves diagnostic accuracy, with future work aimed at enhancing efficiency and expanding to covariant detection and severity assessment.

Noise-assisted hybrid attention networks for low-dose PET and CT denoising.

Positron emission tomography (PET) and computed tomography (CT) play a vital role in tumor-related medical diagnosis, assessment, and treatment planning. However, full-dose PET and CT pose the risk of excessive radiation exposure to patients, whereas low-dose images compromise image quality, impacting subsequent tumor recognition and diseasediagnosis. To solve such problems, we propose a Noise-Assisted Hybrid Attention Network (NAHANet) to reconstruct full-dose PET and CT images from low-dose PET (LDPET) and CT (LDCT) images to reduce patient radiation risks while ensuring the performance of subsequent tumor recognition. NAHANet contains two branches: the noise feature prediction branch (NFPB) and the cascaded reconstruction branch. Among them, NFPB providing noise features for the cascade reconstruction branch. The cascaded reconstruction branch comprises a shallow feature extraction module and a reconstruction module which contains a series of cascaded noise feature fusion blocks (NFFBs). Among these, the NFFB fuses the features extracted from low-dose images with the noise features obtained by NFPB to improve the feature extraction capability. To validate the effectiveness of the NAHANet method, we performed experiments using two public available datasets: the Ultra-low Dose PET Imaging Challenge dataset and Low Dose CT Grand Challengedataset. As a result, the proposed NAHANet achieved higher performance on common indicators. For example, on the CT dataset, the PSNR and SSIM indicators were improved by 4.1dB and 0.06 respectively, and the rMSE indicator was reduced by 5.46 compared with the LDCT; on the PET dataset, the PSNR and SSIM was improved by 3.37dB and 0.02, and the rMSE was reduced by 9.04 compared with theLDPET. This paper proposes a transformer-based denoising algorithm, which utilizes hybrid attention to extract high-level features of low dose images and fuses noise features to optimize the denoising performance of the network, achieving good performance improvements on low-dose CT and PETdatasets.

Pre-trained quantum convolutional neural network for COVID-19 disease classification using computed tomography images.

The COVID-19 pandemic has had a significant influence on economies and healthcare systems around the globe. One of the most important strategies that has proven to be effective in limiting the disease and reducing its rapid spread is early detection and quick isolation of infections. Several diagnostic tools are currently being used for COVID-19 detection using computed tomography (CT) scan and chest X-ray (CXR) images. In this study, a novel deep learning-based model is proposed for rapid detection of COVID-19 using CT-scan images. The model, called pre-trained quantum convolutional neural network (QCNN), seamlessly combines the strength of quantum computing with the feature extraction capabilities of a pre-trained convolutional neural network (CNN), particularly VGG16. By combining the robust feature learning of classical models with the complex data handling of quantum computing, the combination of QCNN and the pre-trained VGG16 model improves the accuracy of feature extraction and classification, which is the significance of the proposed model compared to classical and quantum-based models in previous works. The QCNN model was tested on a SARS-CoV-2 CT dataset, initially without any pre-trained models and then with a variety of pre-trained models, such as ResNet50, ResNet18, VGG16, VGG19, and EfficientNetV2L. The results showed the VGG16 model performs the best. The proposed model achieved 96.78% accuracy, 0.9837 precision, 0.9528 recall, 0.9835 specificity, 0.9678 F1-Score and 0.1373 loss. Our study presents pre-trained QCNN models as a viable technique for COVID-19 disease detection, showcasing their effectiveness in reaching higher accuracy and specificity. The current paper adds to the continuous efforts to utilize artificial intelligence to aid healthcare professionals in the diagnosis of COVID-19 patients.

Diffusion probabilistic priors for zero-shot low-dose CT image denoising.

Denoising low-dose computed tomography (CT) images is a critical task in medical image computing. Supervised deep learning-based approaches have made significant advancements in this area in recent years. However, these methods typically require pairs of low-dose and normal-dose CT images for training, which are challenging to obtain in clinical settings. Existing unsupervised deep learning-based methods often require training with a large number of low-dose CT images or rely on specially designed data acquisition processes to obtain training data. To address these limitations, we propose a novel unsupervised method that only utilizes normal-dose CT images during training, enabling zero-shot denoising of low-dose CT images. Our method leverages the diffusion model, a powerful generative model. We begin by training a cascaded unconditional diffusion model capable of generating high-quality normal-dose CT images from low-resolution to high-resolution. The cascaded architecture makes the training of high-resolution diffusion models more feasible. Subsequently, we introduce low-dose CT images into the reverse process of the diffusion model as likelihood, combined with the priors provided by the diffusion model and iteratively solve multiple maximum a posteriori (MAP) problems to achieve denoising. Additionally, we propose methods to adaptively adjust the coefficients that balance the likelihood and prior in MAP estimations, allowing for adaptation to different noise levels in low-dose CT images. We test our method on low-dose CT datasets of different regions with varying dose levels. The results demonstrate that our method outperforms the state-of-the-art unsupervised method and surpasses several supervised deep learning-based methods. Our method achieves PSNR of 45.02 and 35.35dB on the abdomen CT dataset and the chest CT dataset, respectively, surpassing the best unsupervised algorithm Noise2Sim in the comparative methods by 0.39 and 0.85dB, respectively. We propose a novel low-dose CT image denoising method based on diffusion model. Our proposed method only requires normal-dose CT images as training data, greatly alleviating the data scarcity issue faced by most deep learning-based methods. At the same time, as an unsupervised algorithm, our method achieves very good qualitative and quantitative results. The Codes are available in https://github.com/DeepXuan/Dn-Dp.

A high-fidelity personalised 3d printed simulator for the left atrial appendage occlusion procedure

Purpose This study aims to develop a realistic 3D printing-based simulator for the training and planning of the left atrial appendage occlusion (LAAO) to be used in the cath lab. Design/methodology/approach Starting from a pre-operative computed tomography dataset of a patient already treated with LAAO, the model was obtained, consisting in the right and left heart, opportunely assembled to replicate the position and orientation of the patient's anatomy while lying on the cath lab table. Different 3D printing techniques and materials were used to mimic the interaction between the cardiac tissue and the clinical instrumentation. The simulator was tested in the cath lab under proper image guidance by three LAAO expert operators. The clinicians were required to assign a score in terms of realism to each material used to fabricate the fossa ovalis and the LAA. Findings The simulated interventions were successfully performed by the operators, who were able to navigate in the system and release the occluder device as during a real procedure. The intraoperative images acquired during the simulations were highly comparable with data from a real intervention, with a mean percentage difference below 10%. Originality/value This study demonstrated the feasibility of the proposed simulator to faithfully replicate the LAAO procedure and its potentiality to be used for multiple purposes, including the training of the young clinicians, the evaluation of the most complicated cases and the design of novel occluder devices, in a fully realistic setting.

CLASSIFICATION OF X-RAY AND CT IMAGES IN DIFFERENT COLOR SPACES USING ROBUST CNN

Since deep learning models have been successfully used in many fields, they have been used to identify sick and healthy people in X-ray or Computed Tomography (CT) chest radiology images. In this study, Covid-19 and pneumonia classification is performed on both X-ray and CT images using the robust Convolutional Neural Network (CNN). BGR, HSV, and CIE LAB color space transformations are applied to X-ray and CT images to show that the model performs a successful classification independent of dataset characteristics. The binary classification accuracy rates of Covid-19 and pneumonia for X-ray images and CT images are 98.7% and 98.4%, 97.6% and 99.4%, respectively. Precision, Recall, Specificity, F1 score, and Mean Squared Error metrics are calculated for each X-ray and CT dataset. In addition, 5-fold cross-validation proved accuracy of the model. Although X-ray and CT chest radiology images are transformed into different color spaces, the proposed model performed a successful classification. Thus, even if the image characteristics of the radiology device brands change, the computer-based system will be able to make successful disease diagnoses at low cost where expert personnel are insufficient.

Human-in-the-Loop-A Deep Learning Strategy in Combination with a Patient-Specific Gaussian Mixture Model Leads to the Fast Characterization of Volumetric Ground-Glass Opacity and Consolidation in the Computed Tomography Scans of COVID-19 Patients.

Background/Objectives: The accurate quantification of ground-glass opacities (GGOs) and consolidation volumes has prognostic value in COVID-19 patients. Nevertheless, the accurate manual quantification of the corresponding volumes remains a time-consuming task. Deep learning (DL) has demonstrated good performance in the segmentation of normal lung parenchyma and COVID-19 pneumonia. We introduce a Human-in-the-Loop (HITL) strategy for the segmentation of normal lung parenchyma and COVID-19 pneumonia that is both time efficient and quality effective. Furthermore, we propose a Gaussian Mixture Model (GMM) to classify GGO and consolidation based on a probabilistic characterization and case-sensitive thresholds. Methods: A total of 65 Computed Tomography (CT) scans from 64 patients, acquired between March 2020 and June 2021, were randomly selected. We pretrained a 3D-UNet with an international dataset and implemented a HITL strategy to refine the local dataset with delineations by teams of medical interns, radiology residents, and radiologists. Following each HITL cycle, 3D-UNet was re-trained until the Dice Similarity Coefficients (DSCs) reached the quality criteria set by radiologists (DSC = 0.95/0.8 for the normal lung parenchyma/COVID-19 pneumonia). For the probabilistic characterization, a Gaussian Mixture Model (GMM) was fitted to the Hounsfield Units (HUs) of voxels from the CT scans of patients with COVID-19 pneumonia on the assumption that two distinct populations were superimposed: one for GGO and one for consolidation. Results: Manual delineation of the normal lung parenchyma and COVID-19 pneumonia was performed by seven teams on 65 CT scans from 64 patients (56 ± 16 years old (μ ± σ), 46 males, 62 with reported symptoms). Automated lung/COVID-19 pneumonia segmentation with a DSC > 0.96/0.81 was achieved after three HITL cycles. The HITL strategy improved the DSC by 0.2 and 0.5 for the normal lung parenchyma and COVID-19 pneumonia segmentation, respectively. The distribution of the patient-specific thresholds derived from the GMM yielded a mean of -528.4 ± 99.5 HU (μ ± σ), which is below most of the reported fixed HU thresholds. Conclusions: The HITL strategy allowed for fast and effective annotations, thereby enhancing the quality of segmentation for a local CT dataset. Probabilistic characterization of COVID-19 pneumonia by the GMM enabled patient-specific segmentation of GGO and consolidation. The combination of both approaches is essential to gain confidence in DL approaches in our local environment. The patient-specific probabilistic approach, when combined with the automatic quantification of COVID-19 imaging findings, enhances the understanding of GGO and consolidation during the course of the disease, with the potential to improve the accuracy of clinical predictions.

CRML-Net: Cross-Modal Reasoning and Multi-Task Learning Network for tooth image segmentation

Data from a single modality may suffer from noise, low contrast, or other imaging limitations that affect the model’s accuracy. Furthermore, due to the limited amount of data, most models trained on single-modality data tend to overfit the training set and perform poorly on out-of-domain data. Therefore, in this paper, we propose a network named Cross-Modal Reasoning and Multi-Task Learning Network (CRML-Net), which combines cross-modal reasoning and multi-task learning, aiming to leverage the complementary information between different modalities and tasks to enhance the model’s generalization ability and accuracy. Specifically, CRML-Net consists of two stages. In the first stage, our network extracts a new morphological information modality from the original image and then performs cross-modal fusion with the original modality image, aiming to leverage the morphological information to enhance the model’s robustness to out-of-domain datasets. In the second stage, based on the output of the previous stage, we introduce a multi-task learning mechanism, aiming to improve the model’s performance on unseen data by sharing surface detail information from auxiliary tasks. We validated our method on a publicly available tooth cone beam computed tomography dataset. Our evaluation demonstrates that our method outperforms state-of-the-art approaches.

Cross-modal Transfer Learning Based on an Improved CycleGAN Model for Accurate Kidney Segmentation in Ultrasound Images

ObjectiveDeep-learning algorithms have been widely applied in the field of automatic kidney ultrasound (US) image segmentation. However, obtaining a large number of accurate kidney labels clinically is very difficult and time-consuming. To solve this problem, we have proposed an efficient cross-modal transfer learning method to improve the performance of the segmentation network on a limited labeled kidney US dataset. MethodsWe aim to implement an improved image-to-image translation network called Seg-CycleGAN to generate accurate annotated kidney US data from labeled abdomen computed tomography images. The Seg-CycleGAN framework primarily consists of two structures: (i) a standard CycleGAN network to visually simulate kidney US from a publicly available labeled abdomen computed tomography dataset; (ii) and a segmentation network to ensure accurate kidney anatomical structures in US images. Based on the large number of simulated kidney US images and small number of real annotated kidney US images, we then aimed to employ a fine-tuning strategy to obtain better segmentation results. ResultsTo validate the effectiveness of the proposed method, we tested this method on both normal and abnormal kidney US images. The experimental results showed that the proposed method achieved a segmentation accuracy of 0.8548 in dice similarity coefficient on all testing datasets and 0.7622 on the abnormal testing dataset. ConclusionsCompared with existing data augmentation and transfer learning methods, the proposed method improved the accuracy and generalization of the kidney US image segmentation network on a limited number of training datasets. It therefore has the potential to significantly reduce annotation costs in clinical settings.

HLFSRNN-MIL: A Hybrid Multi-Instance Learning Model for 3D CT Image Classification

At present, many diseases are diagnosed by computer tomography (CT) image technology, which affects the health of the lives of millions of people. In the process of disease confrontation, it is very important for patients to detect diseases in the early stage by deep learning of 3D CT images. The paper offers a hybrid multi-instance learning model (HLFSRNN-MIL), which hybridizes high-low frequency feature fusion (HLFFF) with sequential recurrent neural network (SRNN) for CT image classification tasks. Firstly, the hybrid model uses Resnet-50 as the deep feature. The main feature of the HLFSRNN-MIL lies in its ability to make full use of the advantages of the HLFFF and SRNN methods to make up for their own weakness; i.e., the HLFFF can extract more targeted feature information to avoid the problem of excessive gradient fluctuation during training, and the SRNN is used to process the time-related sequences before classification. The experimental study of the HLFSRNN-MIL model is on two public CT datasets, namely, the Cancer Imaging Archive (TCIA) dataset on lung cancer and the China Consortium of Chest CT Image Investigation (CC-CCII) dataset on pneumonia. The experimental results show that the model exhibits better performance and accuracy. On the TCIA dataset, HLFSRNN-MIL with Residual Network (ResNet) as the feature extractor achieves an accuracy (ACC) of 0.992 and an area under curve (AUC) of 0.997. On the CC-CCII dataset, HLFSRNN-MIL achieves an ACC of 0.994 and an AUC of 0.997. Finally, compared with the existing methods, HLFSRNN-MIL has obvious advantages in all aspects. These experimental results demonstrate that HLFSRNN-MIL can effectively solve the disease problem in the field of 3D CT images.

Self-supervised tomographic image noise suppression via residual image prior network

Computed tomography (CT) denoising is a challenging task in medical imaging that has garnered considerable attention. Supervised networks require a lot of noisy-clean image pairs, which are always unavailable in clinical settings. Existing self-supervised algorithms for suppressing noise with paired noisy images have limitations, such as ignoring the residual between similar image pairs during training and insufficiently learning the spectrum information of images. In this study, we propose a Residual Image Prior Network (RIP-Net) to sufficiently model the residual between the paired similar noisy images. Our approach offers new insights into the field by addressing the limitations of existing methods. We first establish a mathematical theorem clarifying the non-equivalence between similar-image-based self-supervised learning and supervised learning. It helps us better understand the strengths and limitations of self-supervised learning. Secondly, we introduce a novel regularization term to model a low-frequency residual image prior. This can improve the accuracy and robustness of our model. Finally, we design a well-structured denoising network capable of exploring spectrum information while simultaneously sensing context messages. The network has dual paths for modeling high and low-frequency compositions in the raw noisy image. Additionally, context perception modules capture local and global interactions to produce high-quality images. The comprehensive experiments on preclinical photon-counting CT, clinical brain CT, and low-dose CT datasets, demonstrate that our RIP-Net is superior to other unsupervised denoising methods.