CT Datasets Research Articles

Fully automated CT analysis with a deep-learning based algorithm for pre-procedural planning in transcatheter aortic valve implantation

Abstract Background Pre-procedural cardiac computed tomography analysis has emerged to an essential tool in transcatheter aortic valve implantation (TAVI). It facilitates the valve choice and allows for optimal vascular access planning. For this purpose, software programs have been specifically developed to assist a fast and precise analysis of the generated data set in high quality. However, these software programs only assist the evaluator and are not able to perform a complete analysis on their own. Purpose We report the performance of a fully-automated, deep-learning based algorithm for pre-procedural CT analysis as compared to the current clinical standard. Methods Ninety-eight patients with symptomatic severe aortic stenosis undergoing TAVI were retrospectively enrolled. The pre-procedural data set was analyzed in two ways: - conventionally with a commercially available TAVI CT-analysis software by experiences users . - by a fully-automated CT-analysis platform with a deep-learning based algorithm. The current beta-version of the platform allows the determination of the annulus diameter, -area, -perimeter and the distance measurements of the coronary arteries to the aortic annulus. Hence, analyzable parameters were limited to the aforementioned, to ensure comparability. Statistical analysis: Mean, standard deviation, mean of difference and the interclass-correlation coefficient (ICC) were calculated and Bland-Altman plots created. Results The mean annulus diameter was 24.5±2.5mm (conventional) vs. 24.1±2.4 mm (deep learning). The mean of difference was 0.42±0.82mm (Bland-Altmann diagram. Figure 1). The ICC was 0.964 (0.925; 0.980), showing an excellent correlation between the two values. The mean annulus perimeter was 77.7±7.4mm (conventional) vs. 75.6±9.3mm (deep learning), showing a very good correlation of the means [mean of difference: 2.11±5.75mm; ICC: 0.852 (0.759; 0.906)]. The distance from the annulus to the left coronary artery was 14.0±3.2mm (conventional) vs. 12.6±2.8mm (deep learning). We depicted a good correlation between the two values [mean of difference: 1.45±2.52mm; ICC 0.736 (IQR 0.483; 0.850)]. The distance from the annulus to the right coronary artery was 17.1±2.7mm (conventional) vs. 16.5±3.2mm (deep learning), respectively. A very good correlation between the two values could be shown [mean of difference 0.57±2.2mm; ICC 0.822 (0.730; 0.882)], as well. Additionally, both methods visualize the measurements and allow manual adjustments (Figure 2). Conclusion In this retrospective analysis, deep-learning based analysis of peri-procedural derived CT data sets showed an very good correlation with conventional assessment. If results can be sustained in a bigger patient cohort and extended to more complex measurements, this artificial intelligence based fully-automated CT-analysis could emerge to a valuable alternative to conventional CT assessment in the pre-procedural planning for TAVI.Figure 1 - Bland-Altman plotFigure 2- Measurements by both methods

Semantic Segmentation of the Prostate Based on Onefold and Joint Multimodal Medical Images Using YOLOv4 and U-Net

Magnetic Resonance Imaging is increasing in importance in prostate cancer diagnosis due to the high accuracy and quality of the examination procedure. However, this process requires a time-consuming analysis of the results. Currently, machine vision is widely used in many areas. It enables automation and support in radiological studies. Successful detection of primary prostate tumors depends on the effective segmentation of the prostate itself. At times, a CT scan may be performed; alternatively, MRI may be the selected option. The data always reach a bottleneck stage. This paper presents the effective training of deep learning models to segment the prostate based on onefold and multimodal medical images. This approach supports the computer-aided diagnosis (CAD) system for radiologists as the first step in cancer exams. A comparison of two approaches designed for prostate segmentation is described. The first combines YOLOv4, the object detection neural network, and U-Net for a semantic segmentation based on onefold modality MRI images. The second presents the same method trained on multimodal images—a CT and MRI mixed dataset. The learning process was carried out in a cloud environment using GPU cards. The experiments are based on data from 120 patients who have undergone MRI and CT examinations. Several metrics evaluated the trained models. In the prostate semantic segmentation process, better results were achieved by mixed MRI with CT datasets. The best model achieved the value of 0.9685 for the Sørensen–Dice coefficient for the threshold value of 0.6.

The RSNA Abdominal Traumatic Injury CT (RATIC) Dataset.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The RSNA Abdominal Traumatic Injury CT (RATIC) dataset contains 4,274 abdominal CT studies with annotations related to traumatic injuries and is available at https://imaging.rsna.org/dataset/5 and https://www.kaggle.com/competitions/rsna-2023-abdominal-trauma-detection. ©RSNA, 2024.

Automated deep learning-based bone mineral density assessment for opportunistic osteoporosis screening using various CT protocols with multi-vendor scanners

This retrospective study examined the diagnostic efficacy of automated deep learning-based bone mineral density (DL-BMD) measurements for osteoporosis screening using 422 CT datasets from four vendors in two medical centers, encompassing 159 chest, 156 abdominal, and 107 lumbar spine datasets. DL-BMD values on L1 and L2 vertebral bodies were compared with manual BMD (m-BMD) measurements using Pearson’s correlation and intraclass correlation coefficients. Strong agreement was found between m-BMD and DL-BMD in total CT scans (r = 0.953, p < 0.001). The diagnostic performance of DL-BMD was assessed using receiver operating characteristic analysis for osteoporosis and low BMD by dual-energy x-ray absorptiometry (DXA) and m-BMD. Compared to DXA, DL-BMD demonstrated an AUC of 0.790 (95% CI 0.733–0.839) for low BMD and 0.769 (95% CI 0.710–0.820) for osteoporosis, with sensitivity, specificity, and accuracy of 80.8% (95% CI 74.2–86.3%), 56.3% (95% CI 43.4–68.6%), and 74.3% (95% CI 68.3–79.7%) for low BMD and 65.4% (95% CI 50.9–78.0%), 70.9% (95% CI 63.8–77.3%), and 69.7% (95% CI 63.5–75.4%) for osteoporosis, respectively. Compared to m-BMD, DL-BMD showed an AUC of 0.983 (95% CI 0.973–0.993) for low BMD and 0.972 (95% CI 0.958–0.987) for osteoporosis, with sensitivity, specificity, and accuracy of 97.3% (95% CI 94.5–98.9%), 85.2% (95% CI 78.8–90.3%), and 92.7% (95% CI 89.7–95.0%) for low BMD and 94.4% (95% CI 88.3–97.9%), 89.5% (95% CI 85.6–92.7%), and 90.8% (95% CI 87.6–93.4%) for osteoporosis, respectively. The DL-based method can provide accurate and reliable BMD assessments across diverse CT protocols and scanners.

Four-phase CT lesion recognition based on multi-phase information fusion framework and spatiotemporal prediction module

Multiphase information fusion and spatiotemporal feature modeling play a crucial role in the task of four-phase CT lesion recognition. In this paper, we propose a four-phase CT lesion recognition algorithm based on multiphase information fusion framework and spatiotemporal prediction module. Specifically, the multiphase information fusion framework uses the interactive perception mechanism to realize the channel-spatial information interactive weighting between multiphase features. In the spatiotemporal prediction module, we design a 1D deep residual network to integrate multiphase feature vectors, and use the GRU architecture to model the temporal enhancement information between CT slices. In addition, we employ CT image pseudo-color processing for data augmentation and train the whole network based on a multi-task learning framework. We verify the proposed network on a four-phase CT dataset. The experimental results show that the proposed network can effectively fuse the multi-phase information and model the temporal enhancement information between CT slices, showing excellent performance in lesion recognition.

Differential diagnosis between low-risk and high-risk thymoma: Comparison of diagnostic performance of radiologists with and without deep learning model.

There are few CT-based deep learning (DL) studies on thymoma according to the World Health Organization classification. To develop a CT-based DL model to distinguish between low-risk and high-risk thymoma and to compare the diagnostic performance of radiologists with and without the DL model. 159 patients with 160 thymomas were included. A fine-tuning VGG16 network model with Adam optimizer was used, followed by k-fold cross validation. The dataset consisted of three axial slices, including the maximum tumor size from the CT volume data. The data were augmented 50 times by rotation, zoom, shear, and horizontal/vertical flip. Three independent networks for the CT dataset were considered, and the result was determined by voting. Three radiologists independently diagnosed thymomas with and without the model. The area under the curve (AUC) of the diagnostic performance was compared using receiver operating characteristic analysis. Accuracy of the DL model was 71.3%. Diagnostic performance of the radiologists was as follows: AUC and accuracy without the DL model, 0.61-0.68 and 61.9%-69.3%; and with the DL model, 0.66-0.69 and 68.1%-70.0%, respectively. AUC of the diagnostic performance showed no significant differences between radiologists with and without the DL model. The DL model tended to increase the diagnostic accuracy, but AUC was not significantly improved. Diagnostic performance of the DL was comparable to that of radiologists. The DL model assistance tended to increase diagnostic accuracy.

A Novel Network for Low-Dose CT Denoising Based on Dual-Branch Structure and Multi-Scale Residual Attention.

Deep learning-based denoising of low-dose medical CT images has received great attention both from academic researchers and physicians in recent years, and has shown important application value in clinical practice. In this work, a novel two-branch and multi-scale residual attention-based network for low-dose CT image denoising is proposed. It adopts a two-branch framework structure, to extract and fuse image features at shallow and deep levels respectively, to recover image texture and structure information as much as possible. We propose the adaptive dynamic convolution block (ADCB) in the local information extraction layer. It can effectively extract the detailed information of low-dose CT denoising and enables the network to better capture the local details and texture features of the image, thereby improving the denoising effect and image quality. Multi-scale edge enhancement attention block (MEAB) is proposed in the global information extraction layer, to perform feature fusion through dilated convolution and a multi-dimensional attention mechanism. A multi-scale residual convolution block (MRCB) is proposed to integrate feature information and improve the robustness and generalization of the network. To demonstrate the effectiveness of our method, extensive comparison experiments are conducted and the performances evaluated on two publicly available datasets. Our model achieves 29.3004 PSNR, 0.8659 SSIM, and 14.0284 RMSE on the AAPM-Mayo dataset. It is evaluated by adding four different noise levels σ = 15, 30, 45, and 60 on the Qin_LUNG_CT dataset and achieves the best results. Ablation studies show that the proposed ADCB, MEAB, and MRCB modules improve the denoising performances significantly. The source code is available at https://github.com/Ye111-cmd/LDMANet .

Pulmonary emphysema: the assessment of lung perfusion with Dual-Energy CT and pulmonary scintigraphy.

To assess the correlation of quantitative data of pulmonary Perfused Blood Volume (PBV) on Dual-Energy CT (DECT) datasets in patients with moderate - severe Pulmonary Emphysema (PE) with Lung Perfusion Scintigraphy (LPS) as the reference standard. The secondary endpoints are the correlation between the CT densitometric analysis and the visual assessment of parenchymal destruction with PBV. Patients with moderate - severe PE candidate to Lung Volumetric Reduction (LVR), with available a pre-procedural LS and a contrast-enhanced DECT were retrospectively included. DECT studies were performed with a 3rd generation Dual-Source CT and the PBV was obtained with a 3-material decomposition algorithm. The CT densitometric analysis was performed with a dedicated commercial software (Pulmo3D). The Goddard Score was used for visual assessment. The perfusion LS were performed after the administration of albumin macroaggregates labeled with 99mTechnetium. The image revision was performed by two radiologists or nuclear medicine physicians blinded, respectively, to LS and DECT data. The statistical analysis was performed with nonparametric tests. Thirty-one patients (18 males, median age 69 y.o., interquartile range 62-71 y.o.) with moderate - severe PE (Median Goddard Score 14/20 and 31% of emphysematous parenchyma at quantitative CT) candidate to LVR were retrospectively included. The median enhancement on PBV was 17 HU. Significant correlation coefficients were demonstrated between lung PBV and LS, poor in apical regions (Rho = 0.1-0.2) and fair (Rho = 0.3-0.5) in middle and lower regions. No significant correlations were recorded between the CT densitometric analysis, the visual score, and the PBV. Lung perfusion with PBV on DECT is feasible in patients with moderate - severe PE candidate to LVR, and has a poor to fair agreement with LPS.

COVID-19 diagnosis based on CT scan image segmentation using multi-scale convolutional neural network

The COVID-19 pandemic continues to pose significant health challenges worldwide. While traditional methods like Reverse Transcription Polymerase Chain Reaction (RT-PCR) are widely used for diagnosis, they often suffer from limitations in speed and accessibility. This chapter proposes an automatic COVID-19 diagnosis technique using CT scan image segmentation, offering a promising alternative for early detection. The proposed method leverages Convolutional Neural Networks (CNNs), enhanced with a multi-scale approach, to capture more detailed semantic features and achieve high-quality segmentation despite challenges such as low image resolution, varying infection characteristics, and limited training data. To address the data scarcity issue, various data augmentation techniques, including scale variation, translation, and rotation, were applied to enhance the model's performance. The proposed CNN was evaluated using the COVID-19 CT dataset, achieving an overall accuracy of 96.85%, with COVID-19 sensitivity at 93.31%, Common Pneumonia sensitivity at 92.93%, and a true negative rate of 97.82%. These results demonstrate the effectiveness and efficiency of the proposed method in detecting COVID-19 at an early stage, reducing the need for human intervention, and accelerating the diagnostic process. Compared to existing methods, this approach offers significant improvements in accuracy and reliability, making it a valuable tool in the ongoing fight against the pandemic.

Accelerating segmentation of fossil CT scans through Deep Learning

Recent developments in Deep Learning have opened the possibility for automated segmentation of large and highly detailed CT scan datasets of fossil material. However, previous methodologies have required large amounts of training data to reliably extract complex skeletal structures. Here we present a method for automated Deep Learning segmentation to obtain high-fidelity 3D models of fossils digitally extracted from the surrounding rock, training the model with less than 1%-2% of the total CT dataset. This workflow has the capacity to revolutionise the use of Deep Learning to significantly reduce the processing time of such data and boost the availability of segmented CT-scanned fossil material for future research outputs. Our final Unet segmentation model achieved a validation Dice similarity of 0.96.

Comprehensive Clinical Usability-Oriented Contour Quality Evaluation for Deep Learning Auto-segmentation: Combining Multiple Quantitative Metrics Through Machine Learning

PurposeThe current commonly-used metrics for evaluating the quality of auto-segmented contours have limitations and do not always reflect the clinical usefulness of the contours. This work aims to develop a novel contour quality classification (CQC) method by combining multiple quantitative metrics for clinical usability-oriented contour quality evaluation for deep learning-based auto-segmentation (DLAS). MethodsThe CQC was designed to categorize contours on slices as acceptable, minor edit, or major edit based on the expected editing effort/time with supervised ensemble tree classification models using seven quantitative metrics. Organ-specific models were trained for five abdominal organs (pancreas, duodenum, stomach, small and large-bowels) using 50 MRI datasets. Twenty additional MRI and nine CT datasets were employed for testing. Inter-observer variation (IOV) was assessed among six observers and consensus labels were established through majority vote for evaluation. The CQC was also compared with a threshold-based baseline approach. ResultsFor the five organs, the average AUC was 0.982±0.01 and 0.979±0.01, the mean-accuracy was 95.8±1.7% and 94.3±2.1%, and the mean risk-rate was 0.8±0.4% and 0.7±0.5% for MRI and CT testing dataset, respectively. The CQC results closely matched the IOV results (mean-accuracy of 94.2±0.8% and 94.8±1.7%) and were significantly higher than those obtained using the threshold-based method (mean-accuracy of 80.0±4.7%, 83.8±5.2%, and 77.3±6.6% using one, two, and three metrics). ConclusionThe CQC models demonstrated high performance in classifying the quality of contour slices. This method can address the limitations of existing metrics and offers an intuitive and comprehensive solution for clinically oriented evaluation and comparison of DLAS systems.

Enhancing Medical Image Quality Using Fractional Order Denoising Integrated with Transfer Learning

In medical imaging, noise can significantly obscure critical details, complicating diagnosis and treatment. Traditional denoising techniques often struggle to maintain a balance between noise reduction and detail preservation. To address this challenge, we propose an “Efficient Transfer-Learning-Based Fractional Order Image Denoising Approach in Medical Image Analysis (ETLFOD)” method. Our approach uniquely integrates transfer learning with fractional order techniques, leveraging pre-trained models such as DenseNet121 to adapt to the specific needs of medical image denoising. This method enhances denoising performance while preserving essential image details. The ETLFOD model has demonstrated superior performance compared to state-of-the-art (SOTA) techniques. For instance, our DenseNet121 model achieved an accuracy of 98.01%, precision of 98%, and recall of 98%, significantly outperforming traditional denoising methods. Specific results include a 95% accuracy, 98% precision, 99% recall, and 96% F1-score for MRI brain datasets, and an 88% accuracy, 91% precision, 95% recall, and 88% F1-score for COVID-19 lung data. X-ray pneumonia results in the lung CT dataset showed a 92% accuracy, 97% precision, 98% recall, and 93% F1-score. It is important to note that while we report performance metrics in this paper, the primary evaluation of our approach is based on the comparison of original noisy images with the denoised outputs, ensuring a focus on image quality enhancement rather than classification performance.

VSmTrans: A hybrid paradigm integrating self-attention and convolution for 3D medical image segmentation

PurposeVision Transformers recently achieved a competitive performance compared with CNNs due to their excellent capability of learning global representation. However, there are two major challenges when applying them to 3D image segmentation: i) Because of the large size of 3D medical images, comprehensive global information is hard to capture due to the enormous computational costs. ii) Insufficient local inductive bias in Transformers affects the ability to segment detailed features such as ambiguous and subtly defined boundaries. Hence, to apply the Vision Transformer mechanism in the medical image segmentation field, the above challenges need to be overcome adequately. MethodsWe propose a hybrid paradigm, called Variable-Shape Mixed Transformer (VSmTrans), that integrates self-attention and convolution and can enjoy the benefits of free learning of both complex relationships from the self-attention mechanism and the local prior knowledge from convolution. Specifically, we designed a Variable-Shape self-attention mechanism, which can rapidly expand the receptive field without extra computing cost and achieve a good trade-off between global awareness and local details. In addition, the parallel convolution paradigm introduces strong local inductive bias to facilitate the ability to excavate details. Meanwhile, a pair of learnable parameters can automatically adjust the importance of the above two paradigms. Extensive experiments were conducted on two public medical image datasets with different modalities: the AMOS CT dataset and the BraTS2021 MRI dataset. ResultsOur method achieves the best average Dice scores of 88.3 % and 89.7 % on these datasets, which are superior to the previous state-of-the-art Swin Transformer-based and CNN-based architectures. A series of ablation experiments were also conducted to verify the efficiency of the proposed hybrid mechanism and the components and explore the effectiveness of those key parameters in VSmTrans. ConclusionsThe proposed hybrid Transformer-based backbone network for 3D medical image segmentation can tightly integrate self-attention and convolution to exploit the advantages of these two paradigms. The experimental results demonstrate our method's superiority compared to other state-of-the-art methods. The hybrid paradigm seems to be most appropriate to the medical image segmentation field. The ablation experiments also demonstrate that the proposed hybrid mechanism can effectively balance large receptive fields with local inductive biases, resulting in highly accurate segmentation results, especially in capturing details. Our code is available at https://github.com/qingze-bai/VSmTrans.

Interactive Multi-scale Fusion: Advancing Brain Tumor Detection Through Trans-IMSM Model.

Multi-modal medical image (MI) fusion assists in generating collaboration images collecting complement features through the distinct images of several conditions. The images help physicians to diagnose disease accurately. Hence, this research proposes a novel multi-modal MI fusion modal named guided filter-based interactive multi-scale and multi-modal transformer (Trans-IMSM) fusion approach to develop high-quality computed tomography-magnetic resonance imaging (CT-MRI) fused images for brain tumor detection. This research utilizes the CT and MRI brain scan dataset to gather the input CT and MRI images. At first, the data preprocessing is carried out to preprocess these input images to improve the image quality and generalization ability for further analysis. Then, these preprocessed CT and MRI are decomposed into detail and base components utilizing the guided filter-based MI decomposition approach. This approach involves two phases: such as acquiring the image guidance and decomposing the images utilizing the guided filter. A canny operator is employed to acquire the image guidance comprising robust edge for CT and MRI images, and the guided filter is applied to decompose the guidance and preprocessed images. Then, by applying the Trans-IMSM model, fuse the detail components, while a weighting approach is used for the base components. The fused detail and base components are subsequently processed through a gated fusion and reconstruction network, and the final fused images for brain tumor detection are generated. Extensive tests are carried out to compute the Trans-IMSM method's efficacy. The evaluation results demonstrated the robustness and effectiveness, achieving an accuracy of 98.64% and an SSIM of 0.94.

Dual-branch Transformer for semi-supervised medical image segmentation.

In recent years, the use of deep learning for medical image segmentation has become a popular trend, but its development also faces some challenges. Firstly, due to the specialized nature of medical data, precise annotation is time-consuming and labor-intensive. Training neural networks effectively with limited labeled data is a significant challenge in medical image analysis. Secondly, convolutional neural networks commonly used for medical image segmentation research often focus on local features in images. However, the recognition of complex anatomical structures or irregular lesions often requires the assistance of both local and global information, which has led to a bottleneck in its development. Addressing these two issues, in this paper, we propose a novel network architecture. We integrate a shift window mechanism to learn more comprehensive semantic information and employ a semi-supervised learning strategy by incorporating a flexible amount of unlabeled data. Specifically, a typical U-shaped encoder-decoder structure is applied to obtain rich feature maps. Each encoder is designed as a dual-branch structure, containing Swin modules equipped with windows of different size to capture features of multiple scales. To effectively utilize unlabeled data, a level set function is introduced to establish consistency between the function regression and pixel classification. We conducted experiments on the COVID-19 CT dataset and DRIVE dataset and compared our approach with various semi-supervised and fully supervised learning models. On the COVID-19 CT dataset, we achieved a segmentation accuracy of up to 74.56%. Our segmentation accuracy on the DRIVE dataset was 79.79%. The results demonstrate the outstanding performance of our method on several commonly used evaluation metrics. The high segmentation accuracy of our model demonstrates that utilizing Swin modules with different window sizes can enhance the feature extraction capability of the model, and the level set function can enable semi-supervised models to more effectively utilize unlabeled data. This provides meaningful insights for the application of deep learning in medical image segmentation. Our code will be released once the manuscript is accepted for publication.

First implementation of artificial intelligence empowered all-in-one radiotherapy workflow for nasopharyngeal carcinoma.

134 Background: To establish an artificial intelligence (AI)-empowered All-In-One (AIO) workflow for providing one-stop radiotherapy to patients with nasopharyngeal carcinoma (NPC), and evaluate its feasibility and performance. Methods: The NPC-specific AIO workflow operates on a CT-integrated linac and integrates AI contouring and AI planning modules. A 3D U-net was employed for contours generation and 3D dose distribution. Knowledge-based planning approach and a protocol-based approach were used for plan optimization. MRI datasets with contours of primary gross tumors, CT datasets with contours of targets and organs at risk, and radiotherapy treatment planning datasets were collected from 877, 139, and 243 patients, respectively, for the training, validation, and testing of AI contouring and planning models. The NPC-specific AIO workflow underwent real-world clinical testing with an end-to-end evaluation involving 120 patients with NPC. The technical characteristics, implementation procedures and performance of AIO workflow were described and evaluated. Results: From March 2022 to October 2023, 120 patients with newly-diagnosed, non-metastatic NPC underwent AIO workflow, and 117 patients completed it in a median time of 23.2 min (range: 16.3 to 45.8 min). Median translation motions were 0.2 mm (CT scan to planning approval) and 0.1 mm (during beam delivery). AI-generated contours required little revision for clinical target volume (CTV1) and organs at risk (OARs), minor revision for cervical lymph nodes (GTVn) and clinical target volume (CTV2), with median Dice similarity coefficients (DSCs) of 0.98 and 0.94, respectively; more revision for GTVp, with a median DSC of 0.84. Of the 117 AI-generated plannings, 108 (92.3%) passed after initial auto-optimization. Volumes receiving ≥ 100% of the prescribed dose for all planning target volumes was ≥ 97.8%. Mean dosimetric parameters met dose constraints for all OARs except the thyroid and submandibulars. One patient died from acute renal failure after 10 fractions of radiotherapy. At week 12 after radiotherapy completion, 115 patients achieved complete response;1 had stable disease. Grade 3-4 acute effects were reported by 54 of 115 patients (36%). Conclusions: We successfully established an AI-empowered AIO workflow for initial radiotherapy of NPC, confirming its feasibility and safety for clinical application.

Age-related changes in mitral annular disjunction: A retrospective analysis using enhanced cardiac CT

AimsThe current recognition of mitral annular disjunction (MAD) as an anatomical abnormality potentially associated with ventricular arrhythmias has sparked controversy regarding its prevalence and clinical implications. This study aimed to investigate the prevalence and extent of MAD in individuals with no significant structural abnormalities involving the left heart using enhanced cardiac CT, while also exploring potential factors, such as age, that may be associated with MAD. MethodsSystolic datasets of cardiac CT from 742 subjects were retrospectively included. MAD was determined by rotating orthogonal multiplanar reconstruction images around the central axis of the mitral annulus. The maximal distance of disjunction (DMAD) and segments involved (SI, 0 to 5 basal segments at left ventricular wall) was quantified to evaluate the extent of separation. ResultsIn total, 449 (60.5%) had MAD. Subjects with MAD were significantly older (51.3 ± 19.9 years vs. 29.6 ± 20.3 years, P < 0.001). Age was found to be an independent relevant factor for MAD (OR = 1.059; 95%CI: 1.033, 1.085; P < 0.001). Subjects with MAD were then divided into 4 subgroups (G1: ≤20 years, G2: 21–40 years, G3: 41–60 years, G4: ≥61 years). DMAD and SI of each age subgroup were 1.9 ± 0.2 mm, 2.0 ± 1.2 (G1, n = 36), 2.7 ± 0.8 mm, 2.9 ± 1.3 (G2, n = 51), 3.0 ± 0.8 mm, 3.0 ± 1.3 (G3, n = 183), and 3.0 ± 1.0 mm, 3.7 ± 1.1 (G4, n = 179). Age was an independent relevant factor associated with DMAD (R2 = 0.132; β = 0.014; 95%CI: 0.004, 0.024; P = 0.007) and SI (OR = 1.030; 95%CI: 1.005, 1.055; P = 0.016). ConclusionsMAD is a common finding on cardiac CT. Its prevalence and extent increase with age.

Optimized pancreatic tumor imaging diagnosis using deep neural network

In the last few decades, poor prognosis of pancreatic tumor has been an issue of concern in spite of the recent advancements in the different imaging modalities. Small size, similar attenuation to normal sized pancreas or concealed position of pancreas during CT scans are the factors that leads to failure in early diagnosis of pancreatic tumor. In this research, an organized framework is proposed for monitoring, classifying and diagnosing of pancreatic tumor. The suggested model integrates the technique of Deep Neural Network (DNN) and optimistic aspects of nature-inspired algorithms; this model aims to achieve a harmonious combination of both the techniques. The proposed model examines the medical images obtained from CT scans for the presence of pancreatic tumor using SSA-ML image segmentation on CT dataset. Evaluation of suggested model in comparison to other contemporary models IDLDMS, ODL, weighted KLM, Kernel-ELM, and ELM models is also performed in reference to sensitivity, specificity, accuracy and F1 score. The classification accuracy of our model is 99.44 % which reflects its supremacy over other recent models.

Lack of standardisation in the management of complex tibial plateau fractures: a multicentre experience.

In recent years, the trauma mechanisms and fracture types in tibial plateau fractures (TPF) have changed. At the same time, treatment strategies have expanded with the establishment of new classification systems, extension of diagnostics and surgical strategies. Evidence-based recommendations for treatment strategies are rare. The aim of this study is to assess the extent of standardization in the treatment of complex TPF. For the study, specialists in trauma surgery/orthopaedics were presented thin-slice CT data sets of three complex TPFs including 3D reconstructions. A standardized questionnaire on fracture morphology and planned treatment strategy was then completed. A total of 23 surgeons from 7 hospitals (Trauma center levels I-III) were included. All three fractures were most frequently classified as Schatzker type V (fracture I: 52.2%, II: 56.5%, III: 60%). Averaged over all three fractures, 55% of the respondents chose the same patient positioning. The combination of a posteromedial and anterolateral approach was the most frequently chosen approach at 42.7%. Double plating was favored for the surgical treatment of all fractures (70.7%). Preoperative MRI, extended approaches and intraoperative fraturoscopy were significantly more common in level I trauma centres. There are major differences in the management of complex TPF. 360° treatment is carried out in all departments regardless of the level of care, but without further standardization in terms of preoperative imaging, classification, initial treatment, approach, fixation and intraoperative imaging. There are major differences within the departments with different level of care.

Pixel embedding for grayscale medical image classification

In our paper, we present an extension of text embedding architectures for grayscale medical image classification. We introduce a mechanism that combines n-gram features with an efficient pixel flattening technique to preserve spatial information during feature representation generation. Our approach involves flattening all pixels in grayscale medical images using a combination of column-wise, row-wise, diagonal-wise, and anti-diagonal-wise orders. This ensures that spatial dependencies are captured effectively in the feature representations. To evaluate the effectiveness of our method, we conducted a benchmark using 5 grayscale medical image datasets of varying sizes and complexities. 10-fold cross-validation showed that our approach achieved test accuracy score of 99.92 % on the Medical MNIST dataset, 90.06 % on the Chest X-ray Pneumonia dataset, 96.94 % on the Curated Covid CT dataset, 79.11 % on the MIAS dataset and 93.17 % on the Ultrasound dataset. The framework and reproducible code can be found on GitHub at https://github.com/xizhou/pixel_embedding.