scholarly journals Diagnosis of COVID-19 Infection Using Three-Dimensional Semantic Segmentation and Classification of Computed Tomography Images

2021 ◽  
Vol 68 (2) ◽  
pp. 2451-2467
Author(s):  
Javaria Amin ◽  
Muhammad Sharif ◽  
Muhammad Almas Anjum ◽  
Yunyoung Nam ◽  
Seifedine Kadry ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Three Dimensional ◽  
Semantic Segmentation ◽  
Computed Tomography Images

scholarly journals Immersive 3D virtual reality imaging in planning minimally invasive and complex adult cardiac surgery

2020 ◽  
Vol 1 (1) ◽  
pp. 62-70
Author(s):  
Amir H Sadeghi ◽  
Wouter Bakhuis ◽  
Frank Van Schaagen ◽  
Frans B S Oei ◽  
Jos A Bekkers ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Virtual Reality ◽  
Cardiac Surgery ◽  
Heart Surgery ◽  
Preoperative Planning ◽  
Operating Time ◽  
Three Dimensional ◽  
Cardiothoracic Surgery ◽  
Planning Tool ◽  
Computed Tomography Images

Abstract Aims Increased complexity in cardiac surgery over the last decades necessitates more precise preoperative planning to minimize operating time, to limit the risk of complications during surgery and to aim for the best possible patient outcome. Novel, more realistic, and more immersive techniques, such as three-dimensional (3D) virtual reality (VR) could potentially contribute to the preoperative planning phase. This study shows our initial experience on the implementation of immersive VR technology as a complementary research-based imaging tool for preoperative planning in cardiothoracic surgery. In addition, essentials to set up and implement a VR platform are described. Methods Six patients who underwent cardiac surgery at the Erasmus Medical Center, Rotterdam, The Netherlands, between March 2020 and August 2020, were included, based on request by the surgeon and availability of computed tomography images. After 3D VR rendering and 3D segmentation of specific structures, the reconstruction was analysed via a head mount display. All participating surgeons (n = 5) filled out a questionnaire to evaluate the use of VR as preoperative planning tool for surgery. Conclusion Our study demonstrates that immersive 3D VR visualization of anatomy might be beneficial as a supplementary preoperative planning tool for cardiothoracic surgery, and further research on this topic may be considered to implement this innovative tool in daily clinical practice. Lay summary Over the past decades, surgery on the heart and vessels is becoming more and more complex, necessitating more precise and accurate preoperative planning. Nowadays, operative planning is feasible on flat, two-dimensional computer screens, however, requiring a lot of spatial and three-dimensional (3D) thinking of the surgeon. Since immersive 3D virtual reality (VR) is an upcoming imaging technique with promising results in other fields of surgery, we aimed in this study to explore the additional value of this technique in heart surgery. Our surgeons planned six different heart operations by visualizing computed tomography scans with a dedicated VR headset, enabling them to visualize the patient’s anatomy in an immersive and 3D environment. The outcomes of this preliminary study are positive, with a much more reality-like simulation for the surgeon. In such, VR could potentially be beneficial as a preoperative planning tool for complex heart surgery.

Total Wrist Arthroplasty Alignment and Its Potential Association with Clinical Outcomes

2021 ◽  
Author(s):  
Bardiya Akhbari ◽  
Kalpit N. Shah ◽  
Amy M. Morton ◽  
Janine Molino ◽  
Douglas C. Moore ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Clinical Outcomes ◽  
Three Dimensional ◽  
Radial Component ◽  
Single Type ◽  
Radiographic Images ◽  
Computed Tomography Images ◽  
Total Wrist Arthroplasty ◽  
Flexion Extension ◽  
Wrist Arthroplasty

Abstract Purpose There is a lack of quantitative research that describes the alignment and, more importantly, the effects of malalignment on total wrist arthroplasty (TWA). The main goal of this pilot study was to assess the alignment of TWA components in radiographic images and compare them with measures computed by three-dimensional analysis. Using these measures, we then determined if malalignment is associated with range of motion (ROM) or clinical outcomes (PRWHE, PROMIS, QuickDash, and grip strength). Methods Six osteoarthritic patients with a single type of TWA were recruited. Radiographic images, computed tomography images, and clinical outcomes of the wrists were recorded. Using posteroanterior and lateral radiographs, alignment measurements were defined for the radial and carpal components. Radiographic measurements were validated with models reconstructed from computed tomography images using Bland–Altman analysis. Biplanar videoradiography (<1mm and <1 degree accuracy) was used to capture and compute ROM of the TWA components. Linear regression assessed the associations between alignment and outcomes. Results Radiographic measures had a 95% limit-of-agreement (mean difference ±  1.96 × SD) of 3 degrees and 3mm with three-dimensional values, except for the measures of the carpal component in the lateral view. In our small cohort, wrist flexion–extension and radial–ulnar deviation were correlated with volar–dorsal tilt and volar–dorsal offset of the radial component and demonstrated a ROM increase of 3.7 and 1.6 degrees per degree increase in volar tilt, and 10.8 and 4.2 degrees per every millimeter increase in volar offset. The carpal component's higher volar tilt was also associated with improvements in patient-reported pain. Conclusions We determined metrics describing the alignment of TWA, and found the volar tilt and volar offset of the radial component could potentially influence the replaced wrist's ROM. Clinical Relevance TWA component alignment can be measured reliably in radiographs, and may be associated with clinical outcomes. Future studies must evaluate its role in a larger cohort.

scholarly journals Three-dimensional assessment of the anterior and inferior loop of the inferior alveolar nerve using computed tomography images in patients with and without mandibular asymmetry

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Jae-Young Kim ◽  
Michael D. Han ◽  
Kug Jin Jeon ◽  
Jong-Ki Huh ◽  
Kwang-Ho Park
Keyword(s):  
Computed Tomography ◽  
Symmetry Group ◽  
Three Dimensional ◽  
Inferior Alveolar Nerve ◽  
Mental Foramen ◽  
3D Analysis ◽  
Mandibular Asymmetry ◽  
Computed Tomography Images ◽  
Significant Difference ◽  
Mandibular Body

Abstract Background The purpose of this study was to investigate the differences in configuration and dimensions of the anterior loop of the inferior alveolar nerve (ALIAN) in patients with and without mandibular asymmetry. Method Preoperative computed tomography images of patients who had undergone orthognathic surgery from January 2016 to December 2018 at a single institution were analyzed. Subjects were classified into two groups as “Asymmetry group” and “Symmetry group”. The distance from the most anterior and most inferior points of the ALIAN (IANant and IANinf) to the vertical and horizontal reference planes were measured (dAnt and dInf). The distance from IANant and IANinf to the mental foramen were also calculated (dAnt_MF and dInf_MF). The length of the mandibular body and symphysis area were measured. All measurements were analyzed using 3D analysis software. Results There were 57 total eligible subjects. In the Asymmetry group, dAnt and dAnt_MF on the non-deviated side were significantly longer than the deviated side (p < 0.001). dInf_MF on the non-deviated side was also significantly longer than the deviated side (p = 0.001). Mandibular body length was significantly longer on the non-deviated side (p < 0.001). There was no significant difference in length in the symphysis area (p = 0.623). In the Symmetry group, there was no difference between the left and right sides for all variables. Conclusion In asymmetric patients, there is a difference tendency in the ALIAN between the deviated and non-deviated sides. In patients with mandibular asymmetry, this should be considered during surgery in the anterior mandible.

scholarly journals Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 893
Author(s):  
Yazan Qiblawey ◽  
Anas Tahir ◽  
Muhammad E. H. Chowdhury ◽  
Amith Khandakar ◽  
Serkan Kiranyaz ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Early Stage ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Lung Region ◽  
Computed Tomography Images ◽  
Feature Pyramid ◽  
Severity Levels

Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder–Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively.

Automated Pancreas Segmentation And Volumetry Using Deep Neural Network On Computed Tomography

2021 ◽  
Author(s):  
Sang-Heon Lim ◽  
Young Jae Kim ◽  
Yeon-Ho Park ◽  
Doojin Kim ◽  
Kwang Gi Kim ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Automatic Segmentation ◽  
External Validation ◽  
Three Dimensional ◽  
Semantic Segmentation ◽  
Quantitative Information ◽  
Similarity Coefficients ◽  
Internal Validation ◽  
Pancreas Segmentation

Abstract Pancreas segmentation is necessary for observing lesions, analyzing anatomical structures, and predicting patient prognosis. Therefore, various studies have designed segmentation models based on convolutional neural networks for pancreas segmentation. However, the deep learning approach is limited by a lack of data, and studies conducted on a large computed tomography dataset are scarce. Therefore, this study aims to perform deep-learning-based semantic segmentation on 1,006 participants and evaluate the automatic segmentation performance of the pancreas via four individual three-dimensional segmentation networks. In this study, we performed internal validation with 1,006 patients and external validation using the Cancer Imaging Archive (TCIA) pancreas dataset. We obtained mean precision, recall, and dice similarity coefficients of 0.869, 0.842, and 0.842, respectively, for internal validation via a relevant approach among the four deep learning networks. Using the external dataset, the deep learning network achieved mean precision, recall, and dice similarity coefficients of 0.779, 0.749, and 0.735, respectively. We expect that generalized deep-learning-based systems can assist clinical decisions by providing accurate pancreatic segmentation and quantitative information of the pancreas for abdominal computed tomography.

Sign in / Sign up

Export Citation Format

Share Document