scholarly journals Magnetic resonance imaging–based synthetic computed tomography of the lumbar spine for surgical planning: a clinical proof-of-concept

2021 ◽  
Vol 50 (1) ◽  
pp. E13
Author(s):  
Victor E. Staartjes ◽  
Peter R. Seevinck ◽  
W. Peter Vandertop ◽  
Marijn van Stralen ◽  
Marc L. Schröder
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Lumbar Spine ◽  
Surgical Planning ◽  
Visual Inspection ◽  
Ct Scans ◽  
Lumbar Spine Surgery ◽  
Proof Of Concept ◽  
Acquisition Protocol ◽  
Synthetic Ct

OBJECTIVEComputed tomography scanning of the lumbar spine incurs a radiation dose ranging from 3.5 mSv to 19.5 mSv as well as relevant costs and is commonly necessary for spinal neuronavigation. Mitigation of the need for treatment-planning CT scans in the presence of MRI facilitated by MRI-based synthetic CT (sCT) would revolutionize navigated lumbar spine surgery. The authors aim to demonstrate, as a proof of concept, the capability of deep learning–based generation of sCT scans from MRI of the lumbar spine in 3 cases and to evaluate the potential of sCT for surgical planning.METHODSSynthetic CT reconstructions were made using a prototype version of the “BoneMRI” software. This deep learning–based image synthesis method relies on a convolutional neural network trained on paired MRI-CT data. A specific but generally available 4-minute 3D radiofrequency-spoiled T1-weighted multiple gradient echo MRI sequence was supplemented to a 1.5T lumbar spine MRI acquisition protocol.RESULTSIn the 3 presented cases, the prototype sCT method allowed voxel-wise radiodensity estimation from MRI, resulting in qualitatively adequate CT images of the lumbar spine based on visual inspection. Normal as well as pathological structures were reliably visualized. In the first case, in which a spiral CT scan was available as a control, a volume CT dose index (CTDIvol) of 12.9 mGy could thus have been avoided. Pedicle screw trajectories and screw thickness were estimable based on sCT findings.CONCLUSIONSThe evaluated prototype BoneMRI method enables generation of sCT scans from MRI images with only minor changes in the acquisition protocol, with a potential to reduce workflow complexity, radiation exposure, and costs. The quality of the generated CT scans was adequate based on visual inspection and could potentially be used for surgical planning, intraoperative neuronavigation, or for diagnostic purposes in an adjunctive manner.

scholarly journals Confirmation of accuracy/inaccuracy of lumbar pedicle screw placement using postoperative computed tomography

2021 ◽  
Vol 12 ◽  
pp. 518
Author(s):  
Mohamed M. Arnaout ◽  
Magdy O. ElSheikh ◽  
Mansour A. Makia
Keyword(s):  
Computed Tomography ◽  
Lumbar Spine ◽  
Pedicle Screw ◽  
Pedicle Screws ◽  
Operative Intervention ◽  
Screw Placement ◽  
Lumbar Spine Surgery ◽  
Pedicle Screw Placement ◽  
Lumbar Pedicle ◽  
Ct Studies

Background: Transpedicular screws are extensively utilized in lumbar spine surgery. The placement of these screws is typically guided by anatomical landmarks and intraoperative fluoroscopy. Here, we utilized 2-week postoperative computed tomography (CT) studies to confirm the accuracy/inaccuracy of lumbar pedicle screw placement in 145 patients and correlated these findings with clinical outcomes. Methods: Over 6 months, we prospectively evaluated the location of 612 pedicle screws placed in 145 patients undergoing instrumented lumbar fusions addressing diverse pathology with instability. Routine anteroposterior and lateral plain radiographs were obtained 48 h after the surgery, while CT scans were obtained at 2 postoperative weeks (i.e., ideally these should have been performed intraoperatively or within 24–48 h of surgery). Results: Of the 612 screws, minor misplacement of screws (≤2 mm) was seen in 104 patients, moderate misplacement in 34 patients (2–4 mm), and severe misplacement in 7 patients (>4 mm). Notably, all the latter 7 (4.8% of the 145) patients required repeated operative intervention. Conclusion: Transpedicular screw insertion in the lumbar spine carries the risks of pedicle medial/lateral violation that is best confirmed on CT rather than X-rays/fluoroscopy alone. Here, we additional found 7 patients (4.8%) who with severe medial/lateral pedicle breach who warranting repeated operative intervention. In the future, CT studies should be performed intraoperatively or within 24–48 h of surgery to confirm the location of pedicle screws and rule in our out medial or lateral pedicle breaches.

scholarly journals A novel deep learning-based quantification of serial chest computed tomography in Coronavirus Disease 2019 (COVID-19)

2020 ◽  
Author(s):  
Feng Pan ◽  
Lin Li ◽  
Bo Liu ◽  
Tianhe Ye ◽  
Lingli Li ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Quantitative Computed Tomography ◽  
Pulmonary Involvement ◽  
Chest Ct ◽  
Estimation Methods ◽  
Ct Scans ◽  
Severe Group ◽  
Conventional Ct ◽  
Spearman’S Correlation

Abstract Objectives: This study aims to explore and compare a novel deep learning-based quantification with the conventional semi-quantitative computed tomography (CT) scoring for the serial chest CT scans of COVID-19. Materials and Methods: 95 patients with confirmed COVID-19 and a total of 465 serial chest CT scans were involved, including 61 moderate patients (moderate group, 319 chest CT scans) and 34 severe patients (severe group, 146 chest CT scans). Conventional CT scoring and deep learning-based quantification were performed for all chest CT scans for two study goals: 1. Correlation between these two estimations; 2. Exploring the dynamic patterns using these two estimations between moderate and severe groups.Results: The Spearman’s correlation coefficient between these two estimation methods was 0.920 (p<0.001). predicted pulmonary involvement (CT score and percent of pulmonary lesions calculated using deep learning-based quantification) increased more rapidly and reached a higher peak on 23rd days from symptom onset in severe group, which reached a peak on 18th days in moderate group with faster absorption of the lesions. Conclusions: The deep learning-based quantification for COVID-19 showed a good correlation with the conventional CT scoring and demonstrated a potential benefit in the estimation of disease severities of COVID-19.

Selective Densitometry of the Lumbar Spine

2013 ◽  
Author(s):  
Bryant Chu ◽  
Jeremi Leasure ◽  
Dimitriy Kondrashov
Keyword(s):  
Computed Tomography ◽  
Bone Mineral Density ◽  
Lumbar Spine ◽  
Lumbar Vertebrae ◽  
Ct Scans ◽  
Screw Loosening ◽  
Mineral Density ◽  
Hounsfield Units ◽  
Pedicle Screw Loosening ◽  
Posterior Elements

Bone mineral density (BMD) has been identified as a major factor in spine construct strength, with failures resulting in pedicle screw loosening and pullout2. Computed tomography (CT) scans have been shown to effectively measure BMD1,4. Previous research has utilized this linear correlation of CT Hounsfield Units (HU) to BMD in order to determine BMD as a function of anatomic location within cervical vertebrae1; however, the lumbar spine has not yet been reported on. The goal of this study was to describe BMD of anatomical regions within lumbar vertebrae using the correlation between HU and BMD. It was hypothesized that posterior elements of the spine would exhibit significantly different BMD than the vertebral body. This was tested through means comparison of BMD for each anatomical region.

scholarly journals Domain-Adaptive Artificial Intelligence-Based Model for Personalized Diagnosis of Trivial Lesions Related to COVID-19 in Chest Computed Tomography Scans

2021 ◽  
Vol 11 (10) ◽  
pp. 1008
Author(s):  
Muhammad Owais ◽  
Na Rae Baek ◽  
Kang Ryoung Park
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
State Of The Art ◽  
Area Under The Curve ◽  
Ground Glass Opacity ◽  
Visual Assessment ◽  
Ct Scans ◽  
Execution Speed ◽  
Ct Data ◽  
Personalized Diagnosis

Background: Early and accurate detection of COVID-19-related findings (such as well-aerated regions, ground-glass opacity, crazy paving and linear opacities, and consolidation in lung computed tomography (CT) scan) is crucial for preventive measures and treatment. However, the visual assessment of lung CT scans is a time-consuming process particularly in case of trivial lesions and requires medical specialists. Method: A recent breakthrough in deep learning methods has boosted the diagnostic capability of computer-aided diagnosis (CAD) systems and further aided health professionals in making effective diagnostic decisions. In this study, we propose a domain-adaptive CAD framework, namely the dilated aggregation-based lightweight network (DAL-Net), for effective recognition of trivial COVID-19 lesions in CT scans. Our network design achieves a fast execution speed (inference time is 43 ms on a single image) with optimal memory consumption (almost 9 MB). To evaluate the performances of the proposed and state-of-the-art models, we considered two publicly accessible datasets, namely COVID-19-CT-Seg (comprising a total of 3520 images of 20 different patients) and MosMed (including a total of 2049 images of 50 different patients). Results: Our method exhibits average area under the curve (AUC) up to 98.84%, 98.47%, and 95.51% for COVID-19-CT-Seg, MosMed, and cross-dataset, respectively, and outperforms various state-of-the-art methods. Conclusions: These results demonstrate that deep learning-based models are an effective tool for building a robust CAD solution based on CT data in response to present disaster of COVID-19.

scholarly journals Deep Learning for Lung Cancer Nodules Detection and Classification in CT Scans

AI ◽  
2020 ◽  
Vol 1 (1) ◽  
pp. 28-67 ◽  
Author(s):  
Diego Riquelme ◽  
Moulay Akhloufi
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Deep Learning ◽  
Malignant Tumors ◽  
Lung Cancer Screening ◽  
Ct Scans ◽  
Learning Approaches ◽  
Cad Systems ◽  
Detection Systems ◽  
Learning Techniques

Detecting malignant lung nodules from computed tomography (CT) scans is a hard and time-consuming task for radiologists. To alleviate this burden, computer-aided diagnosis (CAD) systems have been proposed. In recent years, deep learning approaches have shown impressive results outperforming classical methods in various fields. Nowadays, researchers are trying different deep learning techniques to increase the performance of CAD systems in lung cancer screening with computed tomography. In this work, we review recent state-of-the-art deep learning algorithms and architectures proposed as CAD systems for lung cancer detection. They are divided into two categories—(1) Nodule detection systems, which from the original CT scan detect candidate nodules; and (2) False positive reduction systems, which from a set of given candidate nodules classify them into benign or malignant tumors. The main characteristics of the different techniques are presented, and their performance is analyzed. The CT lung datasets available for research are also introduced. Comparison between the different techniques is presented and discussed.

scholarly journals Conned by Conn’s Syndrome

2008 ◽  
Vol 12 (2) ◽  
pp. 38
Author(s):  
F Ismail ◽  
Z Lockhat ◽  
S Ellemdin ◽  
L Van der Linde
Keyword(s):  
Computed Tomography ◽  
Surgical Planning ◽  
Ct Scans ◽  
Rare Entity ◽  
Hypertensive Patients ◽  
Conn’S Syndrome ◽  
Aldosterone Producing Adenoma

Conn’s Syndrome is a rare entity amongst hypertensive patients and imaging of the aldosterone producing adenoma (APA) can prove challenging but is none the less very important for surgical planning and cure. We present two patients with MRI confirmation of APA with negative and equivocal computed tomography (CT) scans.

scholarly journals An Objective and Reliable Method for Identifying Sarcopenia in Lumbar Spine Surgery Patients: Using Morphometric Measurements on Computed Tomography Imaging

2020 ◽  
Vol 14 (6) ◽  
pp. 814-820
Author(s):  
Marko Tomov ◽  
Mohammed Ali Alvi ◽  
Mohamed Elminawy ◽  
Bradford Currier ◽  
Michael Yaszemski ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lumbar Spine ◽  
Muscle Mass ◽  
Spine Surgery ◽  
Reliable Method ◽  
Area Ratio ◽  
Lumbar Spine Surgery ◽  
Morphometric Measurements ◽  
Muscle Area ◽  
Paravertebral Muscle

Study Design: A retrospective observational study.Purpose: Establish a quantifiable and reproducible measure of sarcopenia in patients undergoing lumbar spine surgery based on morphometric measurements from readily available preoperative computed tomography (CT) imaging. Overview of Literature: Sarcopenia—the loss of skeletal muscle mass—has been linked with poor outcomes in several surgical disciplines; however, a reliable and quantifiable measure of sarcopenia for future assessment of outcomes in spinal surgery patients has not been established.Methods: A cohort of 90 lumbar spine fusion patients were compared with 295 young, healthy patients obtained from a trauma da¬tabase. Cross-sectional vertebral body (VB) area, as well as the areas of the psoas and paravertebral muscles at mid-point of pedicles at L3 and L4 for both cohorts, was measured using axial CT imaging. Total muscle area-to-VB area ratio was calculated along with intraclass correlation coefficients for interobserver and intraobserver reliability. Finally, T-scores were calculated to help identify those patients with considerably diminished muscle-to-VB area ratios.Results: Both muscle mass and VB areas were considerably larger in males compared with those in females, and the ratio of these two measures was not enough to account for large differences. Thus, a gender-based comparison was made between spine patients and healthy control patients to establish T-scores that would help identify those patients with sarcopenia. The ratio for paravertebral muscle area-to-VB area at the L4 level was the only measure with good interobserver reliability, whereas the other three of the four ratios were moderate. All measurements had excellent correlations for intraobserver reliability.Conclusions: We postulate that a patient with a T-score <−1 for total paravertebral muscle area-to-VB area ratio at the L4 level is the most reliable method of all our measurements that can be used to diagnose a patient undergoing lumbar spine surgery with sarcopenia.

scholarly journals Development of Segmentation and Classification Algorithms for Computed Tomography Images of Human Kidney Stone

2021 ◽  
Vol 5 (5) ◽  
pp. 1-10
Author(s):  
Orobosa Joseph ◽  
Waliu Olalekan Apena
Keyword(s):  
Machine Learning ◽  
Computed Tomography ◽  
Deep Learning ◽  
Decision Support ◽  
Kidney Stone ◽  
Batch Size ◽  
Medical Decision ◽  
Ct Scans ◽  
Dense Layer ◽  
Computed Tomography Images

Computed tomography (CT) scan diagnostics procedures adopt the use of image information retrieval system with the help of radiographer’s expertise. However, this technique is prone to errors. Significant height of accuracy is required in healthcare decision support, as 20% of CT scans are associated with error. The application of artificial intelligence (AI) can improve performance level, mitigate human error, and enhance clinical decision support in the context of time and accuracy. The study introduced machine learning algorithm to analyze stream of anonymous CT scans of kidney. The research adopted deep learning approach for segmentation and classification of kidney stone (renal calculi) images in Python (with Keras and TensorFlow) environment. A control volume of data along with 336 kidney stone images were used to train the deep learning network with 10 testing images. The training images were divided into two sets (folders) as follows; one was labeled as STONE (containing 167 images) and the other as NO-STONE (containing 169 images); 10 iterations were performed for model training. The network layers were structured as input layer in the following with 2-D convolutional neural network machine learning (CNN-ML), ReLU activation, Maxpooling, and fully connected (dense) layer including the sigmoid activation layer. The training adopted a batch size of 8 with 10% validation. The output result, upon testing the model, has an accuracy of 90%, sensitivity value of 80% and effectiveness of 89%. The segmentation and classification algorithm model could be embedded in future CT diagnostic procedure to enhance medical decision support and accuracy.

scholarly journals Deep Learning-Based Three-Dimensional Oral Conical Beam Computed Tomography for Diagnosis

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Yangdong Lin ◽  
Miao He
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Surgical Planning ◽  
Three Dimensional ◽  
Cone Beam ◽  
Facial Surgery ◽  
Cbct Image ◽  
Dimensional Cone ◽  
Computer Based ◽  
Lesion Localization

In order to deeply study oral three-dimensional cone beam computed tomography (CBCT), the diagnosis of oral and facial surgical diseases based on deep learning was studied. The utility model related to a deep learning-based classification algorithm for oral neck and facial surgery diseases (deep diagnosis of oral and maxillofacial diseases, referred to as DDOM) is brought out; in this method, the DDOM algorithm proposed for patient classification, lesion segmentation, and tooth segmentation, respectively, can effectively process the three-dimensional oral CBCT data of patients and carry out patient-level classification. The segmentation results show that the proposed segmentation method can effectively segment the independent teeth in CBCT images, and the vertical magnification error of tooth CBCT images is clear. The average magnification rate was 7.4%. By correcting the equation of R value and CBCT image vertical magnification rate, the magnification error of tooth image length could be reduced from 7.4. According to the CBCT image length of teeth, the distance R from tooth center to FOV center, and the vertical magnification of CBCT image, the data closer to the real tooth size can be obtained, in which the magnification error is reduced to 1.0%. Therefore, it is proved that the 3D oral cone beam electronic computer based on deep learning can effectively assist doctors in three aspects: patient diagnosis, lesion localization, and surgical planning.

Sign in / Sign up

Export Citation Format

Share Document