A Deep Unsupervised Learning Model for Artifact Correction of Pelvis Cone-Beam CT

PurposeIn recent years, cone-beam computed tomography (CBCT) is increasingly used in adaptive radiation therapy (ART). However, compared with planning computed tomography (PCT), CBCT image has much more noise and imaging artifacts. Therefore, it is necessary to improve the image quality and HU accuracy of CBCT. In this study, we developed an unsupervised deep learning network (CycleGAN) model to calibrate CBCT images for the pelvis to extend potential clinical applications in CBCT-guided ART.MethodsTo train CycleGAN to generate synthetic PCT (sPCT), we used CBCT and PCT images as inputs from 49 patients with unpaired data. Additional deformed PCT (dPCT) images attained as CBCT after deformable registration are utilized as the ground truth before evaluation. The trained uncorrected CBCT images are converted into sPCT images, and the obtained sPCT images have the characteristics of PCT images while keeping the anatomical structure of CBCT images unchanged. To demonstrate the effectiveness of the proposed CycleGAN, we use additional nine independent patients for testing.ResultsWe compared the sPCT with dPCT images as the ground truth. The average mean absolute error (MAE) of the whole image on testing data decreased from 49.96 ± 7.21HU to 14.6 ± 2.39HU, the average MAE of fat and muscle ROIs decreased from 60.23 ± 7.3HU to 16.94 ± 7.5HU, and from 53.16 ± 9.1HU to 13.03 ± 2.63HU respectively.ConclusionWe developed an unsupervised learning method to generate high-quality corrected CBCT images (sPCT). Through further evaluation and clinical implementation, it can replace CBCT in ART.

Download Full-text

Fluoroscopic 3D Image Generation from Patient-Specific PCA Motion Models Derived from 4D-CBCT Patient Datasets: A Feasibility Study

10.20944/preprints202111.0519.v1 ◽

2021 ◽

Author(s):

Salam Dhou ◽

Mohanad Alkhodari ◽

Dan Ionascu ◽

Christopher Williams ◽

John H. Lewis

Keyword(s):

Vector Fields ◽

Displacement Vector ◽

Cone Beam Ct ◽

Ground Truth ◽

Absolute Error ◽

Tumor Location ◽

Cone Beam ◽

Patient Specific ◽

3D Image ◽

Motion Models

A method for generating fluoroscopic (time-varying) volumetric images using patient-specific motion models derived from 4-dimensional cone-beam CT (4D-CBCT) images is developed. 4D-CBCT images acquired immediately prior to treatment have the potential to accurately represent patient anatomy and respiration during treatment. Fluoroscopic 3D image estimation is done in two steps: 1) deriving motion models and 2) optimization. To derive motion models, every phase in a 4D-CBCT set is registered to a reference phase chosen from the same set using deformable image registration (DIR). Principal components analysis (PCA) is used to reduce the dimensionality of the displacement vector fields (DVFs) resulting from DIR into a few vectors representing organ motion found in the DVFs. The PCA motion models are optimized iteratively by comparing a cone-beam CT (CBCT) projection to a simulated projection computed from both the motion model and a reference 4D-CBCT phase, resulting in a sequence of fluoroscopic 3D images. Patient datasets were used to evaluate the method by estimating the tumor location in the generated images compared to manually defined ground truth positions. Experimental results showed that the average tumor mean absolute error (MAE) along the superior-inferior (SI) direction and the 95th percentile in two patient datasets were (2.29 mm and 5.79 mm) for patient 1 and (1.89 mm and 4.82 mm) for patient 2. This study has demonstrated the feasibility of deriving 4D-CBCT-based PCA motion models that have the potential to account for the 3D non-rigid patient motion and localize tumors and other patient anatomical structures on the day of treatment.

Download Full-text

A Diagnosis of Maxillary Sinus Fracture with Cone-Beam CT: Case Report and Literature Review

Craniomaxillofacial Trauma & Reconstruction ◽

10.1055/s-0034-1371550 ◽

2014 ◽

Vol 7 (2) ◽

pp. 85-91 ◽

Cited By ~ 8

Author(s):

Selmi Yardimci Yilmaz ◽

Melda Misirlioglu ◽

Mehmet Zahit Adisen

Keyword(s):

Computed Tomography ◽

Case Report ◽

Maxillary Sinus ◽

Cone Beam Ct ◽

Maxillofacial Surgery ◽

Maxillofacial Trauma ◽

Cone Beam ◽

Maxillofacial Region ◽

Emergency Center ◽

Frontal Wall

The purpose of this article is to present the case of maxillofacial trauma patient with maxillary sinus fracture diagnosed with cone-beam computed tomography (CBCT) and to explore the applications of this technique in evaluating the maxillofacial region. A 23-year-old male patient attempted to our clinic who had an injury at midface with complaints of swelling, numbness. The patient was examined before in emergency center but any diagnosis was made about the maxillofacial trauma. The patient re-examined clinically and radiographically. A fracture on the frontal wall of maxillary sinus is determined with the aid of CBCT. The patient consulted with the department of maxillofacial surgery and it is decided that any surgical treatment was not necessary. The emerging technique CBCT would not be the primary choice of imaging maxillofacial trauma. Nevertheless, when advantages considered this imaging procedure could be the modality of choice according to the case.

Download Full-text

Versatility of the cone beam computed tomography in oral surgery: an overview

Surgical Techniques Development ◽

10.4081/std.2011.e31 ◽

2011 ◽

Vol 1 (2) ◽

pp. 31

Author(s):

Kishan G. Panicker ◽

Anuroopa Pudukulangara Nair ◽

Bipin Chandra Reddy

Keyword(s):

Computed Tomography ◽

Alveolar Bone ◽

Oral Surgery ◽

Cone Beam Ct ◽

Cone Beam ◽

Facial Skeleton ◽

Posterior Teeth ◽

True Nature ◽

Root Apices ◽

Relationship Of

Cone beam CT (CBCT) produces threedimensional information on the facial skeleton, teeth and their surrounding tissues; and is increasingly being used in many of the dental specialties. This is usually achieved with a substantially lower effective dose compared with conventional medical computed tomography (CT). Periapical pathologies, root fractures, root canal anatomy and the true nature of the alveolar bone topography around teeth may be assessed. CBCT scans are desirable to assess posterior teeth prior to periapical surgery, as the thickness of the cortical and cancellous bone can be accurately determined as can the inclination of roots in relation to the surrounding jaw. The relationship of anatomical structures such as the maxillary sinus and inferior dental nerve to the root apices may also be clearly visualized. Measurements on CBCT are more accurate when compared with OPG. Therefore, CBCT permits the clinician to have all necessary information when planning dental implants. The purpose of this article is to provide an overview of the unique image display capabilities of maxillofacial CBCT systems and to illustrate specific applications in clinical practice.

Download Full-text

Evaluation of Anatomoradiological Findings on Trigeminal Neuralgia Patients Using Computed Tomography and Cone-Beam Computed Tomography

Diagnostics ◽

10.3390/diagnostics12010073 ◽

2021 ◽

Vol 12 (1) ◽

pp. 73

Author(s):

Seçil Aksoy ◽

Arzu Sayın Şakul ◽

Durmuş İlker Görür ◽

Bayram Ufuk Şakul ◽

Kaan Orhan

Keyword(s):

Computed Tomography ◽

Trigeminal Neuralgia ◽

Cone Beam Ct ◽

Median Plane ◽

Cone Beam ◽

Foramen Ovale ◽

Percutaneous Procedures ◽

The Right ◽

And Control ◽

Supraorbital Foramen

The study aimed to establish and evaluate anatomoradiological landmarks in trigeminal neuralgia patients using computed tomography (CT) and cone-beam CT. CT images of 40 trigeminal neuralgia (TN) and 40 healthy individuals were retrospectively analyzed and enrolled in the study. The width and length of the foramen rotundum (FR), foramen ovale (FO), foramen supraorbitale, and infraorbitale were measured. The distances between these foramen, between these foramen to the median plane, and between the superior orbital fissure, FO, and FR to clinoid processes were also measured bilaterally. Variations were evaluated according to groups. Significant differences were found for width and length of the foramen ovale, length of the foramen supraorbitale, and infraorbitale between TN and control subjects (p < 0.05). On both sides, FO gets narrower and the length of the infraorbital and supraorbital foramen shortens in the TN group. In most of the control patients, the plane which passes through the infraorbital and supraorbital foramen intersects with impression trigeminale; 70% on the right-side, and 67% in the left-side TN groups. This plane does not intersect with impression trigeminale and deviates in certain degrees. The determination of specific landmarks allows customization to individual patient anatomy and may help the surgeon achieve a more selective effect with a variety of percutaneous procedures in trigeminal neuralgia patients.

Download Full-text