scholarly journals Intraoperative Registration of 2D C-arm Images with Preoperative CT Data in Computer Assisted Spine Surgery: Motivation to Use Convolutional Neural Networks for Initial Pose Generator

2019 ◽  
Vol 5 (1) ◽  
pp. 25-28
Author(s):  
Julio Alvarez-Gomez ◽  
Hubert Roth ◽  
Jürgen Wahrburg
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Spine Surgery ◽  
Computer Assisted ◽  
3D Registration ◽  
Registration Process ◽  
Acceptable Range ◽  
Preoperative Ct ◽  
Spatial Attributes ◽  
Ct Data

AbstractIn this paper, we present an approach for getting an initial pose to use in a 2D/3D registration process for computer-assisted spine surgery. This is an iterative process that requires an initial pose close to the actual final pose. When using a proper initial pose, we get registrations within two millimeters of accuracy. Consequently, we developed a fully connected neural network (FCNN), which predicts the pose of a specific 2D image within an acceptable range. Therefore, we can use this result as the initial pose for the registration process. However, the inability of the FCNN for learning spatial attributes, and the decrease of the resolution of the images before inserting them in the FCNN, make the variance of the prediction large enough to make some of the predictions entirely out of the acceptable range. Additionally, new researches in deep learning field have shown that convolutional neural networks (CNNs) offer high advantages when the inputs of the net are images. We consider that using CNNs can help to improve our results, generalizing the system for a greater variety of inputs, and facilitating the integration with our current workflow. Then we present an outline for a CNN for our application, and some further steps we need to complete to achieve this implementation.

Correlation between the extent of pneumatization of Agger agger Nasi nasi cells and the anterior-to-posterior length of the frontal recess: A a computer-assisted anatomical study.

2017 ◽  
Vol 71 (3) ◽  
pp. 43-55
Author(s):  
Ahmet Altıntaş ◽  
Mustafa Çelik ◽  
Yakup Yegin ◽  
Sinan Canpolat ◽  
Burak Olgun ◽  
...  
Keyword(s):  
Cell Volume ◽  
Anatomical Study ◽  
Ct Imaging ◽  
Sinus Surgery ◽  
Computer Assisted ◽  
Frontal Recess ◽  
Preoperative Ct ◽  
The Mean ◽  
Ct Data ◽  
The Right

Objectives: To explore the correlation between the volume of the aAgger nNasi (AN) cell bulge and the A-P length of the frontal recess (FR). Subjects and methods: In total, 120 patients, who underwent septoplasty, were included. All patients underwent preoperative paranasal sinus computed tomography of the paranasal sinuses (PNS CT) imaging. In total, CT data on of all 120 PNSs patients were analyzed in terms of thewith respect to the extent of pneumatization of the AN cell bulge and the A-P dimensions of the FR. Each side was analyzed separately. Results: We included 120 patients,: 78 (65.0%) females and 42 (35.0 %) males. Their average age was 33.7 ± 11.6 years (range: 18–65 years). The mean volume of the AN cell bulge was 0.26 ± 0.4 mm3 on both the right and left sides. The A-P length of the FR was 7.7 ± 2.2 mm. No significant between-side difference in the mean volume of the AN cell bulge was apparent observed (p=0.906). This volume did not differ significantly by age or sex (p=0.844 and p=0.971, respectively). We found no correlation between the volume of the AN cell bulge and the A-P length of the FR (r = 0.098, p=0.192). Conclusion: In the present study, no correlation between AN cell volume and the A-P length of the FR was found. When studying the anatomical complexity of the FR, it is essential to consider the AN cell volume. We suggest that preoperative CT imaging is critical when endoscopic sinus surgery is planned. However, further studies with larger numbers of patients are needed to explore the relationship between AN cell pneumatization and the anatomy of the FR.

Mo2050 – Novel Computer-Assisted Detection System of Colorectal Carcinoid Tumors Using Convolutional Neural Networks

2019 ◽  
Vol 156 (6) ◽  
pp. S-937 ◽  
Author(s):  
Junichi Shibata ◽  
Tsuyoshi Ozawa ◽  
Soichiro Ishihara ◽  
Tatusya Onishi ◽  
Keigo Matsuo ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Detection System ◽  
Carcinoid Tumors ◽  
Computer Assisted ◽  
Computer Assisted Detection ◽  
Colorectal Carcinoid

High-fidelity geometry generation from CT data using convolutional neural networks

2019 ◽  
Author(s):  
Aniket Tekawade ◽  
Brandon A. Sforzo ◽  
Katarzyna E. Matusik ◽  
Alan L. Kastengren ◽  
Christopher F. Powell
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
High Fidelity ◽  
Ct Data

scholarly journals Artificial Intelligence-Based Polyp Detection in Colonoscopy: Where Have We Been, Where Do We Stand, and Where Are We Headed?

2020 ◽  
Vol 36 (6) ◽  
pp. 428-438
Author(s):  
Thomas Wittenberg ◽  
Martin Raithel
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Big Data ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Lesion Detection ◽  
Screening Colonoscopy ◽  
Computer Assisted ◽  
Polyp Detection ◽  
The Past

<b><i>Background:</i></b> In the past, image-based computer-assisted diagnosis and detection systems have been driven mainly from the field of radiology, and more specifically mammography. Nevertheless, with the availability of large image data collections (known as the “Big Data” phenomenon) in correlation with developments from the domain of artificial intelligence (AI) and particularly so-called deep convolutional neural networks, computer-assisted detection of adenomas and polyps in real-time during screening colonoscopy has become feasible. <b><i>Summary:</i></b> With respect to these developments, the scope of this contribution is to provide a brief overview about the evolution of AI-based detection of adenomas and polyps during colonoscopy of the past 35 years, starting with the age of “handcrafted geometrical features” together with simple classification schemes, over the development and use of “texture-based features” and machine learning approaches, and ending with current developments in the field of deep learning using convolutional neural networks. In parallel, the need and necessity of large-scale clinical data will be discussed in order to develop such methods, up to commercially available AI products for automated detection of polyps (adenoma and benign neoplastic lesions). Finally, a short view into the future is made regarding further possibilities of AI methods within colonoscopy. <b><i>Key Messages:</i></b> Research<b><i></i></b>of<b><i></i></b>image-based lesion detection in colonoscopy data has a 35-year-old history. Milestones such as the Paris nomenclature, texture features, big data, and deep learning were essential for the development and availability of commercial AI-based systems for polyp detection.

scholarly journals A Splint-to-CT Data Registration Strategy for Maxillary Navigation Surgery

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Shinsuke Yamamoto ◽  
Shigeo Hara ◽  
Toshihiko Takenobu
Keyword(s):  
Reference Frame ◽  
Computer Assisted ◽  
Navigation Surgery ◽  
Assisted Navigation ◽  
Craniomaxillofacial Surgery ◽  
Data Registration ◽  
Custom Made ◽  
Preoperative Ct ◽  
Maxillary Surgery ◽  
Ct Data

Computer-assisted navigation plays an important role in modern craniomaxillofacial surgery. Although headpins and skull posts are widely used for the fixation of the reference frame, they require the use of invasive procedures. Headbands are easily displaced intraoperatively, thus reducing the accuracy of the surgical outcome. This study reported the utility of a novel splint integrated with a reference frame and registration markers for maxillary navigation surgery. A maxillary splint with a 10 cm resin handle was fabricated before surgery, to fix the reference frame to the splint. The splint was set after the incorporation of fiducial gutta-percha markers into both the splint and resin handle for marker-based pair-point registration. A computed tomography (CT) scan was acquired for preoperative CT-based planning. A marker-based pair-point registration procedure can be completed easily and noninvasively using this custom-made integrated splint, and maxillary navigation surgery can be performed with high accuracy. This method also provides maximum convenience for the surgeon, as the splint does not require reregistration, and can be removed temporarily when required. The splint-to-CT data registration strategy has potential applicability not only for maxillary surgery but also for otolaryngologic surgery, neurosurgery, and surgical repair after craniofacial trauma.

scholarly journals Deep learning models for COVID-19 infected area segmentation in CT images

2020 ◽  
Author(s):  
Athanasios Voulodimos ◽  
Eftychios Protopapadakis ◽  
Iason Katsamenis ◽  
Anastasios Doulamis ◽  
Nikolaos Doulamis
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Class Imbalance ◽  
Semantic Segmentation ◽  
Ct Images ◽  
Learning Models ◽  
Fully Convolutional Neural Networks ◽  
Infected Area ◽  
Ct Data

Recent studies indicated that detecting radiographic patterns on CT chest scans could in some cases yield higher sensitivity and specificity for COVID-19 detection compared to other methods such as RTPCR. In this work, we scrutinize the effectiveness of deep learning models for semantic segmentation of pneumonia infected area segmentation in CT images for the detection of COVID-19. We explore the efficacy of U-Nets and Fully Convolutional Neural Networks in this task using real-world CT data from COVID-19 patients. The results indicate that Fully Convolutional Neural Networks are capable of accurate segmentation despite the class imbalance on the dataset and the man-made annotation errors on the boundaries of symptom manifestation areas, and can be a promising method for further analysis of COVID-19 induced pneumonia symptoms in CT images.

Sign in / Sign up

Export Citation Format

Share Document