4.4 Review

CT image segmentation methods for bone used in medical additive manufacturing

期刊

MEDICAL ENGINEERING & PHYSICS
卷 51, 期 -, 页码 6-16

出版社

ELSEVIER SCI LTD
DOI: 10.1016/j.medengphy.2017.10.008

关键词

3D printing; Additive manufacturing (AM); Computed tomography (CT); Accuracy; Image segmentation

向作者/读者索取更多资源

Aim of the study: The accuracy of additive manufactured medical constructs is limited by errors introduced during image segmentation. The aim of this study was to review the existing literature on different image segmentation methods used in medical additive manufacturing. Methods: Thirty-two publications that reported on the accuracy of bone segmentation based on computed tomography images were identified using PubMed, ScienceDirect, Scopus, and Google Scholar. The advantages and disadvantages of the different segmentation methods used in these studies were evaluated and reported accuracies were compared. Results: The spread between the reported accuracies was large (0.04 mm - 1.9 mm). Global thresholding was the most commonly used segmentation method with accuracies under 0.6 mm. The disadvantage of this method is the extensive manual post-processing required. Advanced thresholding methods could improve the accuracy to under 038 mm. However, such methods are currently not included in commercial software packages. Statistical shape model methods resulted in accuracies from 0.25 mm to 1.9 mm but are only suitable for anatomical structures with moderate anatomical variations. Conclusions: Thresholding remains the most widely used segmentation method in medical additive manufacturing. To improve the accuracy and reduce the costs of patient-specific additive manufactured constructs, more advanced segmentation methods are required. (C) 2017 IPEM. Published by Elsevier Ltd. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.4
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Engineering, Biomedical

Efficient high cone-angle artifact reduction in circular cone-beam CT using deep learning with geometry-aware dimension reduction

Jordi Minnema, Maureen van Eijnatten, Henri der Sarkissian, Shannon Doyle, Juha Koivisto, Jan Wolff, Tymour Forouzanfar, Felix Lucka, Kees Joost Batenburg

Summary: This study introduces a novel deep learning approach to reduce high cone-angle artifacts in CBCT scans through training convolutional neural networks. The results demonstrate that this method significantly reduces artifacts and outperforms conventional methods.

PHYSICS IN MEDICINE AND BIOLOGY (2021)

Review Dentistry, Oral Surgery & Medicine

A review on the application of deep learning for CT reconstruction, bone segmentation and surgical planning in oral and maxillofacial surgery

Jordi Minnema, Anne Ernst, Maureen van Eijnatten, Ruben Pauwels, Tymour Forouzanfar, Kees Joost Batenburg, Jan Wolff

Summary: Computer-assisted surgery (CAS) is widely used in maxillofacial surgery for personalized treatments. However, errors introduced during CT image reconstruction, bone segmentation, and surgical planning can affect treatment outcomes. This study reviews the use of neural networks (NNs) in CAS workflow and discusses their benefits and limitations. Convolutional NNs were commonly used, especially in surgical planning tasks.

DENTOMAXILLOFACIAL RADIOLOGY (2022)

Article Dentistry, Oral Surgery & Medicine

Impact of thyroid gland shielding on radiation doses in dental cone beam computed tomography with small and medium fields of view

Melanie Gruening, Juha Koivisto, James Mah, Axel Bumann

Summary: This study evaluated the impact of thyroid gland shielding on radiation doses in dental CBCT with small and medium FOVs. The results showed that thyroid gland shielding significantly reduced equivalent doses and effective doses in various tissues, and should be used in all possible CBCT examinations.

ORAL SURGERY ORAL MEDICINE ORAL PATHOLOGY ORAL RADIOLOGY (2022)

Article Dentistry, Oral Surgery & Medicine

Influence of head positioning during cone- beam CT imaging on the accuracy of virtual 3D models

Maureen van Eijnatten, Jan Wolff, Ruben Pauwels, Kalle Karhu, Ari Hietanen, Henry der Sarkissian, Juha H. Koivisto

Summary: This study evaluates the impact of four different CBCT imaging positions on the accuracy of 3D models in the orbital area and finds that an elevated imaging position combined with higher voltage improves the accuracy of the resulting 3D models.

DENTOMAXILLOFACIAL RADIOLOGY (2022)

Review Surgery

Computer-aided anatomy recognition in intrathoracic and -abdominal surgery: a systematic review

R. B. den Boer, C. de Jongh, W. T. E. Huijbers, T. J. M. Jaspers, J. P. W. Pluim, R. van Hillegersberg, M. Van Eijnatten, J. P. Ruurda

Summary: This study provides a comprehensive overview of the accuracy of anatomy recognition algorithms in intrathoracic and abdominal surgery. The results show that the accuracy of these algorithms varies substantially, with higher accuracy achieved through training on larger datasets annotated by experts and focusing on less-complex anatomy. The study highlights the emerging field of computer-aided intraoperative anatomy recognition and emphasizes the need for larger datasets and methodological guidelines to improve accuracy and clinical applicability in future research.

SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES (2022)

Article Dentistry, Oral Surgery & Medicine

Comparison of subjective image analysis and effective dose between low- dose cone- beam computed tomography machines

Arnon Charuakkra, Phattaranant Mahasantipiya, Antti Lehtinen, Juha Koivisto, Jorma Jarnstedt

Summary: This study aimed to compare the image quality and effective dose of cone-beam computed tomography (CBCT) between low-dose scanning and standard manufacturer-recommended protocols among different CBCT units. The results showed that high-tube-voltage protocols could remarkably reduce the imaging dose without degrading the image quality. Therefore, low-dose and ultra-low-dose CBCT protocols may be adopted as routine practice for diagnosis and treatment planning.

DENTOMAXILLOFACIAL RADIOLOGY (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Radiation exposure to fetus from extremity CBCT examinations

Agnese Katlapa, Siru M. Kaartinen, Juha Henrik Koivisto, Hanna Matikka

Summary: Fetal doses from extremity CBCT examinations were evaluated at different stages of pregnancy, with factors such as soft tissue layer, tube voltage, add-on device shield and body angulation found to impact fetal dose. The most effective method of reducing fetal dose was using add-on device shielding.

EUROPEAN JOURNAL OF RADIOLOGY (2022)

Article Oncology

Anatomical evaluation of deep-learning synthetic computed tomography images generated from male pelvis cone-beam computed tomography

Yvonne J. M. de Hond, Camiel E. M. Kerckhaert, Maureen A. J. M. van Eijnatten, Paul M. A. van Haaren, Coen W. Hurkmans, Rob H. N. Tijssen

Summary: This study emphasizes the importance of anatomical correctness in synthetic CT scans generated from CBCT scans using different deep-learning models. The results show that although Dual-UNet performs best in standard image quality measures, it performs worst in anatomical comparison, highlighting the importance of adding anatomy-based evaluation of sCTs generated by DL-models. Direct anatomical comparison with CBCT may provide a useful method to assess the clinical applicability of DL-based sCT generation methods in the pelvic area.

PHYSICS & IMAGING IN RADIATION ONCOLOGY (2023)

Article Environmental Sciences

Optimising the parameters of cochlear implant imaging with cone-beam computed tomography

Samuel Soederqvist, Ville Sivonen, Antti Aarnisalo, Harri Karppi, Saku T. Sinkkonen, Juha Koivisto

Summary: The study evaluated the usefulness of a novel cone-beam CT device for imaging the inner ear in cochlear implant recipients. The exposure parameters were optimized to achieve adequate clinical image quality at the lowest effective dose. The results showed that the overall image quality of inner ear structures did not differ between different imaging protocols, and important structures in cochlear implant recipients' inner ears could be visualized with low radiation exposure. However, higher radiation exposure may be necessary to visualize the most delicate structures in the inner ear.

RADIATION PROTECTION DOSIMETRY (2023)

Article Surgery

Deep learning-based recognition of key anatomical structures during robot-assisted minimally invasive esophagectomy

R. B. den Boer, T. J. M. Jaspers, C. de Jongh, J. P. W. Pluim, F. van der Sommen, T. Boers, R. van Hillegersberg, M. A. J. M. Van Eijnatten, J. P. Ruurda

Summary: This study developed a deep learning algorithm to recognize anatomical structures in video frames from robot-assisted minimally invasive esophagectomy (RAMIE) procedures. It shows potential for clinical application and further prospective clinical studies are needed to assess its effectiveness.

SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Assessment of subjective image quality, contrast to noise ratio and modulation transfer function in the middle ear using a novel full body cone beam computed tomography device

Anssi-Kalle Heikkinen, Valtteri Rissanen, Antti A. Aarnisalo, Kristofer Nyman, Saku T. Sinkkonen, Juha Koivisto

Summary: This study aimed to optimize the imaging parameters of a novel full body CBCT device to obtain optimal contrast to noise ratio (CNR) with low effective dose, and to optimize its clinical usability. Through imaging and comparison analysis of five anonymous cadaver temporal bones, it was found that all protocols except for 90 kVp 100 mAs were able to image the finest structures. The best protocol was 90 kV 450 mAs, which exhibited the best clinical image quality at a moderate effective dose of 86.5 mu Sv and was able to distinguish the most delicate middle ear structures in 2D images.

BMC MEDICAL IMAGING (2023)

Article Audiology & Speech-Language Pathology

Spread of the intracochlear electrical field: Implications for assessing electrode array location in cochlear implantation

Samuel Soderqvist, Ville Sivonen, Juha Koivisto, Antti Aarnisalo, Saku T. Sinkkonen

Summary: The electrode-generated intracochlear electrical field can be assessed using monopolar transimpedance matrix (TIMmp) to evaluate the correct alignment of the electrode array, and bipolar TIM (TIMbp) can be used to estimate potential differences. Both TIMmp and TIMbp can be used to estimate the scala area and electrode-medial-wall distance. The results showed that TIMmp had increasing EF peaks from the basal to apical direction and steeper decay near the medial wall, while TIMbp correlated with both scala area and electrode-medial-wall distance.

HEARING RESEARCH (2023)

Review Pharmacology & Pharmacy

Craniocervical Junction Visualization and Radiation Dose Consideration Utilizing Cone Beam Computed Tomography for Upper Cervical Chiropractic Clinical Application a Literature Review

Greg DeNunzio, Tyler Evans, Mychal E. Beebe, Jaime Browning, Juha Koivisto

Summary: This study highlights the detailed information obtained from a CBCT scan of the craniocervical junction and its usefulness for Chiropractors specializing in the upper cervical spine. It compares the radiation dose to patients from radiography and CBCT, and finds that CBCT provides superior visualization of incidental and abnormal findings in the craniocervical junction with equal or lower radiation dose to patients.

DOSE-RESPONSE (2022)

暂无数据