1
|
Sultana J, Naznin M, Faisal TR. SSDL-an automated semi-supervised deep learning approach for patient-specific 3D reconstruction of proximal femur from QCT images. Med Biol Eng Comput 2024; 62:1409-1425. [PMID: 38217823 DOI: 10.1007/s11517-023-03013-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Accepted: 12/27/2023] [Indexed: 01/15/2024]
Abstract
Deep Learning (DL) techniques have recently been used in medical image segmentation and the reconstruction of 3D anatomies of a human body. In this work, we propose a semi-supervised DL (SSDL) approach utilizing a CNN-based 3D U-Net model for femur segmentation from sparsely annotated quantitative computed tomography (QCT) slices. Specifically, QCT slices at the proximal end of the femur forming ball and socket joint with acetabulum were annotated for precise segmentation, where a segmenting binary mask was generated using a 3D U-Net model to segment the femur accurately. A total of 5474 QCT slices were considered for training among which 2316 slices were annotated. 3D femurs were further reconstructed from segmented slices employing polynomial spline interpolation. Both qualitative and quantitative performance of segmentation and 3D reconstruction were satisfactory with more than 90% accuracy achieved for all of the standard performance metrics considered. The spatial overlap index and reproducibility validation metric for segmentation-Dice Similarity Coefficient was 91.8% for unseen patients and 99.2% for validated patients. An average relative error of 12.02% and 10.75% for volume and surface area, respectively, were computed for 3D reconstructed femurs. The proposed approach demonstrates its effectiveness in accurately segmenting and reconstructing 3D femur from QCT slices.
Collapse
Affiliation(s)
- Jamalia Sultana
- Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
| | - Mahmuda Naznin
- Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
| | - Tanvir R Faisal
- Department of Mechanical Engineering, University of Louisiana at Lafayette, Lafayette, LA, 70503, USA.
| |
Collapse
|
2
|
Xue X, Liang D, Wang K, Gao J, Ding J, Zhou F, Xu J, Liu H, Sun Q, Jiang P, Tao L, Shi W, Cheng J. A deep learning-based 3D Prompt-nnUnet model for automatic segmentation in brachytherapy of postoperative endometrial carcinoma. J Appl Clin Med Phys 2024:e14371. [PMID: 38682540 DOI: 10.1002/acm2.14371] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Revised: 02/07/2024] [Accepted: 03/25/2024] [Indexed: 05/01/2024] Open
Abstract
PURPOSE To create and evaluate a three-dimensional (3D) Prompt-nnUnet module that utilizes the prompts-based model combined with 3D nnUnet for producing the rapid and consistent autosegmentation of high-risk clinical target volume (HR CTV) and organ at risk (OAR) in high-dose-rate brachytherapy (HDR BT) for patients with postoperative endometrial carcinoma (EC). METHODS AND MATERIALS On two experimental batches, a total of 321 computed tomography (CT) scans were obtained for HR CTV segmentation from 321 patients with EC, and 125 CT scans for OARs segmentation from 125 patients. The numbers of training/validation/test were 257/32/32 and 87/13/25 for HR CTV and OARs respectively. A novel comparison of the deep learning neural network 3D Prompt-nnUnet and 3D nnUnet was applied for HR CTV and OARs segmentation. Three-fold cross validation and several quantitative metrics were employed, including Dice similarity coefficient (DSC), Hausdorff distance (HD), 95th percentile of Hausdorff distance (HD95%), and intersection over union (IoU). RESULTS The Prompt-nnUnet included two forms of parameters Predict-Prompt (PP) and Label-Prompt (LP), with the LP performing most similarly to the experienced radiation oncologist and outperforming the less experienced ones. During the testing phase, the mean DSC values for the LP were 0.96 ± 0.02, 0.91 ± 0.02, and 0.83 ± 0.07 for HR CTV, rectum and urethra, respectively. The mean HD values (mm) were 2.73 ± 0.95, 8.18 ± 4.84, and 2.11 ± 0.50, respectively. The mean HD95% values (mm) were 1.66 ± 1.11, 3.07 ± 0.94, and 1.35 ± 0.55, respectively. The mean IoUs were 0.92 ± 0.04, 0.84 ± 0.03, and 0.71 ± 0.09, respectively. A delineation time < 2.35 s per structure in the new model was observed, which was available to save clinician time. CONCLUSION The Prompt-nnUnet architecture, particularly the LP, was highly consistent with ground truth (GT) in HR CTV or OAR autosegmentation, reducing interobserver variability and shortening treatment time.
Collapse
Affiliation(s)
- Xian Xue
- Secondary Standard Dosimetry Laboratory, National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention (CDC), Beijing, China
| | - Dazhu Liang
- Digital Health China Technologies Co., LTD, Beijing, China
| | - Kaiyue Wang
- Department of Radiotherapy, Peking University Third Hospital, Beijing, China
| | - Jianwei Gao
- Digital Health China Technologies Co., LTD, Beijing, China
| | - Jingjing Ding
- Department of Radiotherapy, Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Fugen Zhou
- Department of Aero-space Information Engineering, Beihang University, Beijing, China
| | - Juan Xu
- Digital Health China Technologies Co., LTD, Beijing, China
| | - Hefeng Liu
- Digital Health China Technologies Co., LTD, Beijing, China
| | - Quanfu Sun
- Secondary Standard Dosimetry Laboratory, National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention (CDC), Beijing, China
| | - Ping Jiang
- Department of Radiotherapy, Peking University Third Hospital, Beijing, China
| | - Laiyuan Tao
- Digital Health China Technologies Co., LTD, Beijing, China
| | - Wenzhao Shi
- Digital Health China Technologies Co., LTD, Beijing, China
| | - Jinsheng Cheng
- Secondary Standard Dosimetry Laboratory, National Institute for Radiological Protection, Chinese Center for Disease Control and Prevention (CDC), Beijing, China
| |
Collapse
|
3
|
Jeuthe J, Sánchez JCG, Magnusson M, Sandborg M, Tedgren ÅC, Malusek A. SEMI-AUTOMATED 3D SEGMENTATION OF PELVIC REGION BONES IN CT VOLUMES FOR THE ANNOTATION OF MACHINE LEARNING DATASETS. Radiat Prot Dosimetry 2021; 195:172-176. [PMID: 34037238 PMCID: PMC8507443 DOI: 10.1093/rpd/ncab073] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/31/2020] [Revised: 03/24/2021] [Accepted: 04/01/2021] [Indexed: 06/12/2023]
Abstract
Automatic segmentation of bones in computed tomography (CT) images is used for instance in beam hardening correction algorithms where it improves the accuracy of resulting CT numbers. Of special interest are pelvic bones, which-because of their strong attenuation-affect the accuracy of brachytherapy in this region. This work evaluated the performance of the JJ2016 algorithm with the performance of MK2014v2 and JS2018 algorithms; all these algorithms were developed by authors. Visual comparison, and, in the latter case, also Dice similarity coefficients derived from the ground truth were used. It was found that the 3D-based JJ2016 performed better than the 2D-based MK2014v2, mainly because of the more accurate hole filling that benefitted from information in adjacent slices. The neural network-based JS2018 outperformed both traditional algorithms. It was, however, limited to the resolution of 1283 owing to the limited amount of memory in the graphical processing unit (GPU).
Collapse
Affiliation(s)
- Julius Jeuthe
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
| | | | - Maria Magnusson
- Department of Electrical Engineering, Linköping University, Linköping, Sweden
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | - Michael Sandborg
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
| | - Åsa Carlsson Tedgren
- Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden
- Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Stockholm, Sweden
| | | |
Collapse
|
4
|
González Sánchez JC, Magnusson M, Sandborg M, Carlsson Tedgren Å, Malusek A. Segmentation of bones in medical dual-energy computed tomography volumes using the 3D U-Net. Phys Med 2020; 69:241-247. [DOI: 10.1016/j.ejmp.2019.12.014] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/30/2019] [Revised: 12/12/2019] [Accepted: 12/17/2019] [Indexed: 10/25/2022] Open
|
5
|
Magnusson M, Björnfot M, Tedgren ÅC, Carlsson GA, Sandborg M, Malusek A. DIRA-3D—a model-based iterative algorithm for accurate dual-energy dual-source 3D helical CT. Biomed Phys Eng Express 2019. [DOI: 10.1088/2057-1976/ab42ee] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
6
|
Abiri A, Ding Y, Abiri P, Packard RRS, Vedula V, Marsden A, Kuo CCJ, Hsiai TK. Simulating Developmental Cardiac Morphology in Virtual Reality Using a Deformable Image Registration Approach. Ann Biomed Eng 2018; 46:2177-2188. [PMID: 30112710 DOI: 10.1007/s10439-018-02113-z] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2018] [Accepted: 08/07/2018] [Indexed: 10/28/2022]
Abstract
While virtual reality (VR) has potential in enhancing cardiovascular diagnosis and treatment, prerequisite labor-intensive image segmentation remains an obstacle for seamlessly simulating 4-dimensional (4-D, 3-D + time) imaging data in an immersive, physiological VR environment. We applied deformable image registration (DIR) in conjunction with 3-D reconstruction and VR implementation to recapitulate developmental cardiac contractile function from light-sheet fluorescence microscopy (LSFM). This method addressed inconsistencies that would arise from independent segmentations of time-dependent data, thereby enabling the creation of a VR environment that fluently simulates cardiac morphological changes. By analyzing myocardial deformation at high spatiotemporal resolution, we interfaced quantitative computations with 4-D VR. We demonstrated that our LSFM-captured images, followed by DIR, yielded average dice similarity coefficients of 0.92 ± 0.05 (n = 510) and 0.93 ± 0.06 (n = 240) when compared to ground truth images obtained from Otsu thresholding and manual segmentation, respectively. The resulting VR environment simulates a wide-angle zoomed-in view of motion in live embryonic zebrafish hearts, in which the cardiac chambers are undergoing structural deformation throughout the cardiac cycle. Thus, this technique allows for an interactive micro-scale VR visualization of developmental cardiac morphology to enable high resolution simulation for both basic and clinical science.
Collapse
Affiliation(s)
- Arash Abiri
- Department of Bioengineering, University of California, Los Angeles, CA, 90095, USA.,Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, 90095, USA.,Department of Biomedical Engineering, University of California, Irvine, CA, 92697, USA
| | - Yichen Ding
- Department of Bioengineering, University of California, Los Angeles, CA, 90095, USA.,Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, 90095, USA
| | - Parinaz Abiri
- Department of Bioengineering, University of California, Los Angeles, CA, 90095, USA.,Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, 90095, USA
| | - René R Sevag Packard
- Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, 90095, USA
| | - Vijay Vedula
- Department of Pediatrics (Cardiology), Stanford University, Stanford, CA, 94305, USA
| | - Alison Marsden
- Department of Pediatrics (Cardiology), Stanford University, Stanford, CA, 94305, USA.,Department of Bioengineering, Stanford University, Stanford, CA, 94305, USA.,Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, 94305, USA
| | - C-C Jay Kuo
- Department of Electrical Engineering, University of Southern California, Los Angeles, CA, 90089, USA
| | - Tzung K Hsiai
- Department of Bioengineering, University of California, Los Angeles, CA, 90095, USA. .,Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, CA, 90095, USA. .,Medical Engineering, California Institute of Technology, Pasadena, CA, 91125, USA.
| |
Collapse
|
7
|
Yu H, Wang H, Shi Y, Xu K, Yu X, Cao Y. The segmentation of bones in pelvic CT images based on extraction of key frames. BMC Med Imaging 2018; 18:18. [PMID: 29788923 DOI: 10.1186/s12880-018-0260-x] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2017] [Accepted: 05/04/2018] [Indexed: 12/25/2022] Open
Abstract
Background Bone segmentation is important in computed tomography (CT) imaging of the pelvis, which assists physicians in the early diagnosis of pelvic injury, in planning operations, and in evaluating the effects of surgical treatment. This study developed a new algorithm for the accurate, fast, and efficient segmentation of the pelvis. Methods The proposed method consists of two main parts: the extraction of key frames and the segmentation of pelvic CT images. Key frames were extracted based on pixel difference, mutual information and normalized correlation coefficient. In the pelvis segmentation phase, skeleton extraction from CT images and a marker-based watershed algorithm were combined to segment the pelvis. To meet the requirements of clinical application, physician’s judgment is needed. Therefore the proposed methodology is semi-automated. Results In this paper, 5 sets of CT data were used to test the overlapping area, and 15 CT images were used to determine the average deviation distance. The average overlapping area of the 5 sets was greater than 94%, and the minimum average deviation distance was approximately 0.58 pixels. In addition, the key frame extraction efficiency and the running time of the proposed method were evaluated on 20 sets of CT data. For each set, approximately 13% of the images were selected as key frames, and the average processing time was approximately 2 min (the time for manual marking was not included). Conclusions The proposed method is able to achieve accurate, fast, and efficient segmentation of pelvic CT image sequences. Segmentation results not only provide an important reference for early diagnosis and decisions regarding surgical procedures, they also offer more accurate data for medical image registration, recognition and 3D reconstruction.
Collapse
|
8
|
Malusek A, Magnusson M, Sandborg M, Alm Carlsson G. A model-based iterative reconstruction algorithm DIRA using patient-specific tissue classification via DECT for improved quantitative CT in dose planning. Med Phys 2017; 44:2345-2357. [DOI: 10.1002/mp.12238] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2016] [Revised: 02/16/2017] [Accepted: 03/10/2017] [Indexed: 11/10/2022] Open
Affiliation(s)
- Alexandr Malusek
- Radiation Physics, Department of Medical and Health Sciences; Linköping University; Linköping Sweden
- Center for Medical Image Science and Visualization (CMIV); Linköping University; Linköping Sweden
| | - Maria Magnusson
- Radiation Physics, Department of Medical and Health Sciences; Linköping University; Linköping Sweden
- Center for Medical Image Science and Visualization (CMIV); Linköping University; Linköping Sweden
- Computer Vision Laboratory, Department of Electrical Engineering; Linköping University; Linköping Sweden
| | - Michael Sandborg
- Radiation Physics, Department of Medical and Health Sciences; Linköping University; Linköping Sweden
- Center for Medical Image Science and Visualization (CMIV); Linköping University; Linköping Sweden
| | - Gudrun Alm Carlsson
- Radiation Physics, Department of Medical and Health Sciences; Linköping University; Linköping Sweden
- Center for Medical Image Science and Visualization (CMIV); Linköping University; Linköping Sweden
| |
Collapse
|