1
|
Gao C, Shi Y, Yang S, Lei B. SAA-SDM: Neural Networks Faster Learned to Segment Organ Images. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:547-562. [PMID: 38343217 PMCID: PMC11031521 DOI: 10.1007/s10278-023-00947-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/05/2023] [Revised: 10/16/2023] [Accepted: 10/18/2023] [Indexed: 04/20/2024]
Abstract
In the field of medicine, rapidly and accurately segmenting organs in medical images is a crucial application of computer technology. This paper introduces a feature map module, Strength Attention Area Signed Distance Map (SAA-SDM), based on the principal component analysis (PCA) principle. The module is designed to accelerate neural networks' convergence speed in rapidly achieving high precision. SAA-SDM provides the neural network with confidence information regarding the target and background, similar to the signed distance map (SDM), thereby enhancing the network's understanding of semantic information related to the target. Furthermore, this paper presents a training scheme tailored for the module, aiming to achieve finer segmentation and improved generalization performance. Validation of our approach is carried out using TRUS and chest X-ray datasets. Experimental results demonstrate that our method significantly enhances neural networks' convergence speed and precision. For instance, the convergence speed of UNet and UNET + + is improved by more than 30%. Moreover, Segformer achieves an increase of over 6% and 3% in mIoU (mean Intersection over Union) on two test datasets without requiring pre-trained parameters. Our approach reduces the time and resource costs associated with training neural networks for organ segmentation tasks while effectively guiding the network to achieve meaningful learning even without pre-trained parameters.
Collapse
Affiliation(s)
- Chao Gao
- College of Computer and Information Technology, China Three Gorges University, Yichang Hubei, 443002, China
- Hubei Key Laboratory of Intelligent Vision Monitoring for Hydropower Engineering, China Three Gorges University, Yichang Hubei, 443002, China
| | - Yongtao Shi
- College of Computer and Information Technology, China Three Gorges University, Yichang Hubei, 443002, China.
- Hubei Key Laboratory of Intelligent Vision Monitoring for Hydropower Engineering, China Three Gorges University, Yichang Hubei, 443002, China.
| | - Shuai Yang
- College of Computer and Information Technology, China Three Gorges University, Yichang Hubei, 443002, China
- Hubei Key Laboratory of Intelligent Vision Monitoring for Hydropower Engineering, China Three Gorges University, Yichang Hubei, 443002, China
| | - Bangjun Lei
- College of Computer and Information Technology, China Three Gorges University, Yichang Hubei, 443002, China
- Hubei Key Laboratory of Intelligent Vision Monitoring for Hydropower Engineering, China Three Gorges University, Yichang Hubei, 443002, China
| |
Collapse
|
2
|
Li J, Rath B, Hildebrand F, Eschweiler J. Wrist Bone Motion during Flexion-Extension and Radial-Ulnar Deviation: An MRI Study. Life (Basel) 2022; 12:life12101458. [PMID: 36294894 PMCID: PMC9605103 DOI: 10.3390/life12101458] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 09/10/2022] [Accepted: 09/14/2022] [Indexed: 11/16/2022] Open
Abstract
The wrist joint plays a vital role in activities of daily living. Clinical applications, e.g., therapeutic planning, prosthesis design, and wrist biomechanical analysis, require a detailed understanding of wrist maneuvers and motion. The lack of soft tissue information, motion analysis on limited carpal bones, etc., restrain the investigation of wrist kinematics. In this study, we established 3D models of carpal bones with their cartilages, and revealed the helical axes (HA) of all eight carpal bones for the first time. Both left and right hands at different positions of flexion-extension (FE) and radial-ulnar deviation (RUD) from five subjects were in-vivo imaged through a magnetic resonance imaging device. We segmented all of the bones, including cartilage information in the wrist joint, after which we explored the kinematics of all carpal bones with the HA method. The results showed that the HA of all carpal bones for FE bounded tightly and was mainly located slightly above the radius. During the RUD, carpal bones in the distal row rotated along with wrist movement while the scaphoid, lunate, and triquetrum primarily flexed and extended. Further results reported that the carpal bones translated greater in RUD than in FE. With the generation of more delicate wrist models and thorough investigations of carpal motion, a better understanding of wrist kinematics was obtained for further pathologic assessment and surgical treatment.
Collapse
Affiliation(s)
- Jianzhang Li
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany
- Correspondence: ; Tel.: +49-(0)-241-80-88386
| | - Björn Rath
- Department of Orthopaedic Surgery, Klinikum Wels-Grieskirchen, 4600 Wels, Austria
| | - Frank Hildebrand
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany
| | - Jörg Eschweiler
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany
| |
Collapse
|
3
|
Eschweiler J, Migliorini F. Reply to Nikolaidis, P.T.; Afonso, J. Comment on "Eschweiler et al. Anatomy, Biomechanics, and Loads of the Wrist Joint. Life 2022, 12, 188". Life (Basel) 2022; 12:1174. [PMID: 36013353 PMCID: PMC9410372 DOI: 10.3390/life12081174] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Accepted: 07/28/2022] [Indexed: 06/15/2023] Open
Abstract
Pantelis Nikolaidis and Jose Afonso published a letter [...].
Collapse
Affiliation(s)
- Jörg Eschweiler
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, Pauwelsstraße 30, 52074 Aachen, Germany;
| | | |
Collapse
|
4
|
Ji C, Li J, Praster M, Rath B, Hildebrand F, Eschweiler J. Smoothing the Undersampled Carpal Bone Model with Small Volume and Large Curvature: A Feasibility Study. Life (Basel) 2022; 12:life12050770. [PMID: 35629436 PMCID: PMC9145375 DOI: 10.3390/life12050770] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 05/10/2022] [Accepted: 05/18/2022] [Indexed: 12/27/2022] Open
Abstract
The carpal bones are eight small bones with irregularities and high curvature on their surfaces. The 3D model of the carpal bone serves as the foundation of further clinical applications, e.g., wrist kinematic behavior. However, due to the limitation of the Magnetic Resonance Imaging (MRI) technique, reconstructed carpal bone models are discretely undersampled, which has dramatic stair-step effects and leads to abnormal meshes on edges or surfaces, etc. Our study focuses on determining the viability of various smoothing techniques for a carpal model reconstructed by in vivo gathered MR images. Five algorithms, namely the Laplacian smoothing algorithm, the Laplacian smoothing algorithm with pre-dilation, the scale-dependent Laplacian algorithm, the curvature flow algorithm, and the inverse distance algorithm, were chosen for evaluation. The assessment took into account the Relative Volume Difference and the Hausdorff Distance as well as the surface quality and the preservation of morphological and morphometric properties. For the five algorithms, we analyzed the Relative Volume Difference and the Hausdorff Distance for all eight carpal bones. Among all the algorithms, the scale-dependent Laplacian method processed the best result regarding surface quality and the preservation of morphological and morphometric properties. Based on our extensive examinations, the scale-dependent Laplacian algorithm is suitable for the undersampled carpal bone model with small volume and large curvature.
Collapse
Affiliation(s)
- Chengcheng Ji
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany; (C.J.); (M.P.); (F.H.); (J.E.)
| | - Jianzhang Li
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany; (C.J.); (M.P.); (F.H.); (J.E.)
- Correspondence: ; Tel.: +49-(0)-241-808-8386
| | - Maximilian Praster
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany; (C.J.); (M.P.); (F.H.); (J.E.)
| | - Björn Rath
- Department of Orthopaedic Surgery, Klinikum Wels-Grieskirchen, 4600 Wels, Austria;
| | - Frank Hildebrand
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany; (C.J.); (M.P.); (F.H.); (J.E.)
| | - Jörg Eschweiler
- Department of Orthopaedics, Trauma and Reconstructive Surgery, RWTH Aachen University Hospital, 52074 Aachen, Germany; (C.J.); (M.P.); (F.H.); (J.E.)
| |
Collapse
|
5
|
Kang BK, Han Y, Oh J, Lim J, Ryu J, Yoon MS, Lee J, Ryu S. Automatic Segmentation for Favourable Delineation of Ten Wrist Bones on Wrist Radiographs Using Convolutional Neural Network. J Pers Med 2022; 12:776. [PMID: 35629198 PMCID: PMC9147335 DOI: 10.3390/jpm12050776] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 05/05/2022] [Accepted: 05/10/2022] [Indexed: 02/04/2023] Open
Abstract
Purpose: This study aimed to develop and validate an automatic segmentation algorithm for the boundary delineation of ten wrist bones, consisting of eight carpal and two distal forearm bones, using a convolutional neural network (CNN). Methods: We performed a retrospective study using adult wrist radiographs. We labeled the ground truth masking of wrist bones, and propose that the Fine Mask R-CNN consisted of wrist regions of interest (ROI) using a Single-Shot Multibox Detector (SSD) and segmentation via Mask R-CNN, plus the extended mask head. The primary outcome was an improvement in the prediction of delineation via the network combined with ground truth masking, and this was compared between two networks through five-fold validations. Results: In total, 702 images were labeled for the segmentation of ten wrist bones. The overall performance (mean (SD] of Dice coefficient) of the auto-segmentation of the ten wrist bones improved from 0.93 (0.01) using Mask R-CNN to 0.95 (0.01) using Fine Mask R-CNN (p < 0.001). The values of each wrist bone were higher when using the Fine Mask R-CNN than when using the alternative (all p < 0.001). The value derived for the distal radius was the highest, and that for the trapezoid was the lowest in both networks. Conclusion: Our proposed Fine Mask R-CNN model achieved good performance in the automatic segmentation of ten overlapping wrist bones derived from adult wrist radiographs.
Collapse
Affiliation(s)
- Bo-kyeong Kang
- Department of Radiology, College of Medicine, Hanyang University, Seoul 04763, Korea;
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04764, Korea; (M.S.Y.); (J.L.)
| | - Yelin Han
- Department of Computer Science, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Korea;
| | - Jaehoon Oh
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04764, Korea; (M.S.Y.); (J.L.)
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Korea
| | - Jongwoo Lim
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04764, Korea; (M.S.Y.); (J.L.)
- Department of Computer Science, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Korea;
| | - Jongbin Ryu
- Department of Software and Computer Engineering, Ajou University, Suwon 16499, Korea;
- Department of Artificial Intelligence, Ajou University, Suwon 16499, Korea
| | - Myeong Seong Yoon
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04764, Korea; (M.S.Y.); (J.L.)
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Korea
| | - Juncheol Lee
- Machine Learning Research Center for Medical Data, Hanyang University, Seoul 04764, Korea; (M.S.Y.); (J.L.)
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Korea
| | - Soorack Ryu
- Biostatistical Consulting and Research Lab, Medical Research Collaborating Center, Hanyang University, Seoul 04763, Korea;
| |
Collapse
|