1
|
Guo S, Chen H, Sheng X, Xiong Y, Wu M, Fischer K, Tasian GE, Fan Y, Yin S. Cross-modal Transfer Learning Based on an Improved CycleGAN Model for Accurate Kidney Segmentation in Ultrasound Images. ULTRASOUND IN MEDICINE & BIOLOGY 2024:S0301-5629(24)00255-2. [PMID: 39181806 DOI: 10.1016/j.ultrasmedbio.2024.06.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2023] [Revised: 03/28/2024] [Accepted: 06/19/2024] [Indexed: 08/27/2024]
Abstract
OBJECTIVE Deep-learning algorithms have been widely applied in the field of automatic kidney ultrasound (US) image segmentation. However, obtaining a large number of accurate kidney labels clinically is very difficult and time-consuming. To solve this problem, we have proposed an efficient cross-modal transfer learning method to improve the performance of the segmentation network on a limited labeled kidney US dataset. METHODS We aim to implement an improved image-to-image translation network called Seg-CycleGAN to generate accurate annotated kidney US data from labeled abdomen computed tomography images. The Seg-CycleGAN framework primarily consists of two structures: (i) a standard CycleGAN network to visually simulate kidney US from a publicly available labeled abdomen computed tomography dataset; (ii) and a segmentation network to ensure accurate kidney anatomical structures in US images. Based on the large number of simulated kidney US images and small number of real annotated kidney US images, we then aimed to employ a fine-tuning strategy to obtain better segmentation results. RESULTS To validate the effectiveness of the proposed method, we tested this method on both normal and abnormal kidney US images. The experimental results showed that the proposed method achieved a segmentation accuracy of 0.8548 in dice similarity coefficient on all testing datasets and 0.7622 on the abnormal testing dataset. CONCLUSIONS Compared with existing data augmentation and transfer learning methods, the proposed method improved the accuracy and generalization of the kidney US image segmentation network on a limited number of training datasets. It therefore has the potential to significantly reduce annotation costs in clinical settings.
Collapse
Affiliation(s)
- Shuaizi Guo
- School of Computer Science and Technology, Nanjing Tech University, Nanjing, China
| | - Haijie Chen
- School of Computer Science and Technology, Nanjing Tech University, Nanjing, China
| | - Xiangyu Sheng
- School of Computer Science and Technology, Nanjing Tech University, Nanjing, China
| | - Yinzheng Xiong
- Khoury College of Computer Sciences, Northeastern University, Boston, MA, USA
| | - Menglin Wu
- School of Computer Science and Technology, Nanjing Tech University, Nanjing, China; Carbon Medical Device Ltd, Shenzhen, China
| | - Katherine Fischer
- Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, PA, USA; Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, PA, USA
| | - Gregory E Tasian
- Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, PA, USA; Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, PA, USA; Department of Biostatistics, Epidemiology, and Informatics, The University of Pennsylvania, Philadelphia, PA, USA
| | - Yong Fan
- Department of Radiology, Perelman School of Medicine, The University of Pennsylvania, Philadelphia, PA, USA
| | - Shi Yin
- School of Computer Science and Technology, Nanjing Tech University, Nanjing, China.
| |
Collapse
|
2
|
Radiomics Model Based on Enhanced Gradient Level Set Segmentation Algorithm to Predict the Prognosis of Endoscopic Treatment of Sinusitis. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:9511631. [PMID: 35785138 PMCID: PMC9242818 DOI: 10.1155/2022/9511631] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/15/2022] [Revised: 06/01/2022] [Accepted: 06/09/2022] [Indexed: 11/18/2022]
Abstract
Methods Computed tomography (CT) images of sinusitis in 91 patients were collected. By introducing boundary gradient information into the edge detection function, the sensitivity of the level set model to the boundary of different intensities of lesions was adjusted to obtain accurate segmentation results. After that, the segmented CT image was imported into Mazda texture analysis software for feature extraction. Three dimensionality reduction methods were used to screen the best texture features. Four analysis methods in the B11 module were used to calculate the misclassified rate (MCR). Results The segmentation algorithm based on an enhanced gradient level set has good segmentation results for sinusitis lesions. The radiomics results show that the raw data analysis method under the Fisher dimensionality reduction method has a low MCR (25.27%). Conclusion The enhanced gradient level set segmentation algorithm can segment sinusitis lesions accurately. The radiomics model effectively predicts the prognosis of endoscopic treatment of sinusitis.
Collapse
|
3
|
Priyanka A, Ganesan K. Hippocampus segmentation and classification for dementia analysis using pre-trained neural network models. BIOMED ENG-BIOMED TE 2021; 66:581-592. [PMID: 34626530 DOI: 10.1515/bmt-2021-0070] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2021] [Accepted: 09/08/2021] [Indexed: 11/15/2022]
Abstract
The diagnostic and clinical overlap of early mild cognitive impairment (EMCI), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI) and Alzheimer disease (AD) is a vital oncological issue in dementia disorder. This study is designed to examine Whole brain (WB), grey matter (GM) and Hippocampus (HC) morphological variation and identify the prominent biomarkers in MR brain images of demented subjects to understand the severity progression. Curve evolution based on shape constraint is carried out to segment the complex brain structure such as HC and GM. Pre-trained models are used to observe the severity variation in these regions. This work is evaluated on ADNI database. The outcome of the proposed work shows that curve evolution method could segment HC and GM regions with better correlation. Pre-trained models are able to show significant severity difference among WB, GM and HC regions for the considered classes. Further, prominent variation is observed between AD vs. EMCI, AD vs. MCI and AD vs. LMCI in the whole brain, GM and HC. It is concluded that AlexNet model for HC region result in better classification for AD vs. EMCI, AD vs. MCI and AD vs. LMCI with an accuracy of 93, 78.3 and 91% respectively.
Collapse
Affiliation(s)
- Ahana Priyanka
- Department of Electronics Engineering, Madras Institute of Technology, Chennai, India
| | - Kavitha Ganesan
- Department of Electronics Engineering, Madras Institute of Technology, Chennai, India
| |
Collapse
|
4
|
Intelligent Segmentation Algorithm for Diagnosis of Meniere's Disease in the Inner Auditory Canal Using MRI Images with Three-Dimensional Level Set. CONTRAST MEDIA & MOLECULAR IMAGING 2021; 2021:2329313. [PMID: 34366724 PMCID: PMC8315872 DOI: 10.1155/2021/2329313] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/31/2021] [Revised: 06/24/2021] [Accepted: 07/12/2021] [Indexed: 11/23/2022]
Abstract
This paper aimed to explore segmentation effects of the magnetic resonance imaging (MRI) images of the inner auditory canal of patients with Meniere's disease under the intelligent segmentation method of the inner ear based on three-dimensional (3D) level set (IS3DLS). The statistical shape model and the level set segmentation algorithm were combined to propose the IS3DLS. First, the shape training samples of the inner ear model were determined, and the results were manually segmented to further obtain region of interest (ROI) of the inner ear. The IS3DLS was employed to accurately segment MRI images of the inner auditory canal of patients with Meniere's disease. The segmentation performance of IS3DLS was compared with the expert manual segmentation method and the region growth level set-based segmentation algorithm. Results showed that Matthews correlation coefficient (MCC), Dice similarity coefficient (DSC), false positive rate (FPR), and false negative rate (FNR) of this algorithm were 0.9599, 0.9594, 0.0325, and 0.03655, respectively. Therefore, the IS3DLS could achieve good segmentation effect in MRI images of the inner auditory canal of patients with Meniere's disease, which was helpful for diagnosis and subsequent treatment of Meniere's disease.
Collapse
|
5
|
Ma J, He J, Yang X. Learning Geodesic Active Contours for Embedding Object Global Information in Segmentation CNNs. IEEE TRANSACTIONS ON MEDICAL IMAGING 2021; 40:93-104. [PMID: 32897860 DOI: 10.1109/tmi.2020.3022693] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Most existing CNNs-based segmentation methods rely on local appearances learned on the regular image grid, without consideration of the object global information. This article aims to embed the object global geometric information into a learning framework via the classical geodesic active contours (GAC). We propose a level set function (LSF) regression network, supervised by the segmentation ground truth, LSF ground truth and geodesic active contours, to not only generate the segmentation probabilistic map but also directly minimize the GAC energy functional in an end-to-end manner. With the help of geodesic active contours, the segmentation contour, embedded in the level set function, can be globally driven towards the image boundary to obtain lower energy, and the geodesic constraint can lead the segmentation result to have fewer outliers. Extensive experiments on four public datasets show that (1) compared with state-of-the-art (SOTA) learning active contour methods, our method can achieve significantly better performance; (2) compared with recent SOTA methods that are designed for reducing boundary errors, our method also outperforms them with more accurate boundaries; (3) compared with SOTA methods on two popular multi-class segmentation challenge datasets, our method can still obtain superior or competitive results in both organ and tumor segmentation tasks. Our study demonstrates that introducing global information by GAC can significantly improve segmentation performance, especially on reducing the boundary errors and outliers, which is very useful in applications such as organ transplantation surgical planning and multi-modality image registration where boundary errors can be very harmful.
Collapse
|
6
|
Glass-cutting medical images via a mechanical image segmentation method based on crack propagation. Nat Commun 2020; 11:5669. [PMID: 33168802 PMCID: PMC7652839 DOI: 10.1038/s41467-020-19392-7] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2020] [Accepted: 10/07/2020] [Indexed: 11/23/2022] Open
Abstract
Medical image segmentation is crucial in diagnosing and treating diseases, but automatic segmentation of complex images is very challenging. Here we present a method, called the crack propagation method (CPM), based on the principles of fracture mechanics. This unique method converts the image segmentation problem into a mechanical one, extracting the boundary information of the target area by tracing the crack propagation on a thin plate with grooves corresponding to the area edge. The greatest advantage of CPM is in segmenting images involving blurred or even discontinuous boundaries, a task difficult to achieve by existing auto-segmentation methods. The segmentation results for synthesized images and real medical images show that CPM has high accuracy in segmenting complex boundaries. With increasing demand for medical imaging in clinical practice and research, this method will show its unique potential. Automatic segmentation of complex medical images is challenging. Here, the authors present a crack propagation method based on the principles of fracture mechanics: extracting the boundary information of the target area by tracing the crack propagation on a thin plate with grooves corresponding to the area edge.
Collapse
|