A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography
Two-dimensional shear wave elastography (2D-SWE) is an effective and feasible method for plantar fasciitis (PF) evaluation. Until now, only experienced doctors have been able to give relatively accurate evaluation via ultrasound images, resulting in low efficiency and high cost. Therefore, designing...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8830477/ |
| _version_ | 1824042085354831872 |
|---|---|
| author | Junling Gao Lei Xu Ayache Bouakaz Mingxi Wan |
| author_facet | Junling Gao Lei Xu Ayache Bouakaz Mingxi Wan |
| author_sort | Junling Gao |
| collection | DOAJ |
| description | Two-dimensional shear wave elastography (2D-SWE) is an effective and feasible method for plantar fasciitis (PF) evaluation. Until now, only experienced doctors have been able to give relatively accurate evaluation via ultrasound images, resulting in low efficiency and high cost. Therefore, designing automatic algorithms to recognize the pattern of these ultrasound images is urgently required. In recent years, deep learning (DL) has made considerable progress in computer- aided diagnosis (CAD). However, there have been no studies that apply DL to the diagnosis of PF. To achieve robust PF classification, this paper builds a deep Siamese framework with multitask learning and transfer learning (DS-MLTL), which learns discriminative visual features and effective recognition functions using 2D-SWE. The DS-MLTL model comprises two VGG-style branches and a multitask loss including a classification loss and a Siamese loss. The Siamese loss leverages the intrinsic structure (similarities) of different images and contains a contrastive constraint and a similar constraint. In our framework, visual features and the multitask loss are learned jointly, and they can benefit from each other. To train the DS-MLTL model effectively, the model transfers knowledge from the large-scale ImageNet dataset to the PF classification task. For model evaluation, an SWE dataset of plantar fascia, which contains 282 images of a PF pattern and 60 images of a healthy pattern, is collected. Experimental results show that the DS-MLTL method achieves favorable accuracy of 85.09 ± 6.67% and performs better than human-crafted features extracted from B-mode ultrasound and SWE. In addition, DS-MLTL also obtains the best performance compared with different DL models. |
| first_indexed | 2024-12-22T23:36:13Z |
| format | Article |
| id | doaj.art-d1f285fe89c74692876ea2523d8483b8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T23:36:13Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d1f285fe89c74692876ea2523d8483b82022-12-21T18:08:34ZengIEEEIEEE Access2169-35362019-01-01713099913100710.1109/ACCESS.2019.29406458830477A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave ElastographyJunling Gao0https://orcid.org/0000-0001-7161-3718Lei Xu1Ayache Bouakaz2Mingxi Wan3https://orcid.org/0000-0002-6704-1216Department of Biomedical Engineering, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an, ChinaDepartment of Biomedical Engineering, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an, ChinaUMR 1253, iBrain, Université de Tours, Inserm, Tours, FranceDepartment of Biomedical Engineering, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an, ChinaTwo-dimensional shear wave elastography (2D-SWE) is an effective and feasible method for plantar fasciitis (PF) evaluation. Until now, only experienced doctors have been able to give relatively accurate evaluation via ultrasound images, resulting in low efficiency and high cost. Therefore, designing automatic algorithms to recognize the pattern of these ultrasound images is urgently required. In recent years, deep learning (DL) has made considerable progress in computer- aided diagnosis (CAD). However, there have been no studies that apply DL to the diagnosis of PF. To achieve robust PF classification, this paper builds a deep Siamese framework with multitask learning and transfer learning (DS-MLTL), which learns discriminative visual features and effective recognition functions using 2D-SWE. The DS-MLTL model comprises two VGG-style branches and a multitask loss including a classification loss and a Siamese loss. The Siamese loss leverages the intrinsic structure (similarities) of different images and contains a contrastive constraint and a similar constraint. In our framework, visual features and the multitask loss are learned jointly, and they can benefit from each other. To train the DS-MLTL model effectively, the model transfers knowledge from the large-scale ImageNet dataset to the PF classification task. For model evaluation, an SWE dataset of plantar fascia, which contains 282 images of a PF pattern and 60 images of a healthy pattern, is collected. Experimental results show that the DS-MLTL method achieves favorable accuracy of 85.09 ± 6.67% and performs better than human-crafted features extracted from B-mode ultrasound and SWE. In addition, DS-MLTL also obtains the best performance compared with different DL models.https://ieeexplore.ieee.org/document/8830477/Plantar fasciitisSiamese networktransfer learningshear wave elastography |
| spellingShingle | Junling Gao Lei Xu Ayache Bouakaz Mingxi Wan A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography IEEE Access Plantar fasciitis Siamese network transfer learning shear wave elastography |
| title | A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography |
| title_full | A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography |
| title_fullStr | A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography |
| title_full_unstemmed | A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography |
| title_short | A Deep Siamese-Based Plantar Fasciitis Classification Method Using Shear Wave Elastography |
| title_sort | deep siamese based plantar fasciitis classification method using shear wave elastography |
| topic | Plantar fasciitis Siamese network transfer learning shear wave elastography |
| url | https://ieeexplore.ieee.org/document/8830477/ |
| work_keys_str_mv | AT junlinggao adeepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT leixu adeepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT ayachebouakaz adeepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT mingxiwan adeepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT junlinggao deepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT leixu deepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT ayachebouakaz deepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography AT mingxiwan deepsiamesebasedplantarfasciitisclassificationmethodusingshearwaveelastography |