Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network
PurposeMultiple myeloma (MM) and metastasis originated are the two common malignancy diseases in the spine. They usually show similar imaging patterns and are highly demanded to differentiate for precision diagnosis and treatment planning. The objective of this study is therefore to construct a nove...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.981769/full |
| _version_ | 1798002067745275904 |
|---|---|
| author | Kaili Chen Jiashi Cao Jiashi Cao Xin Zhang Xiang Wang Xiangyu Zhao Qingchu Li Song Chen Peng Wang Tielong Liu Juan Du Shiyuan Liu Lichi Zhang |
| author_facet | Kaili Chen Jiashi Cao Jiashi Cao Xin Zhang Xiang Wang Xiangyu Zhao Qingchu Li Song Chen Peng Wang Tielong Liu Juan Du Shiyuan Liu Lichi Zhang |
| author_sort | Kaili Chen |
| collection | DOAJ |
| description | PurposeMultiple myeloma (MM) and metastasis originated are the two common malignancy diseases in the spine. They usually show similar imaging patterns and are highly demanded to differentiate for precision diagnosis and treatment planning. The objective of this study is therefore to construct a novel deep-learning-based method for effective differentiation of two diseases, with the comparative study of traditional radiomics analysis.MethodsWe retrospectively enrolled a total of 217 patients with 269 lesions, who were diagnosed with spinal MM (79 cases, 81 lesions) or spinal metastases originated from lung cancer (138 cases, 188 lesions) confirmed by postoperative pathology. Magnetic resonance imaging (MRI) sequences of all patients were collected and reviewed. A novel deep learning model of the Multi-view Attention-Guided Network (MAGN) was constructed based on contrast-enhanced T1WI (CET1) sequences. The constructed model extracts features from three views (sagittal, coronal and axial) and fused them for a more comprehensive differentiation analysis, and the attention guidance strategy is adopted for improving the classification performance, and increasing the interpretability of the method. The diagnostic efficiency among MAGN, radiomics model and the radiologist assessment were compared by the area under the receiver operating characteristic curve (AUC).ResultsAblation studies were conducted to demonstrate the validity of multi-view fusion and attention guidance strategies: It has shown that the diagnostic model using multi-view fusion achieved higher diagnostic performance [ACC (0.79), AUC (0.77) and F1-score (0.67)] than those using single-view (sagittal, axial and coronal) images. Besides, MAGN incorporating attention guidance strategy further boosted performance as the ACC, AUC and F1-scores reached 0.81, 0.78 and 0.71, respectively. In addition, the MAGN outperforms the radiomics methods and radiologist assessment. The highest ACC, AUC and F1-score for the latter two methods were 0.71, 0.76 & 0.54, and 0.69, 0.71, & 0.65, respectively.ConclusionsThe proposed MAGN can achieve satisfactory performance in differentiating spinal MM between metastases originating from lung cancer, which also outperforms the radiomics method and radiologist assessment. |
| first_indexed | 2024-04-11T11:46:18Z |
| format | Article |
| id | doaj.art-28e1c656ce1f42ad9698f0e195fffd2f |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-11T11:46:18Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-28e1c656ce1f42ad9698f0e195fffd2f2022-12-22T04:25:32ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-09-011210.3389/fonc.2022.981769981769Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided networkKaili Chen0Jiashi Cao1Jiashi Cao2Xin Zhang3Xiang Wang4Xiangyu Zhao5Qingchu Li6Song Chen7Peng Wang8Tielong Liu9Juan Du10Shiyuan Liu11Lichi Zhang12Department of Hematology, Myeloma & Lymphoma Center, Shanghai Changzheng Hospital, Changzheng Hospital of the Naval Medical University, Huangpu, ChinaDepartment of Orthopedics, No. 455 Hospital of Chinese People’s Liberation Army, Shanghai 455 Hospital, Navy Medical University, Shanghai, ChinaDepartment of Orthopaedic Oncology, Spine Tumor Center, Shanghai Changzheng Hospital, Changzheng Hospital of the Navy Medical University, Huangpu, ChinaInstitute for Medical Image Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Radiology, Changzheng Hospital, Shanghai Changzheng Hospital, Navy Medical University, Huangpu, ChinaInstitute for Medical Image Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Radiology, Changzheng Hospital, Shanghai Changzheng Hospital, Navy Medical University, Huangpu, ChinaDepartment of Radiology, Changzheng Hospital, Shanghai Changzheng Hospital, Navy Medical University, Huangpu, ChinaDepartment of Radiology, Changzheng Hospital, Shanghai Changzheng Hospital, Navy Medical University, Huangpu, ChinaDepartment of Orthopaedic Oncology, Spine Tumor Center, Shanghai Changzheng Hospital, Changzheng Hospital of the Navy Medical University, Huangpu, ChinaDepartment of Hematology, Myeloma & Lymphoma Center, Shanghai Changzheng Hospital, Changzheng Hospital of the Naval Medical University, Huangpu, ChinaDepartment of Radiology, Changzheng Hospital, Shanghai Changzheng Hospital, Navy Medical University, Huangpu, ChinaInstitute for Medical Image Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaPurposeMultiple myeloma (MM) and metastasis originated are the two common malignancy diseases in the spine. They usually show similar imaging patterns and are highly demanded to differentiate for precision diagnosis and treatment planning. The objective of this study is therefore to construct a novel deep-learning-based method for effective differentiation of two diseases, with the comparative study of traditional radiomics analysis.MethodsWe retrospectively enrolled a total of 217 patients with 269 lesions, who were diagnosed with spinal MM (79 cases, 81 lesions) or spinal metastases originated from lung cancer (138 cases, 188 lesions) confirmed by postoperative pathology. Magnetic resonance imaging (MRI) sequences of all patients were collected and reviewed. A novel deep learning model of the Multi-view Attention-Guided Network (MAGN) was constructed based on contrast-enhanced T1WI (CET1) sequences. The constructed model extracts features from three views (sagittal, coronal and axial) and fused them for a more comprehensive differentiation analysis, and the attention guidance strategy is adopted for improving the classification performance, and increasing the interpretability of the method. The diagnostic efficiency among MAGN, radiomics model and the radiologist assessment were compared by the area under the receiver operating characteristic curve (AUC).ResultsAblation studies were conducted to demonstrate the validity of multi-view fusion and attention guidance strategies: It has shown that the diagnostic model using multi-view fusion achieved higher diagnostic performance [ACC (0.79), AUC (0.77) and F1-score (0.67)] than those using single-view (sagittal, axial and coronal) images. Besides, MAGN incorporating attention guidance strategy further boosted performance as the ACC, AUC and F1-scores reached 0.81, 0.78 and 0.71, respectively. In addition, the MAGN outperforms the radiomics methods and radiologist assessment. The highest ACC, AUC and F1-score for the latter two methods were 0.71, 0.76 & 0.54, and 0.69, 0.71, & 0.65, respectively.ConclusionsThe proposed MAGN can achieve satisfactory performance in differentiating spinal MM between metastases originating from lung cancer, which also outperforms the radiomics method and radiologist assessment.https://www.frontiersin.org/articles/10.3389/fonc.2022.981769/fullmultiple myeloma (MM)spinal metastaseslung cancerdeep learningattention guidance strategyradiomics |
| spellingShingle | Kaili Chen Jiashi Cao Jiashi Cao Xin Zhang Xiang Wang Xiangyu Zhao Qingchu Li Song Chen Peng Wang Tielong Liu Juan Du Shiyuan Liu Lichi Zhang Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network Frontiers in Oncology multiple myeloma (MM) spinal metastases lung cancer deep learning attention guidance strategy radiomics |
| title | Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network |
| title_full | Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network |
| title_fullStr | Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network |
| title_full_unstemmed | Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network |
| title_short | Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network |
| title_sort | differentiation between spinal multiple myeloma and metastases originated from lung using multi view attention guided network |
| topic | multiple myeloma (MM) spinal metastases lung cancer deep learning attention guidance strategy radiomics |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.981769/full |
| work_keys_str_mv | AT kailichen differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT jiashicao differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT jiashicao differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT xinzhang differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT xiangwang differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT xiangyuzhao differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT qingchuli differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT songchen differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT pengwang differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT tielongliu differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT juandu differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT shiyuanliu differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork AT lichizhang differentiationbetweenspinalmultiplemyelomaandmetastasesoriginatedfromlungusingmultiviewattentionguidednetwork |