A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification
Abstract Deep-learning models have shown promise in differentiating between benign and malignant lesions. Previous studies have primarily focused on specific anatomical regions, overlooking tumors occurring throughout the body with highly heterogeneous whole-body backgrounds. Using neurofibromatosis...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01454-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585388561006592 |
|---|---|
| author | Cheng-Jiang Wei Yan Tang Yang-Bai Sun Tie-Long Yang Cheng Yan Hui Liu Jun Liu Jing-Ning Huang Ming-Han Wang Zhen-Wei Yao Ji-Long Yang Zhi-Chao Wang Qing-Feng Li |
| author_facet | Cheng-Jiang Wei Yan Tang Yang-Bai Sun Tie-Long Yang Cheng Yan Hui Liu Jun Liu Jing-Ning Huang Ming-Han Wang Zhen-Wei Yao Ji-Long Yang Zhi-Chao Wang Qing-Feng Li |
| author_sort | Cheng-Jiang Wei |
| collection | DOAJ |
| description | Abstract Deep-learning models have shown promise in differentiating between benign and malignant lesions. Previous studies have primarily focused on specific anatomical regions, overlooking tumors occurring throughout the body with highly heterogeneous whole-body backgrounds. Using neurofibromatosis type 1 (NF1) as an example, this study developed highly accurate MRI-based deep-learning models for the early automated screening of malignant peripheral nerve sheath tumors (MPNSTs) against complex whole-body background. In a Chinese seven-center cohort, data from 347 subjects were analyzed. Our one-step model incorporated normal tissue/organ labels to provide contextual information, offering a solution for tumors with complex backgrounds. To address privacy concerns, we utilized a lightweight deep neural network suitable for hospital deployment. The final model achieved an accuracy of 85.71% for MPNST diagnosis in the validation cohort and 84.75% accuracy in the independent test set, outperforming another classic two-step model. This success suggests potential for AI models in screening other whole-body primary/metastatic tumors. |
| format | Article |
| id | doaj-art-d7c70073279c4d1984179c37d7af57a4 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-d7c70073279c4d1984179c37d7af57a42025-01-26T12:53:47ZengNature Portfolionpj Digital Medicine2398-63522025-01-01811910.1038/s41746-025-01454-zA multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identificationCheng-Jiang Wei0Yan Tang1Yang-Bai Sun2Tie-Long Yang3Cheng Yan4Hui Liu5Jun Liu6Jing-Ning Huang7Ming-Han Wang8Zhen-Wei Yao9Ji-Long Yang10Zhi-Chao Wang11Qing-Feng Li12Neurofibromatosis Type 1 Center and Laboratory for Neurofibromatosis Type 1 Research, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Radiology, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Musculoskeletal Surgery, Fudan University Shanghai Cancer CenterDepartment of Bone and Soft Tissue Tumor, Tianjin Medical University Cancer Institute and HospitalDepartment of Radiology, Zhongshan Hospital Fudan UniversityDepartment of Radiology, The Fourth Hospital of Hebei Medical UniversityNeurofibromatosis Type 1 Center and Laboratory for Neurofibromatosis Type 1 Research, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of MedicineShanghai Key Laboratory of Sleep Disordered Breathing, Department of Otolaryngology-Head and Neck Surgery, Otolaryngology Institute of Shanghai Jiao Tong University, Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of MedicineDepartment of Ophthalmology, Ninth People’s Hospital, Shanghai JiaoTong University School of Medicine, Shanghai Key Laboratory of Orbital Diseases and Ocular OncologyDepartment of Radiology, Huashan Hospital, Fudan UniversityDepartment of Bone and Soft Tissue Tumor, Tianjin Medical University Cancer Institute and HospitalNeurofibromatosis Type 1 Center and Laboratory for Neurofibromatosis Type 1 Research, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of MedicineNeurofibromatosis Type 1 Center and Laboratory for Neurofibromatosis Type 1 Research, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of MedicineAbstract Deep-learning models have shown promise in differentiating between benign and malignant lesions. Previous studies have primarily focused on specific anatomical regions, overlooking tumors occurring throughout the body with highly heterogeneous whole-body backgrounds. Using neurofibromatosis type 1 (NF1) as an example, this study developed highly accurate MRI-based deep-learning models for the early automated screening of malignant peripheral nerve sheath tumors (MPNSTs) against complex whole-body background. In a Chinese seven-center cohort, data from 347 subjects were analyzed. Our one-step model incorporated normal tissue/organ labels to provide contextual information, offering a solution for tumors with complex backgrounds. To address privacy concerns, we utilized a lightweight deep neural network suitable for hospital deployment. The final model achieved an accuracy of 85.71% for MPNST diagnosis in the validation cohort and 84.75% accuracy in the independent test set, outperforming another classic two-step model. This success suggests potential for AI models in screening other whole-body primary/metastatic tumors.https://doi.org/10.1038/s41746-025-01454-z |
| spellingShingle | Cheng-Jiang Wei Yan Tang Yang-Bai Sun Tie-Long Yang Cheng Yan Hui Liu Jun Liu Jing-Ning Huang Ming-Han Wang Zhen-Wei Yao Ji-Long Yang Zhi-Chao Wang Qing-Feng Li A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification npj Digital Medicine |
| title | A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification |
| title_full | A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification |
| title_fullStr | A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification |
| title_full_unstemmed | A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification |
| title_short | A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification |
| title_sort | multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification |
| url | https://doi.org/10.1038/s41746-025-01454-z |
| work_keys_str_mv | AT chengjiangwei amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT yantang amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT yangbaisun amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT tielongyang amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT chengyan amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT huiliu amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT junliu amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT jingninghuang amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT minghanwang amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT zhenweiyao amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT jilongyang amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT zhichaowang amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT qingfengli amulticenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT chengjiangwei multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT yantang multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT yangbaisun multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT tielongyang multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT chengyan multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT huiliu multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT junliu multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT jingninghuang multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT minghanwang multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT zhenweiyao multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT jilongyang multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT zhichaowang multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification AT qingfengli multicenterstudyofneurofibromatosistype1utilizingdeeplearningforwholebodytumoridentification |