Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system
Pancreatic cystic neoplasms (PCNs) are a group of heterogeneous diseases with distinct prognosis. Existing differential diagnosis methods require invasive biopsy or prolonged monitoring. We sought to develop an inexpensive, non-invasive differential diagnosis system for PCNs based on radiomics featu...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.941744/full |
| _version_ | 1811292956409200640 |
|---|---|
| author | Zhenglin Dong Zhenglin Dong Xiahan Chen Zhaorui Cheng Yuanbo Luo Min He Tao Chen Zijie Zhang Zijie Zhang Xiaohua Qian Wei Chen |
| author_facet | Zhenglin Dong Zhenglin Dong Xiahan Chen Zhaorui Cheng Yuanbo Luo Min He Tao Chen Zijie Zhang Zijie Zhang Xiaohua Qian Wei Chen |
| author_sort | Zhenglin Dong |
| collection | DOAJ |
| description | Pancreatic cystic neoplasms (PCNs) are a group of heterogeneous diseases with distinct prognosis. Existing differential diagnosis methods require invasive biopsy or prolonged monitoring. We sought to develop an inexpensive, non-invasive differential diagnosis system for PCNs based on radiomics features and clinical characteristics for a higher total PCN screening rate. We retrospectively analyzed computed tomography images and clinical data from 129 patients with PCN, including 47 patients with intraductal papillary mucinous neoplasms (IPMNs), 49 patients with serous cystadenomas (SCNs), and 33 patients with mucinous cystic neoplasms (MCNs). Six clinical characteristics and 944 radiomics features were tested, and nine features were finally selected for model construction using DXScore algorithm. A five-fold cross-validation algorithm and a test group were applied to verify the results. In the five-fold cross-validation section, the AUC value of our model was 0.8687, and the total accuracy rate was 74.23%, wherein the accuracy rates of IPMNs, SCNs, and MCNs were 74.26%, 78.37%, and 68.00%, respectively. In the test group, the AUC value was 0.8462 and the total accuracy rate was 73.61%. In conclusion, our research constructed an end-to-end powerful PCN differential diagnosis system based on radiomics method, which could assist decision-making in clinical practice. |
| first_indexed | 2024-04-13T04:54:07Z |
| format | Article |
| id | doaj.art-322a4c3c8aee488d889bc6576fcece7b |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-13T04:54:07Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-322a4c3c8aee488d889bc6576fcece7b2022-12-22T03:01:33ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-12-011210.3389/fonc.2022.941744941744Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted systemZhenglin Dong0Zhenglin Dong1Xiahan Chen2Zhaorui Cheng3Yuanbo Luo4Min He5Tao Chen6Zijie Zhang7Zijie Zhang8Xiaohua Qian9Wei Chen10Department of Biliary-Pancreatic Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of orthopedics, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaSchool of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Rheumatology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Otorhinolaryngology, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Biliary-Pancreatic Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Biliary-Pancreatic Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Biliary-Pancreatic Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Liver Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaSchool of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, ChinaDepartment of Biliary-Pancreatic Surgery, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, ChinaPancreatic cystic neoplasms (PCNs) are a group of heterogeneous diseases with distinct prognosis. Existing differential diagnosis methods require invasive biopsy or prolonged monitoring. We sought to develop an inexpensive, non-invasive differential diagnosis system for PCNs based on radiomics features and clinical characteristics for a higher total PCN screening rate. We retrospectively analyzed computed tomography images and clinical data from 129 patients with PCN, including 47 patients with intraductal papillary mucinous neoplasms (IPMNs), 49 patients with serous cystadenomas (SCNs), and 33 patients with mucinous cystic neoplasms (MCNs). Six clinical characteristics and 944 radiomics features were tested, and nine features were finally selected for model construction using DXScore algorithm. A five-fold cross-validation algorithm and a test group were applied to verify the results. In the five-fold cross-validation section, the AUC value of our model was 0.8687, and the total accuracy rate was 74.23%, wherein the accuracy rates of IPMNs, SCNs, and MCNs were 74.26%, 78.37%, and 68.00%, respectively. In the test group, the AUC value was 0.8462 and the total accuracy rate was 73.61%. In conclusion, our research constructed an end-to-end powerful PCN differential diagnosis system based on radiomics method, which could assist decision-making in clinical practice.https://www.frontiersin.org/articles/10.3389/fonc.2022.941744/fullradiomicscomputed tomographypancreatic cystic neoplasmdifferential diagnosisternary classification model |
| spellingShingle | Zhenglin Dong Zhenglin Dong Xiahan Chen Zhaorui Cheng Yuanbo Luo Min He Tao Chen Zijie Zhang Zijie Zhang Xiaohua Qian Wei Chen Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system Frontiers in Oncology radiomics computed tomography pancreatic cystic neoplasm differential diagnosis ternary classification model |
| title | Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system |
| title_full | Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system |
| title_fullStr | Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system |
| title_full_unstemmed | Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system |
| title_short | Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system |
| title_sort | differential diagnosis of pancreatic cystic neoplasms through a radiomics assisted system |
| topic | radiomics computed tomography pancreatic cystic neoplasm differential diagnosis ternary classification model |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.941744/full |
| work_keys_str_mv | AT zhenglindong differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT zhenglindong differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT xiahanchen differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT zhaoruicheng differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT yuanboluo differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT minhe differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT taochen differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT zijiezhang differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT zijiezhang differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT xiaohuaqian differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem AT weichen differentialdiagnosisofpancreaticcysticneoplasmsthrougharadiomicsassistedsystem |