Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors
Abstract Objectives The objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs). Methods Eighty-one patients, including 51 with grade 1 PNETs and 30 wit...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-025-01555-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594350383562752 |
|---|---|
| author | Shuangyang Mo Cheng Huang Yingwei Wang Shanyu Qin |
| author_facet | Shuangyang Mo Cheng Huang Yingwei Wang Shanyu Qin |
| author_sort | Shuangyang Mo |
| collection | DOAJ |
| description | Abstract Objectives The objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs). Methods Eighty-one patients, including 51 with grade 1 PNETs and 30 with grade 2/3 PNETs, were included in this retrospective study after confirmation through pathological examination. The patients were randomly allocated to the training or test group in a 6:4 ratio. Univariate and multivariate logistic regression were used for screening clinical and ultrasonic characteristics. Ultrasomics is ultrasound-based radiomics. Ultrasomics features were extracted from both the intratumoral and peritumoral regions of conventional EUS images. Subsequently, the dimensionality of these radiomics features was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm. A machine learning algorithm, namely multilayer perception (MLP), was employed to construct prediction models using only the nonzero coefficient features and retained clinical features, respectively. Results One hundred seven ultrasomics features based on EUS were extracted, and only features with nonzero coefficients were ultimately retained. Among all the models, the combined ultrasomics model achieved the greatest performance, with an AUC of 0.858 (95% CI, 0.7512 - 0.9642) in the training group and 0.842 (95% CI, 0.7061 - 0.9785) in the test group. A calibration curve and a decision curve analysis (DCA) also demonstrated its accuracy and utility. Conclusions The integrated model using EUS ultrasomics features from intratumoral and peritumoral tumors accurately predicts PNETs' pathological grades pre-surgery, aiding personalized treatment planning. Trial registration ChiCTR2400091906. |
| format | Article |
| id | doaj-art-88cf9a77134b47639c12b777fef55b12 |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-88cf9a77134b47639c12b777fef55b122025-01-19T12:43:27ZengBMCBMC Medical Imaging1471-23422025-01-0125112010.1186/s12880-025-01555-xEndoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumorsShuangyang Mo0Cheng Huang1Yingwei Wang2Shanyu Qin3Gastroenterology Department/Clinical Nutrition Department, Liuzhou People’s Hospital Affiliated to Guangxi Medical UniversityOncology Department, Liuzhou Peoples’ Hospital Affiliated to Guangxi Medical UniversityGastroenterology Department/Clinical Nutrition Department, Liuzhou People’s Hospital Affiliated to Guangxi Medical UniversityGastroenterology Department, The First Affiliated Hospital of Guangxi Medical UniversityAbstract Objectives The objective is to develop and validate intratumoral and peritumoral ultrasomics models utilizing endoscopic ultrasonography (EUS) to predict pathological grading in pancreatic neuroendocrine tumors (PNETs). Methods Eighty-one patients, including 51 with grade 1 PNETs and 30 with grade 2/3 PNETs, were included in this retrospective study after confirmation through pathological examination. The patients were randomly allocated to the training or test group in a 6:4 ratio. Univariate and multivariate logistic regression were used for screening clinical and ultrasonic characteristics. Ultrasomics is ultrasound-based radiomics. Ultrasomics features were extracted from both the intratumoral and peritumoral regions of conventional EUS images. Subsequently, the dimensionality of these radiomics features was reduced using the least absolute shrinkage and selection operator (LASSO) algorithm. A machine learning algorithm, namely multilayer perception (MLP), was employed to construct prediction models using only the nonzero coefficient features and retained clinical features, respectively. Results One hundred seven ultrasomics features based on EUS were extracted, and only features with nonzero coefficients were ultimately retained. Among all the models, the combined ultrasomics model achieved the greatest performance, with an AUC of 0.858 (95% CI, 0.7512 - 0.9642) in the training group and 0.842 (95% CI, 0.7061 - 0.9785) in the test group. A calibration curve and a decision curve analysis (DCA) also demonstrated its accuracy and utility. Conclusions The integrated model using EUS ultrasomics features from intratumoral and peritumoral tumors accurately predicts PNETs' pathological grades pre-surgery, aiding personalized treatment planning. Trial registration ChiCTR2400091906.https://doi.org/10.1186/s12880-025-01555-xPancreatic neuroendocrine tumorsEndoscopic ultrasonographyUlstrasomicsMachine learningPathological grading |
| spellingShingle | Shuangyang Mo Cheng Huang Yingwei Wang Shanyu Qin Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors BMC Medical Imaging Pancreatic neuroendocrine tumors Endoscopic ultrasonography Ulstrasomics Machine learning Pathological grading |
| title | Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors |
| title_full | Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors |
| title_fullStr | Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors |
| title_full_unstemmed | Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors |
| title_short | Endoscopic ultrasonography-based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors |
| title_sort | endoscopic ultrasonography based intratumoral and peritumoral machine learning ultrasomics model for predicting the pathological grading of pancreatic neuroendocrine tumors |
| topic | Pancreatic neuroendocrine tumors Endoscopic ultrasonography Ulstrasomics Machine learning Pathological grading |
| url | https://doi.org/10.1186/s12880-025-01555-x |
| work_keys_str_mv | AT shuangyangmo endoscopicultrasonographybasedintratumoralandperitumoralmachinelearningultrasomicsmodelforpredictingthepathologicalgradingofpancreaticneuroendocrinetumors AT chenghuang endoscopicultrasonographybasedintratumoralandperitumoralmachinelearningultrasomicsmodelforpredictingthepathologicalgradingofpancreaticneuroendocrinetumors AT yingweiwang endoscopicultrasonographybasedintratumoralandperitumoralmachinelearningultrasomicsmodelforpredictingthepathologicalgradingofpancreaticneuroendocrinetumors AT shanyuqin endoscopicultrasonographybasedintratumoralandperitumoralmachinelearningultrasomicsmodelforpredictingthepathologicalgradingofpancreaticneuroendocrinetumors |