首页|Shandong Provincial Hospital Affiliated to Shandong First Medical University Rep orts Findings in Machine Learning (An ensemble machine learning model assists in the diagnosis of gastric ectopic pancreas and gastric stromal tumors)
Shandong Provincial Hospital Affiliated to Shandong First Medical University Rep orts Findings in Machine Learning (An ensemble machine learning model assists in the diagnosis of gastric ectopic pancreas and gastric stromal tumors)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Machine Learning is th e subject of a report. According to news reporting from Jinan, People's Republic of China, by NewsRx journalists, research stated, "To develop an ensemble machi ne learning (eML) model using multiphase computed tomography (MPCT) for distingu ishing between gastric ectopic pancreas (GEP) and gastric stromal tumors (GIST) in lesions <3 cm. In this study, we retrospectively collec ted MPCT images from 138 patients between April 2017 and June 2023 across two ce nters." Financial support for this research came from National Natural Science Foundatio n of China. The news correspondents obtained a quote from the research from Shandong Provinc ial Hospital Affiliated to Shandong First Medical University, "Cohort 1 comprise d 94 patients divided into a training cohort and an internal validation cohort, while the 44 patients from Cohort 2 constituted the external validation cohort. Deep learning (DL) models were constructed based on the lesion region, and radio mics features were extracted to develop radiomics models, which were later integ rated into the fusion model. Model performance was assessed through the analysis of the area under the receiver operating characteristic curve (AUROC). The diag nostic efficacy of the optimal model was compared with that of a radiologist. Ad ditionally, the radiologist with the assistance of the eML model provides a seco ndary diagnosis, to assess the potential clinical value of the model. After eval uation using an external validation cohort, the radiomics model demonstrated the highest performance in the venous phase, achieving AUROC of 0.87. The DL model showed optimal performance in the non-contrast phase, with AUROC of 0.81. The eM L achieved the best performance across all models, with AUROC of 0.90. The use o f eML-assisted analysis resulted in a significant improvement in the junior radi ologist's accuracy, rising from 0.77 to 0.93 (p <0.05). Ho wever, the senior radiologist's accuracy, while improving from 0.86 to 0.95, did not exhibit a statistically significant difference. eML model based on MPCT can effectively distinguish between GEPs and GISTs <3 cm. The multiphase CT-based fusion model, incorporating radiomics and DL technology, pr oves effective in distinguishing between GEP and gastric stromal tumors, serving as a valuable tool to enhance diagnoses and offering references for clinical de cision-making. No studies yet differentiated these tumors via radiomics or DL. R adiomics and DL methodologies unveil potentially distinct phenotypes within lesi ons. Quantitative analysis on CT for GIST and ectopic pancreas."
JinanPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesGastroenterologyHealth and MedicineMachine LearningPancreasPancreas Research
NETL
NSTL
