A semantic segmentation model for automatic precise identification of pituitary microadenomas with preoperative MRI.

IF 2.4 3区医学 Q2 CLINICAL NEUROLOGY

Neuroradiology Pub Date : 2025-04-04 DOI:10.1007/s00234-025-03599-w

ChenGang Yuan, Hang Qu, HuMing Dai, HaiXiao Jiang, DeMao Cao, LiYing Shao, LiangXue Zhou, AiJun Peng

{"title":"A semantic segmentation model for automatic precise identification of pituitary microadenomas with preoperative MRI.","authors":"ChenGang Yuan, Hang Qu, HuMing Dai, HaiXiao Jiang, DeMao Cao, LiYing Shao, LiangXue Zhou, AiJun Peng","doi":"10.1007/s00234-025-03599-w","DOIUrl":null,"url":null,"abstract":"Purpose: Magnetic resonance imaging (MRI) is an essential technique for diagnosing pituitary adenomas; however, it is also challenging for neurosurgeons to use it to precisely identify some types of microadenomas. A novel neural network model was developed using preoperative MRI to assist clinicians in diagnosing pituitary microadenomas.Method: Sixty patients with pathologically diagnosed pituitary microadenomas, including hyperprolactinemia (n = 19), growth hormone microadenomas (n = 17), and adrenocorticotropin microadenomas (n = 24), were enrolled. An image edge-supervised same receptive field semantic segmentation network was developed based on T1-weighted, T2-weighted, and contrast-enhanced T1-weighted images.Results: The mean Intersection over Unions of our neural network model were 0.7013 ± 0.3400, 0.7295 ± 0.321, and 0.8053 ± 0.3052 for the test sets of T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences, respectively, while the Dice Similarity Coefficient values were 0.8075 ± 0.3895, 0.8192 ± 0.3733, and 0.8860 ± 0.3443 for the corresponding sequences. The performance on contrast-enhanced T1-weighted images was better than that of the other two MR sequences.Conclusions: The image edge-supervised same receptive field segmentation network can potentially be used to precisely identify pituitary microadenomas automatically with preoperative MRI. The developed model exhibited good performance with contrast-enhanced T1-weighted images and could help neurosurgeons accurately determine the locations of pituitary microadenomas.","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neuroradiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00234-025-03599-w","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: Magnetic resonance imaging (MRI) is an essential technique for diagnosing pituitary adenomas; however, it is also challenging for neurosurgeons to use it to precisely identify some types of microadenomas. A novel neural network model was developed using preoperative MRI to assist clinicians in diagnosing pituitary microadenomas.

Method: Sixty patients with pathologically diagnosed pituitary microadenomas, including hyperprolactinemia (n = 19), growth hormone microadenomas (n = 17), and adrenocorticotropin microadenomas (n = 24), were enrolled. An image edge-supervised same receptive field semantic segmentation network was developed based on T1-weighted, T2-weighted, and contrast-enhanced T1-weighted images.

Results: The mean Intersection over Unions of our neural network model were 0.7013 ± 0.3400, 0.7295 ± 0.321, and 0.8053 ± 0.3052 for the test sets of T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences, respectively, while the Dice Similarity Coefficient values were 0.8075 ± 0.3895, 0.8192 ± 0.3733, and 0.8860 ± 0.3443 for the corresponding sequences. The performance on contrast-enhanced T1-weighted images was better than that of the other two MR sequences.

Conclusions: The image edge-supervised same receptive field segmentation network can potentially be used to precisely identify pituitary microadenomas automatically with preoperative MRI. The developed model exhibited good performance with contrast-enhanced T1-weighted images and could help neurosurgeons accurately determine the locations of pituitary microadenomas.

查看原文本刊更多论文

利用术前磁共振成像自动精确识别垂体微腺瘤的语义分割模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Neuroradiology 医学-核医学

CiteScore

5.30

自引率

3.60%

发文量

214

审稿时长

4-8 weeks

期刊介绍： Neuroradiology aims to provide state-of-the-art medical and scientific information in the fields of Neuroradiology, Neurosciences, Neurology, Psychiatry, Neurosurgery, and related medical specialities. Neuroradiology as the official Journal of the European Society of Neuroradiology receives submissions from all parts of the world and publishes peer-reviewed original research, comprehensive reviews, educational papers, opinion papers, and short reports on exceptional clinical observations and new technical developments in the field of Neuroimaging and Neurointervention. The journal has subsections for Diagnostic and Interventional Neuroradiology, Advanced Neuroimaging, Paediatric Neuroradiology, Head-Neck-ENT Radiology, Spine Neuroradiology, and for submissions from Japan. Neuroradiology aims to provide new knowledge about and insights into the function and pathology of the human nervous system that may help to better diagnose and treat nervous system diseases. Neuroradiology is a member of the Committee on Publication Ethics (COPE) and follows the COPE core practices. Neuroradiology prefers articles that are free of bias, self-critical regarding limitations, transparent and clear in describing study participants, methods, and statistics, and short in presenting results. Before peer-review all submissions are automatically checked by iThenticate to assess for potential overlap in prior publication.