Pereira Fernanda Veloso, Ferreira Davi, Garmes Heraldo, Zantut-Wittmann Denise Engelbrecht, Rogério Fabio, Fabbro Mateus Dal, Formentin Cleiton, Forster Carlos Henrique Quartucci, Reis Fabiano
Department of Radiology, School of Medical Sciences, State University of Campinas (UNICAMP), Campinas, São Paulo, Brazil.
CEDS - Computer Science Department at Aeronautics Institute at Technology (ITA), São José Dos Campos, São Paulo, Brazil.
J Imaging Inform Med. 2025 Feb 7. doi: 10.1007/s10278-025-01417-6.
Consistency of pituitary macroadenomas is a key determinant in surgical outcomes, with non-soft consistency linked to more complications and incomplete resections. This study aimed to develop a machine learning model to predict the consistency of pituitary macroadenomas to improve surgical planning and outcomes. A retrospective study of patients with pituitary macroadenomas was conducted. Data included brain magnetic resonance imaging findings (diameter and apparent diffusion coefficient), patient demographics (age and sex), and tumor consistency. Seventy patients were evaluated, 59 with soft consistency and 11 with non-soft consistency. The support vector machine (SVM) was the best model with ROC AUC score of 83.3% [95% CI 65.8, 97.6], AP AUC of 69.8% [95% CI 41.3, 91.1], sensitivity of 73.1% [95% CI 44.4, 100], specificity of 89.8% [95% CI 82, 96.7], F1 score of 0.63 [95% CI 0.36, 0.83], and Matthews correlation coefficient score of 0.57 [95% CI 0.29, 0.79]. These findings indicate a significant improvement over random classification, as confirmed by a permutation test (p < 0.05). Additionally, the model had a 67.4% probability of outperforming the second-best model in cross-validation, as determined through Bayesian analysis, and demonstrated statistical significance (p < 0.05) compared to non-ensemble models. Using explainability heuristics, both 2D and 3D probability maps highlighted areas with a higher probability of non-soft consistency. The attributes most influential in the correct classification by our best model were male sex and age ≤ 42.25 years. Despite some limitations, the SVM model showed promise in predicting tumor consistency, which could aid in surgical planning. To address concerns about generalizability, we have created an open-access repository to promote future external validation studies and collaboration with other research centers, with the goal of enhancing model prediction through transfer learning.
垂体大腺瘤的质地是手术结果的关键决定因素，质地非软与更多并发症及不完全切除相关。本研究旨在开发一种机器学习模型来预测垂体大腺瘤的质地，以改善手术规划和结果。对垂体大腺瘤患者进行了一项回顾性研究。数据包括脑磁共振成像结果（直径和表观扩散系数）、患者人口统计学特征（年龄和性别）以及肿瘤质地。评估了70例患者，其中59例质地软，11例质地非软。支持向量机（SVM）是最佳模型，其ROC AUC得分为83.3% [95% CI 65.8, 97.6]，AP AUC为69.8% [95% CI 41.3, 91.1]，灵敏度为73.1% [95% CI 44.4, 100]，特异性为89.8% [95% CI 82, 96.7]，F1得分为0.63 [95% CI 0.36, 0.83]，马修斯相关系数得分为0.57 [95% CI 0.29, 0.79]。这些结果表明与随机分类相比有显著改善，经排列检验证实（p < 0.05）。此外，通过贝叶斯分析确定，该模型在交叉验证中优于第二佳模型的概率为67.4%，与非集成模型相比具有统计学意义（p < 0.05）。使用可解释性启发法，二维和三维概率图突出了质地非软概率较高的区域。对我们最佳模型正确分类最有影响的属性是男性性别和年龄≤42.25岁。尽管存在一些局限性，但支持向量机模型在预测肿瘤质地方面显示出前景，这有助于手术规划。为解决对可推广性的担忧，我们创建了一个开放获取的储存库，以促进未来的外部验证研究以及与其他研究中心的合作，目标是通过迁移学习增强模型预测。
