García-Mejido José Antonio, Galán-Paez Juan, Solis-Martín David, Fernández-Palacín Fernando, Fernández-Palacín Ana, Sainz-Bueno José Antonio
Department of Surgery, Faculty of Medicine, University of Seville, 41009 Seville, Spain.
Department of Computer Science and Artificial Intelligence, Faculty of Computer Engineering, University of Seville, 41080 Seville, Spain.
J Clin Med. 2025 May 22;14(11):3634. doi: 10.3390/jcm14113634.
The aim of this study was to design a fully automated hybrid AI-based method, combining a convolutional neural network (CNN) and a tree-based model (XGBoost), which was capable of diagnosing different pelvic organ prolapses (POPs) in a dynamic two-dimensional ultrasound study from the midsagittal plane. This was a prospective observational study with 188 patients (99 with POP and 89 without POP). Transperineal pelvic floor ultrasound videos were performed, and normality or POP was defined. These videos were subsequently labeled, and an algorithm was designed to detect POP based on three phases: 1. Segmentation-a CNN was used to locate and identify the visible pelvic organs in each frame of the ultrasound video. The output had a very high dimensionality. 2. Feature engineering and dataset construction-new features related to the position and shape of the organs detected using the CNN were generated. 3. The POP predictive model-this was created from the dataset generated in the feature engineering phase. To evaluate diagnostic performance, accuracy, precision, recall, and F1-score were considered, along with the degree of agreement with the expert examiner. The best agreements were observed in the diagnosis of cystocele and uterine prolapse (88.1%) and enterocoele (81.4%). The proposed methodology showed an accuracy of 96.43%, an overall accuracy of 98.31%, a recall of 100%, and an F1-score of 98.18% in detecting the presence of POP. However, when differentiating between the various types of POP, we observed that the precision, accuracy, recall, and F1-score were higher when detecting cystocele and uterine prolapse. We have developed the first predictive model capable of diagnosing POP in a dynamic, bi-dimensional ultrasound study from the midsagittal plane using deep learning and machine learning techniques.
本研究的目的是设计一种基于人工智能的全自动混合方法，该方法结合了卷积神经网络（CNN）和基于树的模型（XGBoost），能够在中矢状面的动态二维超声研究中诊断不同类型的盆腔器官脱垂（POP）。这是一项前瞻性观察性研究，共有188名患者（99名患有POP，89名未患POP）。进行了经会阴盆底超声检查，并定义了正常或POP情况。随后对这些视频进行标记，并设计了一种算法，基于三个阶段检测POP：1. 分割——使用CNN定位和识别超声视频每一帧中可见的盆腔器官。输出具有非常高的维度。2. 特征工程和数据集构建——生成与使用CNN检测到的器官位置和形状相关的新特征。3. POP预测模型——这是根据特征工程阶段生成的数据集创建的。为了评估诊断性能，考虑了准确性、精确性、召回率和F1分数，以及与专家检查者的一致程度。在膀胱膨出和子宫脱垂（88.1%）以及肠膨出（81.4%）的诊断中观察到最佳一致性。所提出的方法在检测POP存在时的准确率为96.43%，总体准确率为98.31%，召回率为100%，F1分数为98.18%。然而，在区分不同类型的POP时，我们观察到在检测膀胱膨出和子宫脱垂时，精确性、准确性、召回率和F1分数更高。我们开发了第一个能够使用深度学习和机器学习技术在中矢状面的动态二维超声研究中诊断POP的预测模型。
