Department of Medical Physics, University of Wisconsin at Madison, Madison, WI, USA.
Department of Medical Physics, University of Wisconsin at Madison, Madison, WI, USA; Department of Radiology, University of Wisconsin at Madison, Madison, WI, USA; Deparment of Biomedical Engineering, University of Wisconsin at Madison, Madison, WI, USA.
Magn Reson Imaging. 2023 Nov;103:162-168. doi: 10.1016/j.mri.2023.07.015. Epub 2023 Aug 2.
Minimally-invasive surgical techniques for intracerebral hemorrhage (ICH) evacuation use imaging to guide the suction, lysing and/or drainage from the hemorrhage site via various designs. A previous international surgical study has shown that reduction of hematoma volume below 15 ml is indicative of improved long term patient outcomes. The study noted a need for tools to periodically visualize remaining clot during intervention to increase the likelihood of evacuating sufficient clot volumes without endangering rebleeds. Robust segmentation of MRI could guide surgeons and radiologists regarding remaining regions and approaches for prudent evacuation. We thus propose a Convolutional Neural Network (CNN) to identify and autonomously segment clot and peripheral edema in MR images of the brain and generate an estimate of the remaining clot volume.
We used a retrospective, locally-acquired dataset of ICH patient scans taken on 3 T MRI scanners. Three sets of ground truth manual segmentations were independently generated by two imaging scientists and one radiology fellow. Evaluation of clot age was determined based on relative contrast of hemorrhage components and reviewed by a neurosurgeon. Model accuracy was determined by pixel-wise Dice coefficient (DC) calculations between each ground truth manual segmentation and the machine-derived autonomous segmentations.
The model produced autonomous segmentations of clot core with an average DC of 0.75 ± 0.21 relative to manual segmentations of the same scans. For edema, it produced segmentations with an average DC of 0.68 ± 0.16 relative to manual. From these pixel-wise segmentations, clot volume can be calculated. Model-produced segmentations underestimated clot volumes by an average of 17% relative to ground-truth.
The machine learning models were able to identify and segment volumes of ICH components swiftly and accurately.
用于脑内血肿（ICH）清除的微创外科技术使用成像技术通过各种设计引导从血肿部位抽吸、溶解和/或引流。 先前的一项国际外科研究表明，血肿量减少至 15ml 以下表明患者的长期预后得到改善。 该研究指出需要有工具来定期可视化干预过程中残留的凝块，以增加排空足够的凝块体积而不危及再出血的可能性。 对 MRI 的稳健分割可以指导外科医生和放射科医生了解剩余区域，并为明智地清除提供途径。 因此，我们提出了一种卷积神经网络（CNN）来识别和自主分割脑 MRI 图像中的凝块和周围水肿，并生成剩余凝块体积的估计值。
我们使用了在 3T MRI 扫描仪上采集的 ICH 患者扫描的回顾性、本地获得的数据集。 两位成像科学家和一位放射科医师独立生成了三组地面真实手动分割。 根据出血成分的相对对比度确定凝块年龄的评估，并由神经外科医生进行审查。 通过每个地面真实手动分割与机器自主分割之间的像素级 Dice 系数（DC）计算来确定模型的准确性。
该模型生成的凝块核心自主分割的平均 DC 为 0.75±0.21，与相同扫描的手动分割相对应。 对于水肿，它生成的分割的平均 DC 为 0.68±0.16，与手动分割相对应。 可以从这些像素级分割中计算出凝块体积。 与地面真实值相比，模型产生的分割平均低估了 17%的凝块体积。
机器学习模型能够快速准确地识别和分割 ICH 成分的体积。
