Department of Neurosurgery, The People's Hospital of Sixian, Sixian, Anhui Province 234399, China.
Department of Neurosurgery, The Third People's Hospital of Hefei, Hefei 230022, China.
Comput Math Methods Med. 2022 Aug 9;2022:9701702. doi: 10.1155/2022/9701702. eCollection 2022.
To explore the convolutional neural network (CNN) method in measuring hematoma volume-assisted microsurgery for spontaneous cerebral hemorrhage.
A total of 120 patients with spontaneous cerebral hemorrhage were selected and randomly divided into control and CNN groups with 60 patients in each group. Patients in the control group received traditional Tada formula to calculate hematoma volume and microsurgery. Convolutional neural network algorithm segmentation was used to measure hematoma volume, and microsurgery was performed in the CNN group. This article assessed neurological function, ability to live daily, complication rate, and prognosis.
The incidence of postoperative complications in the CNN group (13.33%) was lower than the control group (43.33%). The neurological function and daily living ability in the CNN groups were recovered better. The incidence of poor prognosis in the CNN group (16.67%) was lower than the control group (30.00%).
Convolutional neural network measurement of hematoma volume to assist microsurgical treatment of spontaneous intracerebral hemorrhage patients is conducive to early recovery, reducing the damage to the patients' cerebral nerves.
探讨卷积神经网络（CNN）方法在测量血肿量辅助自发性脑出血微创手术中的应用。
选取 120 例自发性脑出血患者，随机分为对照组和 CNN 组，每组 60 例。对照组患者采用传统的 Tada 公式计算血肿量并接受微创手术。CNN 组采用卷积神经网络算法分割测量血肿量并进行微创手术。本文评估了神经功能、日常生活能力、并发症发生率和预后。
CNN 组（13.33%）术后并发症发生率低于对照组（43.33%）。CNN 组神经功能和日常生活能力恢复更好。CNN 组预后不良发生率（16.67%）低于对照组（30.00%）。
卷积神经网络测量血肿量辅助自发性脑出血患者微创手术有利于早期恢复，减轻对患者脑神经的损伤。
