Prediction of Vestibular Schwannoma Surgical Outcome Using Deep Neural Network

被引:0
|
作者
Yu, Yansuo [1 ]
Song, Gang [2 ]
Zhao, Yixin [1 ]
Liang, Jiantao [2 ]
Liu, Qiang [1 ]
机构
[1] Beijing Inst Petrochem Technol, Acad Artificial Intelligence, Beijing, Peoples R China
[2] Capital Med Univ, XuanWu Hosp, Dept Neurosurg, Beijing, Peoples R China
关键词
Acoustic neuroma; Deep neural network; Machine learning; Surgical outcome; Vestibular schwannoma; FACIAL-NERVE FUNCTION; SURGERY; PRESERVATION;
D O I
10.1016/j.wneu.2023.03.090
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
-OBJECTIVE: To compare shallow machine learning models and deep neural network (DNN) model in prediction of vestibular schwannoma (VS) surgical outcome.-METHODS: One hundred eighty-eight patients with VS were included; all underwent suboccipital retrosigmoid sinus approach, and preoperative magnetic resonance imaging recorded a series of patient characteristics. De-gree of tumor resection was collected during surgery, and facial nerve function was evaluated on the eighth day after surgery. Potential predictors of VS surgical outcome were obtained by univariate analysis, including tumor diameter, tumor volume, tumor surface area, brain tissue edema, tu-mor property, and tumor shape. This study proposes a DNN framework to predict the prognosis of VS surgical out-comes based on potential predictors and compares it with a series of classic machine learning algorithms including logistic regression.-RESULTS: The results showed that 3 predictors of tumor diameter, tumor volume, and tumor surface area were the most important prognostic factors for VS surgical out-comes, followed by tumor shape, while brain tissue edema and tumor property were the least influential. Different from shallow machine learning models, such as logistic regression with average performance (area under the curve: 0.8263; accuracy: 81.38%), the proposed DNN shows better performance, where area under the curve and ac-curacy were 0.8723 and 85.64%, respectively.-CONCLUSIONS: Based on potential risk factors, DNN can be exploited to achieve preoperative automatic assessment of VS surgical outcomes, and its performance is significantly better than other methods. It is therefore highly warranted to continue to investigate their utility as complementary clinical tools in predicting surgical out-comes preoperatively.
引用
收藏
页码:E60 / E67
页数:8
相关论文
共 50 条
  • [1] Prediction of vestibular schwannoma recurrence using artificial neural network
    Abouzari, Mehdi
    Goshtasbi, Khodayar
    Sarna, Brooke
    Khosravi, Pooya
    Reutershan, Trevor
    Mostaghni, Navid
    Lin, Harrison W.
    Djalilian, Hamid R.
    [J]. LARYNGOSCOPE INVESTIGATIVE OTOLARYNGOLOGY, 2020, 5 (02): : 278 - 285
  • [2] Cystic vestibular schwannoma:: surgical outcome
    Fundová, P
    Charabi, S
    Tos, M
    Thomsen, J
    [J]. JOURNAL OF LARYNGOLOGY AND OTOLOGY, 2000, 114 (12): : 935 - 939
  • [3] Attention Guided Network for Vestibular Schwannoma Growth Prediction
    Wang, K.
    Chen, L.
    George-Jones, N.
    Hunter, J.
    Wang, J.
    [J]. MEDICAL PHYSICS, 2021, 48 (06)
  • [4] Surgical Outcomes in Cystic Vestibular Schwannoma Versus Solid Vestibular Schwannoma
    Tang, Ing Ping
    Freeman, Simon R.
    Rutherford, Scott A.
    King, Andrew T.
    Ramsden, Richard T.
    Lloyd, Simon K. W.
    [J]. OTOLOGY & NEUROTOLOGY, 2014, 35 (07) : 1266 - 1270
  • [5] Surgical technique for vestibular schwannoma
    Maruyama, Takashi
    [J]. NEUROLOGICAL SURGERY, 2006, 34 (07): : 681 - 693
  • [6] Surgical Approaches for Vestibular Schwannoma
    Sweeney A.D.
    Carlson M.L.
    Ehtesham M.
    Thompson R.C.
    Haynes D.S.
    [J]. Current Otorhinolaryngology Reports, 2014, 2 (4) : 256 - 264
  • [7] Vestibular Schwannoma Surgical Treatment
    You, Yong-Ping
    Zhang, Jun-Xia
    Lu, Ai-Lin
    Liu, Ning
    [J]. CNS NEUROSCIENCE & THERAPEUTICS, 2013, 19 (05) : 289 - 293
  • [8] Joint Vestibular Schwannoma Enlargement Prediction and Segmentation Using a Deep Multi-task Model
    Wang, Kai
    George-Jones, Nicholas A.
    Chen, Liyuan
    Hunter, Jacob B.
    Wang, Jing
    [J]. LARYNGOSCOPE, 2023, 133 (10): : 2754 - 2760
  • [9] Bridge Damage Prediction Using Deep Neural Network
    Lim, Soram
    Chi, Seokho
    [J]. COMPUTING IN CIVIL ENGINEERING 2019: SMART CITIES, SUSTAINABILITY, AND RESILIENCE, 2019, : 219 - 225
  • [10] Crop Yield Prediction Using Deep Neural Network
    Hague, Fatin Farhan
    Abdelgawad, Ahmed
    Yanambaka, Venkata Prasanth
    Yelamarthi, Kumar
    [J]. 2020 IEEE 6TH WORLD FORUM ON INTERNET OF THINGS (WF-IOT), 2020,