Objective This study aims to construct and validate a predictable deep learning model associated with clinical data and multi-sequence magnetic resonance imaging(MRI)for short-term postoperative facial nerve function ...Objective This study aims to construct and validate a predictable deep learning model associated with clinical data and multi-sequence magnetic resonance imaging(MRI)for short-term postoperative facial nerve function in patients with acoustic neuroma.Methods A total of 110 patients with acoustic neuroma who underwent surgery through the retrosigmoid sinus approach were included.Clinical data and raw features from four MRI sequences(T1-weighted,T2-weighted,T1-weighted contrast enhancement,and T2-weighted-Flair images)were analyzed.Spearman correlation analysis along with least absolute shrinkage and selection operator regression were used to screen combined clinical and radiomic features.Nomogram,machine learning,and convolutional neural network(CNN)models were constructed to predict the prognosis of facial nerve function on the seventh day after surgery.Receiver operating characteristic(ROC)curve and decision curve analysis(DCA)were used to evaluate model performance.A total of 1050 radiomic parameters were extracted,from which 13 radiomic and 3 clinical features were selected.Results The CNN model performed best among all prediction models in the test set with an area under the curve(AUC)of 0.89(95%CI,0.84–0.91).Conclusion CNN modeling that combines clinical and multi-sequence MRI radiomic features provides excellent performance for predicting short-term facial nerve function after surgery in patients with acoustic neuroma.As such,CNN modeling may serve as a potential decision-making tool for neurosurgery.展开更多
Objective To evaluate the long-term facial nerve funtion of patients following microsurgical removal of large and huge acoustic neuroma,and to indentify the factors that influence these outcomes. Methods A retrospecti...Objective To evaluate the long-term facial nerve funtion of patients following microsurgical removal of large and huge acoustic neuroma,and to indentify the factors that influence these outcomes. Methods A retrospective review was performed,which included 176 consecutive patients with a展开更多
Objective To report the authors' experiences in hearing preservation during acoustic neuroma (AN) resection procedures. Methods Two cases of AN removal via retrosigmoid approach were reviewed. Hearing preservation...Objective To report the authors' experiences in hearing preservation during acoustic neuroma (AN) resection procedures. Methods Two cases of AN removal via retrosigmoid approach were reviewed. Hearing preservation was attempted in the aid of endoscopic technique along with continuous monitoring of the compound action potential (CAP) and auditory brainstem response(ABR) during the surgery. Results The tumor in Case 1 was 1.5 cm in diameter. The average pure-tone hearing threshold was 30 dB HL and ABR was normal. Waves I, III and V of ABR were present following tumor removal. At 7th month follow-up, audiometric thresholds and ABR inter-peak intervals had recovered to pre-operative levels, with normal facial nerve function. The patient in Case 2 had bilateral AN. The tumors measured 4.0 cm(left) and 5.0 cm (right) on MRI scans. The AN on the right side was removed first, followed by removal of the left AN four months later. Intraoperative CAP monitoring was employed during removal of the left AN. While efforts to preserve the cochlear nerve were not successful, CAPs were still present after tumor removal. Conclusions Intraoperatively recorded CAPs are not reliable in predicting postoperative hearing outcomes. In contrast, ABRs are an indicator of function of the peripheral auditory pathway. Presence of waves I, III and V following tumor removal may represent preservation of useful hearing.展开更多
Background Although various monitoring techniques have been used routinely in the treatment of the lesions in the skull base, iatrogenic facial paresis or paralysis remains a significant clinical problem. The aim of t...Background Although various monitoring techniques have been used routinely in the treatment of the lesions in the skull base, iatrogenic facial paresis or paralysis remains a significant clinical problem. The aim of this study was to investigate the effect of intraoperative facial motor evoked potentials monitoring with transcranial electrical stimulation on preservation of facial nerve function. Method From January to November 2005, 19 patients with large acoustic neuroma were treated using intraoperative facial motor evoked potentials monitoring with transcranial electrical stimulation （TCEMEP） for preservation of facial nerve function. The relationship between the decrease of MEP amplitude after tumor removal and the postoperative function of the facial nerve was analyzed. Results MEP amplitude decreased more than 75% in 11 patients, of which 6 presented significant facial paralysis （H-B grade 3）, and 5 had mild facial paralysis （H-B grade 2）. In the other 8 patients, whose MEP amplitude decreased less than 75%, 1 experienced significant facial paralysis, 5 had mild facial paralysis, and 2 were normal. Conclusions Intraoperative TCEMEP can be used to predict postoperative function of the facial nerve. The decreased MEP amplitude above 75 % is an alarm point for possible severe facial paralysis.展开更多
文摘Objective This study aims to construct and validate a predictable deep learning model associated with clinical data and multi-sequence magnetic resonance imaging(MRI)for short-term postoperative facial nerve function in patients with acoustic neuroma.Methods A total of 110 patients with acoustic neuroma who underwent surgery through the retrosigmoid sinus approach were included.Clinical data and raw features from four MRI sequences(T1-weighted,T2-weighted,T1-weighted contrast enhancement,and T2-weighted-Flair images)were analyzed.Spearman correlation analysis along with least absolute shrinkage and selection operator regression were used to screen combined clinical and radiomic features.Nomogram,machine learning,and convolutional neural network(CNN)models were constructed to predict the prognosis of facial nerve function on the seventh day after surgery.Receiver operating characteristic(ROC)curve and decision curve analysis(DCA)were used to evaluate model performance.A total of 1050 radiomic parameters were extracted,from which 13 radiomic and 3 clinical features were selected.Results The CNN model performed best among all prediction models in the test set with an area under the curve(AUC)of 0.89(95%CI,0.84–0.91).Conclusion CNN modeling that combines clinical and multi-sequence MRI radiomic features provides excellent performance for predicting short-term facial nerve function after surgery in patients with acoustic neuroma.As such,CNN modeling may serve as a potential decision-making tool for neurosurgery.
文摘Objective To evaluate the long-term facial nerve funtion of patients following microsurgical removal of large and huge acoustic neuroma,and to indentify the factors that influence these outcomes. Methods A retrospective review was performed,which included 176 consecutive patients with a
文摘Objective To report the authors' experiences in hearing preservation during acoustic neuroma (AN) resection procedures. Methods Two cases of AN removal via retrosigmoid approach were reviewed. Hearing preservation was attempted in the aid of endoscopic technique along with continuous monitoring of the compound action potential (CAP) and auditory brainstem response(ABR) during the surgery. Results The tumor in Case 1 was 1.5 cm in diameter. The average pure-tone hearing threshold was 30 dB HL and ABR was normal. Waves I, III and V of ABR were present following tumor removal. At 7th month follow-up, audiometric thresholds and ABR inter-peak intervals had recovered to pre-operative levels, with normal facial nerve function. The patient in Case 2 had bilateral AN. The tumors measured 4.0 cm(left) and 5.0 cm (right) on MRI scans. The AN on the right side was removed first, followed by removal of the left AN four months later. Intraoperative CAP monitoring was employed during removal of the left AN. While efforts to preserve the cochlear nerve were not successful, CAPs were still present after tumor removal. Conclusions Intraoperatively recorded CAPs are not reliable in predicting postoperative hearing outcomes. In contrast, ABRs are an indicator of function of the peripheral auditory pathway. Presence of waves I, III and V following tumor removal may represent preservation of useful hearing.
基金the National Natural Science Foundation of China (No.30571899)
文摘Background Although various monitoring techniques have been used routinely in the treatment of the lesions in the skull base, iatrogenic facial paresis or paralysis remains a significant clinical problem. The aim of this study was to investigate the effect of intraoperative facial motor evoked potentials monitoring with transcranial electrical stimulation on preservation of facial nerve function. Method From January to November 2005, 19 patients with large acoustic neuroma were treated using intraoperative facial motor evoked potentials monitoring with transcranial electrical stimulation （TCEMEP） for preservation of facial nerve function. The relationship between the decrease of MEP amplitude after tumor removal and the postoperative function of the facial nerve was analyzed. Results MEP amplitude decreased more than 75% in 11 patients, of which 6 presented significant facial paralysis （H-B grade 3）, and 5 had mild facial paralysis （H-B grade 2）. In the other 8 patients, whose MEP amplitude decreased less than 75%, 1 experienced significant facial paralysis, 5 had mild facial paralysis, and 2 were normal. Conclusions Intraoperative TCEMEP can be used to predict postoperative function of the facial nerve. The decreased MEP amplitude above 75 % is an alarm point for possible severe facial paralysis.
