Segmentation of Chronic Subdural Hematomas Using 3D Convolutional Neural Networks.

OBJECTIVE: Chronic subdural hematomas (cSDHs) are an increasingly prevalent neurologic disease that often requires surgical intervention to alleviate compression of the brain. Management of cSDHs relies heavily on computed tomography (CT) imaging, and serial imaging is frequently obtained to help direct management. The volume of hematoma provides critical information in guiding therapy and evaluating new methods of management. We set out to develop an automated program to compute the volume of hematoma on CT scans for both pre- and postoperative images. METHODS: A total of 21,710 images (128 CT scans) were manually segmented and used to train a convolutional neural network to automatically segment cSDHs. We included both pre- and postoperative coronal head CTs from patients undergoing surgical management of cSDHs. RESULTS: Our best model achieved a DICE score of 0.8351 on the testing dataset, and an average DICE score of 0.806 ± 0.06 on the validation set. This model was trained on the full dataset with reduced volumes, a network depth of 4, and postactivation residual blocks within the context modules of the encoder pathway. Patch trained models did not perform as well and decreasing the network depth from 5 to 4 did not appear to significantly improve performance. CONCLUSIONS: We successfully trained a convolutional neural network on a dataset of pre- and postoperative head CTs containing cSDH. This tool could assist with automated, accurate measurements for evaluating treatment efficacy.

Systolic pressure response to voluntary apnea predicts sympathetic tone in obstructive sleep apnea as a clinically useful index.

The present investigation tested the hypotheses that systolic arterial pressure (SAP) responses to voluntary apnea (a) serve as a surrogate of sympathetic nerve activity (SNA), (b) can distinguish Obstructive Sleep Apnea (OSA) patients from control subjects and (c) can document autonomic effects of treatment. 9 OSA and 10 control subjects were recruited in a laboratory study; 44 OSA subjects and 78 control subjects were recruited in a clinical study; and 21 untreated OSA subjects and 14 well-treated OSA subjects were recruited into a treatment study. Each subject performed hypoxic and room air voluntary apneas in triplicate. Muscle SNA (MSNA) and continuous AP were measured during each apnea in the laboratory study, while systolic arterial pressure (SAP) responses were measured continuously and by standard auscultation in the clinical and treatment studies. OSA subjects exhibited increased mean arterial pressure (MAP), SAP and MSNA responses to hypoxic apnea (all P<0.01) and the SAP response highly correlated with the MSNA response (R(2)=0.72, P<0.001). Clinical assessment confirmed that OSA subjects exhibited markedly elevated SAP responses (P<0.01), while treated OSA subjects had a decreased SAP response to apnea (P<0.04) compared to poorly treated subjects. These data indicate that (a) OSA subjects exhibit increased pressor and MSNA responses to apnea, and that (b) voluntary apnea may be a clinically useful assessment tool of autonomic dysregulation and treatment efficacy in OSA.