Evaluation of an artificial intelligent hydrocephalus diagnosis model based on transfer learning

Abstract

To design and develop artificial intelligence (AI) hydrocephalus (HYC) imaging diagnostic model using a transfer learning algorithm and evaluate its application in the diagnosis of HYC by non-contrast material-enhanced head computed tomographic (CT) images. A training and validation dataset of non-contrast material-enhanced head CT examinations that comprised of 1000 patients with HYC and 1000 normal people with no HYC accumulating to 28,500 images. Images were pre-processed, and the feature variables were labeled. The feature variables were extracted by the neural network for transfer learning. AI algorithm performance was tested on a separate dataset containing 250 examinations of HYC and 250 of normal. Resident, attending and consultant in the department of radiology were also tested with the test sets, their results were compared with the AI model. Final model performance for HYC showed 93.6% sensitivity (95% confidence interval: 77%, 97%) and 94.4% specificity (95% confidence interval: 79%, 98%), with area under the characteristic curve of 0.93. Accuracy rate of model, resident, attending, and consultant were 94.0%, 93.4%, 95.6%, and 97.0%. AI can effectively identify the characteristics of HYC from CT images of the brain and automatically analyze the images. In the future, AI can provide auxiliary diagnosis of image results and reduce the burden on junior doctors.

Influence of Percutaneous Drainage Surgery and the Interval to Perform Laparoscopic Cholecystectomy on Acute Cholecystitis through Genetic Algorithm-Based Contrast-Enhanced Ultrasound Imaging

“…Generally speaking, cholecystectomy should be performed within 72 hours after the onset of mild AC. Ultrasound is the preferred imaging examination method for suspected AC patients [ 23 ]. The gallbladder wall ultrasound imaging showing streaks, the degree of cholestasis, and gallbladder stone disease are all considered to be related to cholecystitis, and to intravenously inject ultrasound contrast agent can distinguish the diffuse defect of the gallbladder wall [ 24 ].…”

SVM-Based Normal Pressure Hydrocephalus Detection

“…Other groups have already focused on automated NPH detection. Unspecific ventricular enlargement was successfully detected in computed tomography (CT) imaging [22] and machine learning was used to determine most discriminate regions in patients who had been identified by radiologists as having a NPH pattern [12]. In contrast, we compared the performance of an SVM against human read-K f).…”

“…Other groups have already focused on automated NPH detection. Unspecific ventricular enlargement was successfully detected in computed tomography (CT) imaging [ 22 ] and machine learning was used to determine most discriminate regions in patients who had been identified by radiologists as having a NPH pattern [ 12 ]. In contrast, we compared the performance of an SVM against human readings in terms of how reliably NPH patients can be identified in MRI and surpassed the accuracy of others who differentiated NPH, vascular cognitive disease and HC using sulcal patterns [ 23 ] or a 3D convolutional ladder network in the differentiation of NPH, Alzheimer’s dementia and HC [ 24 ].…”

Progression in Neuroimaging of Normal Pressure Hydrocephalus

“…To take the topic further, Duan et al from China reported an artificial intelligence (AI) model designed for a straightforward diagnostic purpose that uses CT images of 1,000 patients with hydrocephalus and 1,000 controls ( 37 ). The model surprisingly delivered 93.6 and 94.4% specificity with an accurate rate of 94%, higher than that of junior residents (93.4%) but still slightly lower than that of more experienced doctors.…”