CT EVALUATION OF VARIOUS LINEAR INDICES IN CHILDREN WITH CLINICALLY SUSPECTED HYDROCEPHALUS

Multiple Machine Learning Approaches for Morphometric Parameters in Prediction of Hydrocephalus

BACKGROUND

The diagnosis of hydrocephalus is mainly based on imaging findings. However, the significance of many imaging indicators may change, especially in some degenerative diseases, and even lead to misdiagnosis.

METHODS

This study explored the effectiveness of commonly used morphological parameters and typical radiographic findings in hydrocephalus diagnosis. The patients' imaging data were divided into three groups, including the hydrocephalus group, the symptomatic group, and the normal control group. The diagnostic validity and weight of various parameters were compared between groups by multiple machine learning methods.

RESULTS

Our results demonstrated that Evans' ratio is the most valuable diagnostic indicator compared to the hydrocephalus group and the normal control group. But frontal horns' ratio is more useful in diagnosing patients with symptoms. Meanwhile, the sign of disproportionately enlarged subarachnoid space and third ventricle enlargement could be effective diagnostic indicators in all situations.

CONCLUSION

Both morphometric parameters and radiological features were essential in diagnosing hydrocephalus, but the weights are different in different situations. The machine learning approaches can be applied to optimize the diagnosis of other diseases and consistently update the clinical diagnostic criteria.

Exploiting lamina terminalis appearance and motion in prediction of hydrocephalus using convolutional LSTM network

BACKGROUND

Evaluation of the lamina terminalis (LT) is crucial for non-invasive evaluation of the CSF diversion for the treatment of hydrocephalus. Together with deep learning algorithms, morphological and physiological analyses of the LT may play an important role in the management of hydrocephalus.

AIM

We aim to show that exploiting the motion of LT can contribute to the evaluation of hydrocephalus using deep learning algorithms.

METHODS

The dataset contains 61 True-fisp data with routine sequences 37 of which are labeled as 'hydrocephalus' and the others as 'normal condition'. A fifteen-year experienced neuroradiologist divided data into two groups. The first group, 'hydrocephalus', consists of patients with typical MRI findings (ventriculomegaly, enlargement of the third ventricular recesses and lateral ventricular horns, decreased mamillo-pontine distance, reduced frontal horn angle, thinning/elevation of the corpus callosum, and non-dilated convexity sulci), and the second group contains samples that did not show any symptoms or neurologic abnormality and labeled as 'normal condition'. The region of interest was determined by the radiologist supervisor to cover the LT. To achieve our purpose, we used both spatial and spatio-temporal analysis with two different deep learning architectures. We utilized Convolutional Neural Networks (CNN) for spatial and Convolutional Long Short-Term Memory (ConvLSTM) models for spatio-temporal analysis using an ROI around LT on sagittal True-fisp images.

RESULTS

Our results show that 80.7% classification accuracy was achieved with the ConvLSTM model exploiting LT motion, whereas 76.5% and 71.6% accuracies were obtained by the 2D CNN model using all frames, and only the first frame from only spatial information, respectively.

CONCLUSION

We suggest that the motion of the LT can be used as an additional attribute to the spatial information to evaluate the hydrocephalus.

Comparison of morphometric parameters in prediction of hydrocephalus using random forests

Ventricles of the human brain enlarge with aging, neurodegenerative diseases, intrinsic, and extrinsic pathologies. The morphometric examination of neuroimages is an effective approach to assess structural changes occurring due to diseases such as hydrocephalus. In this study, we explored the effectiveness of commonly used morphological parameters in hydrocephalus diagnosis. For this purpose, the effect of six common morphometric parameters; Frontal Horns' Length (FHL), Maximum Lateral Length (MLL), Biparietal Diameter (BPD), Evans' Ratio (ER), Cella Media Ratio (CMR), and Frontal Horns' Ratio (FHR) were compared in terms of their importance in predicting hydrocephalus using a Random Forest classifier. The experimental results demonstrated that hydrocephalus can be detected with 91.46 % accuracy using all of these measurements. The accuracy of classification using only CMR and FHL reached up to 93.33 %. In terms of individual performances, CMR and FHL were the top performers whereas BPD and FHR did not contribute as much to the overall accuracy.