Level Set Based Hippocampus Segmentation in MR Images with Improved Initialization Using Region Growing

Deep learning for the diagnosis of mesial temporal lobe epilepsy

OBJECTIVE

This study aimed to enable the automatic detection of the hippocampus and diagnose mesial temporal lobe epilepsy (MTLE) with the hippocampus as the epileptogenic area using artificial intelligence (AI). We compared the diagnostic accuracies of AI and neurosurgical physicians for MTLE with the hippocampus as the epileptogenic area.

METHOD

In this study, we used an AI program to diagnose MTLE. The image sets were processed using a code written in Python 3.7.4. and analyzed using Open Computer Vision 4.5.1. The deep learning model, which was a fine-tuned VGG16 model, consisted of several layers. The diagnostic accuracies of AI and board-certified neurosurgeons were compared.

RESULTS

AI detected the hippocampi automatically and diagnosed MTLE with the hippocampus as the epileptogenic area on both T2-weighted imaging (T2WI) and fluid-attenuated inversion recovery (FLAIR) images. The diagnostic accuracies of AI based on T2WI and FLAIR data were 99% and 89%, respectively, and those of neurosurgeons based on T2WI and FLAIR data were 94% and 95%, respectively. The diagnostic accuracy of AI was statistically higher than that of board-certified neurosurgeons based on T2WI data (p = 0.00129).

CONCLUSION

The deep learning-based AI program is highly accurate and can diagnose MTLE better than some board-certified neurosurgeons. AI can maintain a certain level of output accuracy and can be a reliable assistant to doctors.

Radiomics: a primer on high-throughput image phenotyping

Radiomics is a high-throughput approach to image phenotyping. It uses computer algorithms to extract and analyze a large number of quantitative features from radiological images. These radiomic features collectively describe unique patterns that can serve as digital fingerprints of disease. They may also capture imaging characteristics that are difficult or impossible to characterize by the human eye. The rapid development of this field is motivated by systems biology, facilitated by data analytics, and powered by artificial intelligence. Here, as part of Abdominal Radiology's special issue on Quantitative Imaging, we provide an introduction to the field of radiomics. The technique is formally introduced as an advanced application of data analytics, with illustrating examples in abdominal radiology. Artificial intelligence is then presented as the main driving force of radiomics, and common techniques are defined and briefly compared. The complete step-by-step process of radiomic phenotyping is then broken down into five key phases. Potential pitfalls of each phase are highlighted, and recommendations are provided to reduce sources of variation, non-reproducibility, and error associated with radiomics.

Hippocampus segmentation and classification for dementia analysis using pre-trained neural network models

The diagnostic and clinical overlap of early mild cognitive impairment (EMCI), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI) and Alzheimer disease (AD) is a vital oncological issue in dementia disorder. This study is designed to examine Whole brain (WB), grey matter (GM) and Hippocampus (HC) morphological variation and identify the prominent biomarkers in MR brain images of demented subjects to understand the severity progression. Curve evolution based on shape constraint is carried out to segment the complex brain structure such as HC and GM. Pre-trained models are used to observe the severity variation in these regions. This work is evaluated on ADNI database. The outcome of the proposed work shows that curve evolution method could segment HC and GM regions with better correlation. Pre-trained models are able to show significant severity difference among WB, GM and HC regions for the considered classes. Further, prominent variation is observed between AD vs. EMCI, AD vs. MCI and AD vs. LMCI in the whole brain, GM and HC. It is concluded that AlexNet model for HC region result in better classification for AD vs. EMCI, AD vs. MCI and AD vs. LMCI with an accuracy of 93, 78.3 and 91% respectively.

Extraction of Cerebral Hemorrhage on CT Images Using Level Set Algorithm and Otsu Threshold

Extraction of cerebral hemorrhage on CT images has always been the focus of several research hotspots and is still challenging as it does not show clear boundary. In this paper, a novel segmentation framework is presented for extracting the cerebral hemorrhage in brain CT images with weak boundary. Firstly, we utilize the Otsu threshold algorithm to get the coarse outline approximate to the target boundary as the initial curve of level set algorithm. Then, the active contour model is employed using both edge information and global Gaussian distribution fitting energy of images to modify energy function of level set. The proposed approach is applied on real images which from Quzhou People’s Hospital. Compared to manual delineation, the proposed technique shows a higher JS value than the existing methods and requires less interaction which is listed in the literature.

Performance changes due to differences in training data for cerebral aneurysm detection in head MR angiography images

PURPOSE

The performance of computer-aided detection (CAD) software depends on the quality and quantity of the dataset used for machine learning. If the data characteristics in development and practical use are different, the performance of CAD software degrades. In this study, we investigated changes in detection performance due to differences in training data for cerebral aneurysm detection software in head magnetic resonance angiography images.

MATERIALS AND METHODS

We utilized three types of CAD software for cerebral aneurysm detection in MRA images, which were based on 3D local intensity structure analysis, graph-based features, and convolutional neural network. For each type of CAD software, we compared three types of training pattern, which were two types of training using single-site data and one type of training using multisite data. We also carried out internal and external evaluations.

RESULTS

In training using single-site data, the performance of CAD software largely and unpredictably fluctuated when the training dataset was changed. Training using multisite data did not show the lowest performance among the three training patterns for any CAD software and dataset.

CONCLUSION

The training of cerebral aneurysm detection software using data collected from multiple sites is desirable to ensure the stable performance of the software.

Dual-functional neural network for bilateral hippocampi segmentation and diagnosis of Alzheimer's disease

PURPOSE

Knowing the course of Alzheimer's disease is very important to prevent the deterioration of the disease, and accurate segmentation of sensitive lesions can provide a visual basis for the diagnosis results. This study proposes an improved end-to-end dual-functional 3D convolutional neural network for segmenting bilateral hippocampi from 3D brain MRI scans and diagnosing AD progression states simultaneously.

METHODS

The proposed neural network is based on the V-Net and adopts an end-to-end structure. In order to relieve the excessive amount of convolutional parameters at the bottom of the V-Net, we change them to bottleneck architecture. Based on the segmentation network, we establish a classification network for diagnosing pathological states of brain. In order to balance the two tasks of hippocampi segmentation and brain pathological states diagnosis, we designed a unique loss function. This study included 132 samples, of which 100 were selected as training, and the remaining 32 were used to test the performance of our model. During training, we adopted fivefold cross-validation method.

RESULTS

We selected the intersection over union and dice coefficient to evaluate the hippocampus segmentation performance, while the brain pathological states diagnosis performance was evaluated by accuracy, specificity, sensitivity, precision and F1 score. By using the proposed neural network, the left hippocampi segmentation Iou and dice coefficient reach 0.8240 ± 0.020 and 0.9035 ± 0.020, respectively. The right hippocampi Iou and dice coefficient reach 0.8454 ± 0.023 and 0.9162 ± 0.023, respectively. The accuracy, specificity, sensitivity, precision and F1 score of three-category classification of brain pathology are 84%, 92%, 84%, 86% and 85%, respectively.

CONCLUSION

The proposed neural network has two functions of brain pathological states diagnosis and bilateral hippocampi segmentation with higher robustness and accuracy, respectively. The segmented bilateral hippocampi can be used as a reference for clinical decision making or intervention.