Fast and Precise Hippocampus Segmentation Through Deep Convolutional Neural Network Ensembles and Transfer Learning

A novel cross-layer dual encoding-shared decoding network framework with spatial self-attention mechanism for hippocampus segmentation

Accurate segmentation of the hippocampus from the brain magnetic resonance images (MRIs) is a crucial task in the neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, such as Alzheimer's disease (AD). Automatic segmentation of the hippocampus structures is challenging due to the small volume, complex shape, low contrast and discontinuous boundaries of hippocampus. Although some methods have been developed for the hippocampus segmentation, most of them paid too much attention to the hippocampus shape and volume instead of considering the spatial information. Additionally, the extracted features are independent of each other, ignoring the correlation between the global and local information. In view of this, here we proposed a novel cross-layer dual Encoding-Shared Decoding network framework with Spatial self-Attention mechanism (called ESDSA) for hippocampus segmentation in human brains. Considering that the hippocampus is a relatively small part in MRI, we introduced the spatial self-attention mechanism in ESDSA to capture the spatial information of hippocampus for improving the segmentation accuracy. We also designed a cross-layer dual encoding-shared decoding network to effectively extract the global information of MRIs and the spatial information of hippocampus. The spatial features of hippocampus and the features extracted from the MRIs were combined to realize the hippocampus segmentation. Results on the baseline T1-weighted structural MRI data show that the performance of our ESDSA is superior to other state-of-the-art methods, and the dice similarity coefficient of ESDSA achieves 89.37%. In addition, the dice similarity coefficient of the Spatial Self-Attention mechanism (SSA) strategy and the dual Encoding-Shared Decoding (ESD) strategy is 9.47%, 5.35% higher than that of the baseline U-net, respectively, indicating that the strategies of SSA and ESD can effectively enhance the segmentation accuracy of human brain hippocampus.

DMCA-GAN: Dual Multilevel Constrained Attention GAN for MRI-Based Hippocampus Segmentation

Precise segmentation of the hippocampus is essential for various human brain activity and neurological disorder studies. To overcome the small size of the hippocampus and the low contrast of MR images, a dual multilevel constrained attention GAN for MRI-based hippocampus segmentation is proposed in this paper, which is used to provide a relatively effective balance between suppressing noise interference and enhancing feature learning. First, we design the dual-GAN backbone to effectively compensate for the spatial information damage caused by multiple pooling operations in the feature generation stage. Specifically, dual-GAN performs joint adversarial learning on the multiscale feature maps at the end of the generator, which yields an average Dice coefficient (DSC) gain of 5.95% over the baseline. Next, to suppress MRI high-frequency noise interference, a multilayer information constraint unit is introduced before feature decoding, which improves the sensitivity of the decoder to forecast features by 5.39% and effectively alleviates the network overfitting problem. Then, to refine the boundary segmentation effects, we construct a multiscale feature attention restraint mechanism, which forces the network to concentrate more on effective multiscale details, thus improving the robustness. Furthermore, the dual discriminators D1 and D2 also effectively prevent the negative migration phenomenon. The proposed DMCA-GAN obtained a DSC of 90.53% on the Medical Segmentation Decathlon (MSD) dataset with tenfold cross-validation, which is superior to the backbone by 3.78%.

Deep convolutional neural network for hippocampus segmentation with boundary region refinement

Accurately segmenting the hippocampus from magnetic resonance (MR) brain images is a crucial step in studying brain disorders. However, this task is challenging due to the low signal contrast of hippocampal images, the irregular shape, and small structural size of the hippocampi. In recent years, several deep convolutional networks have been proposed for hippocampus segmentation, which have achieved state-of-the-art performance. These methods typically use large image patches for training the network, as larger patches are beneficial for capturing long-range contextual information. However, this approach increases the computational burden and overlooks the significance of the boundary region. In this study, we propose a deep learning-based method for hippocampus segmentation with boundary region refinement. Our method involves two main steps. First, we propose a convolutional network that takes large image patches as input for initial segmentation. Then, we extract small image patches around the hippocampal boundary for training the second convolutional neural network, which refines the segmentation in the boundary regions. We validate our proposed method on a publicly available dataset and demonstrate that it significantly improves the performance of convolutional neural networks that use single-size image patches as input. In conclusion, our study proposes a novel method for hippocampus segmentation, which improves upon the current state-of-the-art methods. By incorporating a boundary refinement step, our approach achieves higher accuracy in hippocampus segmentation and may facilitate research on brain disorders.

Fine scale hippocampus morphology variation cross 552 healthy subjects from age 20 to 80

The cerebral cortex varies over the course of a person's life span: at birth, the surface is smooth, before becoming more bumpy (deeper sulci and thicker gyri) in middle age, and thinner in senior years. In this work, a similar phenomenon was observed on the hippocampus. It was previously believed the fine-scale morphology of the hippocampus could only be extracted only with high field scanners (7T, 9.4T); however, recent studies show that regular 3T MR scanners can be sufficient for this purpose. This finding opens the door for the study of fine hippocampal morphometry for a large amount of clinical data. In particular, a characteristic bumpy and subtle feature on the inferior aspect of the hippocampus, which we refer to as hippocampal dentation, presents a dramatic degree of variability between individuals from very smooth to highly dentated. In this report, we propose a combined method joining deep learning and sub-pixel level set evolution to efficiently obtain fine-scale hippocampal segmentation on 552 healthy subjects. Through non-linear dentation extraction and fitting, we reveal that the bumpiness of the inferior surface of the human hippocampus has a clear temporal trend. It is bumpiest between 40 and 50 years old. This observation should be aligned with neurodevelopmental and aging stages.

A benchmark for hypothalamus segmentation on T1-weighted MR images

The hypothalamus is a small brain structure that plays essential roles in sleep regulation, body temperature control, and metabolic homeostasis. Hypothalamic structural abnormalities have been reported in neuropsychiatric disorders, such as schizophrenia, amyotrophic lateral sclerosis, and Alzheimer's disease. Although mag- netic resonance (MR) imaging is the standard examination method for evaluating this region, hypothalamic morphological landmarks are unclear, leading to subjec- tivity and high variability during manual segmentation. Due to these limitations, it is common to find contradicting results in the literature regarding hypothalamic volumetry. To the best of our knowledge, only two automated methods are available in the literature for hypothalamus segmentation, the first of which is our previous method based on U-Net. However, both methods present performance losses when predicting images from different datasets than those used in training. Therefore, this project presents a benchmark consisting of a diverse T1-weighted MR image dataset comprising 1381 subjects from IXI, CC359, OASIS, and MiLI (the latter created specifically for this benchmark). All data were provided using automatically generated hypothalamic masks and a subset containing manually annotated masks. As a baseline, a method for fully automated segmentation of the hypothalamus on T1-weighted MR images with a greater generalization ability is presented. The pro- posed method is a teacher-student-based model with two blocks: segmentation and correction, where the second corrects the imperfections of the first block. After using three datasets for training (MiLI, IXI, and CC359), the prediction performance of the model was measured on two test sets: the first was composed of data from IXI, CC359, and MiLI, achieving a Dice coefficient of 0.83; the second was from OASIS, a dataset not used for training, achieving a Dice coefficient of 0.74. The dataset, the baseline model, and all necessary codes to reproduce the experiments are available at https://github.com/MICLab-Unicamp/HypAST and https://sites.google.com/ view/calgary-campinas-dataset/hypothalamus-benchmarking. In addition, a leaderboard will be maintained with predictions for the test set submitted by anyone working on the same task.

A domain adaptation benchmark for T1-weighted brain magnetic resonance image segmentation

Accurate brain segmentation is critical for magnetic resonance imaging (MRI) analysis pipelines. Machine-learning-based brain MR image segmentation methods are among the state-of-the-art techniques for this task. Nevertheless, the segmentations produced by machine learning models often degrade in the presence of expected domain shifts between the test and train sets data distributions. These domain shifts are expected due to several factors, such as scanner hardware and software differences, technology updates, and differences in MRI acquisition parameters. Domain adaptation (DA) methods can make machine learning models more resilient to these domain shifts. This paper proposes a benchmark for investigating DA techniques for brain MR image segmentation using data collected across sites with scanners from different vendors (Philips, Siemens, and General Electric). Our work provides labeled data, publicly available source code for a set of baseline and DA models, and a benchmark for assessing different brain MR image segmentation techniques. We applied the proposed benchmark to evaluate two segmentation tasks: skull-stripping; and white-matter, gray-matter, and cerebrospinal fluid segmentation, but the benchmark can be extended to other brain structures. Our main findings during the development of this benchmark are that there is not a single DA technique that consistently outperforms others, and hyperparameter tuning and computational times for these methods still pose a challenge before broader adoption of these methods in the clinical practice.

3D brain slice classification and feature extraction using Deformable Hierarchical Heuristic Model

Brain tumors are the most frequently occurring and severe type of cancer, with a life expectancy of only a few months in most advanced stages. As a result, planning the best course of therapy is critical to improve a patient's ability to fight cancer and their quality of life. Various imaging modalities, such as computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound imaging, are commonly employed to assess a brain tumor. This research proposes a novel technique for extracting and classifying tumor features in 3D brain slice images. After input images are processed for noise removal, resizing, and smoothening, features of brain tumor are extracted using Volume of Interest (VOI). The extracted features are then classified using the Deformable Hierarchical Heuristic Model-Deep Deconvolutional Residual Network (DHHM-DDRN) based on surfaces, curves, and geometric patterns. Experimental results show that proposed approach obtained an accuracy of 95%, DSC of 83%, precision of 80%, recall of 85%, and F1 score of 55% for classifying brain cancer features.

Deep learning for necrosis detection using canine perivascular wall tumour whole slide images

Necrosis seen in histopathology Whole Slide Images is a major criterion that contributes towards scoring tumour grade which then determines treatment options. However conventional manual assessment suffers from inter-operator reproducibility impacting grading precision. To address this, automatic necrosis detection using AI may be used to assess necrosis for final scoring that contributes towards the final clinical grade. Using deep learning AI, we describe a novel approach for automating necrosis detection in Whole Slide Images, tested on a canine Soft Tissue Sarcoma (cSTS) data set consisting of canine Perivascular Wall Tumours (cPWTs). A patch-based deep learning approach was developed where different variations of training a DenseNet-161 Convolutional Neural Network architecture were investigated as well as a stacking ensemble. An optimised DenseNet-161 with post-processing produced a hold-out test F1-score of 0.708 demonstrating state-of-the-art performance. This represents a novel first-time automated necrosis detection method in the cSTS domain as well specifically in detecting necrosis in cPWTs demonstrating a significant step forward in reproducible and reliable necrosis assessment for improving the precision of tumour grading.

Operationalising fairness in medical AI adoption: detection of early Alzheimer’s disease with 2D CNN

Objectives

To operationalise fairness in the adoption of medical artificial intelligence (AI) algorithms in terms of access to computational resources, the proposed approach is based on a two-dimensional (2D) convolutional neural networks (CNN), which provides a faster, cheaper and accurate-enough detection of early Alzheimer’s disease (AD) and mild cognitive impairment (MCI), without the need for use of large training data sets or costly high-performance computing (HPC) infrastructures.

Methods

The standardised Alzheimer’s Disease Neuroimaging Initiative (ADNI) data sets are used for the proposed model, with additional skull stripping, using the Brain Extraction Tool V.2approach. The 2D CNN architecture is based on LeNet-5, the Leaky Rectified Linear Unit activation function and a Sigmoid function were used, and batch normalisation was added after every convolutional layer to stabilise the learning process. The model was optimised by manually tuning all its hyperparameters.

Results

The model was evaluated in terms of accuracy, recall, precision and f1-score. The results demonstrate that the model predicted MCI with an accuracy of 0.735, passing the random guessing baseline of 0.521 and predicted AD with an accuracy of 0.837, passing the random guessing baseline of 0.536.

Discussion

The proposed approach can assist clinicians in the early diagnosis of AD and MCI, with high-enough accuracy, based on relatively smaller data sets, and without the need of HPC infrastructures. Such an approach can alleviate disparities and operationalise fairness in the adoption of medical algorithms.

Conclusion

Medical AI algorithms should not be focused solely on accuracy but should also be evaluated with respect to how they might impact disparities and operationalise fairness in their adoption.

Hippocampus Segmentation Using U-Net Convolutional Network from Brain Magnetic Resonance Imaging (MRI)

Hippocampus is a part of the limbic system in human brain that plays an important role in forming memories and dealing with intellectual abilities. In most of the neurological disorders related to dementia, such as, Alzheimer's disease, hippocampus is one of the earliest affected regions. Because there are no effective dementia drugs, an ambient assisted living approach may help to prevent or slow the progression of dementia. By segmenting and analyzing the size/shape of hippocampus, it may be possible to classify the early dementia stages. Because of complex structure, traditional image segmentation techniques can't segment hippocampus accurately. Machine learning (ML) is a well known tool in medical image processing that can predict and deliver the outcomes accurately by learning from it's previous results. Convolutional Neural Networks (CNN) is one of the most popular ML algorithms. In this work, a U-Net Convolutional Network based approach is used for hippocampus segmentation from 2D brain images. It is observed that, the original U-Net architecture can segment hippocampus with an average performance rate of 93.6%, which outperforms all other discussed state-of-arts. By using a filter size of [Formula: see text], the original U-Net architecture performs a sequence of convolutional processes. We tweaked the architecture further to extract more relevant features by replacing all [Formula: see text] kernels with three alternative kernels of sizes [Formula: see text], [Formula: see text], and [Formula: see text]. It is observed that, the modified architecture achieved an average performance rate of 96.5%, which outperforms the original U-Net model convincingly.

Automated Segmentation of Midbrain Structures in High-Resolution Susceptibility Maps Based on Convolutional Neural Network and Transfer Learning

Background

Accurate delineation of the midbrain nuclei, the red nucleus (RN), substantia nigra (SN) and subthalamic nucleus (STN), is important in neuroimaging studies of neurodegenerative and other diseases. This study aims to segment midbrain structures in high-resolution susceptibility maps using a method based on a convolutional neural network (CNN).

Methods

The susceptibility maps of 75 subjects were acquired with a voxel size of 0.83 × 0.83 × 0.80 mm³ on a 3T MRI system to distinguish the RN, SN, and STN. A deeply supervised attention U-net was pre-trained with a dataset of 100 subjects containing susceptibility maps with a voxel size of 0.63 × 0.63 × 2.00 mm³ to provide initial weights for the target network. Five-fold cross-validation over the training cohort was used for all the models’ training and selection. The same test cohort was used for the final evaluation of all the models. Dice coefficients were used to assess spatial overlap agreement between manual delineations (ground truth) and automated segmentation. Volume and magnetic susceptibility values in the nuclei extracted with automated CNN delineation were compared to those extracted by manual tracing. Consistencies of volume and magnetic susceptibility values by different extraction strategies were assessed by Pearson correlation coefficients and Bland-Altman analyses.

Results

The automated CNN segmentation method achieved mean Dice scores of 0.903, 0.864, and 0.777 for the RN, SN, and STN, respectively. There were no significant differences between the achieved Dice scores and the inter-rater Dice scores (p > 0.05 for each nucleus). The overall volume and magnetic susceptibility values of the nuclei extracted by the automatic CNN method were significantly correlated with those by manual delineation (p < 0.01).

Conclusion

Midbrain structures can be precisely segmented in high-resolution susceptibility maps using a CNN-based method.

A novel deep learning based hippocampus subfield segmentation method

The automatic assessment of hippocampus volume is an important tool in the study of several neurodegenerative diseases such as Alzheimer's disease. Specifically, the measurement of hippocampus subfields properties is of great interest since it can show earlier pathological changes in the brain. However, segmentation of these subfields is very difficult due to their complex structure and for the need of high-resolution magnetic resonance images manually labeled. In this work, we present a novel pipeline for automatic hippocampus subfield segmentation based on a deeply supervised convolutional neural network. Results of the proposed method are shown for two available hippocampus subfield delineation protocols. The method has been compared to other state-of-the-art methods showing improved results in terms of accuracy and execution time.

Identifying epilepsy based on machine-learning technique with diffusion kurtosis tensor

Introduction

Epilepsy is a serious hazard to human health. Minimally invasive surgery is an extremely effective treatment to refractory epilepsy currently if the location of epileptic foci is given. However, it is challenging to locate the epileptic foci since a multitude of patients are MRI‐negative. It is well known that DKI (diffusion kurtosis imaging) can analyze the pathological changes of local tissues and other regions of epileptic foci at the molecular level. In this article, we propose a new localization way for epileptic foci based on machine‐learning method with kurtosis tensor in DKI.

Methods

We recruited 59 children with hippocampus epilepsy and 70 age‐ and sex‐matched normal controls; their T1‐weighted images and DKI were collected simultaneously. Then, the hippocampus in DKI is segmented based on a mask as a local brain region, and DKE is utilized to estimate the kurtosis tensor of each subject's hippocampus. Finally, the kurtosis tensor is fed into SVM (support vector machine) to identify epilepsy.

Results

The classifier produced 95.24% accuracy for patient versus normal controls, which is higher than that obtained with FA (fractional anisotropy) and MK (mean kurtosis). Experimental results show that the kurtosis tensor is a kind of remarkable feature to identify epilepsy, which indicates that DKI images can act as an important biomarker for epilepsy from the view of clinical diagnosis.

Conclusion

Although the classification task for epileptic patients and normal controls discussed in this article did not directly achieve the location of epileptic foci and only identified epilepsy on certain brain region, the epileptic foci can be located with the results of identifying results on other brain regions.

Charting the human amygdala development across childhood and adolescence: Manual and automatic segmentation

The developmental pattern of the amygdala throughout childhood and adolescence has been inconsistently reported in previous neuroimaging studies. Given the relatively small size of the amygdala on full brain MRI scans, discrepancies may be partly due to methodological differences in amygdalar segmentation. To investigate the impact of volume extraction methods on amygdala volume, we compared FreeSurfer, FSL and volBrain segmentation measurements with those obtained by manual tracing. The manual tracing method, which we used as the 'gold standard', exhibited almost perfect intra- and inter-rater reliability. We observed systematic differences in amygdala volumes between automatic (FreeSurfer and volBrain) and manual methods. Specifically, compared with the manual tracing, FreeSurfer estimated larger amygdalae, and volBrain produced smaller amygdalae while FSL demonstrated a mixed pattern. The tracing bias was not uniform, but higher for smaller amygdalae. We further modeled amygdalar growth curves using accelerated longitudinal cohort data from the Chinese Color Nest Project (http://deepneuro.bnu.edu.cn/?p=163). Trajectory modeling and statistical assessments of the manually traced amygdalae revealed linearly increasing and parallel developmental patterns for both girls and boys, although the amygdalae of boys were larger than those of girls. Compared to these trajectories, the shapes of developmental curves were similar when using the volBrain derived volumes. FreeSurfer derived trajectories had more nonlinearities and appeared flatter. FSL derived trajectories demonstrated an inverted U shape and were significantly different from those derived from manual tracing method. The use of amygdala volumes adjusted for total gray-matter volumes, but not intracranial volumes, resolved the shape discrepancies and led to reproducible growth curves between manual tracing and the automatic methods (except FSL). Our findings revealed steady growth of the human amygdala, mirroring its functional development across the school age. Methodological improvements are warranted for current automatic tools to achieve more accurate amygdala structure at school age, calling for next generation tools.

Advanced Kidney Volume Measurement Method Using Ultrasonography with Artificial Intelligence-Based Hybrid Learning in Children

In this study, we aimed to develop a new automated method for kidney volume measurement in children using ultrasonography (US) with image pre-processing and hybrid learning and to formulate an equation to calculate the expected kidney volume. The volumes of 282 kidneys (141 subjects, <19 years old) with normal function and structure were measured using US. The volumes of 58 kidneys in 29 subjects who underwent US and computed tomography (CT) were determined by image segmentation and compared to those calculated by the conventional ellipsoidal method and CT using intraclass correlation coefficients (ICCs). An expected kidney volume equation was developed using multivariate regression analysis. Manual image segmentation was automated using hybrid learning to calculate the kidney volume. The ICCs for volume determined by image segmentation and ellipsoidal method were significantly different, while that for volume calculated by hybrid learning was significantly higher than that for ellipsoidal method. Volume determined by image segmentation was significantly correlated with weight, body surface area, and height. Expected kidney volume was calculated as (2.22 × weight (kg) + 0.252 × height (cm) + 5.138). This method will be valuable in establishing an age-matched normal kidney growth chart through the accumulation and analysis of large-scale data.

Hippocampus Segmentation Method Based on Subspace Patch-Sparsity Clustering in Noisy Brain MRI

Since the hippocampus is of small size, low contrast, and irregular shape, a novel hippocampus segmentation method based on subspace patch-sparsity clustering in brain MRI is proposed to improve the segmentation accuracy, which requires that the representation coefficients in different subspaces should be as sparse as possible, while the representation coefficients in the same subspace should be as average as possible. By restraining the coefficient matrix with the patch-sparse constraint, the coefficient matrix contains a patch-sparse structure, which is helpful to the hippocampus segmentation. The experimental results show that our proposed method is effective in the noisy brain MRI data, which can well deal with hippocampus segmentation problem.

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.

Black S, Barber P. Combined Atlas and Convolutional Neural Network-Based Segmentation of the Hippocampus from MRI According to the ADNI Harmonized Protocol

Hippocampus atrophy is an early structural feature that can be measured from magnetic resonance imaging (MRI) to improve the diagnosis of neurological diseases. An accurate and robust standardized hippocampus segmentation method is required for reliable atrophy assessment. The aim of this work was to develop and evaluate an automatic segmentation tool (DeepHarp) for hippocampus delineation according to the ADNI harmonized hippocampal protocol (HarP). DeepHarp utilizes a two-step process. First, the approximate location of the hippocampus is identified in T1-weighted MRI datasets using an atlas-based approach, which is used to crop the images to a region-of-interest (ROI) containing the hippocampus. In the second step, a convolutional neural network trained using datasets with corresponding manual hippocampus annotations is used to segment the hippocampus from the cropped ROI. The proposed method was developed and validated using 107 datasets with manually segmented hippocampi according to the ADNI-HarP standard as well as 114 multi-center datasets of patients with Alzheimer's disease, mild cognitive impairment, cerebrovascular disease, and healthy controls. Twenty-three independent datasets manually segmented according to the ADNI-HarP protocol were used for testing to assess the accuracy, while an independent test-retest dataset was used to assess precision. The proposed DeepHarp method achieved a mean Dice similarity score of 0.88, which was significantly better than four other established hippocampus segmentation methods used for comparison. At the same time, the proposed method also achieved a high test-retest precision (mean Dice score: 0.95). In conclusion, DeepHarp can automatically segment the hippocampus from T1-weighted MRI datasets according to the ADNI-HarP protocol with high accuracy and robustness, which can aid atrophy measurements in a variety of pathologies.

Automatic segmentation of hippocampus in hippocampal sparing whole brain radiotherapy: A multitask edge-aware learning

PURPOSE

This study aimed to improve the accuracy of the hippocampus segmentation through multitask edge-aware learning.

METHOD

We developed a multitask framework for computerized hippocampus segmentation. We used three-dimensional (3D) U-net as our backbone model with two training objectives: (a) to minimize the difference between the targeted binary mask and the model prediction; and (b) to optimize an auxiliary edge-prediction task which is designed to guide the model detection of the weak boundary of the hippocampus in model optimization. To balance the multiple task objectives, we proposed an improved gradient normalization by adaptively adjusting the weight of losses from different tasks. A total of 247 T1-weighted MRIs including 131 without contrast and 116 with contrast were collected from 247 patients to train and validate the proposed method. Segmentation was quantitatively evaluated with the dice coefficient (Dice), Hausdorff distance (HD), and average Hausdorff distance (AVD). The 3D U-net was used for baseline comparison. We used a Wilcoxon signed-rank test to compare repeated measurements (Dice, HD, and AVD) by different segmentations.

RESULTS

Through fivefold cross-validation, our multitask edge-aware learning achieved Dice of 0.8483 ± 0.0036, HD of 7.5706 ± 1.2330 mm, and AVD of 0.1522 ± 0.0165 mm, respectively. Conversely, the baseline results were 0.8340 ± 0.0072, 10.4631 ± 2.3736 mm, and 0.1884 ± 0.0286 mm, respectively. With a Wilcoxon signed-rank test, we found that the differences between our method and the baseline were statistically significant (P < 0.05).

CONCLUSION

Our results demonstrated the efficiency of multitask edge-aware learning in hippocampus segmentation for hippocampal sparing whole-brain radiotherapy. The proposed framework may also be useful for other low-contrast small organ segmentations on medical imaging modalities.

Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks

Background: Hippocampus segmentation on magnetic resonance imaging is of key importance for the diagnosis, treatment decision and investigation of neuropsychiatric disorders. Automatic segmentation is an active research field, with many recent models using deep learning. Most current state-of-the art hippocampus segmentation methods train their methods on healthy or Alzheimer's disease patients from public datasets. This raises the question whether these methods are capable of recognizing the hippocampus on a different domain, that of epilepsy patients with hippocampus resection. New Method: In this paper we present a state-of-the-art, open source, ready-to-use, deep learning based hippocampus segmentation method. It uses an extended 2D multi-orientation approach, with automatic pre-processing and orientation alignment. The methodology was developed and validated using HarP, a public Alzheimer's disease hippocampus segmentation dataset. Results and Comparisons: We test this methodology alongside other recent deep learning methods, in two domains: The HarP test set and an in-house epilepsy dataset, containing hippocampus resections, named HCUnicamp. We show that our method, while trained only in HarP, surpasses others from the literature in both the HarP test set and HCUnicamp in Dice. Additionally, Results from training and testing in HCUnicamp volumes are also reported separately, alongside comparisons between training and testing in epilepsy and Alzheimer's data and vice versa. Conclusion: Although current state-of-the-art methods, including our own, achieve upwards of 0.9 Dice in HarP, all tested methods, including our own, produced false positives in HCUnicamp resection regions, showing that there is still room for improvement for hippocampus segmentation methods when resection is involved.

Hippocampus segmentation in CT using deep learning: impact of MR versus CT-based training contours

Purpose: Hippocampus contouring for radiotherapy planning is performed on MR image data due to poor anatomical visibility on computed tomography (CT) data. Deep learning methods for direct CT hippocampus auto-segmentation exist, but use MR-based training contours. We investigate if these can be replaced by CT-based contours without loss in segmentation performance. This would remove the MR not only from inference but also from training.

Approach: The hippocampus was contoured by medical experts on MR and CT data of 45 patients. Convolutional neural networks (CNNs) for hippocampus segmentation on CT were trained on CT-based or propagated MR-based contours. In both cases, their predictions were evaluated against the MR-based contours considered as the ground truth. Performance was measured using several metrics, including Dice score, surface distances, and contour Dice score. Bayesian dropout was used to estimate model uncertainty.

Results: CNNs trained on propagated MR contours (median Dice 0.67) significantly outperform those trained on CT contours (0.59) and also experts contouring manually on CT (0.59). Differences between the latter two are not significant. Training on MR contours results in lower model uncertainty than training on CT contours. All contouring methods (manual or CNN) on CT perform significantly worse than a CNN segmenting the hippocampus directly on MR (median Dice 0.76). Additional data augmentation by rigid transformations improves the quantitative results but the difference remains significant.

Conclusions: CT-based training contours for CT hippocampus segmentation cannot replace propagated MR-based contours without significant loss in performance. However, if MR-based contours are used, the resulting segmentations outperform experts in contouring the hippocampus on CT.

Identifying Epilepsy Based on Deep Learning Using DKI Images

Epilepsy is a serious hazard to human health. Minimally invasive surgery is currently an extremely effective treatment to refractory epilepsy. However, it is challenging to localize the lesion for most patients because they are MRI negative. The identification of epileptic foci in local brain region will be helpful to the localization of epileptic foci because we can infer whether there is a lesion from the results of the classification. For the sake of simplicity and the data we collected, only the hippocampus was segmented as a local brain region and classified in this paper. We recruited 59 children with hippocampus epilepsy and 70 age- and sex-matched normal controls, and diffusion kurtosis images (DKI) for all subjects were collected because DKI can understand the pathological changes of local tissues and other regions of epileptic foci at the molecular level. Then, a mask of hippocampus was made to segment the hippocampus of FA, MD, and MK images for all subjects, which are the parameter images of DKI and were used to perform the independent-sample t-test and the classification task. At last, a convolutional neural network (CNN) based on transfer learning technique was developed to extract features of FA, MD, MK, and the fusion of FA and MK, and support vector machine was employed to classify epilepsy and normal control. Finally, the classifier produced 90.8% accuracy for patient vs. normal controls. Experimental results showed that the features extraction based on CNN is very effective, and the high accuracy of classification means that FA and MK are two remarkable features to identify epilepsy, which indicates that DKI images can act as an important biomarker for epilepsy from the point of view of clinical diagnosis.

Diverse Applications of Artificial Intelligence in Neuroradiology

Recent advances in artificial intelligence (AI) and deep learning (DL) hold promise to augment neuroimaging diagnosis for patients with brain tumors and stroke. Here, the authors review the diverse landscape of emerging neuroimaging applications of AI, including workflow optimization, lesion segmentation, and precision education. Given the many modalities used in diagnosing neurologic diseases, AI may be deployed to integrate across modalities (MR imaging, computed tomography, PET, electroencephalography, clinical and laboratory findings), facilitate crosstalk among specialists, and potentially improve diagnosis in patients with trauma, multiple sclerosis, epilepsy, and neurodegeneration. Together, there are myriad applications of AI for neuroradiology."

Automated MRI volumetry as a diagnostic tool for Alzheimer's disease: Validation of icobrain dm

•

icobrain dm is an automated brain MRI segmentation faster than Freesurfer.

•

Significantly higher accuracy was obtained for several brain structures, including hippocampus.

•

icobrain dm volumes had a test-retest error below normal annual atrophy rates.

•

icobrain dm temporal lobe volume had highest sensitivity in discriminating Alzheimer's.

Brain volumes computed from magnetic resonance images have potential for assisting with the diagnosis of individual dementia patients, provided that they have low measurement error and high reliability. In this paper we describe and validate icobrain dm, an automatic tool that segments brain structures that are relevant for differential diagnosis of dementia, such as the hippocampi and cerebral lobes. Experiments were conducted in comparison to the widely used FreeSurfer software. The hippocampus segmentations were compared against manual segmentations, with significantly higher Dice coefficients obtained with icobrain dm (25–75th quantiles: 0.86–0.88) than with FreeSurfer (25–75th quantiles: 0.80–0.83). Other brain structures were also compared against manual delineations, with icobrain dm showing lower volumetric errors overall. Test-retest experiments show that the precision of all measurements is higher for icobrain dm than for FreeSurfer except for the parietal cortex volume. Finally, when comparing volumes obtained from Alzheimer's disease patients against age-matched healthy controls, all measures achieved high diagnostic performance levels when discriminating patients from cognitively healthy controls, with the temporal cortex volume measured by icobrain dm reaching the highest diagnostic performance level (area under the receiver operating characteristic curve = 0.99) in this dataset.

Multi-atlas label fusion with random local binary pattern features: Application to hippocampus segmentation

Automatic and reliable segmentation of the hippocampus from magnetic resonance (MR) brain images is extremely important in a variety of neuroimage studies. To improve the hippocampus segmentation performance, a local binary pattern based feature extraction method is developed for machine learning based multi-atlas hippocampus segmentation. Under the framework of multi-atlas image segmentation (MAIS), a set of selected atlases are registered to images to be segmented using a non-linear image registration algorithm. The registered atlases are then used as training data to build linear regression models for segmenting the images based on the image features, referred to as random local binary pattern (RLBP), extracted using a novel image feature extraction method. The RLBP based MAIS algorithm has been validated for segmenting hippocampus based on a data set of 135 T1 MR images which are from the Alzheimer’s Disease Neuroimaging Initiative database (adni.loni.usc.edu). By using manual segmentation labels produced by experienced tracers as the standard of truth, six segmentation evaluation metrics were used to evaluate the image segmentation results by comparing automatic segmentation results with the manual segmentation labels. We further computed Cohen’s d effect size to investigate the sensitivity of each segmenting method in detecting volumetric differences of the hippocampus between different groups of subjects. The evaluation results showed that our method was competitive to state-of-the-art label fusion methods in terms of accuracy. Hippocampal volumetric analysis showed that the proposed RLBP method performed well in detecting the volumetric differences of the hippocampus between groups of Alzheimer’s disease patients, mild cognitive impairment subjects, and normal controls. These results have demonstrated that the RLBP based multi-atlas image segmentation method could facilitate efficient and accurate extraction of the hippocampus and may help predict Alzheimer’s disease. The codes of the proposed method is available (https://www.nitrc.org/frs/?group_id=1242).