Using deep Siamese neural networks for detection of brain asymmetries associated with Alzheimer's Disease and Mild Cognitive Impairment

Utilizing Siamese 4D-AlzNet and Transfer Learning to Identify Stages of Alzheimer's Disease

Alzheimer's disease (AD) is the general form of dementia, leading to a progressive neurological disorder characterized by memory loss due to brain cell damage. Artificial Intelligence (AI) assists in the early identification and prediction of AD patients, determining future risks and benefits for radiologists and doctors to save time and cost. Since deep learning (DL) approaches work well with massive datasets and have recently become helpful for AD detection, there remains an area for improvement in automating detection performance. Present approaches somehow addressed the challenges of limited annotated data samples for binary classification. This contrasts with prior state-of-the-art techniques, which were constrained by their incapacity to capture abstract-level information. In this paper, we proposed a Siamese 4D-AlzNet model comprised of four parallel convolutional neural network (CNN) streams (Five CNN layer blocks) and customized transfer learning models (Frozen VGG-19, Frozen VGG-16, and customized AlexNet). Siamese 4D-AlzNet was vertically and horizontally stored, and the spatial features were passed to the final layer for classification. For experiments, T1-weighted MRI images comprised of four distinct subject classes, normal control (NC), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI), and AD, have been employed. Our proposed models achieved outstanding accuracy, with a remarkable 95.05% accuracy distinguishing between normal and AD subjects. The performance across remaining binary class pairs consistently exceeded 90%. We thoroughly compared our model with the latest methods using the same dataset as our reference. Our proposed model improved NC-AD and MCI-AD classification accuracy by 2% 7%.

Hybrid representation learning for cognitive diagnosis in late-life depression over 5 years with structural MRI

Late-life depression (LLD) is a highly prevalent mood disorder occurring in older adults and is frequently accompanied by cognitive impairment (CI). Studies have shown that LLD may increase the risk of Alzheimer's disease (AD). However, the heterogeneity of presentation of geriatric depression suggests that multiple biological mechanisms may underlie it. Current biological research on LLD progression incorporates machine learning that combines neuroimaging data with clinical observations. There are few studies on incident cognitive diagnostic outcomes in LLD based on structural MRI (sMRI). In this paper, we describe the development of a hybrid representation learning (HRL) framework for predicting cognitive diagnosis over 5 years based on T1-weighted sMRI data. Specifically, we first extract prediction-oriented MRI features via a deep neural network, and then integrate them with handcrafted MRI features via a Transformer encoder for cognitive diagnosis prediction. Two tasks are investigated in this work, including (1) identifying cognitively normal subjects with LLD and never-depressed older healthy subjects, and (2) identifying LLD subjects who developed CI (or even AD) and those who stayed cognitively normal over five years. We validate the proposed HRL on 294 subjects with T1-weighted MRIs from two clinically harmonized studies. Experimental results suggest that the HRL outperforms several classical machine learning and state-of-the-art deep learning methods in LLD identification and prediction tasks.

Advancements in computer-assisted diagnosis of Alzheimer's disease: A comprehensive survey of neuroimaging methods and AI techniques for early detection

Alzheimer's Disease (AD) is a brain disorder that causes the brain to shrink and eventually causes brain cells to die. This neurological condition progressively hampers cognitive and memory functions, along with the ability to carry out fundamental tasks over time. From the symptoms it is very difficult to detect during its early stage. It has become necessary to develop a computer assisted diagnostic models for the early AD detection. This survey work, discussed about a review of 110 published AD detection methods and techniques from the year 2011 to till-date. This study lies in its comprehensive exploration of AD detection methods using a range of artificial intelligence (AI) techniques and neuroimaging modalities. By collecting and analysing 50 papers related to AD diagnosis datasets, the study provides a comprehensive understanding of the diversity of input types, subjects, and classes used in AD research. Summarizing 60 papers on methodologies gives researchers a succinct overview of various approaches that contribute to enhancing detection accuracy. From the review, data are acquired and pre-processed form multiple modalities of neuroimaging. This paper mainly focused on review of different datasets used, various feature extraction methods, parameters used in neuro images. To diagnosis the Alzheimer's disease, the existing methods utilized three most common artificial intelligence techniques such as machine learning, deep learning, and transfer learning. We conclude this survey work by providing future perspectives for AD diagnosis at early stage.

Distortion correction of functional MRI without reverse phase encoding scans or field maps

Functional magnetic resonance images (fMRI) acquired using echo planar sequences typically suffer from spatial distortions due to susceptibility induced off-resonance fields, which may cause geometric mismatch with structural images and affect subsequent quantification and localization of brain function. State-of-the art distortion correction methods (for example, using FSL's topup or AFNI's 3dQwarp algorithms) require the collection of additional scans - either field maps or images with reverse phase encoding directions (i.e., blip-up/blip-down acquisitions) - to estimate and correct distortions. However, not all imaging protocols acquire these additional data and thus cannot take advantage of these post-acquisition corrections. In this study, we aim to enable state-of-the art processing of historical or limited datasets that do not include specific sequences for distortion correction by using only the acquired functional data and a single commonly acquired structural image. To achieve this, we synthesize an undistorted image with contrast similar to the fMRI data and use the non-distorted synthetic image as an anatomical target for distortion correction. We evaluate the efficacy of this approach, named SynBOLD-DisCo (Synthetic BOLD contrast for Distortion Correction), and show that this distortion correction process yields fMRI data that are geometrically similar to non-distorted structural images, with distortion correction virtually equivalent to acquisitions that do contain both blip-up/blip-down images. Our method is available as a Singularity container, source code, and an executable trained model to facilitate evaluation and integration into existing fMRI preprocessing pipelines.

Deep learning for collateral evaluation in ischemic stroke with imbalanced data

PURPOSE

Collateral evaluation is typically done using visual inspection of cerebral images and thus suffers from intra- and inter-rater variability. Large open databases of ischemic stroke patients are rare, limiting the use of deep learning methods in treatment decision-making.

METHODS

We adapted a pre-trained EfficientNet B0 network through transfer learning to improve collateral evaluation using slice-based and subject-level classification. Our method uses stacking and overlapping of 2D slices from a patient's 4D computed tomography angiography (CTA) and a majority voting scheme to determine a patient's final collateral grade based on all classified 2D MIPs. Class imbalance is handled in the evaluation process by using the focal loss with class weight to penalize the majority class.

RESULTS

We evaluated our method using a nine-fold cross-validation performed with 83 subjects. Mean sensitivity of 0.71, specificity of 0.84, and a weighted F1 score of 0.71 in multi-class (good, intermediate, and poor) classification were obtained. Considering treatment effect, a dichotomized decision is also made for collateral scoring of a subject based on two classes (good/intermediate and poor) which achieves a sensitivity of 0.89 and specificity of 0.96 with a weighted F1 score of 0.95.

CONCLUSION

An automatic and robust collateral assessment method that mitigates the issues with the small imbalanced dataset was developed. Computer-aided evaluation of collaterals can help decision-making of ischemic stroke treatment strategy in clinical settings.

SAN-Net: Learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input; i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.

Four-way classification of Alzheimer's disease using deep Siamese convolutional neural network with triplet-loss function

Alzheimer's disease (AD) is a neurodegenerative disease that causes irreversible damage to several brain regions, including the hippocampus causing impairment in cognition, function, and behaviour. Early diagnosis of the disease will reduce the suffering of the patients and their family members. Towards this aim, in this paper, we propose a Siamese Convolutional Neural Network (SCNN) architecture that employs the triplet-loss function for the representation of input MRI images as k-dimensional embeddings. We used both pre-trained and non-pretrained CNNs to transform images into the embedding space. These embeddings are subsequently used for the 4-way classification of Alzheimer's disease. The model efficacy was tested using the ADNI and OASIS datasets which produced an accuracy of 91.83% and 93.85%, respectively. Furthermore, obtained results are compared with similar methods proposed in the literature.

Episodic Memory-Related Imaging Features as Valuable Biomarkers for the Diagnosis of Alzheimer's Disease: A Multicenter Study Based on Machine Learning

BACKGROUND

Individualized and reliable biomarkers are crucial for diagnosing Alzheimer's disease (AD). However, lack of accessibility and neurobiological correlation are the main obstacles to their clinical application. Machine learning algorithms can effectively identify personalized biomarkers based on the prominent symptoms of AD.

METHODS

Episodic memory-related magnetic resonance imaging (MRI) features of 143 patients with amnesic mild cognitive impairment (MCI) were identified using a multivariate relevance vector regression algorithm. The support vector machine classification model was constructed using these MRI features and verified in 2 independent datasets (N = 994). The neurobiological basis was also investigated based on cognitive assessments, neuropathologic biomarkers of cerebrospinal fluid, and positron emission tomography images of amyloid-β plaques.

RESULTS

The combination of gray matter volume and amplitude of low-frequency fluctuation MRI features accurately predicted episodic memory impairment in individual patients with amnesic MCI (r = 0.638) when measured using an episodic memory assessment panel. The MRI features that contributed to episodic memory prediction were primarily distributed across the default mode network and limbic network. The classification model based on these features distinguished patients with AD from normal control subjects with more than 86% accuracy. Furthermore, most identified episodic memory-related regions showed significantly different amyloid-β positron emission tomography measurements among the AD, MCI, and normal control groups. Moreover, the classification outputs significantly correlated with cognitive assessment scores and cerebrospinal fluid pathological biomarkers' levels in the MCI and AD groups.

CONCLUSIONS

Neuroimaging features can reflect individual episodic memory function and serve as potential diagnostic biomarkers of AD.

Asymmetry-enhanced attention network for Alzheimer's diagnosis with structural Magnetic Resonance Imaging

BACKGROUND AND OBJECTIVE

With the aging of the global population becoming severe, Alzheimer's disease (AD) has become one of the world's most common senile diseases. Many studies have suggested that the brain's left-right asymmetry is one of the possible diagnostic landmarks for AD. However, most published approaches to classification problems may not adequately explore the asymmetry between the left and right hemispheres. At the same time, the relationship between asymmetry traits and other classifier features remains understudied.

METHODS

In this paper, we proposed an asymmetry enhanced attention network (ASEAN) for AD diagnosis that effectively combines the anatomical asymmetry characteristics of the brain to enhance the accuracy and stability of classification tasks. First, we proposed a multi-scale asymmetry feature extraction module (MSAF) that can extract the asymmetry features of the brain from various scales. Second, we proposed an asymmetry refinement module (ARM) that considers the dependency between feature maps to suppress the irrelevant regions of the asymmetric feature maps. In addition, a parameter-free attention module was introduced to infer 4D attention weights and improve the network's representation capability.

RESULTS

The proposed method achieved performance improvements on two databases: Alzheimer's Disease Neuroimaging Initiative (ADNI) and Australian Imaging, Biomarkers and Lifestyle (AIBL). For the classification tasks on ADNI, the proposed method achieves 92.1% accuracy, 96.2% sensitivity, and 91.3% specificity on the AD vs. CN (Cognitively Normal) task. Compared with state-of-the-art methods, the proposed method could achieve comparable results.

CONCLUSION

The proposed model can extract long-range left-right brain similarity as complementary information and improve the model's diagnostic performance. A large number of experiments also support the model's validity. At the same time, this work provides a valuable reference for other neurological diseases, particularly those that exhibit left-right brain asymmetry during development.

Bilateral Analysis Boosts the Performance of Mammography-based Deep Learning Models in Breast Cancer Risk Prediction

Breast cancer is one of the leading causes of death among women. Early prediction of breast cancer can significantly improve the survival rates. Breast density was proven as a reliable risk factor. Deep learning models can learn subtle cues in the mammogram images. CNN models were recently shown to improve the risk discrimination in full-field mammograms. This study aims to improve risk prediction models using bilateral analysis. Bilateral analysis is the process of comparing two breasts to verify presence of anomalies. We developed a Siamese neural network to leverage the bilateral information and asymmetries between the two mammograms of the same patient. We tested our model on 271 patients and compared the results of our Siamese model against the traditional unilateral CNN model. Our results showed AUCs of 0.75 and 0.70 respectively (p = 0.0056). The Siamese model also exhibits higher sensitivity, specificity, precision, and false positive rate with values of 0.68, 0.69, 0.71, 0.31 respectively. While the CNN values were 0.61, 0.66, 0.67, 0.34 respectively. We merged both models by two techniques using pre-trained weights and weighted voting ensemble. The merging technique boosted the AUC to 0.78. The results suggest that bilateral analysis can significantly improve the risk discrimination.

Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer's disease based on cerebral gray matter changes

This study aimed to analyse cerebral grey matter changes in mild cognitive impairment (MCI) using voxel-based morphometry and to diagnose early Alzheimer's disease using deep learning methods based on convolutional neural networks (CNNs) evaluating these changes. Participants (111 MCI, 73 normal cognition) underwent 3-T structural magnetic resonance imaging. The obtained images were assessed using voxel-based morphometry, including extraction of cerebral grey matter, analyses of statistical differences, and correlation analyses between cerebral grey matter and clinical cognitive scores in MCI. The CNN-based deep learning method was used to extract features of cerebral grey matter images. Compared to subjects with normal cognition, participants with MCI had grey matter atrophy mainly in the entorhinal cortex, frontal cortex, and bilateral frontotemporal lobes (p < 0.0001). This atrophy was significantly correlated with the decline in cognitive scores (p < 0.01). The accuracy, sensitivity, and specificity of the CNN model for identifying participants with MCI were 80.9%, 88.9%, and 75%, respectively. The area under the curve of the model was 0.891. These findings demonstrate that research based on brain morphology can provide an effective way for the clinical, non-invasive, objective evaluation and identification of early Alzheimer's disease.

Deep Learning Classification of Breast Cancer Tissue from Terahertz Imaging Through Wavelet Synchro-Squeezed Transformation and Transfer Learning

Terahertz imaging and spectroscopy is an exciting technology that has the potential to provide insights in medical imaging. Prior research has leveraged statistical inference to classify tissue regions from terahertz images. To date, these approaches have shown that the segmentation problem is challenging for images of fresh tissue and for tumors that have invaded muscular regions. Artificial intelligence, particularly machine learning and deep learning, has been shown to improve performance in some medical imaging challenges. This paper builds on that literature by modifying a set of deep learning approaches to the challenge of classifying tissue regions of images captured by terahertz imaging and spectroscopy of freshly excised murine xenograft tissue. Our approach is to preprocess the images through a wavelet synchronous-squeezed transformation (WSST) to convert time-sequential terahertz data of each THz pixel to a spectrogram. Spectrograms are used as input tensors to a deep convolution neural network for pixel-wise classification. Based on the classification result of each pixel, a cancer tissue segmentation map is achieved. In experimentation, we adopt leave-one-sample-out cross-validation strategy, and evaluate our chosen networks and results using multiple metrics such as accuracy, precision, intersection, and size. The results from this experimentation demonstrate improvement in classification accuracy compared to statistical methods, an improvement to segmentation between muscle and cancerous regions in xenograft tumors, and identify areas to improve the imaging and classification methodology.

Content-based image retrieval with a Convolutional Siamese Neural Network: Distinguishing lung cancer and tuberculosis in CT images

BACKGROUND

CT findings of lung cancer and tuberculosis are sometimes similar, potentially leading to misdiagnosis. This study aims to combine deep learning and content-based image retrieval (CBIR) to distinguish lung cancer (LC) from nodular/mass atypical tuberculosis (NMTB) in CT images.

METHODS

This study proposes CBIR with a convolutional Siamese neural network (CBIR-CSNN). First, the lesion patches are cropped out to compose LC and NMTB datasets and the pairs of two arbitrary patches form a patch-pair dataset. Second, this patch-pair dataset is utilized to train a CSNN. Third, a test patch is treated as a query. The distance between this query and 20 patches in both datasets is calculated using the trained CSNN. The patches closest to the query are used to give the final prediction by majority voting. One dataset of 719 patients is used to train and test the CBIR-CSNN. Another external dataset with 30 patients is employed to verify CBIR-CSNN.

RESULTS

The CBIR-CSNN achieves excellent performance at the patch level with an mAP (Mean Average Precision) of 0.953, an accuracy of 0.947, and an area under the curve (AUC) of 0.970. At the patient level, the CBIR-CSNN correctly predicted all labels. In the external dataset, the CBIR-CSNN has an accuracy of 0.802 and AUC of 0.858 at the patch level, and 0.833 and 0.902 at the patient level.

CONCLUSIONS

This CBIR-CSNN can accurately and automatically distinguish LC from NMTB using CT images. CBIR-CSNN has excellent representation capability, compatibility with few-shot learning, and visual explainability.

Machine learning techniques demonstrating individual movement patterns of the vertebral column: the fingerprint of spinal motion

Surface topography systems enable the capture of spinal dynamic movement; however, it is unclear whether vertebral dynamics are unique enough to identify individuals. Therefore, in this study, we investigated whether the identification of individuals is possible based on dynamic spinal data. Three different data representations were compared (automated extracted features using contrastive loss and triplet loss functions, as well as simple descriptive statistics). High accuracies indicated the possible existence of a personal spinal 'fingerprint', therefore enabling subject recognition. The present work forms the basis for an objective comparison of subjects and the transfer of the method to clinical use cases.

MDAN: Mirror Difference Aware Network for Brain Stroke Lesion Segmentation

Brain stroke lesion segmentation is of great importance for stroke rehabilitation neuroimaging analysis. Due to the large variance of stroke lesion shapes and similarities of tissue intensity distribution, it remains a challenging task. To help detect abnormalities, the anatomical symmetries of brain magnetic resonance (MR) images have been widely used as visual cues for clinical practices. However, most methods do not fully utilize structural symmetry information in brain images segmentation. This paper presents a novel mirror difference aware network (MDAN) for stroke lesion segmentation in an encoder-decoder architecture, aiming at holistically exploiting the symmetries of image features. Specifically, a differential feature augmentation (DFA) module is developed in the encoding path to highlight the semantically pathological asymmetries of the features in abnormalities. In the DFA module, a Siamese contrastive supervised loss is designed to enhance discriminative features, and a mirror position-based difference augmentation (MDA) module is used to further magnify the discrepancy information. Moreover, mirror feature fusion (MFF) modules are applied to fuse and transfer the information both of the original input and the horizontally flipped features to the decoding path. Extensive experiments on the Anatomical Tracings of Lesions After Stroke (ATLAS) dataset show the proposed MDAN outperforms the state-of-the-art methods.

Compare and contrast: Detecting mammographic soft-tissue lesions with C2-Net

Detecting breast soft-tissue lesions including masses, structural distortions and asymmetries is of great importance due to the high risk leading to breast cancer. Most existing deep learning based approaches detect lesions with only unilateral images. However, multi-view mammogram images provide highly related and complementary information which helps to make the clinical analysis more comprehensive and reliable. In this paper, we propose a multi-view network for breast soft-tissue lesion detection called C²-Net (Compare and Contrast, C²) that fuses information across different views. The proposed model contains the following three modules. The spatial context enhancing (SCE) module compares ipsilateral views and extracts complementary features to model lesion inherent 3D structure. The multi-scale kernel pooling (MKP) module contrasts contralateral views with added misalignment tolerance. Finally, the logic guided fusion (LGF) module fuses multi-view features by enhancing logic modeling capacity. Experimental results on both the public DDSM dataset and the in-house multi-center dataset demonstrate that the proposed method has achieved state-of-the-art performance.

[Research on the application of convolution neural network in the diagnosis of Alzheimer's disease]

With the wide application of deep learning technology in disease diagnosis, especially the outstanding performance of convolutional neural network (CNN) in computer vision and image processing, more and more studies have proposed to use this algorithm to achieve the classification of Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal cognition (CN). This article systematically reviews the application progress of several classic convolutional neural network models in brain image analysis and diagnosis at different stages of Alzheimer's disease, and discusses the existing problems and gives the possible development directions in order to provide some references.

Siamese Neural Networks: An Overview

Similarity has always been a key aspect in computer science and statistics. Any time two element vectors are compared, many different similarity approaches can be used, depending on the final goal of the comparison (Euclidean distance, Pearson correlation coefficient, Spearman's rank correlation coefficient, and others). But if the comparison has to be applied to more complex data samples, with features having different dimensionality and types which might need compression before processing, these measures would be unsuitable. In these cases, a siamese neural network may be the best choice: it consists of two identical artificial neural networks each capable of learning the hidden representation of an input vector. The two neural networks are both feedforward perceptrons, and employ error back-propagation during training; they work parallelly in tandem and compare their outputs at the end, usually through a cosine distance. The output generated by a siamese neural network execution can be considered the semantic similarity between the projected representation of the two input vectors. In this overview we first describe the siamese neural network architecture, and then we outline its main applications in a number of computational fields since its appearance in 1994. Additionally, we list the programming languages, software packages, tutorials, and guides that can be practically used by readers to implement this powerful machine learning model.

Whole brain volume and cortical thickness abnormalities in Wilson's disease: a clinical correlation study

Wilson's disease (WD) is an inherited autosomal recessive disorder of copper metabolism, and its neurological and neuropsychiatric manifestations are associated with copper accumulation in brain. A few neuroimaging studies have shown that gray matter atrophy in WD affects both subcortical structures and cortex. This study aims to quantitatively evaluate the morphometric brain abnormalities in patients with WD in terms of whole brain volume and cortical thickness and their associations with clinical severity of WD. Thirty patients clinically diagnosed as WD with neurological manifestations and 25 healthy controls (HC) were recruited. 3D T1-weighted images were segmented into 276 whole-brain regions of interest (ROIs) and 68 cortical ROIs. WD-vs-HC group comparisons were then conducted for each ROI. The associations between those morphometric measurements and the Global Assessment Scale (GAS) score for WD were analyzed. Compared with HC, significant WD-related volumetric decreases were found in the bilateral subcortical nuclei (putamen, globus pallidus, caudate nucleus, substantia nigra, red nucleus and thalamus), diffuse white matter and several gray matter regions. WD patients showed reduced cortical thickness in the left precentral gyrus and the left insula. Further, the volumes of the right globus pallidus, bilateral putamen, right external capsule and left superior longitudinal fasciculus were negatively correlated with GAS. Our results indicated that significant WD-related morphometric abnormalities were quantified in terms of whole-brain volumes and cortical thicknesses, some of which correlated significantly to the clinical severity of WD. Those morphometrics may provide a potentially effective biomarker of WD.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps

Diffusion magnetic resonance images may suffer from geometric distortions due to susceptibility induced off resonance fields, which cause geometric mismatch with anatomical images and ultimately affect subsequent quantification of microstructural or connectivity indices. State-of-the art diffusion distortion correction methods typically require data acquired with reverse phase encoding directions, resulting in varying magnitudes and orientations of distortion, which allow estimation of an undistorted volume. Alternatively, additional field maps acquisitions can be used along with sequence information to determine warping fields. However, not all imaging protocols include these additional scans and cannot take advantage of state-of-the art distortion correction. To avoid additional acquisitions, structural MRI (undistorted scans) can be used as registration targets for intensity driven correction. In this study, we aim to (1) enable susceptibility distortion correction with historical and/or limited diffusion datasets that do not include specific sequences for distortion correction and (2) avoid the computationally intensive registration procedure typically required for distortion correction using structural scans. To achieve these aims, we use deep learning (3D U-nets) to synthesize an undistorted b0 image that matches geometry of structural T1w images and intensity contrasts from diffusion images. Importantly, the training dataset is heterogenous, consisting of varying acquisitions of both structural and diffusion. We apply our approach to a withheld test set and show that distortions are successfully corrected after processing. We quantitatively evaluate the proposed distortion correction and intensity-based registration against state-of-the-art distortion correction (FSL topup). The results illustrate that the proposed pipeline results in b0 images that are geometrically similar to non-distorted structural images, and more closely match state-of-the-art correction with additional acquisitions. In addition, we show generalizability of the proposed approach to datasets that were not in the original training / validation / testing datasets. These datasets included varying populations, contrasts, resolutions, and magnitudes and orientations of distortion and show efficacious distortion correction. The method is available as a Singularity container, source code, and an executable trained model to facilitate evaluation.

Artificial intelligence in medical imaging

The medical specialty radiology has experienced a number of extremely important and influential technical developments in the past that have affected how medical imaging is deployed. Artificial intelligence (AI) is potentially another such development that will introduce fundamental changes into the practice of radiology. In this commentary the historical evolution of some major changes in radiology are traced as background to how AI may also be embraced into practice. Potential new capabilities provided by AI offer exciting prospects for more efficient and effective use of medical images.