Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Radiology Radiology

Building a comprehensive cardiovascular magnetic resonance exam on a commercial 0.55 T system: A pictorial essay on potential applications.

In Frontiers in cardiovascular medicine

BACKGROUND : Contemporary advances in low-field magnetic resonance imaging systems can potentially widen access to cardiovascular magnetic resonance (CMR) imaging. We present our initial experience in building a comprehensive CMR protocol on a commercial 0.55 T system with a gradient performance of 26 mT/m amplitude and 45 T/m/s slew rate. To achieve sufficient image quality, we adapted standard imaging techniques when possible, and implemented compressed-sensing (CS) based techniques when needed in an effort to compensate for the inherently low signal-to-noise ratio at lower field strength.

METHODS : A prototype CMR exam was built on an 80 cm, ultra-wide bore commercial 0.55 T MR system. Implementation of all components aimed to overcome the inherently lower signal of low-field and the relatively longer echo and repetition times owing to the slower gradients. CS-based breath-held and real-time cine imaging was built utilizing high acceleration rates to meet nominal spatial and temporal resolution recommendations. Similarly, CS 2D phase-contrast cine was implemented for flow. Dark-blood turbo spin echo sequences with deep learning based denoising were implemented for morphology assessment. Magnetization-prepared single-shot myocardial mapping techniques incorporated additional source images. CS-based dynamic contrast-enhanced imaging was implemented for myocardial perfusion and 3D MR angiography. Non-contrast 3D MR angiography was built with electrocardiogram-triggered, navigator-gated magnetization-prepared methods. Late gadolinium enhanced (LGE) tissue characterization methods included breath-held segmented and free-breathing single-shot imaging with motion correction and averaging using an increased number of source images. Proof-of-concept was demonstrated through porcine infarct model, healthy volunteer, and patient scans.

RESULTS : Reasonable image quality was demonstrated for cardiovascular structure, function, flow, and LGE assessment. Low-field afforded utilization of higher flip angles for cine and MR angiography. CS-based techniques were able to overcome gradient speed limitations and meet spatial and temporal resolution recommendations with imaging times comparable to higher performance scanners. Tissue mapping and perfusion imaging require further development.

CONCLUSION : We implemented cardiac applications demonstrating the potential for comprehensive CMR on a novel commercial 0.55 T system. Further development and validation studies are needed before this technology can be applied clinically.

Varghese Juliet, Jin Ning, Giese Daniel, Chen Chong, Liu Yingmin, Pan Yue, Nair Nikita, Shalaan Mahmoud T, Khan Mahmood, Tong Matthew S, Ahmad Rizwan, Han Yuchi, Simonetti Orlando P

2023

0.55 T, CMR, LGE, MRA, cine, flow, low-field

General General

Modelling blood flow in patients with heart valve disease using deep learning: A computationally efficient method to expand diagnostic capabilities in clinical routine.

In Frontiers in cardiovascular medicine

INTRODUCTION : The computational modelling of blood flow is known to provide vital hemodynamic parameters for diagnosis and treatment-support for patients with valvular heart disease. However, most diagnosis/treatment-support solutions based on flow modelling proposed utilize time- and resource-intensive computational fluid dynamics (CFD) and are therefore difficult to implement into clinical practice. In contrast, deep learning (DL) algorithms provide results quickly with little need for computational power. Thus, modelling blood flow with DL instead of CFD may substantially enhances the usability of flow modelling-based diagnosis/treatment support in clinical routine. In this study, we propose a DL-based approach to compute pressure and wall-shear-stress (WSS) in the aorta and aortic valve of patients with aortic stenosis (AS).

METHODS : A total of 103 individual surface models of the aorta and aortic valve were constructed from computed tomography data of AS patients. Based on these surface models, a total of 267 patient-specific, steady-state CFD simulations of aortic flow under various flow rates were performed. Using this simulation data, an artificial neural network (ANN) was trained to compute spatially resolved pressure and WSS using a centerline-based representation. An unseen test subset of 23 cases was used to compare both methods.

RESULTS : ANN and CFD-based computations agreed well with a median relative difference between both methods of 6.0% for pressure and 4.9% for wall-shear-stress. Demonstrating the ability of DL to compute clinically relevant hemodynamic parameters for AS patients, this work presents a possible solution to facilitate the introduction of modelling-based treatment support into clinical practice.

Yevtushenko Pavlo, Goubergrits Leonid, Franke Benedikt, Kuehne Titus, Schafstedde Marie

2023

aortic stenosis, artificial neural network, computational fluid dynamics, deep learning, heart valve disease, image-based modelling, in-silico modelling

Radiology Radiology

The application of machine learning in early diagnosis of osteoarthritis: a narrative review.

In Therapeutic advances in musculoskeletal disease

Osteoarthritis (OA) is the commonest musculoskeletal disease worldwide, with an increasing prevalence due to aging. It causes joint pain and disability, decreased quality of life, and a huge burden on healthcare services for society. However, the current main diagnostic methods are not suitable for early diagnosing patients of OA. The use of machine learning (ML) in OA diagnosis has increased dramatically in the past few years. Hence, in this review article, we describe the research progress in the application of ML in the early diagnosis of OA, discuss the current trends and limitations of ML approaches, and propose future research priorities to apply the tools in the field of OA. Accurate ML-based predictive models with imaging techniques that are sensitive to early changes in OA ahead of the emergence of clinical features are expected to address the current dilemma. The diagnostic ability of the fusion model that combines multidimensional information makes patient-specific early diagnosis and prognosis estimation of OA possible in the future.

Xuan Anran, Chen Haowei, Chen Tianyu, Li Jia, Lu Shilong, Fan Tianxiang, Zeng Dong, Wen Zhibo, Ma Jianhua, Hunter David, Ding Changhai, Zhu Zhaohua

2023

early diagnosis, machine learning, osteoarthritis, prediction model

General General

Acquisition of bipedal locomotion in a neuromusculoskeletal model with unilateral transtibial amputation.

In Frontiers in bioengineering and biotechnology

Adaptive locomotion is an essential behavior for animals to survive. The central pattern generator in the spinal cord is responsible for the basic rhythm of locomotion through sensory feedback coordination, resulting in energy-efficient locomotor patterns. Individuals with symmetrical body proportions exhibit an energy-efficient symmetrical gait on flat ground. In contrast, individuals with lower limb amputation, who have morphologically asymmetrical body proportions, exhibit asymmetrical gait patterns. However, it remains unclear how the nervous system adjusts the control of the lower limbs. Thus, in this study, we investigated how individuals with unilateral transtibial amputation control their left and right lower limbs during locomotion using a two-dimensional neuromusculoskeletal model. The model included a musculoskeletal model with 7 segments and 18 muscles, as well as a neural model with a central pattern generator and sensory feedback systems. Specifically, we examined whether individuals with unilateral transtibial amputation acquire prosthetic gait through a symmetric or asymmetric feedback control for the left and right lower limbs. After acquiring locomotion, the metabolic costs of transport and the symmetry of the spatiotemporal gait factors were evaluated. Regarding the metabolic costs of transportation, the symmetric control model showed values approximately twice those of the asymmetric control model, whereas both scenarios showed asymmetry of spatiotemporal gait patterns. Our results suggest that individuals with unilateral transtibial amputation can reacquire locomotion by modifying sensory feedback parameters. In particular, the model reacquired reasonable locomotion for activities of daily living by re-searching asymmetric feedback parameters for each lower limb. These results could provide insight into effective gait assessment and rehabilitation methods to reacquire locomotion in individuals with unilateral transtibial amputation.

Ichimura Daisuke, Hobara Hiroaki, Hisano Genki, Maruyama Tsubasa, Tada Mitsunori

2023

amputee locomotion, central pattern generator, neuromusculoskeletal model, pathological locomotion, sensory feedback, unilateral transtibial amputation

Public Health Public Health

How social media expression can reveal personality.

In Frontiers in psychiatry

BACKGROUND : Personality psychology studies personality and its variation among individuals and is an essential branch of psychology. In recent years, machine learning research related to personality assessment has started to focus on the online environment and showed outstanding performance in personality assessment. However, the aspects of the personality of these prediction models measure remain unclear because few studies focus on the interpretability of personality prediction models. The objective of this study is to develop and validate a machine learning model with domain knowledge introduced to enhance accuracy and improve interpretability.

METHODS : Study participants were recruited via an online experiment platform. After excluding unqualified participants and downloading the Weibo posts of eligible participants, we used six psycholinguistic and mental health-related lexicons to extract textual features. Then the predictive personality model was developed using the multi-objective extra trees method based on 3,411 pairs of social media expression and personality trait scores. Subsequently, the prediction model's validity and reliability were evaluated, and each lexicon's feature importance was calculated. Finally, the interpretability of the machine learning model was discussed.

RESULTS : The features from Culture Value Dictionary were found to be the most important predictors. The fivefold cross-validation results regarding the prediction model for personality traits ranged between 0.44 and 0.48 (p < 0.001). The correlation coefficients of five personality traits between the two "split-half" datasets data ranged from 0.84 to 0.88 (p < 0.001). Moreover, the model performed well in terms of contractual validity.

CONCLUSION : By introducing domain knowledge to the development of a machine learning model, this study not only ensures the reliability and validity of the prediction model but also improves the interpretability of the machine learning method. The study helps explain aspects of personality measured by such prediction models and finds a link between personality and mental health. Our research also has positive implications regarding the combination of machine learning approaches and domain knowledge in the field of psychiatry and its applications to mental health.

Han Nuo, Li Sijia, Huang Feng, Wen Yeye, Su Yue, Li Linyan, Liu Xiaoqian, Zhu Tingshao

2023

Big Five, domain knowledge, machine learning, mental health, personality, psychological lexicons, social media

General General

Incorporating multi-stage diagnosis status to mine associations between genetic risk variants and the multi-modality phenotype network in major depressive disorder.

In Frontiers in psychiatry

Depression (major depressive disorder, MDD) is a common and serious medical illness. Globally, it is estimated that 5% of adults suffer from depression. Recently, imaging genetics receives growing attention and become a powerful strategy for discoverying the associations between genetic variants (e.g., single-nucleotide polymorphisms, SNPs) and multi-modality brain imaging data. However, most of the existing MDD imaging genetic research studies conducted by clinicians usually utilize simple statistical analysis methods and only consider single-modality brain imaging, which are limited in the deeper discovery of the mechanistic understanding of MDD. It is therefore imperative to utilize a powerful and efficient technology to fully explore associations between genetic variants and multi-modality brain imaging. In this study, we developed a novel imaging genetic association framework to mine the multi-modality phenotype network between genetic risk variants and multi-stage diagnosis status. Specifically, the multi-modality phenotype network consists of voxel node features and connectivity edge features from structural magnetic resonance imaging (sMRI) and resting-state functional magnetic resonance imaging (rs-fMRI). Thereafter, an association model based on multi-task learning strategy was adopted to fully explore the relationship between the MDD risk SNP and the multi-modality phenotype network. The multi-stage diagnosis status was introduced to further mine the relation among the multiple modalities of different subjects. A multi-modality brain imaging data and genotype data were collected by us from two hospitals. The experimental results not only demonstrate the effectiveness of our proposed method but also identify some consistent and stable brain regions of interest (ROIs) biomarkers from the node and edge features of multi-modality phenotype network. Moreover, four new and potential risk SNPs associated with MDD were discovered.

Zhang Li, Pang Mengqian, Liu Xiaoyun, Hao Xiaoke, Wang Meiling, Xie Chunming, Zhang Zhijun, Yuan Yonggui, Zhang Daoqiang

2023

imaging genetics, major depressive disorder, multi-modality, multi-stage diagnosis status, single-nucleotide polymorphisms