Characterizing microstructural development in the fetal brain using diffusion MRI from 23 to 36 weeks of gestation.

We utilized motion-corrected diffusion tensor imaging (DTI) to evaluate microstructural changes in healthy fetal brains during the late second and third trimesters. Data were derived from fetal magnetic resonance imaging scans conducted as part of a prospective study spanning from 2013 March to 2019 May. The study included 44 fetuses between the gestational ages (GAs) of 23 and 36 weeks. We reconstructed fetal brain DTI using a motion-tracked slice-to-volume registration framework. Images were segmented into 14 regions of interest (ROIs) through label propagation using a fetal DTI atlas, with expert refinement. Statistical analysis involved assessing changes in fractional anisotropy (FA) and mean diffusivity (MD) throughout gestation using mixed-effects models, and identifying points of change in trajectory for ROIs with nonlinear trends. Results showed significant GA-related changes in FA and MD in all ROIs except in the thalamus' FA and corpus callosum's MD. Hemispheric asymmetries were found in the FA of the periventricular white matter (pvWM), intermediate zone, and subplate and in the MD of the ganglionic eminence and pvWM. This study provides valuable insight into the normal patterns of development of MD and FA in the fetal brain. These changes are closely linked with cytoarchitectonic changes and display indications of early functional specialization.

Detailed anatomic segmentations of a fetal brain diffusion tensor imaging atlas between 23 and 30 weeks of gestation.

This work presents detailed anatomic labels for a spatiotemporal atlas of fetal brain Diffusion Tensor Imaging (DTI) between 23 and 30 weeks of post-conceptional age. Additionally, we examined developmental trajectories in fractional anisotropy (FA) and mean diffusivity (MD) across gestational ages (GA). We performed manual segmentations on a fetal brain DTI atlas. We labeled 14 regions of interest (ROIs): cortical plate (CP), subplate (SP), Intermediate zone-subventricular zone-ventricular zone (IZ/SVZ/VZ), Ganglionic Eminence (GE), anterior and posterior limbs of the internal capsule (ALIC, PLIC), genu (GCC), body (BCC), and splenium (SCC) of the corpus callosum (CC), hippocampus, lentiform Nucleus, thalamus, brainstem, and cerebellum. A series of linear regressions were used to assess GA as a predictor of FA and MD for each ROI. The combination of MD and FA allowed the identification of all ROIs. Increasing GA was significantly associated with decreasing FA in the CP, SP, IZ/SVZ/IZ, GE, ALIC, hippocampus, and BCC (p < .03, for all), and with increasing FA in the PLIC and SCC (p < .002, for both). Increasing GA was significantly associated with increasing MD in the CP, SP, IZ/SVZ/IZ, GE, ALIC, and CC (p < .03, for all). We developed a set of expert-annotated labels for a DTI spatiotemporal atlas of the fetal brain and presented a pilot analysis of developmental changes in cerebral microstructure between 23 and 30 weeks of GA.

Population Atlas Analysis of Emerging Brain Structural Connections in the Human Fetus.

BACKGROUND: A lack of in utero imaging data hampers our understanding of the connections in the human fetal brain. Generalizing observations from postmortem subjects and premature newborns is inaccurate due to technical and biological differences. PURPOSE: To evaluate changes in fetal brain structural connectivity between 23 and 35 weeks postconceptional age using a spatiotemporal atlas of diffusion tensor imaging (DTI). STUDY TYPE: Retrospective. POPULATION: Publicly available diffusion atlases, based on 60 healthy women (age 18-45 years) with normal prenatal care, from 23 and 35 weeks of gestation. FIELD STRENGTH/SEQUENCE: 3.0 Tesla/DTI acquired with diffusion-weighted echo planar imaging (EPI). ASSESSMENT: We performed whole-brain fiber tractography from DTI images. The cortical plate of each diffusion atlas was segmented and parcellated into 78 regions derived from the Edinburgh Neonatal Atlas (ENA33). Connectivity matrices were computed, representing normalized fiber connections between nodes. We examined the relationship between global efficiency (GE), local efficiency (LE), small-worldness (SW), nodal efficiency (NE), and betweenness centrality (BC) with gestational age (GA) and with laterality. STATISTICAL TESTS: Linear regression was used to analyze changes in GE, LE, NE, and BC throughout gestation, and to assess changes in laterality. The t-tests were used to assess SW. P-values were corrected using Holm-Bonferroni method. A corrected P-value <0.05 was considered statistically significant. RESULTS: Network analysis revealed a significant weekly increase in GE (5.83%/week, 95% CI 4.32-7.37), LE (5.43%/week, 95% CI 3.63-7.25), and presence of SW across GA. No significant hemisphere differences were found in GE (P = 0.971) or LE (P = 0.458). Increasing GA was significantly associated with increasing NE in 41 nodes, increasing BC in 3 nodes, and decreasing BC in 2 nodes. DATA CONCLUSION: Extensive network development and refinement occur in the second and third trimesters, marked by a rapid increase in global integration and local segregation. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Insights from the IronTract challenge: Optimal methods for mapping brain pathways from multi-shell diffusion MRI.

Limitations in the accuracy of brain pathways reconstructed by diffusion MRI (dMRI) tractography have received considerable attention. While the technical advances spearheaded by the Human Connectome Project (HCP) led to significant improvements in dMRI data quality, it remains unclear how these data should be analyzed to maximize tractography accuracy. Over a period of two years, we have engaged the dMRI community in the IronTract Challenge, which aims to answer this question by leveraging a unique dataset. Macaque brains that have received both tracer injections and ex vivo dMRI at high spatial and angular resolution allow a comprehensive, quantitative assessment of tractography accuracy on state-of-the-art dMRI acquisition schemes. We find that, when analysis methods are carefully optimized, the HCP scheme can achieve similar accuracy as a more time-consuming, Cartesian-grid scheme. Importantly, we show that simple pre- and post-processing strategies can improve the accuracy and robustness of many tractography methods. Finally, we find that fiber configurations that go beyond crossing (e.g., fanning, branching) are the most challenging for tractography. The IronTract Challenge remains open and we hope that it can serve as a valuable validation tool for both users and developers of dMRI analysis methods.

Learning to estimate the fiber orientation distribution function from diffusion-weighted MRI.

Estimation of white matter fiber orientation distribution function (fODF) is the essential first step for reliable brain tractography and connectivity analysis. Most of the existing fODF estimation methods rely on sub-optimal physical models of the diffusion signal or mathematical simplifications, which can impact the estimation accuracy. In this paper, we propose a data-driven method that avoids some of these pitfalls. Our proposed method is based on a multilayer perceptron that learns to map the diffusion-weighted measurements, interpolated onto a fixed spherical grid in the q space, to the target fODF. Importantly, we also propose methods for synthesizing reliable simulated training data. We show that the model can be effectively trained with simulated or real training data. Our phantom experiments show that the proposed method results in more accurate fODF estimation and tractography than several competing methods including the multi-tensor model, Bayesian estimation, spherical deconvolution, and two other machine learning techniques. On real data, we compare our method with other techniques in terms of accuracy of estimating the ground-truth fODF. The results show that our method is more accurate than other methods, and that it performs better than the competing methods when applied to under-sampled diffusion measurements. We also compare our method with the Sparse Fascicle Model in terms of expert ratings of the accuracy of reconstruction of several commissural, projection, association, and cerebellar tracts. The results show that the tracts reconstructed with the proposed method are rated significantly higher by three independent experts. Our study demonstrates the potential of data-driven methods for improving the accuracy and robustness of fODF estimation.

Deep learning-based parameter estimation in fetal diffusion-weighted MRI.

Diffusion-weighted magnetic resonance imaging (DW-MRI) of fetal brain is challenged by frequent fetal motion and signal to noise ratio that is much lower than non-fetal imaging. As a result, accurate and robust parameter estimation in fetal DW-MRI remains an open problem. Recently, deep learning techniques have been successfully used for DW-MRI parameter estimation in non-fetal subjects. However, none of those prior works has addressed the fetal brain because obtaining reliable fetal training data is challenging. To address this problem, in this work we propose a novel methodology that utilizes fetal scans as well as scans from prematurely-born infants. High-quality newborn scans are used to estimate accurate maps of the parameter of interest. These parameter maps are then used to generate DW-MRI data that match the measurement scheme and noise distribution that are characteristic of fetal data. In order to demonstrate the effectiveness and reliability of the proposed data generation pipeline, we used the generated data to train a convolutional neural network (CNN) to estimate color fractional anisotropy (CFA). We evaluated the trained CNN on independent sets of fetal data in terms of reconstruction accuracy, precision, and expert assessment of reconstruction quality. Results showed significantly lower reconstruction error (n=100,p<0.001) and higher reconstruction precision (n=20,p<0.001) for the proposed machine learning pipeline compared with standard estimation methods. Expert assessments on 20 fetal test scans showed significantly better overall reconstruction quality (p<0.001) and more accurate reconstruction of 11 regions of interest (p<0.001) with the proposed method.

A sinogram denoising algorithm for low-dose computed tomography.

BACKGROUND: From the viewpoint of the patients' health, reducing the radiation dose in computed tomography (CT) is highly desirable. However, projection measurements acquired under low-dose conditions will contain much noise. Therefore, reconstruction of high-quality images from low-dose scans requires effective denoising of the projection measurements. METHODS: We propose a denoising algorithm that is based on maximizing the data likelihood and sparsity in the gradient domain. For Poisson noise, this formulation automatically leads to a locally adaptive denoising scheme. Because the resulting optimization problem is hard to solve and may also lead to artifacts, we suggest an explicitly local denoising method by adapting an existing algorithm for normally-distributed noise. We apply the proposed method on sets of simulated and real cone-beam projections and compare its performance with two other algorithms. RESULTS: The proposed algorithm effectively suppresses the noise in simulated and real CT projections. Denoising of the projections with the proposed algorithm leads to a substantial improvement of the reconstructed image in terms of noise level, spatial resolution, and visual quality. CONCLUSION: The proposed algorithm can suppress very strong quantum noise in CT projections. Therefore, it can be used as an effective tool in low-dose CT.

A detailed spatio-temporal atlas of the white matter tracts for the fetal brain.

This study presents the construction of a comprehensive spatiotemporal atlas detailing the development of white matter tracts in the fetal brain using diffusion magnetic resonance imaging (dMRI). Our research leverages data collected from fetal MRI scans conducted between 22 and 37 weeks of gestation, capturing the dynamic changes in the brain's microstructure during this critical period. The atlas includes 60 distinct white matter tracts, including commissural, projection, and association fibers. We employed advanced fetal dMRI processing techniques and tractography to map and characterize the developmental trajectories of these tracts. Our findings reveal that the development of these tracts is characterized by complex patterns of fractional anisotropy (FA) and mean diffusivity (MD), reflecting key neurodevelopmental processes such as axonal growth, involution of the radial-glial scaffolding, and synaptic pruning. This atlas can serve as a useful resource for neuroscience research and clinical practice, improving our understanding of the fetal brain and potentially aiding in the early diagnosis of neurodevelopmental disorders. By detailing the normal progression of white matter tract development, the atlas can be used as a benchmark for identifying deviations that may indicate neurological anomalies or predispositions to disorders.

Deep learning microstructure estimation of developing brains from diffusion MRI: A newborn and fetal study.

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results than standard methods such as Constrained Spherical Deconvolution and two state-of-the-art deep learning methods. For voxels with one and two fibers, respectively, our method shows an agreement rate in terms of the number of fibers of 77.5% and 22.2%, which is 3% and 5.4% higher than other deep learning methods, and an angular error of 10° and 20°, which is 6° and 5° lower than other deep learning methods. To determine baselines for assessing the performance of our method, we compute agreement metrics using densely sampled newborn data. Moreover, we demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical external datasets of newborns and fetuses. We validate fetal FODs, successfully estimated for the first time with deep learning, using post-mortem histological data. Our results show the advantage of deep learning in computing the fiber orientation density for the developing brain from in-vivo dMRI measurements that are often very limited due to constrained acquisition times. Our findings also highlight the intrinsic limitations of dMRI for probing the developing brain microstructure.

Advances in Fetal Brain Imaging.

Over the last 20 years, there have been remarkable developments in fetal brain MR imaging analysis methods. This article delves into the specifics of structural imaging, diffusion imaging, functional MR imaging, and spectroscopy, highlighting the latest advancements in motion correction, fetal brain development atlases, and the challenges and innovations. Furthermore, this article explores the clinical applications of these advanced imaging techniques in comprehending and diagnosing fetal brain development and abnormalities.

Prostate Cancer Risk Stratification by Digital Histopathology and Deep Learning.

PURPOSE: Prostate cancer (PCa) represents a highly heterogeneous disease that requires tools to assess oncologic risk and guide patient management and treatment planning. Current models are based on various clinical and pathologic parameters including Gleason grading, which suffers from a high interobserver variability. In this study, we determine whether objective machine learning (ML)-driven histopathology image analysis would aid us in better risk stratification of PCa. MATERIALS AND METHODS: We propose a deep learning, histopathology image-based risk stratification model that combines clinicopathologic data along with hematoxylin and eosin- and Ki-67-stained histopathology images. We train and test our model, using a five-fold cross-validation strategy, on a data set from 502 treatment-naïve PCa patients who underwent radical prostatectomy (RP) between 2000 and 2012. RESULTS: We used the concordance index as a measure to evaluate the performance of various risk stratification models. Our risk stratification model on the basis of convolutional neural networks demonstrated superior performance compared with Gleason grading and the Cancer of the Prostate Risk Assessment Post-Surgical risk stratification models. Using our model, 3.9% of the low-risk patients were correctly reclassified to be high-risk and 21.3% of the high-risk patients were correctly reclassified as low-risk. CONCLUSION: These findings highlight the importance of ML as an objective tool for histopathology image assessment and patient risk stratification. With further validation on large cohorts, the digital pathology risk classification we propose may be helpful in guiding administration of adjuvant therapy including radiotherapy after RP.

Improving Calibration and Out-of-Distribution Detection in Deep Models for Medical Image Segmentation.

Convolutional Neural Networks (CNNs) have proved to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical image datasets is still challenging, with many studies promoting techniques such as transfer learning. Moreover, these models are infamous for producing over-confident predictions and for failing silently when presented with out-of-distribution (OOD) test data. In this paper, for improving prediction calibration we advocate for multi-task learning, i.e., training a single model on several different datasets, spanning different organs of interest and different imaging modalities. We show that multi-task learning can significantly improve model confidence calibration. For OOD detection, we propose a novel method based on spectral analysis of CNN feature maps. We show that different datasets, representing different imaging modalities and/or different organs of interest, have distinct spectral signatures, which can be used to identify whether or not a test image is similar to the images used for training. We show that our proposed method is more accurate than several competing methods, including methods based on prediction uncertainty and image classification.

TBSS++: A novel computational method for Tract-Based Spatial Statistics.

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. One of the most common computations in dMRI involves cross-subject tract-specific analysis, whereby dMRI-derived biomarkers are compared between cohorts of subjects. The accuracy and reliability of these studies hinges on the ability to compare precisely the same white matter tracts across subjects. This is an intricate and error-prone computation. Existing computational methods such as Tract-Based Spatial Statistics (TBSS) suffer from a host of shortcomings and limitations that can seriously undermine the validity of the results. We present a new computational framework that overcomes the limitations of existing methods via (i) accurate segmentation of the tracts, and (ii) precise registration of data from different subjects/scans. The registration is based on fiber orientation distributions. To further improve the alignment of cross-subject data, we create detailed atlases of white matter tracts. These atlases serve as an unbiased reference space where the data from all subjects is registered for comparison. Extensive evaluations show that, compared with TBSS, our proposed framework offers significantly higher reproducibility and robustness to data perturbations. Our method promises a drastic improvement in accuracy and reproducibility of cross-subject dMRI studies that are routinely used in neuroscience and medical research.

Direct segmentation of brain white matter tracts in diffusion MRI.

The brain white matter consists of a set of tracts that connect distinct regions of the brain. Segmentation of these tracts is often needed for clinical and research studies. Diffusion-weighted MRI offers unique contrast to delineate these tracts. However, existing segmentation methods rely on intermediate computations such as tractography or estimation of fiber orientation density. These intermediate computations, in turn, entail complex computations that can result in unnecessary errors. Moreover, these intermediate computations often require dense multi-shell measurements that are unavailable in many clinical and research applications. As a result, current methods suffer from low accuracy and poor generalizability. Here, we propose a new deep learning method that segments these tracts directly from the diffusion MRI data, thereby sidestepping the intermediate computation errors. Our experiments show that this method can achieve segmentation accuracy that is on par with the state of the art methods (mean Dice Similarity Coefficient of 0.826). Compared with the state of the art, our method offers far superior generalizability to undersampled data that are typical of clinical studies and to data obtained with different acquisition protocols. Moreover, we propose a new method for detecting inaccurate segmentations and show that it is more accurate than standard methods that are based on estimation uncertainty quantification. The new methods can serve many critically important clinical and scientific applications that require accurate and reliable non-invasive segmentation of white matter tracts.

A computational framework for characterizing normative development of structural brain connectivity in the perinatal stage.

Quantitative assessment of the brain's structural connectivity in the perinatal stage is useful for studying normal and abnormal neurodevelopment. However, estimation of the structural connectome from diffusion MRI data involves a series of complex and ill-posed computations. For the perinatal period, this analysis is further challenged by the rapid brain development and difficulties of imaging subjects at this stage. These factors, along with high inter-subject variability, have made it difficult to chart the normative development of the structural connectome. Hence, there is a lack of baseline trends in connectivity metrics that can be used as reliable references for assessing normal and abnormal brain development at this critical stage. In this paper we propose a computational framework, based on spatio-temporal atlases, for determining such baselines. We apply the framework on data from 169 subjects between 33 and 45 postmenstrual weeks. We show that this framework can unveil clear and strong trends in the development of structural connectivity in the perinatal stage. Some of our interesting findings include that connection weighting based on neurite density produces more consistent trends and that the trends in global efficiency, local efficiency, and characteristic path length are more consistent than in other metrics.

Learning to segment fetal brain tissue from noisy annotations.

Automatic fetal brain tissue segmentation can enhance the quantitative assessment of brain development at this critical stage. Deep learning methods represent the state of the art in medical image segmentation and have also achieved impressive results in brain segmentation. However, effective training of a deep learning model to perform this task requires a large number of training images to represent the rapid development of the transient fetal brain structures. On the other hand, manual multi-label segmentation of a large number of 3D images is prohibitive. To address this challenge, we segmented 272 training images, covering 19-39 gestational weeks, using an automatic multi-atlas segmentation strategy based on deformable registration and probabilistic atlas fusion, and manually corrected large errors in those segmentations. Since this process generated a large training dataset with noisy segmentations, we developed a novel label smoothing procedure and a loss function to train a deep learning model with smoothed noisy segmentations. Our proposed methods properly account for the uncertainty in tissue boundaries. We evaluated our method on 23 manually-segmented test images of a separate set of fetuses. Results show that our method achieves an average Dice similarity coefficient of 0.893 and 0.916 for the transient structures of younger and older fetuses, respectively. Our method generated results that were significantly more accurate than several state-of-the-art methods including nnU-Net that achieved the closest results to our method. Our trained model can serve as a valuable tool to enhance the accuracy and reproducibility of fetal brain analysis in MRI.

Characterizing normal perinatal development of the human brain structural connectivity.

Early brain development is characterized by the formation of a highly organized structural connectome. The interconnected nature of this connectome underlies the brain's cognitive abilities and influences its response to diseases and environmental factors. Hence, quantitative assessment of structural connectivity in the perinatal stage is useful for studying normal and abnormal neurodevelopment. However, estimation of the connectome from diffusion MRI data involves complex computations. For the perinatal period, these computations are further challenged by the rapid brain development and imaging difficulties. Combined with high inter-subject variability, these factors make it difficult to chart the normal development of the structural connectome. As a result, there is a lack of reliable normative baselines of structural connectivity metrics at this critical stage in brain development. In this study, we developed a computational framework, based on spatio-temporal averaging, for determining such baselines. We used this framework to analyze the structural connectivity between 33 and 44 postmenstrual weeks using data from 166 subjects. Our results unveiled clear and strong trends in the development of structural connectivity in perinatal stage. Connection weighting based on fractional anisotropy and neurite density produced the most consistent results. We observed increases in global and local efficiency, a decrease in characteristic path length, and widespread strengthening of the connections within and across brain lobes and hemispheres. We also observed asymmetry patterns that were consistent between different connection weighting approaches. The new computational method and results are useful for assessing normal and abnormal development of the structural connectome early in life.

Deep learning microstructure estimation of developing brains from diffusion MRI: a newborn and fetal study.

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation of FODs requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results to standard methods such as Constrained Spherical Deconvolution. We demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical datasets of newborns and fetuses. Additionally, we compute agreement metrics within the HARDI newborn dataset, and validate fetal FODs with post-mortem histological data. The results of this study show the advantage of deep learning in inferring the microstructure of the developing brain from in-vivo dMRI measurements that are often very limited due to subject motion and limited acquisition times, but also highlight the intrinsic limitations of dMRI in the analysis of the developing brain microstructure. These findings, therefore, advocate for the need for improved methods that are tailored to studying the early development of human brain.

CROSS-AGE AND CROSS-SITE DOMAIN SHIFT IMPACTS ON DEEP LEARNING-BASED WHITE MATTER FIBER ESTIMATION IN NEWBORN AND BABY BRAINS.

Deep learning models have shown great promise in estimating tissue microstructure from limited diffusion magnetic resonance imaging data. However, these models face domain shift challenges when test and train data are from different scanners and protocols, or when the models are applied to data with inherent variations such as the developing brains of infants and children scanned at various ages. Several techniques have been proposed to address some of these challenges, such as data harmonization or domain adaptation in the adult brain. However, those techniques remain unexplored for the estimation of fiber orientation distribution functions in the rapidly developing brains of infants. In this work, we extensively investigate the age effect and domain shift within and across two different cohorts of 201 newborns and 165 babies using the Method of Moments and fine-tuning strategies. Our results show that reduced variations in the microstructural development of babies in comparison to newborns directly impact the deep learning models' cross-age performance. We also demonstrate that a small number of target domain samples can significantly mitigate domain shift problems.

LigaNET: A multi-modal deep learning approach to predict the risk of subsequent anterior cruciate ligament injury after surgery.

Anterior cruciate ligament (ACL) injuries are a common cause of soft tissue injuries in young active individuals, leading to a significant risk of premature joint degeneration. Postoperative management of such injuries, in particular returning patients to athletic activities, is a challenge with immediate and long-term implications including the risk of subsequent injury. In this study, we present LigaNET, a multi-modal deep learning pipeline that predicts the risk of subsequent ACL injury following surgical treatment. Postoperative MRIs (n=1,762) obtained longitudinally between 3 to 24 months after ACL surgery from a cohort of 159 patients along with 11 non-imaging outcomes were used to train and test: 1) a 3D CNN to predict subsequent ACL injury from segmented ACLs, 2) a 3D CNN to predict injury from the whole MRI, 3) a logistic regression classifier predict injury from non-imaging data, and 4) a multi-modal pipeline by fusing the predictions of each classifier. The CNN using the segmented ACL achieved an accuracy of 77.6% and AUROC of 0.84, which was significantly better than the CNN using the whole knee MRI (accuracy: 66.6%, AUROC: 0.70; P<.001) and the non-imaging classifier (accuracy: 70.1%, AUROC: 0.75; P=.039). The fusion of all three classifiers resulted in highest classification performance (accuracy: 80.6%, AUROC: 0.89), which was significantly better than each individual classifier (P<.001). The developed multi-modal approach had similar performance in predicting the risk of subsequent ACL injury from any of the imaging sequences (P>.10). Our results demonstrate that a deep learning approach can achieve high performance in identifying patients at high risk of subsequent ACL injury after surgery and may be used in clinical decision making to improve postoperative management (e.g., safe return to sports) of ACL injured patients.