Real-time placental vessel segmentation in fetoscopic laser surgery for Twin-to-Twin Transfusion Syndrome.

Twin-to-Twin Transfusion Syndrome (TTTS) is a rare condition that affects about 15% of monochorionic pregnancies, in which identical twins share a single placenta. Fetoscopic laser photocoagulation (FLP) is the standard treatment for TTTS, which significantly improves the survival of fetuses. The aim of FLP is to identify abnormal connections between blood vessels and to laser ablate them in order to equalize blood supply to both fetuses. However, performing fetoscopic surgery is challenging due to limited visibility, a narrow field of view, and significant variability among patients and domains. In order to enhance the visualization of placental vessels during surgery, we propose TTTSNet, a network architecture designed for real-time and accurate placental vessel segmentation. Our network architecture incorporates a novel channel attention module and multi-scale feature fusion module to precisely segment tiny placental vessels. To address the challenges posed by FLP-specific fiberscope and amniotic sac-based artifacts, we employed novel data augmentation techniques. These techniques simulate various artifacts, including laser pointer, amniotic sac particles, and structural and optical fiber artifacts. By incorporating these simulated artifacts during training, our network architecture demonstrated robust generalizability. We trained TTTSNet on a publicly available dataset of 2060 video frames from 18 independent fetoscopic procedures and evaluated it on a multi-center external dataset of 24 in-vivo procedures with a total of 2348 video frames. Our method achieved significant performance improvements compared to state-of-the-art methods, with a mean Intersection over Union of 78.26% for all placental vessels and 73.35% for a subset of tiny placental vessels. Moreover, our method achieved 172 and 152 frames per second on an A100 GPU, and Clara AGX, respectively. This potentially opens the door to real-time application during surgical procedures. The code is publicly available at https://github.com/SanoScience/TTTSNet.

Automated echocardiography view classification and quality assessment with recognition of unknown views.

Purpose: Interpreting echocardiographic exams requires substantial manual interaction as videos lack scan-plane information and have inconsistent image quality, ranging from clinically relevant to unrecognizable. Thus, a manual prerequisite step for analysis is to select the appropriate views that showcase both the target anatomy and optimal image quality. To automate this selection process, we present a method for automatic classification of routine views, recognition of unknown views, and quality assessment of detected views. Approach: We train a neural network for view classification and employ the logit activations from the neural network for unknown view recognition. Subsequently, we train a linear regression algorithm that uses feature embeddings from the neural network to predict view quality scores. We evaluate the method on a clinical test set of 2466 echocardiography videos with expert-annotated view labels and a subset of 438 videos with expert-rated view quality scores. A second observer annotated a subset of 894 videos, including all quality-rated videos. Results: The proposed method achieved an accuracy of 84.9 % ± 0.67 for the joint objective of routine view classification and unknown view recognition, whereas a second observer reached an accuracy of 87.6%. For view quality assessment, the method achieved a Spearman's rank correlation coefficient of 0.71, whereas a second observer reached a correlation coefficient of 0.62. Conclusion: The proposed method approaches expert-level performance, enabling fully automatic selection of the most appropriate views for manual or automatic downstream analysis.

Inter-vendor harmonization of CT reconstruction kernels using unpaired image translation.

The reconstruction kernel in computed tomography (CT) generation determines the texture of the image. Consistency in reconstruction kernels is important as the underlying CT texture can impact measurements during quantitative image analysis. Harmonization (i.e., kernel conversion) minimizes differences in measurements due to inconsistent reconstruction kernels. Existing methods investigate harmonization of CT scans in single or multiple manufacturers. However, these methods require paired scans of hard and soft reconstruction kernels that are spatially and anatomically aligned. Additionally, a large number of models need to be trained across different kernel pairs within manufacturers. In this study, we adopt an unpaired image translation approach to investigate harmonization between and across reconstruction kernels from different manufacturers by constructing a multipath cycle generative adversarial network (GAN). We use hard and soft reconstruction kernels from the Siemens and GE vendors from the National Lung Screening Trial dataset. We use 50 scans from each reconstruction kernel and train a multipath cycle GAN. To evaluate the effect of harmonization on the reconstruction kernels, we harmonize 50 scans each from Siemens hard kernel, GE soft kernel and GE hard kernel to a reference Siemens soft kernel (B30f) and evaluate percent emphysema. We fit a linear model by considering the age, smoking status, sex and vendor and perform an analysis of variance (ANOVA) on the emphysema scores. Our approach minimizes differences in emphysema measurement and highlights the impact of age, sex, smoking status and vendor on emphysema quantification.

ATOMMIC: An Advanced Toolbox for Multitask Medical Imaging Consistency to facilitate Artificial Intelligence applications from acquisition to analysis in Magnetic Resonance Imaging.

BACKGROUND AND OBJECTIVES: Artificial intelligence (AI) is revolutionizing Magnetic Resonance Imaging (MRI) along the acquisition and processing chain. Advanced AI frameworks have been applied in various successive tasks, such as image reconstruction, quantitative parameter map estimation, and image segmentation. However, existing frameworks are often designed to perform tasks independently of each other or are focused on specific models or single datasets, limiting generalization. This work introduces the Advanced Toolbox for Multitask Medical Imaging Consistency (ATOMMIC), a novel open-source toolbox that streamlines AI applications for accelerated MRI reconstruction and analysis. ATOMMIC implements several tasks using deep learning (DL) models and enables MultiTask Learning (MTL) to perform related tasks in an integrated manner, targeting generalization in the MRI domain. METHODS: We conducted a comprehensive literature review and analyzed 12,479 GitHub repositories to assess the current landscape of AI frameworks for MRI. Subsequently, we demonstrate how ATOMMIC standardizes workflows and improves data interoperability, enabling effective benchmarking of various DL models across MRI tasks and datasets. To showcase ATOMMIC's capabilities, we evaluated twenty-five DL models on eight publicly available datasets, focusing on accelerated MRI reconstruction, segmentation, quantitative parameter map estimation, and joint accelerated MRI reconstruction and segmentation using MTL. RESULTS: ATOMMIC's high-performance training and testing capabilities, utilizing multiple GPUs and mixed precision support, enable efficient benchmarking of multiple models across various tasks. The framework's modular architecture implements each task through a collection of data loaders, models, loss functions, evaluation metrics, and pre-processing transformations, facilitating seamless integration of new tasks, datasets, and models. Our findings demonstrate that ATOMMIC supports MTL for multiple MRI tasks with harmonized complex-valued and real-valued data support while maintaining active development and documentation. Task-specific evaluations demonstrate that physics-based models outperform other approaches in reconstructing highly accelerated acquisitions. These high-quality reconstruction models also show superior accuracy in estimating quantitative parameter maps. Furthermore, when combining high-performing reconstruction models with robust segmentation networks through MTL, performance is improved in both tasks. CONCLUSIONS: ATOMMIC advances MRI reconstruction and analysis by leveraging MTL and ensuring consistency across tasks, models, and datasets. This comprehensive framework serves as a versatile platform for researchers to use existing AI methods and develop new approaches in medical imaging.

Quantitative Analysis of Small Intestinal Motility in 3D Cine-MRI Using Centerline-Aware Motion Estimation.

BACKGROUND: Currently available tools for noninvasive motility quantification of the small intestine are limited to dynamic 2D MRI scans, which are limited in their ability to differentiate between types of intestinal motility. PURPOSE: To develop a method for quantification and characterization of small intestinal motility in 3D, capable of differentiating motile, non-motile and peristaltic motion patterns. STUDY TYPE: Prospective. SUBJECTS: Fourteen healthy volunteers (127 small intestinal segments) and 10 patients with Crohn's disease (87 small intestinal segments). FIELD STRENGTH/SEQUENCE: 3.0 T, 3D balanced fast field echo sequence, 1 volume per second. ASSESSMENT: Using deformable image registration between subsequent volumes, the local velocity within the intestinal lumen was quantified. Average velocity and average absolute velocity along intestinal segments were used with linear classifiers to differentiate motile from non-motile intestines, as well as erratic motility from peristalsis. The mean absolute velocity of small intestinal content was compared between healthy volunteers and Crohn's disease patients, and the discriminative power of the proposed motility metrics for detecting motility and peristalsis was determined. The consensus of two observers was used as referenced standard. STATISTICAL TESTS: Student's t-test to assess differences between groups; area under the receiver operating characteristic curve (AUC) to assess discriminative ability. P < 0.001 was considered significant. RESULTS: A significant difference in the absolute velocity of intestinal content between Crohn's patients and healthy volunteers was observed (median [IQR] 1.06 [0.61, 1.56] mm/s vs. 1.84 [1.37, 2.43] mm/s), which was consistent with manual reference annotations of motile activity. The proposed method had a strong discriminative performance for detecting non-motile intestines (AUC 0.97) and discernible peristalsis (AUC 0.81). DATA CONCLUSION: Analysis of 3D cine-MRI using centerline-aware motion estimation has the potential to allow noninvasive characterization of small intestinal motility and peristaltic motion in 3D. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Low muscle quality on a procedural computed tomography scan assessed with deep learning as a practical useful predictor of mortality in patients with severe aortic valve stenosis.

BACKGROUND & AIMS: Accurate diagnosis of sarcopenia requires evaluation of muscle quality, which refers to the amount of fat infiltration in muscle tissue. In this study, we aim to investigate whether we can independently predict mortality risk in transcatheter aortic valve implantation (TAVI) patients, using automatic deep learning algorithms to assess muscle quality on procedural computed tomography (CT) scans. METHODS: This study included 1199 patients with severe aortic stenosis who underwent transcatheter aortic valve implantation (TAVI) between January 2010 and January 2020. A procedural CT scan was performed as part of the preprocedural-TAVI evaluation, and the scans were analyzed using deep-learning-based software to automatically determine skeletal muscle density (SMD) and intermuscular adipose tissue (IMAT). The association of SMD and IMAT with all-cause mortality was analyzed using a Cox regression model, adjusted for other known mortality predictors, including muscle mass. RESULTS: The mean age of the participants was 80 ± 7 years, 53% were female. The median observation time was 1084 days, and the overall mortality rate was 39%. We found that the lowest tertile of muscle quality, as determined by SMD, was associated with an increased risk of mortality (HR 1.40 [95%CI: 1.15-1.70], p < 0.01). Similarly, low muscle quality as defined by high IMAT in the lowest tertile was also associated with increased mortality risk (HR 1.24 [95%CI: 1.01-1.52], p = 0.04). CONCLUSIONS: Our findings suggest that deep learning-assessed low muscle quality, as indicated by fat infiltration in muscle tissue, is a practical, useful and independent predictor of mortality after TAVI.

Graph neural networks for automatic extraction and labeling of the coronary artery tree in CT angiography.

Purpose: Automatic comprehensive reporting of coronary artery disease (CAD) requires anatomical localization of the coronary artery pathologies. To address this, we propose a fully automatic method for extraction and anatomical labeling of the coronary artery tree using deep learning. Approach: We include coronary CT angiography (CCTA) scans of 104 patients from two hospitals. Reference annotations of coronary artery tree centerlines and labels of coronary artery segments were assigned to 10 segment classes following the American Heart Association guidelines. Our automatic method first extracts the coronary artery tree from CCTA, automatically placing a large number of seed points and simultaneous tracking of vessel-like structures from these points. Thereafter, the extracted tree is refined to retain coronary arteries only, which are subsequently labeled with a multi-resolution ensemble of graph convolutional neural networks that combine geometrical and image intensity information from adjacent segments. Results: The method is evaluated on its ability to extract the coronary tree and to label its segments, by comparing the automatically derived and the reference labels. A separate assessment of tree extraction yielded an F1 score of 0.85. Evaluation of our combined method leads to an average F1 score of 0.74. Conclusions: The results demonstrate that our method enables fully automatic extraction and anatomical labeling of coronary artery trees from CCTA scans. Therefore, it has the potential to facilitate detailed automatic reporting of CAD.

Competing risk analysis of cardiovascular disease risk in breast cancer patients receiving a radiation boost.

BACKGROUND: Thoracic radiotherapy may damage the myocardium and arteries, increasing cardiovascular disease (CVD) risk. Women with a high local breast cancer (BC) recurrence risk may receive an additional radiation boost to the tumor bed. OBJECTIVE: We aimed to evaluate the CVD risk and specifically ischemic heart disease (IHD) in BC patients treated with a radiation boost, and investigated whether this was modified by age. METHODS: We identified 5260 BC patients receiving radiotherapy between 2005 and 2016 without a history of CVD. Boost data were derived from hospital records and the national cancer registry. Follow-up data on CVD events were obtained from Statistics Netherlands until December 31, 2018. The relation between CVD and boost was evaluated with competing risk survival analysis. RESULTS: 1917 (36.4%) received a boost. Mean follow-up was 80.3 months (SD37.1) and the mean age 57.8 years (SD10.7). Interaction between boost and age was observed for IHD: a boost was significantly associated with IHD incidence in patients younger than 40 years but not in patients over 40 years. The subdistribution hazard ratio (sHR) was calculated for ages from 25 to 75 years, showing a sHR range from 5.1 (95%CI 1.2-22.6) for 25-year old patients to sHR 0.5 (95%CI 0.2-1.02) for 75-year old patients. CONCLUSION: In patients younger than 40, a radiation boost is significantly associated with an increased risk of CVD. In absolute terms, the increased risk was low. In older patients, there was no association between boost and CVD risk, which is likely a reflection of appropriate patient selection.

Evaluation of Mean Shift, ComBat, and CycleGAN for Harmonizing Brain Connectivity Matrices Across Sites.

Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph measures derived from these matrices before and after applying three harmonization techniques: mean shift, ComBat, and CycleGAN. The sample comprises 168 age-matched, sex-matched normal subjects from two studies: the Vanderbilt Memory and Aging Project (VMAP) and the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD). First, we plotted the graph measures and used coefficient of variation (CoV) and the Mann-Whitney U test to evaluate different methods' effectiveness in removing site effects on the matrices and the derived graph measures. ComBat effectively eliminated site effects for global efficiency and modularity and outperformed the other two methods. However, all methods exhibited poor performance when harmonizing average betweenness centrality. Second, we tested whether our harmonization methods preserved correlations between age and graph measures. All methods except for CycleGAN in one direction improved correlations between age and global efficiency and between age and modularity from insignificant to significant with p-values less than 0.05.

Robust Deformable Image Registration Using Cycle-Consistent Implicit Representations.

Recent works in medical image registration have proposed the use of Implicit Neural Representations, demonstrating performance that rivals state-of-the-art learning-based methods. However, these implicit representations need to be optimized for each new image pair, which is a stochastic process that may fail to converge to a global minimum. To improve robustness, we propose a deformable registration method using pairs of cycle-consistent Implicit Neural Representations: each implicit representation is linked to a second implicit representation that estimates the opposite transformation, causing each network to act as a regularizer for its paired opposite. During inference, we generate multiple deformation estimates by numerically inverting the paired backward transformation and evaluating the consensus of the optimized pair. This consensus improves registration accuracy over using a single representation and results in a robust uncertainty metric that can be used for automatic quality control. We evaluate our method with a 4D lung CT dataset. The proposed cycle-consistent optimization method reduces the optimization failure rate from 2.4% to 0.0% compared to the current state-of-the-art. The proposed inference method improves landmark accuracy by 4.5% and the proposed uncertainty metric detects all instances where the registration method fails to converge to a correct solution. We verify the generalizability of these results to other data using a centerline propagation task in abdominal 4D MRI, where our method achieves a 46% improvement in propagation consistency compared with single-INR registration and demonstrates a strong correlation between the proposed uncertainty metric and registration accuracy.

Automatic Coronary Artery Plaque Quantification and CAD-RADS Prediction Using Mesh Priors.

Coronary artery disease (CAD) remains the leading cause of death worldwide. Patients with suspected CAD undergo coronary CT angiography (CCTA) to evaluate the risk of cardiovascular events and determine the treatment. Clinical analysis of coronary arteries in CCTA comprises the identification of atherosclerotic plaque, as well as the grading of any coronary artery stenosis typically obtained through the CAD-Reporting and Data System (CAD-RADS). This requires analysis of the coronary lumen and plaque. While voxel-wise segmentation is a commonly used approach in various segmentation tasks, it does not guarantee topologically plausible shapes. To address this, in this work, we propose to directly infer surface meshes for coronary artery lumen and plaque based on a centerline prior and use it in the downstream task of CAD-RADS scoring. The method is developed and evaluated using a total of 2407 CCTA scans. Our method achieved lesion-wise volume intraclass correlation coefficients of 0.98, 0.79, and 0.85 for calcified, non-calcified, and total plaque volume respectively. Patient-level CAD-RADS categorization was evaluated on a representative hold-out test set of 300 scans, for which the achieved linearly weighted kappa ( κ ) was 0.75. CAD-RADS categorization on the set of 658 scans from another hospital and scanner led to a κ of 0.71. The results demonstrate that direct inference of coronary artery meshes for lumen and plaque is feasible, and allows for the automated prediction of routinely performed CAD-RADS categorization.

Predicting Age from White Matter Diffusivity with Residual Learning.

Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI's advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction.

Roadmap on the use of artificial intelligence for imaging of vulnerable atherosclerotic plaque in coronary arteries.

Artificial intelligence (AI) is likely to revolutionize the way medical images are analysed and has the potential to improve the identification and analysis of vulnerable or high-risk atherosclerotic plaques in coronary arteries, leading to advances in the treatment of coronary artery disease. However, coronary plaque analysis is challenging owing to cardiac and respiratory motion, as well as the small size of cardiovascular structures. Moreover, the analysis of coronary imaging data is time-consuming, can be performed only by clinicians with dedicated cardiovascular imaging training, and is subject to considerable interreader and intrareader variability. AI has the potential to improve the assessment of images of vulnerable plaque in coronary arteries, but requires robust development, testing and validation. Combining human expertise with AI might facilitate the reliable and valid interpretation of images obtained using CT, MRI, PET, intravascular ultrasonography and optical coherence tomography. In this Roadmap, we review existing evidence on the application of AI to the imaging of vulnerable plaque in coronary arteries and provide consensus recommendations developed by an interdisciplinary group of experts on AI and non-invasive and invasive coronary imaging. We also outline future requirements of AI technology to address bias, uncertainty, explainability and generalizability, which are all essential for the acceptance of AI and its clinical utility in handling the anticipated growing volume of coronary imaging procedures.

Dynamic prediction of malignant ventricular arrhythmias using neural networks in patients with an implantable cardioverter-defibrillator.

BACKGROUND: Risk stratification for ventricular arrhythmias currently relies on static measurements that fail to adequately capture dynamic interactions between arrhythmic substrate and triggers over time. We trained and internally validated a dynamic machine learning (ML) model and neural network that extracted features from longitudinally collected electrocardiograms (ECG), and used these to predict the risk of malignant ventricular arrhythmias. METHODS: A multicentre study in patients implanted with an implantable cardioverter-defibrillator (ICD) between 2007 and 2021 in two academic hospitals was performed. Variational autoencoders (VAEs), which combine neural networks with variational inference principles, and can learn patterns and structure in data without explicit labelling, were trained to encode the mean ECG waveforms from the limb leads into 16 variables. Supervised dynamic ML models using these latent ECG representations and clinical baseline information were trained to predict malignant ventricular arrhythmias treated by the ICD. Model performance was evaluated on a hold-out set, using time-dependent receiver operating characteristic (ROC) and calibration curves. FINDINGS: 2942 patients (61.7 ± 13.9 years, 25.5% female) were included, with a total of 32,129 ECG recordings during a mean follow-up of 43.9 ± 35.9 months. The mean time-varying area under the ROC curve for the dynamic model was 0.738 ± 0.07, compared to 0.639 ± 0.03 for a static (i.e. baseline-only model). Feature analyses indicated dynamic changes in latent ECG representations, particularly those affecting the T-wave morphology, were of highest importance for model predictions. INTERPRETATION: Dynamic ML models and neural networks effectively leverage routinely collected longitudinal ECG recordings for personalised and updated predictions of malignant ventricular arrhythmias, outperforming static models. FUNDING: This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T).

BabyNet＋＋: Fetal birth weight prediction using biometry multimodal data acquired less than 24 hours before delivery.

Accurate prediction of fetal weight at birth is essential for effective perinatal care, particularly in the context of antenatal management, which involves determining the timing and mode of delivery. The current standard of care involves performing a prenatal ultrasound 24 hours prior to delivery. However, this task presents challenges as it requires acquiring high-quality images, which becomes difficult during advanced pregnancy due to the lack of amniotic fluid. In this paper, we present a novel method that automatically predicts fetal birth weight by using fetal ultrasound video scans and clinical data. Our proposed method is based on a Transformer-based approach that combines a Residual Transformer Module with a Dynamic Affine Feature Map Transform. This method leverages tabular clinical data to evaluate 2D+t spatio-temporal features in fetal ultrasound video scans. Development and evaluation were carried out on a clinical set comprising 582 2D fetal ultrasound videos and clinical records of pregnancies from 194 patients performed less than 24 hours before delivery. Our results show that our method outperforms several state-of-the-art automatic methods and estimates fetal birth weight with an accuracy comparable to human experts. Hence, automatic measurements obtained by our method can reduce the risk of errors inherent in manual measurements. Observer studies suggest that our approach may be used as an aid for less experienced clinicians to predict fetal birth weight before delivery, optimizing perinatal care regardless of the available expertise.

Spatio-temporal physics-informed learning: A novel approach to CT perfusion analysis in acute ischemic stroke.

CT perfusion imaging is important in the imaging workup of acute ischemic stroke for evaluating affected cerebral tissue. CT perfusion analysis software produces cerebral perfusion maps from commonly noisy spatio-temporal CT perfusion data. High levels of noise can influence the results of CT perfusion analysis, necessitating software tuning. This work proposes a novel approach for CT perfusion analysis that uses physics-informed learning, an optimization framework that is robust to noise. In particular, we propose SPPINN: Spatio-temporal Perfusion Physics-Informed Neural Network and research spatio-temporal physics-informed learning. SPPINN learns implicit neural representations of contrast attenuation in CT perfusion scans using the spatio-temporal coordinates of the data and employs these representations to estimate a continuous representation of the cerebral perfusion parameters. We validate the approach on simulated data to quantify perfusion parameter estimation performance. Furthermore, we apply the method to in-house patient data and the public Ischemic Stroke Lesion Segmentation 2018 benchmark data to assess the correspondence between the perfusion maps and reference standard infarct core segmentations. Our method achieves accurate perfusion parameter estimates even with high noise levels and differentiates healthy tissue from infarcted tissue. Moreover, SPPINN perfusion maps accurately correspond with reference standard infarct core segmentations. Hence, we show that using spatio-temporal physics-informed learning for cerebral perfusion estimation is accurate, even in noisy CT perfusion data. The code for this work is available at https://github.com/lucasdevries/SPPINN.

Stochastic co-teaching for training neural networks with unknown levels of label noise.

Label noise hampers supervised training of neural networks. However, data without label noise is often infeasible to attain, especially for medical tasks. Attaining high-quality medical labels would require a pool of experts and their consensus reading, which would be extremely costly. Several methods have been proposed to mitigate the adverse effects of label noise during training. State-of-the-art methods use multiple networks that exploit different decision boundaries to identify label noise. Among the best performing methods is co-teaching. However, co-teaching comes with the requirement of knowing label noise a priori. Hence, we propose a co-teaching method that does not require any prior knowledge about the level of label noise. We introduce stochasticity to select or reject training instances. We have extensively evaluated the method on synthetic experiments with extreme label noise levels and applied it to real-world medical problems of ECG classification and cardiac MRI segmentation. Results show that the approach is robust to its hyperparameter choice and applies to various classification tasks with unknown levels of label noise.

Deep learning for estimation of fetal weight throughout the pregnancy from fetal abdominal ultrasound.

BACKGROUND: Fetal weight is currently estimated from fetal biometry parameters using heuristic mathematical formulas. Fetal biometry requires measurements of the fetal head, abdomen, and femur. However, this examination is prone to inter- and intraobserver variability because of factors, such as the experience of the operator, image quality, maternal characteristics, or fetal movements. Our study tested the hypothesis that a deep learning method can estimate fetal weight based on a video scan of the fetal abdomen and gestational age with similar performance to the full biometry-based estimations provided by clinical experts. OBJECTIVE: This study aimed to develop and test a deep learning method to automatically estimate fetal weight from fetal abdominal ultrasound video scans. STUDY DESIGN: A dataset of 900 routine fetal ultrasound examinations was used. Among those examinations, 800 retrospective ultrasound video scans of the fetal abdomen from 700 pregnant women between 15 6/7 and 41 0/7 weeks of gestation were used to train the deep learning model. After the training phase, the model was evaluated on an external prospectively acquired test set of 100 scans from 100 pregnant women between 16 2/7 and 38 0/7 weeks of gestation. The deep learning model was trained to directly estimate fetal weight from ultrasound video scans of the fetal abdomen. The deep learning estimations were compared with manual measurements on the test set made by 6 human readers with varying levels of expertise. Human readers used standard 3 measurements made on the standard planes of the head, abdomen, and femur and heuristic formula to estimate fetal weight. The Bland-Altman analysis, mean absolute percentage error, and intraclass correlation coefficient were used to evaluate the performance and robustness of the deep learning method and were compared with human readers. RESULTS: Bland-Altman analysis did not show systematic deviations between readers and deep learning. The mean and standard deviation of the mean absolute percentage error between 6 human readers and the deep learning approach was 3.75%±2.00%. Excluding junior readers (residents), the mean absolute percentage error between 4 experts and the deep learning approach was 2.59%±1.11%. The intraclass correlation coefficients reflected excellent reliability and varied between 0.9761 and 0.9865. CONCLUSION: This study reports the use of deep learning to estimate fetal weight using only ultrasound video of the fetal abdomen from fetal biometry scans. Our experiments demonstrated similar performance of human measurements and deep learning on prospectively acquired test data. Deep learning is a promising approach to directly estimate fetal weight using ultrasound video scans of the fetal abdomen.

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

AIMS: Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features. METHODS AND RESULTS: A multicentre study of 1010 patients (64.9 ± 10.8 years, 26.8% female) with ischaemic, dilated, or non-ischaemic cardiomyopathy, and LVEF ≤ 35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD in two academic hospitals was performed. For each patient, a raw 12-lead, 10-s ECG was obtained within 90 days before ICD implantation, and clinical details were collected. Supervised ML models were trained and validated on a development cohort (n = 550) from Hospital A to predict ICD non-arrhythmic mortality at three-year follow-up (i.e. mortality without prior appropriate ICD-therapy). Model performance was evaluated on an external patient cohort from Hospital B (n = 460). At three-year follow-up, 16.0% of patients had died, with 72.8% meeting criteria for non-arrhythmic mortality. Extreme gradient boosting models identified patients with non-arrhythmic mortality with an area under the receiver operating characteristic curve (AUROC) of 0.90 [95% confidence intervals (CI) 0.80-1.00] during internal validation. In the external cohort, the AUROC was 0.79 (95% CI 0.75-0.84). CONCLUSIONS: ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within three years after device implantation in a primary prevention population, with robust performance in an independent cohort.