Blinded, randomized trial of sonographer versus AI cardiac function assessment.

Artificial intelligence (AI) has been developed for echocardiography1-3, although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or sonographer assessment and final cardiologist assessment, evaluated by the proportion of studies with substantial change (more than 5% change). From 3,769 echocardiographic studies screened, 274 studies were excluded owing to poor image quality. The proportion of studies substantially changed was 16.8% in the AI group and 27.2% in the sonographer group (difference of -10.4%, 95% confidence interval: -13.2% to -7.7%, P < 0.001 for non-inferiority, P < 0.001 for superiority). The mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29% in the AI group and 7.23% in the sonographer group (difference of -0.96%, 95% confidence interval: -1.34% to -0.54%, P < 0.001 for superiority). The AI-guided workflow saved time for both sonographers and cardiologists, and cardiologists were not able to distinguish between the initial assessments by AI versus the sonographer (blinding index of 0.088). For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers.

Video-based AI for beat-to-beat assessment of cardiac function.

Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease1, screening for cardiotoxicity2 and decisions regarding the clinical management of patients with a critical illness3. However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training4,5. Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.

AI-ENABLED ASSESSMENT OF CARDIAC FUNCTION AND VIDEO QUALITY IN EMERGENCY DEPARTMENT POINT-OF-CARE ECHOCARDIOGRAMS.

BACKGROUND: The adoption of point-of-care ultrasound (POCUS) has greatly improved the ability to rapidly evaluate unstable emergency department (ED) patients at the bedside. One major use of POCUS is to obtain echocardiograms to assess cardiac function. OBJECTIVES: We developed EchoNet-POCUS, a novel deep learning system, to aid emergency physicians (EPs) in interpreting POCUS echocardiograms and to reduce operator-to-operator variability. METHODS: We collected a new dataset of POCUS echocardiogram videos obtained in the ED by EPs and annotated the cardiac function and quality of each video. Using this dataset, we train EchoNet-POCUS to evaluate both cardiac function and video quality in POCUS echocardiograms. RESULTS: EchoNet-POCUS achieves an area under the receiver operating characteristic curve (AUROC) of 0.92 (0.89-0.94) for predicting whether cardiac function is abnormal and an AUROC of 0.81 (0.78-0.85) for predicting video quality. CONCLUSIONS: EchoNet-POCUS can be applied to bedside echocardiogram videos in real time using commodity hardware, as we demonstrate in a prospective pilot study.

The Diversity-Innovation Paradox in Science.

Prior work finds a diversity paradox: Diversity breeds innovation, yet underrepresented groups that diversify organizations have less successful careers within them. Does the diversity paradox hold for scientists as well? We study this by utilizing a near-complete population of ∼1.2 million US doctoral recipients from 1977 to 2015 and following their careers into publishing and faculty positions. We use text analysis and machine learning to answer a series of questions: How do we detect scientific innovations? Are underrepresented groups more likely to generate scientific innovations? And are the innovations of underrepresented groups adopted and rewarded? Our analyses show that underrepresented groups produce higher rates of scientific novelty. However, their novel contributions are devalued and discounted: For example, novel contributions by gender and racial minorities are taken up by other scholars at lower rates than novel contributions by gender and racial majorities, and equally impactful contributions of gender and racial minorities are less likely to result in successful scientific careers than for majority groups. These results suggest there may be unwarranted reproduction of stratification in academic careers that discounts diversity's role in innovation and partly explains the underrepresentation of some groups in academia.

Generalized analog thresholding for spike acquisition at ultralow sampling rates.

Efficient spike acquisition techniques are needed to bridge the divide from creating large multielectrode arrays (MEA) to achieving whole-cortex electrophysiology. In this paper, we introduce generalized analog thresholding (gAT), which achieves millisecond temporal resolution with sampling rates as low as 10 Hz. Consider the torrent of data from a single 1,000-channel MEA, which would generate more than 3 GB/min using standard 30-kHz Nyquist sampling. Recent neural signal processing methods based on compressive sensing still require Nyquist sampling as a first step and use iterative methods to reconstruct spikes. Analog thresholding (AT) remains the best existing alternative, where spike waveforms are passed through an analog comparator and sampled at 1 kHz, with instant spike reconstruction. By generalizing AT, the new method reduces sampling rates another order of magnitude, detects more than one spike per interval, and reconstructs spike width. Unlike compressive sensing, the new method reveals a simple closed-form solution to achieve instant (noniterative) spike reconstruction. The base method is already robust to hardware nonidealities, including realistic quantization error and integration noise. Because it achieves these considerable specifications using hardware-friendly components like integrators and comparators, generalized AT could translate large-scale MEAs into implantable devices for scientific investigation and medical technology.

Deep learning for transesophageal echocardiography view classification.

Transesophageal echocardiography (TEE) imaging is a vital tool used in the evaluation of complex cardiac pathology and the management of cardiac surgery patients. A key limitation to the application of deep learning strategies to intraoperative and intraprocedural TEE data is the complexity and unstructured nature of these images. In the present study, we developed a deep learning-based, multi-category TEE view classification model that can be used to add structure to intraoperative and intraprocedural TEE imaging data. More specifically, we trained a convolutional neural network (CNN) to predict standardized TEE views using labeled intraoperative and intraprocedural TEE videos from Cedars-Sinai Medical Center (CSMC). We externally validated our model on intraoperative TEE videos from Stanford University Medical Center (SUMC). Accuracy of our model was high across all labeled views. The highest performance was achieved for the Trans-Gastric Left Ventricular Short Axis View (area under the receiver operating curve [AUC] = 0.971 at CSMC, 0.957 at SUMC), the Mid-Esophageal Long Axis View (AUC = 0.954 at CSMC, 0.905 at SUMC), the Mid-Esophageal Aortic Valve Short Axis View (AUC = 0.946 at CSMC, 0.898 at SUMC), and the Mid-Esophageal 4-Chamber View (AUC = 0.939 at CSMC, 0.902 at SUMC). Ultimately, we demonstrate that our deep learning model can accurately classify standardized TEE views, which will facilitate further downstream deep learning analyses for intraoperative and intraprocedural TEE imaging.

Electrocardiographic deep learning for predicting post-procedural mortality: a model development and validation study.

BACKGROUND: Preoperative risk assessments used in clinical practice are insufficient in their ability to identify risk for postoperative mortality. Deep-learning analysis of electrocardiography can identify hidden risk markers that can help to prognosticate postoperative mortality. We aimed to develop a prognostic model that accurately predicts postoperative mortality in patients undergoing medical procedures and who had received preoperative electrocardiographic diagnostic testing. METHODS: In a derivation cohort of preoperative patients with available electrocardiograms (ECGs) from Cedars-Sinai Medical Center (Los Angeles, CA, USA) between Jan 1, 2015 and Dec 31, 2019, a deep-learning algorithm was developed to leverage waveform signals to discriminate postoperative mortality. We randomly split patients (8:1:1) into subsets for training, internal validation, and final algorithm test analyses. Model performance was assessed using area under the receiver operating characteristic curve (AUC) values in the hold-out test dataset and in two external hospital cohorts and compared with the established Revised Cardiac Risk Index (RCRI) score. The primary outcome was post-procedural mortality across three health-care systems. FINDINGS: 45 969 patients had a complete ECG waveform image available for at least one 12-lead ECG performed within the 30 days before the procedure date (59 975 inpatient procedures and 112 794 ECGs): 36 839 patients in the training dataset, 4549 in the internal validation dataset, and 4581 in the internal test dataset. In the held-out internal test cohort, the algorithm discriminates mortality with an AUC value of 0·83 (95% CI 0·79-0·87), surpassing the discrimination of the RCRI score with an AUC of 0·67 (0·61-0·72). The algorithm similarly discriminated risk for mortality in two independent US health-care systems, with AUCs of 0·79 (0·75-0·83) and 0·75 (0·74-0·76), respectively. Patients determined to be high risk by the deep-learning model had an unadjusted odds ratio (OR) of 8·83 (5·57-13·20) for postoperative mortality compared with an unadjusted OR of 2·08 (0·77-3·50) for postoperative mortality for RCRI scores of more than 2. The deep-learning algorithm performed similarly for patients undergoing cardiac surgery (AUC 0·85 [0·77-0·92]), non-cardiac surgery (AUC 0·83 [0·79-0·88]), and catheterisation or endoscopy suite procedures (AUC 0·76 [0·72-0·81]). INTERPRETATION: A deep-learning algorithm interpreting preoperative ECGs can improve discrimination of postoperative mortality. The deep-learning algorithm worked equally well for risk stratification of cardiac surgeries, non-cardiac surgeries, and catheterisation laboratory procedures, and was validated in three independent health-care systems. This algorithm can provide additional information to clinicians making the decision to perform medical procedures and stratify the risk of future complications. FUNDING: National Heart, Lung, and Blood Institute.

Dynamic analysis of naive adaptive brain-machine interfaces.

The closed-loop operation of brain-machine interfaces (BMI) provides a context to discover foundational principles behind human-computer interaction, with emerging clinical applications to stroke, neuromuscular diseases, and trauma. In the canonical BMI, a user controls a prosthetic limb through neural signals that are recorded by electrodes and processed by a decoder into limb movements. In laboratory demonstrations with able-bodied test subjects, parameters of the decoder are commonly tuned using training data that include neural signals and corresponding overt arm movements. In the application of BMI to paralysis or amputation, arm movements are not feasible, and imagined movements create weaker, partially unrelated patterns of neural activity. BMI training must begin naive, without access to these prototypical methods for parameter initialization used in most laboratory BMI demonstrations. Naive adaptive BMI refer to a class of methods recently introduced to address this problem. We first identify the basic elements of existing approaches based on adaptive filtering and define a decoder, ReFIT-PPF to represent these existing approaches. We then present Joint RSE, a novel approach that logically extends prior approaches. Using recently developed human- and synthetic-subjects closed-loop BMI simulation platforms, we show that Joint RSE significantly outperforms ReFIT-PPF and nonadaptive (static) decoders. Control experiments demonstrate the critical role of jointly estimating neural parameters and user intent. In addition, we show that nonzero sensorimotor delay in the user significantly degrades ReFIT-PPF but not Joint RSE, owing to differences in the prior on intended velocity. Paradoxically, substantial differences in the nature of sensory feedback between these methods do not contribute to differences in performance between Joint RSE and ReFIT-PPF. Instead, BMI performance improvement is driven by machine learning, which outpaces rates of human learning in the human-subjects simulation platform. In this regime, nuances of error-related feedback to the human user are less relevant to rapid BMI mastery.

Video-Based Deep Learning for Automated Assessment of Left Ventricular Ejection Fraction in Pediatric Patients.

BACKGROUND: Significant interobserver and interstudy variability occurs for left ventricular (LV) functional indices despite standardization of measurement techniques. Artificial intelligence models trained on adult echocardiograms are not likely to be applicable to a pediatric population. We present EchoNet-Peds, a video-based deep learning algorithm, which matches human expert performance of LV segmentation and ejection fraction (EF). METHODS: A large pediatric data set of 4,467 echocardiograms was used to develop EchoNet-Peds. EchoNet-Peds was trained on 80% of the data for segmentation of the left ventricle and estimation of LVEF. The remaining 20% was used to fine-tune and validate the algorithm. RESULTS: In both apical 4-chamber and parasternal short-axis views, EchoNet-Peds segments the left ventricle with a Dice similarity coefficient of 0.89. EchoNet-Peds estimates EF with a mean absolute error of 3.66% and can routinely identify pediatric patients with systolic dysfunction (area under the curve of 0.95). EchoNet-Peds was trained on pediatric echocardiograms and performed significantly better to estimate EF (P < .001) than an adult model applied to the same data. CONCLUSIONS: Accurate, rapid automation of EF assessment and recognition of systolic dysfunction in a pediatric population are feasible using EchoNet-Peds with the potential for far-reaching clinical impact. In addition, the first large pediatric data set of annotated echocardiograms is now publicly available for efforts to develop pediatric-specific artificial intelligence algorithms.

Interpretable deep learning prediction of 3d assessment of cardiac function.

As deep learning plays an increasing role in making medical decisions, explainability is playing an increasing role in satisfying regulatory requirements and facilitating trust and transparency in deep learning approaches. In cardiac imaging, the task of accurately assessing left-ventricular function is crucial for evaluating patient risk, diagnosing cardiovascular disease, and clinical decision making. Previous video based methods to predict ejection fraction yield high accuracy but at the expense of explainability and did not utilize the standard clinical workflow. More explainable methods that match the clinical workflow, using 2D semantic segmentation, have been explored but found to have lower accuracy. To simultaneously increase accuracy and utilize an approach that matches the standard clinical workflow, we propose a frame-by-frame 3D depth-map approach that is both accurate (mean absolute error of 6.5%) and explainable, utilizing the conventional clinical workflow with method of discs evaluation of left ventricular volume. This method is more reproducible than human evaluation and generates volume predictions that can be interpreted by clinicians and provide the opportunity to intervene and adjust the deep learning prediction.

CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq.

Single-cell RNA sequencing (scRNA-seq) has the potential to provide powerful, high-resolution signatures to inform disease prognosis and precision medicine. This paper takes an important first step towards this goal by developing an interpretable machine learning algorithm, CloudPred, to predict individuals' disease phenotypes from their scRNA-seq data. Predicting phenotype from scRNA-seq is challenging for standard machine learning methods-the number of cells measured can vary by orders of magnitude across individuals and the cell populations are also highly heterogeneous. Typical analysis creates pseudo-bulk samples which are biased toward prior annotations and also lose the single cell resolution. CloudPred addresses these challenges via a novel end-to-end differentiable learning algorithm which is coupled with a biologically informed mixture of cell types model. CloudPred automatically infers the cell subpopulation that are salient for the phenotype without prior annotations. We developed a systematic simulation platform to evaluate the performance of CloudPred and several alternative methods we propose, and find that CloudPred outperforms the alternative methods across several settings. We further validated CloudPred on a real scRNA-seq dataset of 142 lupus patients and controls. CloudPred achieves AUROC of 0.98 while identifying a specific subpopulation of CD4 T cells whose presence is highly indicative of lupus. CloudPred is a powerful new framework to predict clinical phenotypes from scRNA-seq data and to identify relevant cells.

Confounders mediate AI prediction of demographics in medical imaging.

Deep learning has been shown to accurately assess "hidden" phenotypes from medical imaging beyond traditional clinician interpretation. Using large echocardiography datasets from two healthcare systems, we test whether it is possible to predict age, race, and sex from cardiac ultrasound images using deep learning algorithms and assess the impact of varying confounding variables. Using a total of 433,469 videos from Cedars-Sinai Medical Center and 99,909 videos from Stanford Medical Center, we trained video-based convolutional neural networks to predict age, sex, and race. We found that deep learning models were able to identify age and sex, while unable to reliably predict race. Without considering confounding differences between categories, the AI model predicted sex with an AUC of 0.85 (95% CI 0.84-0.86), age with a mean absolute error of 9.12 years (95% CI 9.00-9.25), and race with AUCs ranging from 0.63 to 0.71. When predicting race, we show that tuning the proportion of confounding variables (age or sex) in the training data significantly impacts model AUC (ranging from 0.53 to 0.85), while sex and age prediction was not particularly impacted by adjusting race proportion in the training dataset AUC of 0.81-0.83 and 0.80-0.84, respectively. This suggests significant proportion of AI's performance on predicting race could come from confounding features being detected. Further work remains to identify the particular imaging features that associate with demographic information and to better understand the risks of demographic identification in medical AI as it pertains to potentially perpetuating bias and disparities.

AI-enabled in silico immunohistochemical characterization for Alzheimer's disease.

We develop a deep learning approach, in silico immunohistochemistry (IHC), which takes routinely collected histochemical-stained samples as input and computationally generates virtual IHC slide images. We apply in silico IHC to Alzheimer's disease samples, where several hallmark changes are conventionally identified using IHC staining across many regions of the brain. In silico IHC computationally identifies neurofibrillary tangles, ß-amyloid plaques, and neuritic plaques at a high spatial resolution directly from the histochemical images, with areas under the receiver operating characteristic curve of between 0.88 and 0.92. In silico IHC learns to identify subtle cellular morphologies associated with these lesions and can generate in silico IHC slides that capture key features of the actual IHC.

Super-resolved spatial transcriptomics by deep data fusion.

Current methods for spatial transcriptomics are limited by low spatial resolution. Here we introduce a method that integrates spatial gene expression data with histological image data from the same tissue section to infer higher-resolution expression maps. Using a deep generative model, our method characterizes the transcriptome of micrometer-scale anatomical features and can predict spatial gene expression from histology images alone.

High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep Learning.

IMPORTANCE: Early detection and characterization of increased left ventricular (LV) wall thickness can markedly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating causes of increased wall thickness, such as hypertrophy, cardiomyopathy, and cardiac amyloidosis. OBJECTIVE: To assess the accuracy of a deep learning workflow in quantifying ventricular hypertrophy and predicting the cause of increased LV wall thickness. DESIGN, SETTINGS, AND PARTICIPANTS: This cohort study included physician-curated cohorts from the Stanford Amyloid Center and Cedars-Sinai Medical Center (CSMC) Advanced Heart Disease Clinic for cardiac amyloidosis and the Stanford Center for Inherited Cardiovascular Disease and the CSMC Hypertrophic Cardiomyopathy Clinic for hypertrophic cardiomyopathy from January 1, 2008, to December 31, 2020. The deep learning algorithm was trained and tested on retrospectively obtained independent echocardiogram videos from Stanford Healthcare, CSMC, and the Unity Imaging Collaborative. MAIN OUTCOMES AND MEASURES: The main outcome was the accuracy of the deep learning algorithm in measuring left ventricular dimensions and identifying patients with increased LV wall thickness diagnosed with hypertrophic cardiomyopathy and cardiac amyloidosis. RESULTS: The study included 23 745 patients: 12 001 from Stanford Health Care (6509 [54.2%] female; mean [SD] age, 61.6 [17.4] years) and 1309 from CSMC (808 [61.7%] female; mean [SD] age, 62.8 [17.2] years) with parasternal long-axis videos and 8084 from Stanford Health Care (4201 [54.0%] female; mean [SD] age, 69.1 [16.8] years) and 2351 from CSMS (6509 [54.2%] female; mean [SD] age, 69.6 [14.7] years) with apical 4-chamber videos. The deep learning algorithm accurately measured intraventricular wall thickness (mean absolute error [MAE], 1.2 mm; 95% CI, 1.1-1.3 mm), LV diameter (MAE, 2.4 mm; 95% CI, 2.2-2.6 mm), and posterior wall thickness (MAE, 1.4 mm; 95% CI, 1.2-1.5 mm) and classified cardiac amyloidosis (area under the curve [AUC], 0.83) and hypertrophic cardiomyopathy (AUC, 0.98) separately from other causes of LV hypertrophy. In external data sets from independent domestic and international health care systems, the deep learning algorithm accurately quantified ventricular parameters (domestic: R2, 0.96; international: R2, 0.90). For the domestic data set, the MAE was 1.7 mm (95% CI, 1.6-1.8 mm) for intraventricular septum thickness, 3.8 mm (95% CI, 3.5-4.0 mm) for LV internal dimension, and 1.8 mm (95% CI, 1.7-2.0 mm) for LV posterior wall thickness. For the international data set, the MAE was 1.7 mm (95% CI, 1.5-2.0 mm) for intraventricular septum thickness, 2.9 mm (95% CI, 2.4-3.3 mm) for LV internal dimension, and 2.3 mm (95% CI, 1.9-2.7 mm) for LV posterior wall thickness. The deep learning algorithm accurately detected cardiac amyloidosis (AUC, 0.79) and hypertrophic cardiomyopathy (AUC, 0.89) in the domestic external validation site. CONCLUSIONS AND RELEVANCE: In this cohort study, the deep learning model accurately identified subtle changes in LV wall geometric measurements and the causes of hypertrophy. Unlike with human experts, the deep learning workflow is fully automated, allowing for reproducible, precise measurements, and may provide a foundation for precision diagnosis of cardiac hypertrophy.

How to evaluate deep learning for cancer diagnostics - factors and recommendations.

The large volume of data used in cancer diagnosis presents a unique opportunity for deep learning algorithms, which improve in predictive performance with increasing data. When applying deep learning to cancer diagnosis, the goal is often to learn how to classify an input sample (such as images or biomarkers) into predefined categories (such as benign or cancerous). In this article, we examine examples of how deep learning algorithms have been implemented to make predictions related to cancer diagnosis using clinical, radiological, and pathological image data. We present a systematic approach for evaluating the development and application of clinical deep learning algorithms. Based on these examples and the current state of deep learning in medicine, we discuss the future possibilities in this space and outline a roadmap for implementations of deep learning in cancer diagnosis.

Deep learning evaluation of biomarkers from echocardiogram videos.

BACKGROUND: Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results. METHODS: We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets. FINDINGS: On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques. INTERPRETATION: These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods. FUNDING: J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship.

Integrating spatial gene expression and breast tumour morphology via deep learning.

Spatial transcriptomics allows for the measurement of RNA abundance at a high spatial resolution, making it possible to systematically link the morphology of cellular neighbourhoods and spatially localized gene expression. Here, we report the development of a deep learning algorithm for the prediction of local gene expression from haematoxylin-and-eosin-stained histopathology images using a new dataset of 30,612 spatially resolved gene expression data matched to histopathology images from 23 patients with breast cancer. We identified over 100 genes, including known breast cancer biomarkers of intratumoral heterogeneity and the co-localization of tumour growth and immune activation, the expression of which can be predicted from the histopathology images at a resolution of 100 µm. We also show that the algorithm generalizes well to The Cancer Genome Atlas and to other breast cancer gene expression datasets without the need for re-training. Predicting the spatially resolved transcriptome of a tissue directly from tissue images may enable image-based screening for molecular biomarkers with spatial variation.

Deep learning interpretation of echocardiograms.

Echocardiography uses ultrasound technology to capture high temporal and spatial resolution images of the heart and surrounding structures, and is the most common imaging modality in cardiovascular medicine. Using convolutional neural networks on a large new dataset, we show that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation. Our deep learning model, EchoNet, accurately identified the presence of pacemaker leads (AUC = 0.89), enlarged left atrium (AUC = 0.86), left ventricular hypertrophy (AUC = 0.75), left ventricular end systolic and diastolic volumes ( R 2 = 0.74 and R 2 = 0.70), and ejection fraction ( R 2 = 0.50), as well as predicted systemic phenotypes of age ( R 2 = 0.46), sex (AUC = 0.88), weight ( R 2 = 0.56), and height ( R 2 = 0.33). Interpretation analysis validates that EchoNet shows appropriate attention to key cardiac structures when performing human-explainable tasks and highlights hypothesis-generating regions of interest when predicting systemic phenotypes difficult for human interpretation. Machine learning on echocardiography images can streamline repetitive tasks in the clinical workflow, provide preliminary interpretation in areas with insufficient qualified cardiologists, and predict phenotypes challenging for human evaluation.

Accelerated Stochastic Power Iteration.

Principal component analysis (PCA) is one of the most powerful tools in machine learning. The simplest method for PCA, the power iteration, requires O ( 1 / Δ ) full-data passes to recover the principal component of a matrix with eigen-gap Δ. Lanczos, a significantly more complex method, achieves an accelerated rate of O ( 1 / Δ ) passes. Modern applications, however, motivate methods that only ingest a subset of available data, known as the stochastic setting. In the online stochastic setting, simple algorithms like Oja's iteration achieve the optimal sample complexity O ( σ 2 / Δ 2 ) . Unfortunately, they are fully sequential, and also require O ( σ 2 / Δ 2 ) iterations, far from the O ( 1 / Δ ) rate of Lanczos. We propose a simple variant of the power iteration with an added momentum term, that achieves both the optimal sample and iteration complexity. In the full-pass setting, standard analysis shows that momentum achieves the accelerated rate, O ( 1 / Δ ) . We demonstrate empirically that naively applying momentum to a stochastic method, does not result in acceleration. We perform a novel, tight variance analysis that reveals the "breaking-point variance" beyond which this acceleration does not occur. By combining this insight with modern variance reduction techniques, we construct stochastic PCA algorithms, for the online and offline setting, that achieve an accelerated iteration complexity O ( 1 / Δ ) . Due to the embarassingly parallel nature of our methods, this acceleration translates directly to wall-clock time if deployed in a parallel environment. Our approach is very general, and applies to many non-convex optimization problems that can now be accelerated using the same technique.