Daniel C Elton

Daniel C Elton
Massachusetts General Hospital | MGH · Data Science Office

Ph.D.
These days I'm spending more time blogging. Consider subscribing to my Substack : https://moreisdifferent.substack.com/

About

63
Publications
20,032
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
883
Citations
Introduction
Researching application of deep learning and AI to make automated measurements in medical scans and accelerate scientific research. Intellectual interests include neuroscience & philosophy. Previously worked on molecular dynamics and quantum simulation of water.
Additional affiliations
January 2019 - October 2019
National Institutes of Health
Position
  • Researcher
August 2010 - present
Stony Brook University
Position
  • Research Assistant

Publications

Publications (63)
Preprint
Full-text available
Artificial intelligence has made great strides since the deep learning revolution, but AI systems still struggle to extrapolate outside of their training data and adapt to new situations. For inspiration we look to the domain of science, where scientists have been able to develop theories which show remarkable ability to extrapolate and sometimes p...
Preprint
Full-text available
The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is always possible to approximate the input-output relations of deep neural networks with human-understandable rules or a post-hoc model, the discovery of the double desce...
Article
Full-text available
Background: Abdominal aortic atherosclerotic plaque burden may have clinical significance but manual measurement is time-consuming and impractical. Purpose: To perform external validation on an automated atherosclerotic plaque detector for noncontrast and postcontrast abdominal CT. Materials and methods: The training data consisted of 114 nonc...
Article
Full-text available
Background CT biomarkers both inside and outside the pancreas can potentially be used to diagnose type 2 diabetes mellitus. Previous studies on this topic have shown significant results but were limited by manual methods and small study samples. Purpose To investigate abdominal CT biomarkers for type 2 diabetes mellitus in a large clinical data set...
Article
Full-text available
Traditionally, atherosclerotic risk factors for cardiovascular disease and cancer are assessed using coronary artery calcium scoring. However, this neglects the impact of atherosclerotic disease more proximal to the cancer site. This study assesses whether aortoiliac atherosclerotic plaque is associated with prostate cancer. The dataset consisted o...
Article
Full-text available
Purpose: Early detection and size quantification of renal calculi are important for optimizing treatment and preventing severe kidney stone disease. Prior work has shown that volumetric measurements of kidney stones are more informative and reproducible than linear measurements. Deep learning based systems that use abdominal non-contrast CT scans...
Article
Accurate and reliable detection of abnormal lymph nodes in magnetic resonance (MR) images is very helpful for the diagnosis and treatment of numerous diseases. However, it is still a challenging task due to similar appearances between abnormal lymph nodes and other tissues. In this paper, we propose a novel network based on an improved Mask R-CNN f...
Preprint
Full-text available
Identification of lymph nodes (LN) in T2 Magnetic Resonance Imaging (MRI) is an important step performed by radiologists during the assessment of lymphoproliferative diseases. The size of the nodes play a crucial role in their staging, and radiologists sometimes use an additional contrast sequence such as diffusion weighted imaging (DWI) for confir...
Article
Full-text available
Background Imaging assessment for hepatomegaly is not well defined and currently uses suboptimal, unidimensional measures. Liver volume provides a more direct measure for organ enlargement. Purpose To determine organ volume and to establish thresholds for hepatomegaly with use of a validated deep learning artificial intelligence tool that automatic...
Preprint
Full-text available
Francis Bacon popularized the idea that science is based on a process of induction by which repeated observations are, in some unspecified way, generalized to theories based on the assumption that the future resembles the past. This idea was criticized by Hume and others as untenable leading to the famous problem of induction. It wasn't until the w...
Chapter
Reliable localization of abnormal lymph nodes in T2 Magnetic Resonance Imaging (MRI) scans is needed for staging and treatment of lymphoproliferative diseases. Radiologists need to accurately characterize the size and shape of the lymph nodes and may require an additional contrast sequence such as diffusion weighted imaging (DWI) for staging confir...
Chapter
Medical image classification (for example, lesions on MRI scans) is a very challenging task due to the complicated relationships between different lesion sub-types and expensive cost to collect high quality labelled training datasets. Graph model has been used to model the complicated relationship for medical imaging classification successfully in...
Preprint
Full-text available
Cardiovascular disease is the number one cause of mortality worldwide. Risk prediction can help incentivize lifestyle changes and inform targeted preventative treatment. In this work we explore utilizing a convolutional neural network (CNN) to predict cardiovascular disease risk from abdominal CT scans taken for routine CT colonography in otherwise...
Chapter
Full-text available
Elton, Daniel C.Recently researchers have started using explainability techniques for several different applications—to help foresee how a model might operate in the field, to persuade others to trust a model, and to assist with debugging errors. A large number of explainability techniques have been published with very little empirical testing to s...
Chapter
Full-text available
Pathological science occurs when well-intentioned scientists spend extended time and resources studying a phenomena that isn’t real. Researchers who get caught up in pathological science are usually following the scientific method and performing careful experiments, but they get tricked by nature. The study of water has had several protracted episo...
Article
Full-text available
Purpose: Fully automated CT-based algorithms for quantifying bone, muscle, and fat have been validated for unenhanced abdominal scans. The purpose of this study was to determine and correct for the effect of intravenous (IV) contrast on these automated body composition measures. Materials and methods: Initial study cohort consisted of 1211 healt...
Article
Full-text available
Abdominal CT is a frequently performed imaging examination for a wide variety of clinical indications. In addition to the immediate reason for scanning, each CT examination contains robust additional data on body composition that generally go unused in routine clinical practice. There is now growing interest in harnessing this additional informatio...
Article
Full-text available
Artificial intelligence has made great strides since the deep learning revolution, but AI systems remain incapable of learning principles and rules which allow them to extrapolate outside of their training data to new situations. For inspiration we look to the domain of science, where scientists have been able to develop theories which show remarka...
Preprint
Full-text available
Pathological science occurs when well-intentioned scientists spend extended time and resources studying a phenomena that isn't real. Researchers who get caught up in pathological science are usually following the scientific method and performing careful experiments, but they get tricked by nature. The study of water has had several protracted episo...
Chapter
Current deep learning based segmentation models generalize poorly to different domains due to the lack of sufficient labelled image data. An important example in radiology is generalizing from contrast enhanced CT to non-contrast CT. In real-world clinical applications, cross-domain image analysis tools are in high demand since medical images from...
Chapter
Full-text available
We present a novel method for small bowel segmentation where a cylindrical topological constraint based on persistent homology is applied. To address the touching issue which could break the applied constraint, we propose to augment a network with an additional branch to predict an inner cylinder of the small bowel. Since the inner cylinder is free...
Article
Full-text available
Background: Hepatic attenuation at unenhanced CT is linearly correlated with MR proton density fat fraction (PDFF). Liver fat quantification at contrast-enhanced CT is more challenging. Objective: To evaluate liver steatosis categorization on contrast-enhanced CT using a fully-automated deep learning volumetric hepatosplenic segmentation algorithm...
Article
Full-text available
The existence of the exclusion zone (EZ), a layer of water in which plastic microspheres are repelled from hydrophilic surfaces, has now been independently demonstrated by several groups. A better understanding of the mechanisms which generate EZs would help with understanding the possible importance of EZs in biology and in engineering application...
Preprint
Full-text available
We present a novel method for small bowel segmentation where a cylindrical topological constraint based on persistent homology is applied. To address the touching issue which could break the applied constraint, we propose to augment a network with an additional branch to predict an inner cylinder of the small bowel. Since the inner cylinder is free...
Preprint
Full-text available
Current deep learning based segmentation models often generalize poorly between domains due to insufficient training data. In real-world clinical applications, cross-domain image analysis tools are in high demand since medical images from different domains are often needed to achieve a precise diagnosis. An important example in radiology is general...
Chapter
Full-text available
The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is often possible to approximate the input-output relations of deep neural networks with a few human-understandable rules, the discovery of the double descent phenomena su...
Preprint
Full-text available
Calcified plaque in the aorta and pelvic arteries is associated with coronary artery calcification and is a strong predictor of heart attack. Current calcified plaque detection models show poor generalizability to different domains (ie. pre-contrast vs. post-contrast CT scans). Many recent works have shown how cross domain object detection can be i...
Preprint
Full-text available
The vertebral levels of the spine provide a useful coordinate system when making measurements of plaque, muscle, fat, and bone mineral density. Correctly classifying vertebral levels with high accuracy is challenging due to the similar appearance of each vertebra, the curvature of the spine, and the possibility of anomalies such as fractured verteb...
Preprint
Please see the new version , published in MDPI: Exclusion Zone Phenomena in Water—A Critical Review of Experimental Findings and Theories https://www.mdpi.com/1422-0067/21/14/5041
Article
Full-text available
The heat transfer properties of the organic molecular crystal α-RDX were studied using three phonon scattering based thermal conductivity models. It was found that the widely used Peierls-Boltzmann model for thermal transport in crystalline materials breaks down for α-RDX. We show this breakdown is due to a large degree of anharmonicity that leads...
Article
Full-text available
In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules- in our review...
Preprint
Full-text available
The heat transfer properties of the organic molecular crystal α -RDX were studied using three phonon-based thermal conductivity models. It was found that the widely used Peierls-Boltzmann model for thermal transport in crystalline materials breaks down for α -RDX. We show this breakdown is due to a large degree of anharmonicity that leads to a domi...
Preprint
Full-text available
The heat transfer properties of the organic molecular crystal ${\alpha}$-RDX were studied using three phonon-based thermal conductivity models. It was found that the widely used Peierls-Boltzmann model for thermal transport in crystalline materials breaks down for ${\alpha}$-RDX. We show this breakdown is due to a large degree of anharmonicity that...
Preprint
Full-text available
In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules - in our review...
Preprint
Full-text available
The number of scientific journal articles and reports being published about energetic materials every year is growing exponentially, and therefore extracting relevant information and actionable insights from the latest research is becoming a considerable challenge. In this work we explore how techniques from natural language processing and machine...
Article
It is now established that nuclear quantum motion plays an important role in determining water's hydrogen bonding, structure, and dynamics. Such effects are important to include in density functional theory (DFT) based molecular dynamics simulation of water. The standard way of treating nuclear quantum effects, path integral molecular dynamics (PIM...
Preprint
Due to its high computational speed and accuracy compared to ab-initio quantum chemistry and forcefield modeling, the prediction of molecular properties using machine learning has received great attention in the fields of materials design and drug discovery. A main ingredient required for machine learning is a training dataset consisting of molecul...
Preprint
Full-text available
The microscale thermal transport properties of $\alpha$RDX are believed to be major factors in the initiation process. In this study we present a thorough examination of phonon properties which dominate energy storage and transport in $\alpha$RDX. The phonon lifetimes are determined for all phonon branches, revealing the characteristic time scale o...
Preprint
Full-text available
The microscale thermal transport properties of αRDX are believed to be major factors in the initiation process. In this study we present a thorough examination of phonon properties which dominate energy storage and transport in αRDX. The phonon lifetimes are determined for all phonon branches, revealing the characteristic time scale of energy trans...
Preprint
Full-text available
This short report details the mathematical properties of the stretched exponential function and some of its applications in materials science. G(tau) distributions for different values of the stretching parameter beta are provided.
Preprint
Full-text available
In this work, we discuss use of machine learning techniques for rapid prediction of detonation properties including explosive energy, detonation velocity, and detonation pressure. Further, analysis is applied to individual molecules in order to explore the contribution of bonding motifs to these properties. Feature descriptors evaluated include Mor...
Article
Full-text available
We present a proof of concept that machine learning techniques can be used to predict the properties of CNOHF energetic molecules from their molecular structures. We focus on a small but diverse dataset consisting of 109 molecular structures spread across ten compound classes. Up until now, candidate molecules for energetic materials have been scre...
Preprint
We present a proof of concept that machine learning techniques can be used to predict the properties of CNOHF energetic molecules from their molecular structures. We focus on a small but diverse dataset consisting of 109 molecular structures spread across ten compound classes. Up until now, candidate molecules for energetic materials have been scre...
Article
Full-text available
We critically review the literature on the Debye absorption peak of liquid water and the excess response found on the high frequency side of the Debye peak. We find a lack of agreement on the microscopic phenomena underlying both of these features. To better understand the molecular origin of Debye peak we ran large scale molecular dynamics simulat...
Article
Full-text available
The local structure of liquid water as a function of temperature is a source of intense research. This structure is intimately linked to the dynamics of water molecules, which can be measured using Raman and infrared spectroscopies. The assignment of spectral peaks depends on whether they are collective modes or single-molecule motions. Vibrational...
Data
Supplementary Figures 1-7, Supplementary Table 1, Supplementary Notes 1-2 and Supplementary References
Article
In this work we show that on subpicosecond time scales optical phonon modes can propagate through the H-bond network of water over relatively long distances (2-4 nm). Using molecular dynamics simulation we find propagating optical phonons in the librational and OH stretching bands. The OH stretching phonon only appears when a polarizable model (TTM...
Article
Full-text available
We present a critical comparison of the dielectric properties of three models of water-TIP4P/2005, TIP4P/2005f, and TTM3F. Dipole spatial correlation is measured using the distance dependent Kirkwood function along with one-dimensional and two-dimensional dipole correlation functions. We find that the introduction of flexibility alone does not sign...
Article
As it is well known, water has a high dielectric constant, which is connected both to the molecular dipole moment and to the intermolecular bonding through hydrogen bonds. Although some classical force fields can reproduce this dielectric constant, they do not take into account the environment-dependent perturbations of the individual dipoles and t...
Article
Full-text available
The inertial range scaling of certain mixed third-order moments of velocity and magnetic field fluctuations in a turbulent MHD plasma such as the solar wind is related to the energy dissipation rate of the turbulence. We have used this relation to measure energy dissipation rates in the solar wind and other statistical methods to estimate the accur...
Article
Full-text available
Politano and Pouquet's law, a generalization of Kolmogorov's four-fifths law to incompressible MHD, makes it possible to measure the energy cascade rate in incompressible MHD turbulence by means of third-order moments. In hydrodynamics, accurate measurement of third-order moments requires large amounts of data because the probability dist...
Article
Full-text available
For years it was common to assume that the spectrum of interplanetary fluctuations was a remnant signature of solar photospheric sources imparting a spectrum on propagating Alfven waves as they passed through the acceleration region and into the solar wind. Such a spectrum was merely a remnant of the acceleration region dynamics and assumed to poss...

Network

Cited By

Projects

Projects (4)
Project
Understanding the mechanism of thermal transport (diffusive or ballistic) in complex energetic crystals using quasi-harmonic and anharmonic lattice dynamics and molecular dynamics-based approaches. Identifying critical bonds distortions which play a key role in transferring energy to key phonon modes leading to phenomena resulting in initiation.
Project
The usual technique that physicists use to approximate the quantum mechanics of electrons in condensed matter systems, density functional theory, does not work well for water and much work is being done to understand its shortcomings. One usual assumption is that only electrons need to be treated quantum mechanically. We argue that for water both electrons and nuclei need to be treated quantum mechanically and that density functionals should be tested with nuclear quantum effects included. Our  custom code (PIMD-F90 on GitHub) implements a novel algorithm which greatly speeds up the calculation of nuclear quantum effects with only minor losses in accuracy. Accurate first principles simulations are important for developing energy materials and in computational drug design