Showing 1–20 of 23 results
David H. Gutman
Using an efficient algorithmic implementation of Caratheodory's theorem, we propose three enhanced versions of the Projection and Rescaling algorithm's basic procedures each of which improves upon the order of complexity of its analogue in [Mathematical Programming Series A, 166 (2017), pp. 87-111].
David Huckleberry Gutman, George Lobo
This paper presents the first optimal-rate $p$-th order methods with $p\geq 1$ for finding first and second-order stationary points of non-convex smooth objective functions over Riemannian manifolds. In contrast to the geodesically convex setting, we definitively establish that the optimal oracle complexity of non-convex optimization over manifolds matches that over Euclidean space. In parallel with the complexity analysis, we introduce a general framework for systematically studying higher-order regularity on Riemannian manifolds that characterizes its joint dependence on the objective function and the chosen retraction. To the best of our knowledge, this framework constitutes the first known application in optimization of pullback connections and the Sasaki metric to the study of retraction-based pullbacks of the objective function. We provide clean derivative bounds based on a new covariant Faà di Bruno formula derived within our framework. For $p=3$, our methods are fully implementable via a new Krylov-based framework for minimizing quartically regularized cubic polynomials. This is the first Krylov method for this class of polynomials and may be of independent interest beyond Riemannian optimization.
Leandro Maia, David Huckleberry Gutman, Ryan Christopher Hughes
This paper expands the Cyclic Block Proximal Gradient method for block separable composite minimization by allowing for inexactly computed gradients and proximal maps. The resultant algorithm, the Inexact Cyclic Block Proximal Gradient (I-CBPG) method, shares the same convergence rate as its exactly computed analogue provided the allowable errors decrease sufficiently quickly or are pre-selected to be sufficiently small. We provide numerical experiments that showcase the practical computational advantage of I-CBPG for certain fixed tolerances of approximation error and for a dynamically decreasing error tolerance regime in particular. We establish a tight relationship between inexact proximal map evaluations and $δ$-subgradients in our $δ$-Second Prox Theorem. This theorem forms the foundation of our convergence analysis and enables us to show that inexact gradient computations and other notions of inexact proximal map computation can be subsumed within a single unifying framework.
Leandro Farias Maia, David Huckleberry Gutman
This work provides the first convergence analysis for the Randomized Block Coordinate Descent method for minimizing a function that is both Hölder smooth and block Hölder smooth. Our analysis applies to objective functions that are non-convex, convex, and strongly convex. For non-convex functions, we show that the expected gradient norm reduces at an $O\left(k^{\fracγ{1+γ}}\right)$ rate, where $k$ is the iteration count and $γ$ is the Hölder exponent. For convex functions, we show that the expected suboptimality gap reduces at the rate $O\left(k^{-γ}\right)$. In the strongly convex setting, we show this rate for the expected suboptimality gap improves to $O\left(k^{-\frac{2γ}{1-γ}}\right)$ when $γ>1$ and to a linear rate when $γ=1$. Notably, these new convergence rates coincide with those furnished in the existing literature for the Lipschitz smooth setting.
Subhanik Purkayastha, Hrithwik Shalu, David Gutman, Shakeel Modak, Ellen Basu, Brian Kushner, Kim Kramer, Sofia Haque, Joseph Stember
Artificial intelligence (AI) in radiology has made great strides in recent years, but many hurdles remain. Overfitting and lack of generalizability represent important ongoing challenges hindering accurate and dependable clinical deployment. If AI algorithms can avoid overfitting and achieve true generalizability, they can go from the research realm to the forefront of clinical work. Recently, small data AI approaches such as deep neuroevolution (DNE) have avoided overfitting small training sets. We seek to address both overfitting and generalizability by applying DNE to a virtually pooled data set consisting of images from various institutions. Our use case is classifying neuroblastoma brain metastases on MRI. Neuroblastoma is well-suited for our goals because it is a rare cancer. Hence, studying this pediatric disease requires a small data approach. As a tertiary care center, the neuroblastoma images in our local Picture Archiving and Communication System (PACS) are largely from outside institutions. These multi-institutional images provide a heterogeneous data set that can simulate real world clinical deployment. As in prior DNE work, we used a small training set, consisting of 30 normal and 30 metastasis-containing post-contrast MRI brain scans, with 37% outside images. The testing set was enriched with 83% outside images. DNE converged to a testing set accuracy of 97%. Hence, the algorithm was able to predict image class with near-perfect accuracy on a testing set that simulates real-world data. Hence, the work described here represents a considerable contribution toward clinically feasible AI.
Noel Codella, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba, Aadi Kalloo, Konstantinos Liopyris, Michael Marchetti, Harald Kittler, Allan Halpern
This work summarizes the results of the largest skin image analysis challenge in the world, hosted by the International Skin Imaging Collaboration (ISIC), a global partnership that has organized the world's largest public repository of dermoscopic images of skin. The challenge was hosted in 2018 at the Medical Image Computing and Computer Assisted Intervention (MICCAI) conference in Granada, Spain. The dataset included over 12,500 images across 3 tasks. 900 users registered for data download, 115 submitted to the lesion segmentation task, 25 submitted to the lesion attribute detection task, and 159 submitted to the disease classification task. Novel evaluation protocols were established, including a new test for segmentation algorithm performance, and a test for algorithm ability to generalize. Results show that top segmentation algorithms still fail on over 10% of images on average, and algorithms with equal performance on test data can have different abilities to generalize. This is an important consideration for agencies regulating the growing set of machine learning tools in the healthcare domain, and sets a new standard for future public challenges in healthcare.
Noel Codella, Quoc-Bao Nguyen, Sharath Pankanti, David Gutman, Brian Helba, Allan Halpern, John R. Smith
Melanoma is the deadliest form of skin cancer. While curable with early detection, only highly trained specialists are capable of accurately recognizing the disease. As expertise is in limited supply, automated systems capable of identifying disease could save lives, reduce unnecessary biopsies, and reduce costs. Toward this goal, we propose a system that combines recent developments in deep learning with established machine learning approaches, creating ensembles of methods that are capable of segmenting skin lesions, as well as analyzing the detected area and surrounding tissue for melanoma detection. The system is evaluated using the largest publicly available benchmark dataset of dermoscopic images, containing 900 training and 379 testing images. New state-of-the-art performance levels are demonstrated, leading to an improvement in the area under receiver operating characteristic curve of 7.5% (0.843 vs. 0.783), in average precision of 4% (0.649 vs. 0.624), and in specificity measured at the clinically relevant 95% sensitivity operating point 2.9 times higher than the previous state-of-the-art (36.8% specificity compared to 12.5%). Compared to the average of 8 expert dermatologists on a subset of 100 test images, the proposed system produces a higher accuracy (76% vs. 70.5%), and specificity (62% vs. 59%) evaluated at an equivalent sensitivity (82%).
Veronica Rotemberg, Nicholas Kurtansky, Brigid Betz-Stablein, Liam Caffery, Emmanouil Chousakos, Noel Codella, Marc Combalia, Stephen Dusza, Pascale Guitera, David Gutman, Allan Halpern, Harald Kittler, Kivanc Kose, Steve Langer, Konstantinos Lioprys, Josep Malvehy, Shenara Musthaq, Jabpani Nanda, Ofer Reiter, George Shih, Alexander Stratigos, Philipp Tschandl, Jochen Weber, H. Peter Soyer
Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 histopathologically confirmed melanomas compared with benign melanoma mimickers.
David Gutman, Noel C. F. Codella, Emre Celebi, Brian Helba, Michael Marchetti, Nabin Mishra, Allan Halpern
In this article, we describe the design and implementation of a publicly accessible dermatology image analysis benchmark challenge. The goal of the challenge is to sup- port research and development of algorithms for automated diagnosis of melanoma, a lethal form of skin cancer, from dermoscopic images. The challenge was divided into sub-challenges for each task involved in image analysis, including lesion segmentation, dermoscopic feature detection within a lesion, and classification of melanoma. Training data included 900 images. A separate test dataset of 379 images was provided to measure resultant performance of systems developed with the training data. Ground truth for both training and test sets was generated by a panel of dermoscopic experts. In total, there were 79 submissions from a group of 38 participants, making this the largest standardized and comparative study for melanoma diagnosis in dermoscopic images to date. While the official challenge duration and ranking of participants has concluded, the datasets remain available for further research and development.
David A. Clunie, Adam Flanders, Adam Taylor, Brad Erickson, Brian Bialecki, David Brundage, David Gutman, Fred Prior, J Anthony Seibert, John Perry, Judy Wawira Gichoya, Justin Kirby, Katherine Andriole, Luke Geneslaw, Steve Moore, TJ Fitzgerald, Wyatt Tellis, Ying Xiao, Keyvan Farahani
This report addresses the technical aspects of de-identification of medical images of human subjects and biospecimens, such that re-identification risk of ethical, moral, and legal concern is sufficiently reduced to allow unrestricted public sharing for any purpose, regardless of the jurisdiction of the source and distribution sites. All medical images, regardless of the mode of acquisition, are considered, though the primary emphasis is on those with accompanying data elements, especially those encoded in formats in which the data elements are embedded, particularly Digital Imaging and Communications in Medicine (DICOM). These images include image-like objects such as Segmentations, Parametric Maps, and Radiotherapy (RT) Dose objects. The scope also includes related non-image objects, such as RT Structure Sets, Plans and Dose Volume Histograms, Structured Reports, and Presentation States. Only de-identification of publicly released data is considered, and alternative approaches to privacy preservation, such as federated learning for artificial intelligence (AI) model development, are out of scope, as are issues of privacy leakage from AI model sharing. Only technical issues of public sharing are addressed.
Noel C. F. Codella, David Gutman, M. Emre Celebi, Brian Helba, Michael A. Marchetti, Stephen W. Dusza, Aadi Kalloo, Konstantinos Liopyris, Nabin Mishra, Harald Kittler, Allan Halpern
This article describes the design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge. The goal is to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer. The challenge was divided into 3 tasks: lesion segmentation, feature detection, and disease classification. Participation involved 593 registrations, 81 pre-submissions, 46 finalized submissions (including a 4-page manuscript), and approximately 50 attendees, making this the largest standardized and comparative study in this field to date. While the official challenge duration and ranking of participants has concluded, the dataset snapshots remain available for further research and development.
David H. Gutman, Javier F. Pena
The condition number of a differentiable convex function, namely the ratio of its smoothness to strong convexity constants, is closely tied to fundamental properties of the function. In particular, the condition number of a quadratic convex function is the square of the aspect ratio of a canonical ellipsoid associated to the function. Furthermore, the condition number of a function bounds the linear rate of convergence of the gradient descent algorithm for unconstrained convex minimization. We propose a condition number of a differentiable convex function relative to a reference convex set and distance function pair. This relative condition number is defined as the ratio of a relative smoothness to a relative strong convexity constants. We show that the relative condition number extends the main properties of the traditional condition number both in terms of its geometric insight and in terms of its role in characterizing the linear convergence of first-order methods for constrained convex minimization. When the reference set $X$ is a convex cone or a polyhedron and the function $f$ is of the form $f = g\circ A$, we provide characterizations of and bounds on the condition number of $f$ relative to $X$ in terms of the usual condition number of $g$ and a suitable condition number of the pair $(A,X)$.
Sanghoon Lee, Mohamed Amgad, Deepak R. Chittajallu, Matt McCormick, Brian P Pollack, Habiba Elfandy, Hagar Hussein, David A Gutman, Lee AD Cooper
Extracting quantitative phenotypic information from whole-slide images presents significant challenges for investigators who are not experienced in developing image analysis algorithms. We present new software that enables rapid learn-by-example training of machine learning classifiers for detection of histologic patterns in whole-slide imaging datasets. HistomicsML2.0 uses convolutional networks to be readily adaptable to a variety of applications, provides a web-based user interface, and is available as a software container to simplify deployment.
Kamal Shadi, Saideh Bakhshi, David A. Gutman, Helen S. Mayberg, Constantine Dovrolis
Recent progress in diffusion MRI and tractography algorithms as well as the launch of the Human Connectome Project (HCP) have provided brain research with an abundance of structural connectivity data. In this work, we describe and evaluate a method that can infer the structural brain network that interconnects a given set of Regions of Interest (ROIs) from tractography data. The proposed method, referred to as Minimum Asymmetry Network Inference Algorithm (MANIA), differs from prior work because it does not determine the connectivity between two ROIs based on an arbitrary connectivity threshold. Instead, we exploit a basic limitation of the tractography process: the observed streamlines from a source to a target do not provide any information about the polarity of the underlying white matter, and so if there are some fibers connecting two voxels (or two ROIs) X and Y tractography should be able in principle to follow this connection in both directions, from X to Y and from Y to X. We leverage this limitation to formulate the network inference process as an optimization problem that minimizes the (appropriately normalized) asymmetry of the observed network. We evaluate the proposed method on a noise model that randomly corrupts the observed connectivity of synthetic networks. As a case-study, we apply MANIA on diffusion MRI data from 28 healthy subjects to infer the structural network between 18 corticolimbic ROIs that are associated with various neuropsychiatric conditions including depression, anxiety and addiction.
Colton Mikes, Ismael R. de Farias, David Huckleberry Gutman, Victoria E. Howle
This paper introduces a quantum-classical hybrid algorithm for generalized pattern search (GPS) algorithms. We introduce a quantum search step algorithm using amplitude amplification, which reduces the number of oracle calls needed during the search step from O(N) classical calls to O(N^(1/2)) quantum calls. This work addresses three fundamental issues with using a quantum search step with GPS. First we address the need to mark an improved mesh point, a requirement of the amplitude amplification algorithm. Second, we introduce a modified version of the amplitude amplification algorithm QSearch, which is guaranteed to terminate using a finite number of iterations. Third, we avoid disrupting the GPS algorithm's convergence by limiting the quantum algorithm to the search step.
David Huckleberry Gutman, Nam Ho-Nguyen
We extend coordinate descent to manifold domains, and provide convergence analyses for geodesically convex and non-convex smooth objective functions. Our key insight is to draw an analogy between coordinate blocks in Euclidean space and tangent subspaces of a manifold. Hence, our method is called tangent subspace descent (TSD). The core principle behind ensuring convergence of TSD is the appropriate choice of subspace at each iteration. To this end, we propose two novel conditions, the gap ensuring and $C$-randomized norm conditions on deterministic and randomized modes of subspace selection respectively, that promise convergence for smooth functions and that are satisfied in practical contexts. We propose two subspace selection rules of particular practical interest that satisfy these conditions: a deterministic one for the manifold of square orthogonal matrices, and a randomized one for the Stiefel manifold. Our proof-of-concept numerical experiments on the orthogonal Procrustes problem demonstrate TSD's efficacy.
Leandro Farias Maia, David H. Gutman, Renato D. C. Monteiro, Gilson N. Silva
This paper develops an adaptive proximal alternating direction method of multipliers (ADMM) for solving linearly constrained, composite optimization problems under the assumption that the smooth component of the objective is weakly convex, while the non-smooth component is convex and block-separable. The proposed method is adaptive to all problem parameters, including smoothness and weak convexity constants, and allows each of its block proximal subproblems to be inexactly solved. Each iteration of our adaptive proximal ADMM consists of two steps: the sequential solution of each block proximal subproblem; and adaptive tests to decide whether to perform a full Lagrange multiplier and/or penalty parameter update(s). Without any rank assumptions on the constraint matrices, it is shown that the adaptive proximal ADMM obtains an approximate first-order stationary point of the constrained problem in a number of iterations that matches the state-of-the-art complexity for the class of proximal ADMM's. The three proof-of-concept numerical experiments that conclude the paper suggest our adaptive proximal ADMM enjoys significant computational benefits.
David H. Gutman, Javier F. Peña
We show that the iterates generated by a generic first-order meta-algorithm satisfy a canonical perturbed Fenchel duality inequality. The latter in turn readily yields a unified derivation of the best known convergence rates for various popular first-order algorithms including the conditional gradient method as well as the main kinds of Bregman proximal methods: subgradient, gradient, fast gradient, and universal gradient methods.
Denis Schapiro, Clarence Yapp, Artem Sokolov, Sheila M. Reynolds, Yu-An Chen, Damir Sudar, Yubin Xie, Jeremy L. Muhlich, Raquel Arias-Camison, Sarah Arena, Adam J. Taylor, Milen Nikolov, Madison Tyler, Jia-Ren Lin, Erik A. Burlingame, Human Tumor Atlas Network, Young H. Chang, Samouil L Farhi, Vésteinn Thorsson, Nithya Venkatamohan, Julia L. Drewes, Dana Pe'er, David A. Gutman, Markus D. Herrmann, Nils Gehlenborg, Peter Bankhead, Joseph T. Roland, John M. Herndon, Michael P. Snyder, Michael Angelo, Garry Nolan, Jason R. Swedlow, Nikolaus Schultz, Daniel T. Merrick, Sarah A. Mazzilli, Ethan Cerami, Scott J. Rodig, Sandro Santagata, Peter K. Sorger
The imminent release of tissue atlases combining multi-channel microscopy with single cell sequencing and other omics data from normal and diseased specimens creates an urgent need for data and metadata standards that guide data deposition, curation and release. We describe a Minimum Information about highly multiplexed Tissue Imaging (MITI) standard that applies best practices developed for genomics and other microscopy data to highly multiplexed tissue images and traditional histology.
Mohamed Amgad, Lamees A. Atteya, Hagar Hussein, Kareem Hosny Mohammed, Ehab Hafiz, Maha A. T. Elsebaie, Ahmed M. Alhusseiny, Mohamed Atef AlMoslemany, Abdelmagid M. Elmatboly, Philip A. Pappalardo, Rokia Adel Sakr, Pooya Mobadersany, Ahmad Rachid, Anas M. Saad, Ahmad M. Alkashash, Inas A. Ruhban, Anas Alrefai, Nada M. Elgazar, Ali Abdulkarim, Abo-Alela Farag, Amira Etman, Ahmed G. Elsaeed, Yahya Alagha, Yomna A. Amer, Ahmed M. Raslan, Menatalla K. Nadim, Mai A. T. Elsebaie, Ahmed Ayad, Liza E. Hanna, Ahmed Gadallah, Mohamed Elkady, Bradley Drumheller, David Jaye, David Manthey, David A. Gutman, Habiba Elfandy, Lee A. D. Cooper
High-resolution mapping of cells and tissue structures provides a foundation for developing interpretable machine-learning models for computational pathology. Deep learning algorithms can provide accurate mappings given large numbers of labeled instances for training and validation. Generating adequate volume of quality labels has emerged as a critical barrier in computational pathology given the time and effort required from pathologists. In this paper we describe an approach for engaging crowds of medical students and pathologists that was used to produce a dataset of over 220,000 annotations of cell nuclei in breast cancers. We show how suggested annotations generated by a weak algorithm can improve the accuracy of annotations generated by non-experts and can yield useful data for training segmentation algorithms without laborious manual tracing. We systematically examine interrater agreement and describe modifications to the MaskRCNN model to improve cell mapping. We also describe a technique we call Decision Tree Approximation of Learned Embeddings (DTALE) that leverages nucleus segmentations and morphologic features to improve the transparency of nucleus classification models. The annotation data produced in this study are freely available for algorithm development and benchmarking at: https://sites.google.com/view/nucls.