Expert-validated estimation of diagnostic uncertainty for deep neural networks in diabetic retinopathy detection.

Abstract:

:Deep learning-based systems can achieve a diagnostic performance comparable to physicians in a variety of medical use cases including the diagnosis of diabetic retinopathy. To be useful in clinical practice, it is necessary to have well calibrated measures of the uncertainty with which these systems report their decisions. However, deep neural networks (DNNs) are being often overconfident in their predictions, and are not amenable to a straightforward probabilistic treatment. Here, we describe an intuitive framework based on test-time data augmentation for quantifying the diagnostic uncertainty of a state-of-the-art DNN for diagnosing diabetic retinopathy. We show that the derived measure of uncertainty is well-calibrated and that experienced physicians likewise find cases with uncertain diagnosis difficult to evaluate. This paves the way for an integrated treatment of uncertainty in DNN-based diagnostic systems.

journal_name

Med Image Anal

journal_title

Medical image analysis

authors

Ayhan MS,Kühlewein L,Aliyeva G,Inhoffen W,Ziemssen F,Berens P

doi

10.1016/j.media.2020.101724

subject

Has Abstract

pub_date

2020-08-01 00:00:00

pages

101724

eissn

1361-8415

issn

1361-8423

pii

S1361-8415(20)30088-8

journal_volume

64

pub_type

杂志文章
  • Groupwise multi-atlas segmentation of the spinal cord's internal structure.

    abstract::The spinal cord is an essential and vulnerable component of the central nervous system. Differentiating and localizing the spinal cord internal structure (i.e., gray matter vs. white matter) is critical for assessment of therapeutic impacts and determining prognosis of relevant conditions. Fortunately, new magnetic re...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2014.01.003

    authors: Asman AJ,Bryan FW,Smith SA,Reich DS,Landman BA

    更新日期:2014-04-01 00:00:00

  • Automated annotation and quantitative description of ultrasound videos of the fetal heart.

    abstract::Interpretation of ultrasound videos of the fetal heart is crucial for the antenatal diagnosis of congenital heart disease (CHD). We believe that automated image analysis techniques could make an important contribution towards improving CHD detection rates. However, to our knowledge, no previous work has been done in t...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2016.11.006

    authors: Bridge CP,Ioannou C,Noble JA

    更新日期:2017-02-01 00:00:00

  • An efficient Riemannian statistical shape model using differential coordinates: With application to the classification of data from the Osteoarthritis Initiative.

    abstract::We propose a novel Riemannian framework for statistical analysis of shapes that is able to account for the nonlinearity in shape variation. By adopting a physical perspective, we introduce a differential representation that puts the local geometric variability into focus. We model these differential coordinates as ele...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2017.09.004

    authors: von Tycowicz C,Ambellan F,Mukhopadhyay A,Zachow S

    更新日期:2018-01-01 00:00:00

  • Towards model-based analysis of cardiac MR tagging data: relation between left ventricular shear strain and myofiber orientation.

    abstract::Many cardiac pathologies are reflected in abnormal myocardial deformation, accessible through magnetic resonance tagging (MRT). Interpretation of the MRT data is difficult, since the relation between pathology and deformation is not straightforward. Mathematical models of cardiac mechanics could be used to translate m...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2006.04.001

    authors: Ubbink SW,Bovendeerd PH,Delhaas T,Arts T,van de Vosse FN

    更新日期:2006-08-01 00:00:00

  • Groupwise registration with global-local graph shrinkage in atlas construction.

    abstract::Graph-based groupwise registration methods are widely used in atlas construction. Given a group of images, a graph is built whose nodes represent the images, and whose edges represent a geodesic path between two nodes. The distribution of images on an image manifold is explored through edge traversal in a graph. The f...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2020.101711

    authors: Fu T,Yang J,Li Q,Ai D,Song H,Jiang Y,Wang Y,Frangi AF

    更新日期:2020-08-01 00:00:00

  • Group-level cortical surface parcellation with sulcal pits labeling.

    abstract::Sulcal pits are the points of maximal depth within the folds of the cortical surface. These shape descriptors give a unique opportunity to access to a rich, fine-scale representation of the geometry and the developmental milestones of the cortical surface. However, using sulcal pits analysis at group level requires ne...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2020.101749

    authors: Kaltenmark I,Deruelle C,Brun L,Lefèvre J,Coulon O,Auzias G

    更新日期:2020-12-01 00:00:00

  • A comparison of freehand three-dimensional ultrasound reconstruction techniques.

    abstract::Three-dimensional freehand ultrasound imaging produces a set of irregularly spaced B-scans, which are typically reconstructed on a regular grid for visualization and data analysis. Most standard reconstruction algorithms are designed to minimize computational requirements and do not exploit the underlying shape of the...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/s1361-8415(99)80028-0

    authors: Rohling R,Gee A,Berman L

    更新日期:1999-12-01 00:00:00

  • Independent component analysis using prior information for signal detection in a functional imaging system of the retina.

    abstract::Independent component analysis (ICA) is a statistical technique that estimates a set of sources mixed by an unknown mixing matrix using only a set of observations. For this purpose, the only assumption is that the sources are statistically independent. In many applications, some information about the nature of the unk...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2010.06.009

    authors: Barriga ES,Pattichis M,Ts'o D,Abramoff M,Kardon R,Kwon Y,Soliz P

    更新日期:2011-02-01 00:00:00

  • CHAOS Challenge - combined (CT-MR) healthy abdominal organ segmentation.

    abstract::Segmentation of abdominal organs has been a comprehensive, yet unresolved, research field for many years. In the last decade, intensive developments in deep learning (DL) introduced new state-of-the-art segmentation systems. Despite outperforming the overall accuracy of existing systems, the effects of DL model proper...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2020.101950

    authors: Kavur AE,Gezer NS,Barış M,Aslan S,Conze PH,Groza V,Pham DD,Chatterjee S,Ernst P,Özkan S,Baydar B,Lachinov D,Han S,Pauli J,Isensee F,Perkonigg M,Sathish R,Rajan R,Sheet D,Dovletov G,Speck O,Nürnberger A,Maier-H

    更新日期:2020-12-25 00:00:00

  • Self-similarity weighted mutual information: a new nonrigid image registration metric.

    abstract::Mutual information (MI) has been widely used as a similarity measure for rigid registration of multi-modal and uni-modal medical images. However, robust application of MI to deformable registration is challenging mainly because rich structural information, which are critical cues for successful deformable registration...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2013.12.003

    authors: Rivaz H,Karimaghaloo Z,Collins DL

    更新日期:2014-02-01 00:00:00

  • A novel deformation method for fast simulation of biological tissue formed by fibers and fluid.

    abstract::This paper presents a new approach to the simulation of soft tissues deformation suitable for real time computation, particularly intriguing for medical applications. The approach implements a quasi-static solution for elastic global deformations of objects filled with fluid and fibers, which can be a good approximati...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2012.04.002

    authors: Costa IF

    更新日期:2012-07-01 00:00:00

  • Dynamically constructed network with error correction for accurate ventricle volume estimation.

    abstract::Automated ventricle volume estimation (AVVE) on cardiac magnetic resonance (CMR) images is very important for clinical cardiac disease diagnosis. However, current AVVE methods ignore the error correction for the estimated volume. This results in clinically intolerable ventricle volume estimation error and further lead...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2020.101723

    authors: Luo G,Wang W,Tam C,Wang K,Cao S,Zhang H,Chen B,Li S

    更新日期:2020-08-01 00:00:00

  • Understanding the phase contrast optics to restore artifact-free microscopy images for segmentation.

    abstract::Phase contrast, a noninvasive microscopy imaging technique, is widely used to capture time-lapse images to monitor the behavior of transparent cells without staining or altering them. Due to the optical principle, phase contrast microscopy images contain artifacts such as the halo and shade-off that hinder image segme...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2011.12.006

    authors: Yin Z,Kanade T,Chen M

    更新日期:2012-07-01 00:00:00

  • CorteXpert: A model-based method for automatic renal cortex segmentation.

    abstract::This paper introduces a model-based approach for a fully automatic delineation of kidney and cortex tissue from contrast-enhanced abdominal CT scans. The proposed framework, named CorteXpert, consists of two new strategies for kidney tissue delineation: cortex model adaptation and non-uniform graph search. CorteXpert ...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2017.06.010

    authors: Xiang D,Bagci U,Jin C,Shi F,Zhu W,Yao J,Sonka M,Chen X

    更新日期:2017-12-01 00:00:00

  • Generalised coherent point drift for group-wise multi-dimensional analysis of diffusion brain MRI data.

    abstract::A probabilistic framework for registering generalised point sets comprising multiple voxel-wise data features such as positions, orientations and scalar-valued quantities, is proposed. It is employed for the analysis of magnetic resonance diffusion tensor image (DTI)-derived quantities, such as fractional anisotropy (...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2019.01.001

    authors: Ravikumar N,Gooya A,Beltrachini L,Frangi AF,Taylor ZA

    更新日期:2019-04-01 00:00:00

  • Ultrasound-fluoroscopy registration for prostate brachytherapy dosimetry.

    abstract::Prostate brachytherapy is a treatment for prostate cancer using radioactive seeds that are permanently implanted in the prostate. The treatment success depends on adequate coverage of the target gland with a therapeutic dose, while sparing the surrounding tissue. Since seed implantation is performed under transrectal ...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2012.06.001

    authors: Dehghan E,Lee J,Fallavollita P,Kuo N,Deguet A,Le Y,Clif Burdette E,Song DY,Prince JL,Fichtinger G

    更新日期:2012-10-01 00:00:00

  • Respiratory motion models: a review.

    abstract::The problem of respiratory motion has proved a serious obstacle in developing techniques to acquire images or guide interventions in abdominal and thoracic organs. Motion models offer a possible solution to these problems, and as a result the field of respiratory motion modelling has become an active one over the past...

    journal_title:Medical image analysis

    pub_type: 杂志文章,评审

    doi:10.1016/j.media.2012.09.005

    authors: McClelland JR,Hawkes DJ,Schaeffter T,King AP

    更新日期:2013-01-01 00:00:00

  • Automated preoperative planning of femoral stem in total hip arthroplasty from 3D CT data: atlas-based approach and comparative study.

    abstract::Atlas-based methods for automated preoperative planning of the femoral stem implant in total hip arthroplasty are described. Statistical atlases are constructed from a number of past preoperative plans prepared by experienced surgeons in order to represent the surgeon's expertise of the planning. Two types of atlases ...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2011.10.005

    authors: Otomaru I,Nakamoto M,Kagiyama Y,Takao M,Sugano N,Tomiyama N,Tada Y,Sato Y

    更新日期:2012-02-01 00:00:00

  • Automated size-specific dose estimates using deep learning image processing.

    abstract::An automated vendor-independent system for dose monitoring in computed tomography (CT) medical examinations involving ionizing radiation is presented in this paper. The system provides precise size-specific dose estimates (SSDE) following the American Association of Physicists in Medicine regulations. Our dose managem...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2020.101898

    authors: Juszczyk J,Badura P,Czajkowska J,Wijata A,Andrzejewski J,Bozek P,Smolinski M,Biesok M,Sage A,Rudzki M,Wieclawek W

    更新日期:2021-02-01 00:00:00

  • Joint optimization of segmentation and shape prior from level-set-based statistical shape model, and its application to the automated segmentation of abdominal organs.

    abstract::The goal of this study is to provide a theoretical framework for accurately optimizing the segmentation energy considering all of the possible shapes generated from the level-set-based statistical shape model (SSM). The proposed algorithm solves the well-known open problem, in which a shape prior may not be optimal in...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2015.11.003

    authors: Saito A,Nawano S,Shimizu A

    更新日期:2016-02-01 00:00:00

  • Discriminant snakes for 3D reconstruction of anatomical organs.

    abstract::In this work a new statistic deformable model for 3D segmentation of anatomical organs in medical images is proposed. A statistic discriminant snake performs a supervised learning of the object boundary in an image slice to segment the next slice of the image sequence. Each part of the object boundary is projected in ...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/s1361-8415(03)00014-8

    authors: Pardo XM,Radeva P,Cabello D

    更新日期:2003-09-01 00:00:00

  • A symbolic environment for visualizing activated foci in functional neuroimaging datasets.

    abstract::This paper presents a symbolic visualization environment known as the Corner Cube environment, which was developed to facilitate rapid examination and comparison of activated foci defined by analyses of functional neuroimaging datasets. We have performed a comparative evaluation of this environment against maximum-int...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/s1361-8415(98)80020-0

    authors: Rehm K,Lakshminaryan K,Frutiger S,Schaper KA,Sumners DW,Strother SC,Anderson JR,Rottenberg DA

    更新日期:1998-09-01 00:00:00

  • High resolution cortical bone thickness measurement from clinical CT data.

    abstract::The distribution of cortical bone in the proximal femur is believed to be a critical component in determining fracture resistance. Current CT technology is limited in its ability to measure cortical thickness, especially in the sub-millimetre range which lies within the point spread function of today's clinical scanne...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2010.01.003

    authors: Treece GM,Gee AH,Mayhew PM,Poole KE

    更新日期:2010-06-01 00:00:00

  • LinSEM: Linearizing segmentation evaluation metrics for medical images.

    abstract::Numerous algorithms are available for segmenting medical images. Empirical discrepancy metrics are commonly used in measuring the similarity or difference between segmentations by algorithms and "true" segmentations. However, one issue with the commonly used metrics is that the same metric value often represents diffe...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2019.101601

    authors: Li J,Udupa JK,Tong Y,Wang L,Torigian DA

    更新日期:2020-02-01 00:00:00

  • Automatic detection of over 100 anatomical landmarks in medical CT images: A framework with independent detectors and combinatorial optimization.

    abstract::An automatic detection method for 197 anatomically defined landmarks in computed tomography (CT) volumes is presented. The proposed method can handle missed landmarks caused by detection failure, a limited imaging range and other problems using a novel combinatorial optimization framework with a two-stage sampling alg...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2016.04.001

    authors: Hanaoka S,Shimizu A,Nemoto M,Nomura Y,Miki S,Yoshikawa T,Hayashi N,Ohtomo K,Masutani Y

    更新日期:2017-01-01 00:00:00

  • Classification of hemodynamics from dynamic-susceptibility-contrast magnetic resonance (DSC-MR) brain images using noiseless independent factor analysis.

    abstract::Dynamic-susceptibility-contrast (DSC) magnetic resonance imaging records signal changes on images when the injected contrast-agent particles pass through a human brain. The temporal signal changes on different brain tissues manifest distinct blood-supply patterns which are vital for the profound analysis of cerebral h...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2007.02.002

    authors: Chou YC,Teng MM,Guo WY,Hsieh JC,Wu YT

    更新日期:2007-06-01 00:00:00

  • Capturing intraoperative deformations: research experience at Brigham and Women's Hospital.

    abstract::During neurosurgical procedures the objective of the neurosurgeon is to achieve the resection of as much diseased tissue as possible while achieving the preservation of healthy brain tissue. The restricted capacity of the conventional operating room to enable the surgeon to visualize critical healthy brain structures ...

    journal_title:Medical image analysis

    pub_type: 杂志文章,评审

    doi:10.1016/j.media.2004.11.005

    authors: Warfield SK,Haker SJ,Talos IF,Kemper CA,Weisenfeld N,Mewes AU,Goldberg-Zimring D,Zou KH,Westin CF,Wells WM,Tempany CM,Golby A,Black PM,Jolesz FA,Kikinis R

    更新日期:2005-04-01 00:00:00

  • Advances and challenges in deformable image registration: From image fusion to complex motion modelling.

    abstract::Over the past 20 years, the field of medical image registration has significantly advanced from multi-modal image fusion to highly non-linear, deformable image registration for a wide range of medical applications and imaging modalities, involving the compensation and analysis of physiological organ motion or of tissu...

    journal_title:Medical image analysis

    pub_type: 社论

    doi:10.1016/j.media.2016.06.031

    authors: Schnabel JA,Heinrich MP,Papież BW,Brady SJM

    更新日期:2016-10-01 00:00:00

  • Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks.

    abstract::Pixelwise segmentation of the left ventricular (LV) myocardium and the four cardiac chambers in 2-D steady state free precession (SSFP) cine sequences is an essential preprocessing step for a wide range of analyses. Variability in contrast, appearance, orientation, and placement of the heart between patients, clinical...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2018.05.008

    authors: Vigneault DM,Xie W,Ho CY,Bluemke DA,Noble JA

    更新日期:2018-08-01 00:00:00

  • Disentangled representation learning in cardiac image analysis.

    abstract::Typically, a medical image offers spatial information on the anatomy (and pathology) modulated by imaging specific characteristics. Many imaging modalities including Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) can be interpreted in this way. We can venture further and consider that a medical image na...

    journal_title:Medical image analysis

    pub_type: 杂志文章

    doi:10.1016/j.media.2019.101535

    authors: Chartsias A,Joyce T,Papanastasiou G,Semple S,Williams M,Newby DE,Dharmakumar R,Tsaftaris SA

    更新日期:2019-12-01 00:00:00