Abstract:
:Classification of digital pathology images is imperative in cancer diagnosis and prognosis. Recent advancements in deep learning and computer vision have greatly benefited the pathology workflow by developing automated solutions for classification tasks. However, the cost and time for acquiring high quality task-specific large annotated training data are subject to intra- and inter-observer variability, thus challenging the adoption of such tools. To address these challenges, we propose a classification framework via co-representation learning to maximize the learning capability of deep neural networks while using a reduced amount of training data. The framework captures the class-label information and the local spatial distribution information by jointly optimizing a categorical cross-entropy objective and a deep metric learning objective respectively. A deep metric learning objective is incorporated to enhance the classification, especially in the low training data regime. Further, a neighborhood-aware multiple similarity sampling strategy, and a soft-multi-pair objective that optimizes interactions between multiple informative sample pairs, is proposed to accelerate deep metric learning. We evaluate the proposed framework on five benchmark datasets from three digital pathology tasks, i.e., nuclei classification, mitosis detection, and tissue type classification. For all the datasets, our framework achieves state-of-the-art performance when using approximately only 50% of the training data. On using complete training data, the proposed framework outperforms the state-of-the-art on all the five datasets.
journal_name
Med Image Analjournal_title
Medical image analysisauthors
Pati P,Foncubierta-Rodríguez A,Goksel O,Gabrani Mdoi
10.1016/j.media.2020.101859subject
Has Abstractpub_date
2021-01-01 00:00:00pages
101859eissn
1361-8415issn
1361-8423pii
S1361-8415(20)30223-1journal_volume
67pub_type
杂志文章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
更新日期:2010-06-01 00:00:00
abstract::A novel method for estimating a field of fiber orientation distribution (FOD) based on signal de-convolution from a given set of diffusion weighted magnetic resonance (DW-MR) images is presented. We model the FOD by higher order Cartesian tensor basis using a parametrization that explicitly enforces the positive semi-...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2012.07.002
更新日期:2012-08-01 00:00:00
abstract::In this note we summarize the history of computer aided surgery in orthopaedics and traumatology from the end of the nineteenth century to currently observable future trends. We concentrate on the two major components of such systems, pre-operative planning and intra-operative execution. The evolution of the necessary...
journal_title:Medical image analysis
pub_type: 社论
doi:10.1016/j.media.2016.06.033
更新日期:2016-10-01 00:00:00
abstract::In this paper, we present a generative Bayesian approach for estimating the low-dimensional latent space of diffeomorphic shape variability in a population of images. We develop a latent variable model for principal geodesic analysis (PGA) that provides a probabilistic framework for factor analysis in the space of dif...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.04.009
更新日期:2015-10-01 00:00:00
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
更新日期:2020-08-01 00:00:00
abstract::In minimally invasive surgery, deployment of motion compensation, dynamic active constraints and adaptive intra-operative guidance require accurate estimation of deforming tissue in 3D. To this end, the use of vision-based techniques is advantageous in that it does not require the integration of additional hardware to...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2011.02.010
更新日期:2012-04-01 00:00:00
abstract::Automated delineation of anatomical structures in chest radiographs is difficult due to superimposition of multiple structures. In this work an automated technique to segment the clavicles in posterior-anterior chest radiographs is presented in which three methods are combined. Pixel classification is applied in two s...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2012.06.009
更新日期:2012-12-01 00:00:00
abstract::Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is chal...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2019.101561
更新日期:2020-01-01 00:00:00
abstract::Label fusion is a critical step in many image segmentation frameworks (e.g., multi-atlas segmentation) as it provides a mechanism for generalizing a collection of labeled examples into a single estimate of the underlying segmentation. In the multi-label case, typical label fusion algorithms treat all labels equally - ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2014.06.005
更新日期:2014-10-01 00:00:00
abstract::We propose HookNet, a semantic segmentation model for histopathology whole-slide images, which combines context and details via multiple branches of encoder-decoder convolutional neural networks. Concentric patches at multiple resolutions with different fields of view, feed different branches of HookNet, and intermedi...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2020.101890
更新日期:2021-02-01 00:00:00
abstract::A deformable registration method is described that enables automatic alignment of magnetic resonance (MR) and 3D transrectal ultrasound (TRUS) images of the prostate gland. The method employs a novel "model-to-image" registration approach in which a deformable model of the gland surface, derived from an MR image, is r...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2010.11.003
更新日期:2012-04-01 00:00:00
abstract::As a common disease in the elderly, neural foramina stenosis (NFS) brings a significantly negative impact on the quality of life due to its symptoms including pain, disability, fall risk and depression. Accurate boundary delineation is essential to the clinical diagnosis and treatment of NFS. However, existing clinica...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2016.10.009
更新日期:2017-02-01 00:00:00
abstract::We present an algorithm estimating the width of retinal vessels in fundus camera images. The algorithm uses a novel parametric surface model of the cross-sectional intensities of vessels, and ensembles of bagged decision trees to estimate the local width from the parameters of the best-fit surface. We report comparati...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2013.07.006
更新日期:2013-12-01 00:00:00
abstract::Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.09.005
更新日期:2016-01-01 00:00:00
abstract::Vascular pressure differences are established risk markers for a number of cardiovascular diseases. Relative pressures are, however, often driven by turbulence-induced flow fluctuations, where conventional non-invasive methods may yield inaccurate results. Recently, we proposed a novel method for non-turbulent flows, ...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2019.101627
更新日期:2020-02-01 00:00:00
abstract::The automatic extraction of blood vessels in non-fluorescein eye fundus images is a tough task in applications such as diabetic retinopathy screening. However, vessel shapes have complex variations, and accurate modeling of retinal vascular structures is challenging. We have therefore developed a new approach to accur...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.09.002
更新日期:2015-12-01 00:00:00
abstract::Image registration is an important task in medical image analysis. Whereas most methods are designed for the registration of two images (pairwise registration), there is an increasing interest in simultaneously aligning more than two images using groupwise registration. Multimodal registration in a groupwise setting r...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2018.02.003
更新日期:2018-05-01 00:00:00
abstract::Automated quantitative estimation of spinal curvature is an important task for the ongoing evaluation and treatment planning of Adolescent Idiopathic Scoliosis (AIS). It solves the widely accepted disadvantage of manual Cobb angle measurement (time-consuming and unreliable) which is currently the gold standard for AIS...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2018.05.005
更新日期:2018-08-01 00:00:00
abstract::Segmentation of the skull in medical imagery is an important stage in applications that require the construction of realistic models of the head. Such models are used, for example, to simulate the behavior of electro-magnetic fields in the head and to model the electrical activity of the cortex in EEG and MEG data. In...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(00)00016-5
更新日期:2000-09-01 00:00:00
abstract::Fine-featured elastograms may provide additional information of radiological interest in the context of in vivo elastography. Here a new image processing pipeline called ESP (Elastography Software Pipeline) is developed to create Magnetic Resonance Elastography (MRE) maps of viscoelastic parameters (complex modulus ma...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2016.05.012
更新日期:2017-01-01 00:00:00
abstract::The ability to predict patient-specific soft tissue deformations is key for computer-integrated surgery systems and the core enabling technology for a new era of personalized medicine. Element-Free Galerkin (EFG) methods are better suited for solving soft tissue deformation problems than the finite element method (FEM...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2019.06.004
更新日期:2019-08-01 00:00:00
abstract::Simulating cardiac electromechanical activity is of great interest for a better understanding of pathologies and for therapy planning. Design and validation of such models is difficult due to the lack of clinical data. XMR systems are a new type of interventional facility in which patients can be rapidly transferred b...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2005.05.003
更新日期:2005-10-01 00:00:00
abstract::Accurate segmentation of a pulmonary nodule is an important and active area of research in medical image processing. Although many algorithms have been reported in literature for this problem, those that are applicable to various density types have not been available until recently. In this paper, we propose a new alg...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2010.08.005
更新日期:2011-02-01 00:00:00
abstract::An automated segmentation method is presented for multi-organ segmentation in abdominal CT images. Dictionary learning and sparse coding techniques are used in the proposed method to generate target specific priors for segmentation. The method simultaneously learns dictionaries which have reconstructive power and clas...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2015.04.015
更新日期:2015-07-01 00:00:00
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
更新日期:2019-12-01 00:00:00
abstract::This paper describes a new robust and fully automatic method for calibration of three-dimensional (3D) freehand ultrasound called Confhusius (CalibratiON for FreeHand UltraSound Imaging USage). 3D Freehand ultrasound consists in mounting a position sensor on a standard probe. The echographic B-scans can be localized i...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2004.06.021
更新日期:2005-02-01 00:00:00
abstract::Traditionally, segmentation and registration have been solved as two independent problems, even though it is often the case that the solution to one impacts the solution to the other. In this paper, we introduce a geometric, variational framework that uses active contours to simultaneously segment and register feature...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/s1361-8415(03)00004-5
更新日期:2003-06-01 00:00:00
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
更新日期:2020-02-01 00:00:00
abstract::The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thu...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2014.05.004
更新日期:2014-10-01 00:00:00
abstract::Neural cell instance segmentation, which aims at joint detection and segmentation of every neural cell in a microscopic image, is essential to many neuroscience applications. The challenge of this task involves cell adhesion, cell distortion, unclear cell contours, low-contrast cell protrusion structures, and backgrou...
journal_title:Medical image analysis
pub_type: 杂志文章
doi:10.1016/j.media.2019.05.004
更新日期:2019-07-01 00:00:00