Abstract:
:Risk stratification (characterization) of tumors from radiology images can be more accurate and faster with computer-aided diagnosis (CAD) tools. Tumor characterization through such tools can also enable non-invasive cancer staging, prognosis, and foster personalized treatment planning as a part of precision medicine. In this papet, we propose both supervised and unsupervised machine learning strategies to improve tumor characterization. Our first approach is based on supervised learning for which we demonstrate significant gains with deep learning algorithms, particularly by utilizing a 3D convolutional neural network and transfer learning. Motivated by the radiologists' interpretations of the scans, we then show how to incorporate task-dependent feature representations into a CAD system via a graph-regularized sparse multi-task learning framework. In the second approach, we explore an unsupervised learning algorithm to address the limited availability of labeled training data, a common problem in medical imaging applications. Inspired by learning from label proportion approaches in computer vision, we propose to use proportion-support vector machine for characterizing tumors. We also seek the answer to the fundamental question about the goodness of "deep features" for unsupervised tumor classification. We evaluate our proposed supervised and unsupervised learning algorithms on two different tumor diagnosis challenges: lung and pancreas with 1018 CT and 171 MRI scans, respectively, and obtain the state-of-the-art sensitivity and specificity results in both problems.
journal_name
IEEE Trans Med Imagingjournal_title
IEEE transactions on medical imagingauthors
Hussein S,Kandel P,Bolan CW,Wallace MB,Bagci Udoi
10.1109/TMI.2019.2894349subject
Has Abstractpub_date
2019-08-01 00:00:00pages
1777-1787issue
8eissn
0278-0062issn
1558-254Xjournal_volume
38pub_type
杂志文章abstract::While plane-wave imaging can improve the performance of power Doppler by enabling much longer ensembles than systems using focused beams, the long-ensemble averaging of the zero-lag autocorrelation R(0) estimates does not directly decrease the mean noise level, but only decreases its variance. Spatial variation of the...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2017.2699672
更新日期:2017-09-01 00:00:00
abstract::We describe a nonparametric framework for incorporating information from co-registered anatomical images into positron emission tomographic (PET) image reconstruction through priors based on information theoretic similarity measures. We compare and evaluate the use of mutual information (MI) and joint entropy (JE) bet...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2010.2076827
更新日期:2011-03-01 00:00:00
abstract::Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A compute...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2014.2315206
更新日期:2014-07-01 00:00:00
abstract::Optical coherence tomography (OCT) is a well-established image modality in ophthalmology and used daily in the clinic. Automatic evaluation of such datasets requires an accurate segmentation of the retinal cell layers. However, due to the naturally low signal to noise ratio and the resulting bad image quality, this ta...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2012.2225152
更新日期:2013-03-01 00:00:00
abstract::Adolescence is a transitional period between the childhood and adulthood with physical changes, as well as increasing emotional development. Studies have shown that the emotional sensitivity is related to a second period of rapid brain growth. However, there is little focus on the trend of brain development during thi...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2926667
更新日期:2020-02-01 00:00:00
abstract::An accurate diagnosis of burns and pressure ulcers in the early stages can be made by computerized image processing. This study describes a critical assessment of potential methodologies for noninvasive wound evaluation using a color imaging system. We also developed a method for quantifying histological readings and ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.552057
更新日期:1997-02-01 00:00:00
abstract::Active shape models bear a great promise for model-based medical image analysis. Their practical use, though, is undermined due to the need to train such models on large image databases. Automatic building of point distribution models (PDMs) has been successfully addressed and a number of autolandmarking techniques ar...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2008.2004819
更新日期:2008-11-01 00:00:00
abstract::We present and validate a novel registration algorithm mapping two data sets, generated from a rigid object, in the presence of Gaussian noise. The proposed method is based on the Unscented Kalman Filter (UKF) algorithm that is generally employed for analyzing nonlinear systems corrupted by additive Gaussian noise. Fi...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/tmi.2007.901984
更新日期:2007-12-01 00:00:00
abstract::We investigate using dual time-point PET data to perform Patlak modeling. This approach can be used for whole body dynamic PET studies in which we compute voxel-wise estimates of Patlak parameters using two frames of data for each bed position. Our approach directly uses list-mode arrival times for each event to estim...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2014.2298868
更新日期:2014-04-01 00:00:00
abstract::Recently, deep neural networks have been widely and successfully applied in computer vision tasks and have attracted growing interest in medical imaging. One barrier for the application of deep neural networks to medical imaging is the need for large amounts of prior training pairs, which is not always feasible in cli...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2018.2888491
更新日期:2019-07-01 00:00:00
abstract::Remarkable progress in positron emission tomography (PET) development has occurred in recent years, in hardware, software, and computer implementation of image reconstruction. Recent development in PET scanners such as the high-resolution research tomograph (HRRT) developed by CTI (now Siemens) represents such a case ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/tmi.2007.892644
更新日期:2007-06-01 00:00:00
abstract::This paper addresses the long object problem in helical cone-beam computed tomography. We present the PHI-method, a new algorithm for the exact reconstruction of a region-of-interest (ROI) of a long object from axially truncated data extending only slightly beyond the ROI. The PHI-method is an extension of the Radon-m...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.870247
更新日期:2000-05-01 00:00:00
abstract::X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using l...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2018.2823768
更新日期:2018-06-01 00:00:00
abstract::Two-dimensional ultrasound sector scans of the left ventricle (LV) are commonly used to diagnose cardiac mechanical function. Present quantification procedures of wall motion by this technique entail inaccuracies, mainly due to relatively poor image quality and the absence of a definition of the relative position of t...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.1987.4307836
更新日期:1987-01-01 00:00:00
abstract::Electromagnetic brain imaging is the reconstruction of brain activity from non-invasive recordings of the magnetic fields and electric potentials. An enduring challenge in this imaging modality is estimating the number, location, and time course of sources, especially for the reconstruction of distributed brain source...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2932290
更新日期:2020-03-01 00:00:00
abstract::Alzheimer's disease (AD) is a serious neurodegenerative condition that affects millions of individuals across the world. As the average age of individuals in the United States and the world increases, the prevalence of AD will continue to grow. To address this public health problem, the research community has develope...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2958943
更新日期:2020-06-01 00:00:00
abstract::Micro-computed tomography (micro-CT) has been widely used to generate high-resolution 3-D tissue images from small animals nondestructively, especially for mineralized skeletal tissues. However, its application to the analysis of soft cardiovascular tissues has been limited by poor inter-tissue contrast. Recent ex viv...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2012.2209183
更新日期:2013-01-01 00:00:00
abstract::The interest of compressive sampling in ultrasound imaging has been recently extensively evaluated by several research teams. Following the different application setups, it has been shown that the RF data may be reconstructed from a small number of measurements and/or using a reduced number of ultrasound pulse emissio...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2015.2493241
更新日期:2016-03-01 00:00:00
abstract::Monte Carlo (MC) simulation provides a flexible and robust framework to efficiently evaluate and optimize image processing methods in emission tomography. In this work we present Brain-VISET (Voxel-based Iterative Simulation for Emission Tomography), a method that aims to simulate realistic [ (99m) Tc]-SPECT and [ (18...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2014.2326041
更新日期:2014-10-01 00:00:00
abstract::Biomedical applications such as cell tracking and angiography require the detection of low concentrations of superparamagnetic iron oxide nanoparticles (SPIOs) for imaging purposes. Magnetic particle imaging (MPI) is a new technology which enables the quantitative and time-resolved localization of SPIO distributions. ...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2015.2501462
更新日期:2016-03-01 00:00:00
abstract::Three-dimensional Fourier transform (3-DFT) magnetic resonance imaging (MRI) offers advantages in terms of signal-to-noise (S/N) per unit of time for the case where a large number of slices is desired. This advantage is enhanced when the relaxation time, T(1 ), is short. Because time limitations in 3-DFT imaging force...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/42.97588
更新日期:1991-01-01 00:00:00
abstract::Passive monitoring of the thermal noise variances of the channels of a receive array was shown to reveal respiratory motion of the underlying anatomy, a so called "noise navigator". There is, however, an inevitable trade off between the accuracy and temporal resolution of the noise navigator due to its passive nature....
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2018.2808699
更新日期:2018-08-01 00:00:00
abstract::Glaucoma is a leading cause of irreversible blindness. Accurate segmentation of the optic disc (OD) and optic cup (OC) from fundus images is beneficial to glaucoma screening and diagnosis. Recently, convolutional neural networks demonstrate promising progress in the joint OD and OC segmentation. However, affected by t...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2019.2899910
更新日期:2019-11-01 00:00:00
abstract::Radiofrequency ablation (RFA) is an established treatment for liver cancer when resection is not possible. Yet, its optimal delivery is challenged by the presence of large blood vessels and the time-varying thermal conductivity of biological tissue. Incomplete treatment and an increased risk of recurrence are therefor...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2015.2406575
更新日期:2015-07-01 00:00:00
abstract::An automatic system is presented to find the location of the major anatomical structures in color fundus photographs; the optic disc, the macula, and the vascular arch. These structures are found by fitting a single point-distribution-model to the image, that contains points on each structure. The method can handle op...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2006.885336
更新日期:2007-01-01 00:00:00
abstract::Most X-ray fluoroscopy systems are stationary and impose restrictions on the measurement of dynamic joint motion; for example, knee-joint kinematics during gait is usually measured with the subject ambulating on a treadmill. We developed a computer-controlled, mobile, biplane, X-ray fluoroscopy system to track human b...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2015.2473168
更新日期:2016-01-01 00:00:00
abstract::Tracking subcellular structures as well as viral structures displayed as 'particles' in fluorescence microscopy images yields quantitative information on the underlying dynamical processes. We have developed an approach for tracking multiple fluorescent particles based on probabilistic data association. The approach c...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2014.2359541
更新日期:2015-02-01 00:00:00
abstract::The magnetic particle imaging (MPI) method directly images the magnetization of super-paramagnetic iron oxide (SPIO) nanoparticles, which are contrast agents commonly used in magnetic resonance imaging (MRI). MPI, as originally envisioned, requires a high-bandwidth receiver coil and preamplifier, which are difficult t...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2009.2013849
更新日期:2009-08-01 00:00:00
abstract::The segmentation of the human airway tree from volumetric computed tomography (CT) images builds an important step for many clinical applications and for physiological studies. Previously proposed algorithms suffer from one or several problems: leaking into the surrounding lung parenchyma, the need for the user to man...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2005.857654
更新日期:2005-12-01 00:00:00
abstract::Microwave radar imaging is promising as a complementary medical imaging modality. However, the unique nature of the images means interpretation can be difficult. As a result, it is important to understand the sources of image differences, and how much variability is inherent in the imaging system itself. To address th...
journal_title:IEEE transactions on medical imaging
pub_type: 杂志文章
doi:10.1109/TMI.2018.2806878
更新日期:2018-08-01 00:00:00