Medical image analysis
-
Medical image analysis · Aug 2019
Comparative StudyConvolutional sparse kernel network for unsupervised medical image analysis.
The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems. Such supervised approaches, however, are difficult to implement in the medical domain where large volumes of labelled data are difficult to obtain due to the complexity of manual annotation and inter- and intra-observer variability in label assignment. We propose a new convolutional sparse kernel network (CSKN), which is a hierarchical unsupervised feature learning framework that addresses the challenge of learning representative visual features in medical image analysis domains where there is a lack of annotated training data. ⋯ We evaluated our framework in medical image retrieval and classification on three public datasets. Our results show that our CSKN had better accuracy when compared to other conventional unsupervised methods and comparable accuracy to methods that used state-of-the-art supervised convolutional neural networks (CNNs). Our findings indicate that our unsupervised CSKN provides an opportunity to leverage unannotated big data in medical imaging repositories.
-
Medical image analysis · Jan 2019
A collaborative computer aided diagnosis (C-CAD) system with eye-tracking, sparse attentional model, and deep learning.
Computer aided diagnosis (CAD) tools help radiologists to reduce diagnostic errors such as missing tumors and misdiagnosis. Vision researchers have been analyzing behaviors of radiologists during screening to understand how and why they miss tumors or misdiagnose. In this regard, eye-trackers have been instrumental in understanding visual search processes of radiologists. ⋯ The proposed C-CAD system has been tested in a lung cancer screening experiment with multiple radiologists, reading low dose chest CTs. Promising results support the efficiency, accuracy and applicability of the proposed C-CAD system in a real radiology room setting. We have also shown that our framework is generalizable to more complex applications such as prostate cancer screening with multi-parametric magnetic resonance imaging (mp-MRI).
-
Medical image analysis · Aug 2018
Automated comprehensive Adolescent Idiopathic Scoliosis assessment using MVC-Net.
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 assessment. Attempts have been made to improve the reliability of automated Cobb angle estimation. ⋯ By utilizing an iterative multi-task training algorithm to train the Spinal Landmark Estimator and Cobb Angle Estimator in tandem, the MVC-Net leverages the multi-task relationship between landmark and angle estimation to reliably detect all the required vertebrae for accurate Cobb angles estimation. Experimental results on 526 x-ray images from 154 patients show an impressive 4.04° Circular Mean Absolute Error (CMAE) in AP Cobb angle and 4.07° CMAE in LAT Cobb angle estimation, which demonstrates the MVC-Net's capability of robust and accurate estimation of Cobb angles in multi-view x-rays. Our method therefore provides clinicians with a framework for efficient, accurate, and reliable estimation of spinal curvature for comprehensive AIS assessment.
-
Medical image analysis · Aug 2018
Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks.
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 views, scanners, and protocols makes fully automatic semantic segmentation a notoriously difficult problem. Here, we present Ω-Net (Omega-Net): A novel convolutional neural network (CNN) architecture for simultaneous localization, transformation into a canonical orientation, and semantic segmentation. ⋯ In addition, to be comparable with other works, Ω-Net was retrained from scratch using five-fold cross-validation on the publicly available 2017 MICCAI Automated Cardiac Diagnosis Challenge (ACDC) dataset. The Ω-Net outperformed the state-of-the-art method in segmentation of the LV and RV bloodpools, and performed slightly worse in segmentation of the LV myocardium. We conclude that this architecture represents a substantive advancement over prior approaches, with implications for biomedical image segmentation more generally.
-
Medical image analysis · May 2018
Comparative StudyHeterogeneous Multifrequency Direct Inversion (HMDI) for magnetic resonance elastography with application to a clinical brain exam.
A new viscoelastic wave inversion method for MRE, called Heterogeneous Multifrequency Direct Inversion (HMDI), was developed which accommodates heterogeneous elasticity within a direct inversion (DI) by incorporating first-order gradients and combining results from a narrow band of multiple frequencies. The method is compared with a Helmholtz-type DI, Multifrequency Dual Elasto-Visco inversion (MDEV), both on ground-truth Finite Element Method simulations at varied noise levels and a prospective in vivo brain cohort of 48 subjects ages 18-65. In simulated data, MDEV recovered background material within 5% and HMDI within 1% of prescribed up to SNR of 20 dB. ⋯ In comparison to MDEV, HMDI showed better preservation of recovered target shapes, more noise-robustness, and stabler recovery values in regions with rapid property change, however summary statistics for both methods were quite similar. By eliminating homogeneity assumptions within a fast, fully automatic, regularization-free direct inversion, HMDI appears to be a worthwhile addition to the MRE image reconstruction repertoire. In addition to supporting the literature showing decrease in brain viscoelasticity with age, our work supports a wide range of inter-individual variation in brain MRE results.