arXiv subjects

Jin Jin

Publications and source records attributed to Jin Jin.

29 records · Page 2Linked to original sources

arXiv2023

Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End

Autonomous robots must navigate reliably in unknown environments even under compromised exteroceptive perception, or perception failures. Such failures often occur when harsh environments lead to degraded sensing, or when the perception algorithm misinterprets the scene due to limited generalization. In this paper, we model perception failures as invisible obstacles and pits, and train a reinforcement learning (RL) based local navigation policy to guide our legged robot. Unlike previous works relying on heuristics and anomaly detection to update navigational information, we train our navigation policy to reconstruct the environment information in the latent space from corrupted perception and react to perception failures end-to-end. To this end, we incorporate both proprioception and exteroception into our policy inputs, thereby enabling the policy to sense collisions on different body parts and pits, prompting corresponding reactions. We validate our approach in simulation and on the real quadruped robot ANYmal running in real-time (<10 ms CPU inference). In a quantitative comparison with existing heuristic-based locally reactive planners, our policy increases the success rate over 30% when facing perception failures. Project Page: https://bit.ly/45NBTuh.

cs.RO↗

arXiv2023

NeXtQSM -- A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data

Deep learning based Quantitative Susceptibility Mapping (QSM) has shown great potential in recent years, obtaining similar results to established non-learning approaches. Many current deep learning approaches are not data consistent, require in vivo training data or solve the QSM problem in consecutive steps resulting in the propagation of errors. Here we aim to overcome these limitations and developed a framework to solve the QSM processing steps jointly. We developed a new hybrid training data generation method that enables the end-to-end training for solving background field correction and dipole inversion in a data-consistent fashion using a variational network that combines the QSM model term and a learned regularizer. We demonstrate that NeXtQSM overcomes the limitations of previous deep learning methods. NeXtQSM offers a new deep learning based pipeline for computing quantitative susceptibility maps that integrates each processing step into the training and provides results that are robust and fast.

eess.IV↗

arXiv2022

Deep-learning-enabled Brain Hemodynamic Mapping Using Resting-state fMRI

Cerebrovascular disease is a leading cause of death globally. Prevention and early intervention are known to be the most effective forms of its management. Non-invasive imaging methods hold great promises for early stratification, but at present lack the sensitivity for personalized prognosis. Resting-state functional magnetic resonance imaging (rs-fMRI), a powerful tool previously used for mapping neural activity, is available in most hospitals. Here we show that rs-fMRI can be used to map cerebral hemodynamic function and delineate impairment. By exploiting time variations in breathing pattern during rs-fMRI, deep learning enables reproducible mapping of cerebrovascular reactivity (CVR) and bolus arrive time (BAT) of the human brain using resting-state CO2 fluctuations as a natural 'contrast media'. The deep-learning network was trained with CVR and BAT maps obtained with a reference method of CO2-inhalation MRI, which included data from young and older healthy subjects and patients with Moyamoya disease and brain tumors. We demonstrate the performance of deep-learning cerebrovascular mapping in the detection of vascular abnormalities, evaluation of revascularization effects, and vascular alterations in normal aging. In addition, cerebrovascular maps obtained with the proposed method exhibited excellent reproducibility in both healthy volunteers and stroke patients. Deep-learning resting-state vascular imaging has the potential to become a useful tool in clinical cerebrovascular imaging.

eess.IV↗

arXiv2021

A powerful test for differentially expressed gene pathways via graph-informed structural equation modeling

A major task in genetic studies is to identify genes related to human diseases and traits to understand functional characteristics of genetic mutations and enhance patient diagnosis. Besides marginal analyses of individual genes, identification of gene pathways, i.e., a set of genes with known interactions that collectively contribute to specific biological functions, can provide more biologically meaningful results. Such gene pathway analysis can be formulated into a high-dimensional two-sample testing problem. Due to the typically limited sample size of gene expression datasets, most existing two-sample tests may have compromised powers because they ignore or only inefficiently incorporate the auxiliary pathway information on gene interactions. We propose T2-DAG, a Hotelling's $T^2$-type test for detecting differentially expressed gene pathways, which efficiently leverages the auxiliary pathway information on gene interactions through a linear structural equation model. We establish the asymptotic distribution of the test statistic under pertinent assumptions. Simulation studies under various scenarios show that T2-DAG outperforms several representative existing methods with well-controlled type-I error rates and substantially improved powers, even with incomplete or inaccurate pathway information or unadjusted confounding effects. We also illustrate the performance of T2-DAG in an application to detect differentially expressed KEGG pathways between different stages of lung cancer.

stat.ME↗

arXiv2021

Multi-resolution Super Learner for Voxel-wise Classification of Prostate Cancer Using Multi-parametric MRI

While current research has shown the importance of Multi-parametric MRI (mpMRI) in diagnosing prostate cancer (PCa), further investigation is needed for how to incorporate the specific structures of the mpMRI data, such as the regional heterogeneity and between-voxel correlation within a subject. This paper proposes a machine learning-based method for improved voxel-wise PCa classification by taking into account the unique structures of the data. We propose a multi-resolution modeling approach to account for regional heterogeneity, where base learners trained locally at multiple resolutions are combined using the super learner, and account for between-voxel correlation by efficient spatial Gaussian kernel smoothing. The method is flexible in that the super learner framework allows implementation of any classifier as the base learner, and can be easily extended to classifying cancer into more sub-categories. We describe detailed classification algorithm for the binary PCa status, as well as the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to enhance the detection of the less prevalent cancer categories. We illustrate the advantages of the proposed approach over conventional modeling and machine learning approaches through simulations and application to in vivo data.

stat.ML↗

arXiv2020

DR^2Track: Towards Real-Time Visual Tracking for UAV via Distractor Repressed Dynamic Regression

Visual tracking has yielded promising applications with unmanned aerial vehicle (UAV). In literature, the advanced discriminative correlation filter (DCF) type trackers generally distinguish the foreground from the background with a learned regressor which regresses the implicit circulated samples into a fixed target label. However, the predefined and unchanged regression target results in low robustness and adaptivity to uncertain aerial tracking scenarios. In this work, we exploit the local maximum points of the response map generated in the detection phase to automatically locate current distractors. By repressing the response of distractors in the regressor learning, we can dynamically and adaptively alter our regression target to leverage the tracking robustness as well as adaptivity. Substantial experiments conducted on three challenging UAV benchmarks demonstrate both excellent performance and extraordinary speed (~50fps on a cheap CPU) of our tracker.

cs.CV↗

arXiv2020

Automatic Failure Recovery and Re-Initialization for Online UAV Tracking with Joint Scale and Aspect Ratio Optimization

Current unmanned aerial vehicle (UAV) visual tracking algorithms are primarily limited with respect to: (i) the kind of size variation they can deal with, (ii) the implementation speed which hardly meets the real-time requirement. In this work, a real-time UAV tracking algorithm with powerful size estimation ability is proposed. Specifically, the overall tracking task is allocated to two 2D filters: (i) translation filter for location prediction in the space domain, (ii) size filter for scale and aspect ratio optimization in the size domain. Besides, an efficient two-stage re-detection strategy is introduced for long-term UAV tracking tasks. Large-scale experiments on four UAV benchmarks demonstrate the superiority of the presented method which has computation feasibility on a low-cost CPU.

cs.CV↗

arXiv2020

Bayesian Methods for the Analysis of Early-Phase Oncology Basket Trials with Information Borrowing across Cancer Types

Research in oncology has changed the focus from histological properties of tumors in a specific organ to a specific genomic aberration potentially shared by multiple cancer types. This motivates the basket trial, which assesses the efficacy of treatment simultaneously on multiple cancer types that have a common aberration. Although the assumption of homogeneous treatment effects seems reasonable given the shared aberration, in reality, the treatment effect may vary by cancer type, and potentially only a subgroup of the cancer types respond to the treatment. Various approaches have been proposed to increase the trial power by borrowing information across cancer types, which, however, tend to inflate the type I error rate. In this paper, we review some representative Bayesian information borrowing methods for the analysis of early-phase basket trials. We then propose a novel method called the Bayesian hierarchical model with a correlated prior (CBHM), which conducts more flexible borrowing across cancer types according to sample similarity. We did simulation studies to compare CBHM with independent analysis and three information borrowing approaches: the conventional Bayesian hierarchical model, the EXNEX approach and Liu's two-stage approach. Simulation results show that all information borrowing approaches substantially improve the power of independent analysis if a large proportion of the cancer types truly respond to the treatment. Our proposed CBHM approach shows an advantage over the existing information borrowing approaches, with a power similar to that of EXNEX or Liu's approach, but the potential to provide substantially better control of type I error rate.

stat.AP↗

arXiv2020

Bayesian Spatial Models for Voxel-wise Prostate Cancer Classification Using Multi-parametric MRI Data

Multi-parametric magnetic resonance imaging (mpMRI) plays an increasingly important role in the diagnosis of prostate cancer. Various computer-aided detection algorithms have been proposed for automated prostate cancer detection by combining information from various mpMRI data components. However, there exist other features of mpMRI, including the spatial correlation between voxels and between-patient heterogeneity in the mpMRI parameters, that have not been fully explored in the literature but could potentially improve cancer detection if leveraged appropriately. This paper proposes novel voxel-wise Bayesian classifiers for prostate cancer that account for the spatial correlation and between-patient heterogeneity in mpMRI. Modeling the spatial correlation is challenging due to the extreme high dimensionality of the data, and we consider three computationally efficient approaches using Nearest Neighbor Gaussian Process (NNGP), knot-based reduced-rank approximation, and a conditional autoregressive (CAR) model, respectively. The between-patient heterogeneity is accounted for by adding a subject-specific random intercept on the mpMRI parameter model. Simulation results show that properly modeling the spatial correlation and between-patient heterogeneity improves classification accuracy. Application to in vivo data illustrates that classification is improved by spatial modeling using NNGP and reduced-rank approximation but not the CAR model, while modeling the between-patient heterogeneity does not further improve our classifier. Among our proposed models, the NNGP-based model is recommended considering its robust classification accuracy and high computational efficiency.

stat.AP↗

arXiv2019

Improving FLAIR SAR efficiency at 7T by adaptive tailoring of adiabatic pulse power using deep convolutional neural networks

Purpose: The purpose of this study is to demonstrate a method for Specific Absorption Rate (SAR) reduction for T2-FLAIR MRI sequences at 7T by predicting the required adiabatic pulse power and scaling the amplitude in a slice-wise fashion. Methods: We used a TR-FOCI adiabatic pulse for spin inversion in a T2-FLAIR sequence to improve B1+ homogeneity and calculate the pulse power required for adiabaticity slice-by-slice to minimize the SAR. Drawing on the implicit B1+ inhomogeneity present in a standard localizer scan, 3D AutoAlign localizers and SA2RAGE B1+ maps were acquired in eight volunteers. A convolutional neural network (CNN) was then trained to predict the B1+ profile from the localizers and scale factors for the pulse power for each slice were calculated. The ability to predict the B1+ profile as well as how the derived pulse scale factors affected the FLAIR inversion efficiency were assessed in transverse, sagittal, and coronal orientations. Results: The predicted B1+ maps matched the measured B1+ maps with a mean difference of 4.45% across all slices. The acquisition in the transverse orientation was shown to be most effective for this method and delivered a 40% reduction in SAR along with 1min and 30-sec reduction in scan time (28%) without degradation of image quality. Conclusion: We propose a SAR reduction technique based on the prediction of B1+ profiles from standard localizer scans using a CNN and show that scaling the inversion pulse power slice-by-slice for FLAIR sequences at 7T reduces SAR and scan time without compromising image quality.

eess.IV↗

arXiv2011

Electrical Transport Properties of Graphene Nanoribbons Produced from Sonicating Graphite in Solution

A simple one-stage solution-based method was developed to produce graphene nanoribbons by sonicating graphite powder in organic solutions with polymer surfactant. The graphene nanoribbons were deposited on silicon substrate, and characterized by Raman spectroscopy and atomic force microscopy. Single-layer and few-layer graphene nanoribbons with a width ranging from sub-10 nm to tens of nm and length ranging from hundreds of nm to 1 μm were routinely observed. Electrical transport properties of individual graphene nanoribbons were measured in both the back-gate and polymer-electrolyte top-gate configurations. The mobility of the graphene nanoribbons was found to be over an order of magnitude higher when measured in the latter than in the former configuration (without the polymer electrolyte), which can be attributed to the screening of the charged impurities by the counter-ions in the polymer electrolyte. This finding suggests that the charge transport in these solution-produced graphene nanoribbons is largely limited by charged impurity scattering.

cond-mat.mtrl-sci↗