Qi Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qi Yang has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Bennett A. Landman
Department of Electrical and Computer Engineering Vanderbilt University Nashville Tennessee USA
9 shared publications - Ho Hin Lee
Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
7 shared publications - Leon Y. Cai
Johns Hopkins University School of Medicine
6 shared publications - Xin Yu
Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
6 shared publications - Shunxing Bao
Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
5 shared publications - Yucheng Tang
NVIDIA, Santa Clara, California, United States
5 shared publications
Latest Publications
- Open Access
- 1 March 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 12 (02) , 1-17
Multi-contrast computed tomography atlas of healthy pancreas with dense displacement sampling registration
PurposeDiverse population demographics can lead to substantial variation in the human anatomy. Therefore, standard anatomical atlases are needed for interpreting organ-specific analyses. Among abdominal organs, the pancreas exhibits notable variability in volumetric morphology, shape, and appearance, complicating the generalization of population-wide features. Understanding the common features of a healthy pancreas is crucial for identifying biomarkers and diagnosing pancreatic diseases.ApproachWe propose a high-resolution CT atlas framework optimized for the healthy pancreas. We introduce a deep-learning-based preprocessing technique to extract abdominal ROIs and leverage a hierarchical registration pipeline to align pancreatic anatomy across populations. Briefly, DEEDS affine and non-rigid registration techniques are employed to transfer patient abdominal volumes to a fixed high-resolution atlas template. To generate and evaluate the pancreas atlas, multi-phase contrast CT scans of 443 subjects (aged 15 to 50 years, with no reported history of pancreatic disease) were processed.ResultsThe two-stage DEEDS affine and non-rigid registration outperforms other state-of-the-art tools, achieving the highest scores for pancreas label transfer across all phases (non-contrast: 0.497, arterial: 0.505, portal venous: 0.494, delayed: 0.497). External evaluation with 100 portal venous scans and 13 labeled abdominal organs shows a mean Dice score of 0.504. The low variance between the pancreases of registered subjects and the obtained pancreas atlas further illustrates the generalizability of the proposed method.ConclusionWe introduce a high-resolution pancreas atlas framework to generalize healthy biomarkers across populations with multi-contrast abdominal CT. The atlases and the associated pancreas organ labels are publicly available through the Human Biomolecular Atlas Program (HuBMAP).
- 1 March 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 12 (02) , 1-17
Open AccessMulti-contrast computed tomography atlas of healthy pancreas with dense displacement sampling registration
PurposeDiverse population demographics can lead to substantial variation in the human anatomy. Therefore, standard anatomical atlases are needed for interpreting organ-specific analyses. Among abdominal organs, the pancreas exhibits notable variability in volumetric morphology, shape, and appearance, complicating the generalization of population-wide features. Understanding the common features of a healthy pancreas is crucial for identifying biomarkers and diagnosing pancreatic diseases.ApproachWe propose a high-resolution CT atlas framework optimized for the healthy pancreas. We introduce a deep-learning-based preprocessing technique to extract abdominal ROIs and leverage a hierarchical registration pipeline to align pancreatic anatomy across populations. Briefly, DEEDS affine and non-rigid registration techniques are employed to transfer patient abdominal volumes to a fixed high-resolution atlas template. To generate and evaluate the pancreas atlas, multi-phase contrast CT scans of 443 subjects (aged 15 to 50 years, with no reported history of pancreatic disease) were processed.ResultsThe two-stage DEEDS affine and non-rigid registration outperforms other state-of-the-art tools, achieving the highest scores for pancreas label transfer across all phases (non-contrast: 0.497, arterial: 0.505, portal venous: 0.494, delayed: 0.497). External evaluation with 100 portal venous scans and 13 labeled abdominal organs shows a mean Dice score of 0.504. The low variance between the pancreases of registered subjects and the obtained pancreas atlas further illustrates the generalizability of the proposed method.ConclusionWe introduce a high-resolution pancreas atlas framework to generalize healthy biomarkers across populations with multi-contrast abdominal CT. The atlases and the associated pancreas organ labels are publicly available through the Human Biomolecular Atlas Program (HuBMAP).
- Open Access
- 1 November 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (06) , 1-14
Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement
PurposeEye morphology varies significantly across the population, especially for the orbit and optic nerve. These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference.ApproachTo tackle these limitations, we propose a process for creating high-resolution unbiased eye atlases. First, to restore spatial details from scans with a low through-plane resolution compared with a high in-plane resolution, we apply a deep learning-based super-resolution algorithm. Then, we generate an initial unbiased reference with an iterative metric-based registration using a small portion of subject scans. We register the remaining scans to this template and refine the template using an unsupervised deep probabilistic approach that generates a more expansive deformation field to enhance the organ boundary alignment. We demonstrate this framework using magnetic resonance images across four different tissue contrasts, generating four atlases in separate spatial alignments.ResultsWhen refining the template with sufficient subjects, we find a significant improvement using the Wilcoxon signed-rank test in the average Dice score across four labeled regions compared with a standard registration framework consisting of rigid, affine, and deformable transformations. These results highlight the effective alignment of eye organs and boundaries using our proposed process.ConclusionsBy combining super-resolution preprocessing and deep probabilistic models, we address the challenge of generating an eye atlas to serve as a standardized reference across a largely variable population.
- 1 November 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (06) , 1-14
Open AccessSuper-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement
PurposeEye morphology varies significantly across the population, especially for the orbit and optic nerve. These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference.ApproachTo tackle these limitations, we propose a process for creating high-resolution unbiased eye atlases. First, to restore spatial details from scans with a low through-plane resolution compared with a high in-plane resolution, we apply a deep learning-based super-resolution algorithm. Then, we generate an initial unbiased reference with an iterative metric-based registration using a small portion of subject scans. We register the remaining scans to this template and refine the template using an unsupervised deep probabilistic approach that generates a more expansive deformation field to enhance the organ boundary alignment. We demonstrate this framework using magnetic resonance images across four different tissue contrasts, generating four atlases in separate spatial alignments.ResultsWhen refining the template with sufficient subjects, we find a significant improvement using the Wilcoxon signed-rank test in the average Dice score across four labeled regions compared with a standard registration framework consisting of rigid, affine, and deformable transformations. These results highlight the effective alignment of eye organs and boundaries using our proposed process.ConclusionsBy combining super-resolution preprocessing and deep probabilistic models, we address the challenge of generating an eye atlas to serve as a standardized reference across a largely variable population.
- Open Access
- 1 July 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (04) , 044007-18
Characterizing patterns of diffusion tensor imaging variance in aging brains
Large datasets enable the exploration of questions that would be impractical with smaller- or moderate-sized datasets while giving rise to the development and application of deep learning models, which can assimilate complex data. One prevalent challenge is that large datasets often comprise samples aggregated from distinct sources at different time points using diverse technologies, causing data heterogeneity, experimental variations, and statistical biases if the analysis is not executed appropriately.1 In such scenarios, understanding the variance and variability of data is of great importance. The general linear model,2 a structured and widely used framework for relationship modeling, allows us to illustrate the importance. The general linear model is assessed through regression. A linear regression can be expressed by , where the response variable , the covariate matrix , and the regression coefficients are conventionally represented in matrix forms given by- 1 July 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (04) , 044007-18
Open AccessCharacterizing patterns of diffusion tensor imaging variance in aging brains
Large datasets enable the exploration of questions that would be impractical with smaller- or moderate-sized datasets while giving rise to the development and application of deep learning models, which can assimilate complex data. One prevalent challenge is that large datasets often comprise samples aggregated from distinct sources at different time points using diverse technologies, causing data heterogeneity, experimental variations, and statistical biases if the analysis is not executed appropriately.1 In such scenarios, understanding the variance and variability of data is of great importance. The general linear model,2 a structured and widely used framework for relationship modeling, allows us to illustrate the importance. The general linear model is assessed through regression. A linear regression can be expressed by , where the response variable , the covariate matrix , and the regression coefficients are conventionally represented in matrix forms given by - Open Access
- 1 March 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (02) , 024011-21
Empirical assessment of the assumptions of ComBat with diffusion tensor imaging
Diffusion-weighted magnetic resonance imaging (dMRI) is a non-invasive imaging modality that provides insight into the white matter (WM) microstructure in the brain.1 In diffusion tensor imaging (DTI), the signal from a dMRI scan is modeled as tensors that describe the direction and degree of water diffusion at each voxel.2 One of the most common ways to study a DTI model is through scalar metrics. Two of the most common diffusion scalars are fractional anisotropy (FA), which describes the directedness of diffusion, and mean diffusivity (MD), which describes the average magnitude of diffusion. While DTI is limited in its ability to describe crossing axon fibers in the brain,2 it is still useful to study the changes in brain morphology due to disease or aging.3 – 5
- 1 March 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (02) , 024011-21
Open AccessEmpirical assessment of the assumptions of ComBat with diffusion tensor imaging
Diffusion-weighted magnetic resonance imaging (dMRI) is a non-invasive imaging modality that provides insight into the white matter (WM) microstructure in the brain.1 In diffusion tensor imaging (DTI), the signal from a dMRI scan is modeled as tensors that describe the direction and degree of water diffusion at each voxel.2 One of the most common ways to study a DTI model is through scalar metrics. Two of the most common diffusion scalars are fractional anisotropy (FA), which describes the directedness of diffusion, and mean diffusivity (MD), which describes the average magnitude of diffusion. While DTI is limited in its ability to describe crossing axon fibers in the brain,2 it is still useful to study the changes in brain morphology due to disease or aging.3 – 5
- Top Cited Papers
- 25 August 2023
- Published by Elsevier in Medical Image Analysis
- Vol. 90, 102939
UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation
- 25 August 2023
- Published by Elsevier in Medical Image Analysis
- Vol. 90, 102939
Top Cited PapersUNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation
- Open Access
- 1 July 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10 (04) , 044001-12
Single slice thigh CT muscle group segmentation with domain adaptation and self-training
PurposeThigh muscle group segmentation is important for assessing muscle anatomy, metabolic disease, and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging, including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single-slice computed tomography (CT) thigh images is challenging.ApproachWe propose an unsupervised domain adaptation pipeline with self-training to transfer labels from three-dimensional MR to single CT slices. First, we transform the image appearance from MR to CT with CycleGAN and feed the synthesized CT images to a segmenter simultaneously. Single CT slices are divided into hard and easy cohorts based on the entropy of pseudo-labels predicted by the segmenter. After refining easy cohort pseudo-labels based on anatomical assumption, self-training with easy and hard splits is applied to fine-tune the segmenter.ResultsOn 152 withheld single CT thigh images, the proposed pipeline achieved a mean Dice of 0.888 (0.041) across all muscle groups, including gracilis, hamstrings, quadriceps femoris, and sartorius muscle.ConclusionsTo our best knowledge, this is the first pipeline to achieve domain adaptation from MR to CT for thigh images. The proposed pipeline effectively and robustly extracts muscle groups on two-dimensional single-slice CT thigh images. The container is available for public use in GitHub repository available at: https://github.com/MASILab/DA_CT_muscle_seg.
- 1 July 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10 (04) , 044001-12
Open AccessSingle slice thigh CT muscle group segmentation with domain adaptation and self-training
PurposeThigh muscle group segmentation is important for assessing muscle anatomy, metabolic disease, and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging, including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single-slice computed tomography (CT) thigh images is challenging.ApproachWe propose an unsupervised domain adaptation pipeline with self-training to transfer labels from three-dimensional MR to single CT slices. First, we transform the image appearance from MR to CT with CycleGAN and feed the synthesized CT images to a segmenter simultaneously. Single CT slices are divided into hard and easy cohorts based on the entropy of pseudo-labels predicted by the segmenter. After refining easy cohort pseudo-labels based on anatomical assumption, self-training with easy and hard splits is applied to fine-tune the segmenter.ResultsOn 152 withheld single CT thigh images, the proposed pipeline achieved a mean Dice of 0.888 (0.041) across all muscle groups, including gracilis, hamstrings, quadriceps femoris, and sartorius muscle.ConclusionsTo our best knowledge, this is the first pipeline to achieve domain adaptation from MR to CT for thigh images. The proposed pipeline effectively and robustly extracts muscle groups on two-dimensional single-slice CT thigh images. The container is available for public use in GitHub repository available at: https://github.com/MASILab/DA_CT_muscle_seg.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (9) , 4444-4453
Semantic-Aware Contrastive Learning for Multi-Object Medical Image Segmentation
Medical image segmentation, or computing voxel-wise semantic masks, is a fundamental yet challenging task in medical imaging domain. To increase the ability of encoder-decoder neural networks to perform this task across large clinical cohorts, contrastive learning provides an opportunity to stabilize model initialization and enhances downstream tasks performance without ground-truth voxel-wise labels. However, multiple target objects with different semantic meanings and contrast level may exist in a single image, which poses a problem for adapting traditional contrastive learning methods from prevalent “image-level classification” to “pixel-level segmentation”. In this article, we propose a simple semantic-aware contrastive learning approach leveraging attention masks and image-wise labels to advance multi-object semantic segmentation. Briefly, we embed different semantic objects to different clusters rather than the traditional image-level embeddings. We evaluate our proposed method on a multi-organ medical image segmentation task with both in-house data and MICCAI Challenge 2015 BTCV datasets. Compared with current state-of-the-art training strategies, our proposed pipeline yields a substantial improvement of 5.53% and 6.09% on Dice score for both medical image segmentation cohorts respectively (p-value $<$ 0.01). The performance of the proposed method is further assessed on external medical image cohort via MICCAI Challenge FLARE 2021 dataset, and achieves a substantial improvement from Dice 0.922 to 0.933 (p-value $<$ 0.01).
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (9) , 4444-4453
Semantic-Aware Contrastive Learning for Multi-Object Medical Image Segmentation
Medical image segmentation, or computing voxel-wise semantic masks, is a fundamental yet challenging task in medical imaging domain. To increase the ability of encoder-decoder neural networks to perform this task across large clinical cohorts, contrastive learning provides an opportunity to stabilize model initialization and enhances downstream tasks performance without ground-truth voxel-wise labels. However, multiple target objects with different semantic meanings and contrast level may exist in a single image, which poses a problem for adapting traditional contrastive learning methods from prevalent “image-level classification” to “pixel-level segmentation”. In this article, we propose a simple semantic-aware contrastive learning approach leveraging attention masks and image-wise labels to advance multi-object semantic segmentation. Briefly, we embed different semantic objects to different clusters rather than the traditional image-level embeddings. We evaluate our proposed method on a multi-organ medical image segmentation task with both in-house data and MICCAI Challenge 2015 BTCV datasets. Compared with current state-of-the-art training strategies, our proposed pipeline yields a substantial improvement of 5.53% and 6.09% on Dice score for both medical image segmentation cohorts respectively (p-value $<$ 0.01). The performance of the proposed method is further assessed on external medical image cohort via MICCAI Challenge FLARE 2021 dataset, and achieves a substantial improvement from Dice 0.922 to 0.933 (p-value $<$ 0.01).
- Open Access
Convolutional-recurrent neural networks approximate diffusion tractography from T1-weighted MRI and associated anatomical context
Diffusion MRI (dMRI) streamline tractography is the gold-standard for in vivo estimation of white matter (WM) pathways in the brain. However, the high angular resolution dMRI acquisitions capable of fitting the microstructural models needed for tractography are often time-consuming and not routinely collected clinically, restricting the scope of tractography analyses. To address this limitation, we build on recent advances in deep learning which have demonstrated that streamline propagation can be learned from dMRI directly without traditional model fitting. Specifically, we propose learning the streamline propagator from T1w MRI to facilitate arbitrary tractography analyses when dMRI is unavailable. To do so, we present a novel convolutional-recurrent neural network (CoRNN) trained in a teacher-student framework that leverages T1w MRI, associated anatomical context, and streamline memory from data acquired for the Human Connectome Project. We characterize our approach under two common tractography paradigms, WM bundle analysis and structural connectomics, and find approximately a 5-15% difference between measures computed from streamlines generated with our approach and those generated using traditional dMRI tractography. When placed in the literature, these results suggest that the accuracy of WM measures computed from T1w MRI with our method is on the level of scan-rescan dMRI variability and raise an important question: is tractography truly a microstructural phenomenon, or has dMRI merely facilitated its discovery and implementation?
Open AccessConvolutional-recurrent neural networks approximate diffusion tractography from T1-weighted MRI and associated anatomical context
Diffusion MRI (dMRI) streamline tractography is the gold-standard for in vivo estimation of white matter (WM) pathways in the brain. However, the high angular resolution dMRI acquisitions capable of fitting the microstructural models needed for tractography are often time-consuming and not routinely collected clinically, restricting the scope of tractography analyses. To address this limitation, we build on recent advances in deep learning which have demonstrated that streamline propagation can be learned from dMRI directly without traditional model fitting. Specifically, we propose learning the streamline propagator from T1w MRI to facilitate arbitrary tractography analyses when dMRI is unavailable. To do so, we present a novel convolutional-recurrent neural network (CoRNN) trained in a teacher-student framework that leverages T1w MRI, associated anatomical context, and streamline memory from data acquired for the Human Connectome Project. We characterize our approach under two common tractography paradigms, WM bundle analysis and structural connectomics, and find approximately a 5-15% difference between measures computed from streamlines generated with our approach and those generated using traditional dMRI tractography. When placed in the literature, these results suggest that the accuracy of WM measures computed from T1w MRI with our method is on the level of scan-rescan dMRI variability and raise an important question: is tractography truly a microstructural phenomenon, or has dMRI merely facilitated its discovery and implementation?
- Open Access
- 19 May 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (05) , 052405-11
Label efficient segmentation of single slice thigh CT with two-stage pseudo labels
Estimating volumes and masses of total body components is important for research of cancer, joint replacement, and exercise physiology.1 Full body CT scans can be used to calculate whole body compositions directly. However, it is hard to acquire a typical full body CT in the usual medical context due to the intense radiology dose. Mourtzakis et al.2 proposed that body components measured on abdomen or thigh slices are highly correlated with the mass of whole-body tissues. Thus, accurate segmentation of thigh slices can quantify tissue area properties to estimate body composition without requiring additional irradiation or examinations. Thus, this paper aims to segment muscle, fat, and bones from 2D thigh and lower leg CT slices.
- 19 May 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (05) , 052405-11
Open AccessLabel efficient segmentation of single slice thigh CT with two-stage pseudo labels
Estimating volumes and masses of total body components is important for research of cancer, joint replacement, and exercise physiology.1 Full body CT scans can be used to calculate whole body compositions directly. However, it is hard to acquire a typical full body CT in the usual medical context due to the intense radiology dose. Mourtzakis et al.2 proposed that body components measured on abdomen or thigh slices are highly correlated with the mass of whole-body tissues. Thus, accurate segmentation of thigh slices can quantify tissue area properties to estimate body composition without requiring additional irradiation or examinations. Thus, this paper aims to segment muscle, fat, and bones from 2D thigh and lower leg CT slices.
- 7 February 2022
- Published by Wiley in Medical Physics
- Vol. 49 (4) , 2502-2513
Learning white matter subject‐specific segmentation from structural MRI
Purpose: Mapping brain white matter (WM) is essential for building an understanding of brain anatomy and function. Tractography‐based methods derived from diffusion‐weighted MRI (dMRI) are the principal tools for investigating WM. These procedures rely on time‐consuming dMRI acquisitions that may not always be available, especially for legacy or time‐constrained studies. To address this problem, we aim to generate WM tracts from structural magnetic resonance imaging (MRI) image by deep learning.Methods: Following recently proposed innovations in structural anatomical segmentation, we evaluate the feasibility of training multiply spatial localized convolution neural networks to learn context from fixed spatial patches from structural MRI on standard template. We focus on six widely used dMRI tractography algorithms (TractSeg, RecoBundles, XTRACT, Tracula, automated fiber quantification (AFQ), and AFQclipped) and train 125 U‐Net models to learn these techniques from 3870 T1‐weighted images from the Baltimore Longitudinal Study of Aging, the Human Connectome Project S1200 release, and scans acquired at Vanderbilt University.Results: The proposed framework identifies fiber bundles with high agreement against tractography‐based pathways with a median Dice coefficient from 0.62 to 0.87 on a test cohort, achieving improved subject‐specific accuracy when compared to population atlas‐based methods. We demonstrate the generalizability of the proposed framework on three externally available datasets.Conclusions: We show that patch‐wise convolutional neural network can achieve robust bundle segmentation from T1w. We envision the use of this framework for visualizing the expected course of WM pathways when dMRI is not available.
- 7 February 2022
- Published by Wiley in Medical Physics
- Vol. 49 (4) , 2502-2513
Learning white matter subject‐specific segmentation from structural MRI
Purpose: Mapping brain white matter (WM) is essential for building an understanding of brain anatomy and function. Tractography‐based methods derived from diffusion‐weighted MRI (dMRI) are the principal tools for investigating WM. These procedures rely on time‐consuming dMRI acquisitions that may not always be available, especially for legacy or time‐constrained studies. To address this problem, we aim to generate WM tracts from structural magnetic resonance imaging (MRI) image by deep learning.Methods: Following recently proposed innovations in structural anatomical segmentation, we evaluate the feasibility of training multiply spatial localized convolution neural networks to learn context from fixed spatial patches from structural MRI on standard template. We focus on six widely used dMRI tractography algorithms (TractSeg, RecoBundles, XTRACT, Tracula, automated fiber quantification (AFQ), and AFQclipped) and train 125 U‐Net models to learn these techniques from 3870 T1‐weighted images from the Baltimore Longitudinal Study of Aging, the Human Connectome Project S1200 release, and scans acquired at Vanderbilt University.Results: The proposed framework identifies fiber bundles with high agreement against tractography‐based pathways with a median Dice coefficient from 0.62 to 0.87 on a test cohort, achieving improved subject‐specific accuracy when compared to population atlas‐based methods. We demonstrate the generalizability of the proposed framework on three externally available datasets.Conclusions: We show that patch‐wise convolutional neural network can achieve robust bundle segmentation from T1w. We envision the use of this framework for visualizing the expected course of WM pathways when dMRI is not available.