Xiang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiang Li has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Kyle J. Lafata
Department of Electrical and Computer Engineering, Duke University
3 shared publications - Laura Barisoni
Division of AI and Computational Pathology, Department of Pathology, Duke University, Durham, North Carolina
2 shared publications - Andrew Janowczyk
Department of Biomedical Engineering, Emory University and Georgia Institute of Technology
1 shared publication - Breylon A. Riley
Duke University, Medical Physics Graduate Program, Durham, North Carolina, United States
1 shared publication - Chunhao Wang
Department of Radiation Oncology Duke University Durham North Carolina USA
1 shared publication - David M. Brizel
Department of Head and Neck Surgery & Communication Sciences, Duke University School of Medicine, Durham, North Carolina, USA
1 shared publication
Latest Publications
- Open Access
- 1 September 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (05) , 057501-17
Characterization of arteriosclerosis based on computer-aided measurements of intra-arterial thickness
Previous studies have shown that the severity of arterio- and arteriolosclerosis is associated with the risk of kidney disease progression across various disease etiologies.1 – 3 Unlike atherosclerosis, which is a specific form of arterial thickening or hardening caused by atheroma plaque build-up in the inner lining of large arteries such as the carotid artery, arterio- and arteriolosclerosis affects medium- and small-sized arteries and arterioles within the kidney parenchyma. Arterio- and arteriolosclerosis, characterized by fibrous thickening of the intima and hypertrophy of the media, and arteriolar hyalinosis, a lesion of eosin and periodic acid–schiff (PAS)-positive amorphous material deposited in the vessel wall, are manifestations of chronic damage of kidney arteries and arterioles.4,5 Thus, the quantification of chronic vascular changes present in renal biopsies is relevant to the diagnosis and prognostication of kidney failure and to informing treatment selection.5 – 7 In clinical practice, biopsies are visually inspected to semi-quantitatively assess the extent of intima and media thickening.5 However, this approach may be influenced by inherent cognitive and visual biases,8 with the precision and accuracy of these observations limited by high inter- and intra-observer variability.9 – 12
- 1 September 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (05) , 057501-17
Open AccessCharacterization of arteriosclerosis based on computer-aided measurements of intra-arterial thickness
Previous studies have shown that the severity of arterio- and arteriolosclerosis is associated with the risk of kidney disease progression across various disease etiologies.1 – 3 Unlike atherosclerosis, which is a specific form of arterial thickening or hardening caused by atheroma plaque build-up in the inner lining of large arteries such as the carotid artery, arterio- and arteriolosclerosis affects medium- and small-sized arteries and arterioles within the kidney parenchyma. Arterio- and arteriolosclerosis, characterized by fibrous thickening of the intima and hypertrophy of the media, and arteriolar hyalinosis, a lesion of eosin and periodic acid–schiff (PAS)-positive amorphous material deposited in the vessel wall, are manifestations of chronic damage of kidney arteries and arterioles.4,5 Thus, the quantification of chronic vascular changes present in renal biopsies is relevant to the diagnosis and prognostication of kidney failure and to informing treatment selection.5 – 7 In clinical practice, biopsies are visually inspected to semi-quantitatively assess the extent of intima and media thickening.5 However, this approach may be influenced by inherent cognitive and visual biases,8 with the precision and accuracy of these observations limited by high inter- and intra-observer variability.9 – 12
- 1 March 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (02) , 024007-15
Prognostic value of different discretization parameters in 18fluorodeoxyglucose positron emission tomography radiomics of oropharyngeal squamous cell carcinoma
PurposeWe aim to interrogate the role of positron emission tomography (PET) image discretization parameters on the prognostic value of radiomic features in patients with oropharyngeal cancer.ApproachA prospective clinical trial (NCT01908504) enrolled patients with oropharyngeal squamous cell carcinoma (N=69; mixed HPV status) undergoing definitive radiotherapy and evaluated intra-treatment 18fluorodeoxyglucose PET as a potential imaging biomarker of early metabolic response. The primary tumor volume was manually segmented by a radiation oncologist on PET/CT images acquired two weeks into treatment (20 Gy). From this, 54 radiomic texture features were extracted. Two image discretization techniques—fixed bin number (FBN) and fixed bin size (FBS)—were considered to evaluate systematic changes in the bin number ({32, 64, 128, 256} gray levels) and bin size ({0.10, 0.15, 0.22, 0.25} bin-widths). For each discretization-specific radiomic feature space, an LASSO-regularized logistic regression model was independently trained to predict residual and/or recurrent disease. The model training was based on Monte Carlo cross-validation with a 20% testing hold-out, 50 permutations, and minor-class up-sampling to account for imbalanced outcomes data. Performance differences among the discretization-specific models were quantified via receiver operating characteristic curve analysis. A final parameter-optimized logistic regression model was developed by incorporating different settings parameterizations into the same model.ResultsFBN outperformed FBS in predicting residual and/or recurrent disease. The four FBN models achieved AUC values of 0.63, 0.61, 0.65, and 0.62 for 32, 64, 128, and 256 gray levels, respectively. By contrast, the average AUC of the four FBS models was 0.53. The parameter-optimized model, comprising features joint entropy (FBN = 64) and information measure correlation 1 (FBN = 128), achieved an AUC of 0.70. Kaplan–Meier analyses identified these features to be associated with disease-free survival (p=0.0158 and p=0.0180, respectively; log-rank test).ConclusionsOur findings suggest that the prognostic value of individual radiomic features may depend on feature-specific discretization parameter settings.
- 1 March 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (02) , 024007-15
Prognostic value of different discretization parameters in 18fluorodeoxyglucose positron emission tomography radiomics of oropharyngeal squamous cell carcinoma
PurposeWe aim to interrogate the role of positron emission tomography (PET) image discretization parameters on the prognostic value of radiomic features in patients with oropharyngeal cancer.ApproachA prospective clinical trial (NCT01908504) enrolled patients with oropharyngeal squamous cell carcinoma (N=69; mixed HPV status) undergoing definitive radiotherapy and evaluated intra-treatment 18fluorodeoxyglucose PET as a potential imaging biomarker of early metabolic response. The primary tumor volume was manually segmented by a radiation oncologist on PET/CT images acquired two weeks into treatment (20 Gy). From this, 54 radiomic texture features were extracted. Two image discretization techniques—fixed bin number (FBN) and fixed bin size (FBS)—were considered to evaluate systematic changes in the bin number ({32, 64, 128, 256} gray levels) and bin size ({0.10, 0.15, 0.22, 0.25} bin-widths). For each discretization-specific radiomic feature space, an LASSO-regularized logistic regression model was independently trained to predict residual and/or recurrent disease. The model training was based on Monte Carlo cross-validation with a 20% testing hold-out, 50 permutations, and minor-class up-sampling to account for imbalanced outcomes data. Performance differences among the discretization-specific models were quantified via receiver operating characteristic curve analysis. A final parameter-optimized logistic regression model was developed by incorporating different settings parameterizations into the same model.ResultsFBN outperformed FBS in predicting residual and/or recurrent disease. The four FBN models achieved AUC values of 0.63, 0.61, 0.65, and 0.62 for 32, 64, 128, and 256 gray levels, respectively. By contrast, the average AUC of the four FBS models was 0.53. The parameter-optimized model, comprising features joint entropy (FBN = 64) and information measure correlation 1 (FBN = 128), achieved an AUC of 0.70. Kaplan–Meier analyses identified these features to be associated with disease-free survival (p=0.0158 and p=0.0180, respectively; log-rank test).ConclusionsOur findings suggest that the prognostic value of individual radiomic features may depend on feature-specific discretization parameter settings.
- 20 December 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 8 (06) , 067501-18
Deep learning segmentation of glomeruli on kidney donor frozen sections
Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution (n = 123) and at external institutions (n = 135) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (ratio: 0.8:0.2), and external WSIs were used as an independent testing dataset. Nonsclerotic (n = 22767) and sclerotic (n = 1366) glomeruli were manually annotated by study pathologists on all WSIs. A nine-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of nonsclerotic and sclerotic glomeruli. DL-derived, manual segmentation, and reported glomerular count (standard of care) were compared. Results: The average Dice similarity coefficient testing was 0.90 and 0.83. And the F1, recall, and precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for nonsclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation-derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. We represent the first step toward new protocols for the evaluation of donor kidney biopsies.
- 20 December 2021
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 8 (06) , 067501-18
Deep learning segmentation of glomeruli on kidney donor frozen sections
Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution (n = 123) and at external institutions (n = 135) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (ratio: 0.8:0.2), and external WSIs were used as an independent testing dataset. Nonsclerotic (n = 22767) and sclerotic (n = 1366) glomeruli were manually annotated by study pathologists on all WSIs. A nine-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of nonsclerotic and sclerotic glomeruli. DL-derived, manual segmentation, and reported glomerular count (standard of care) were compared. Results: The average Dice similarity coefficient testing was 0.90 and 0.83. And the F1, recall, and precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for nonsclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation-derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. We represent the first step toward new protocols for the evaluation of donor kidney biopsies.