Yue Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yue Han has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Edward Delp
Department of Electrical and Computer Engineering and Department of Biomedical Engineering, Purdue University, West Lafayette, IN, USA
3 shared publications Daisy Xin
HP Labs, HP Inc
2 shared publicationsJan Allebach
Video and Image Processing Laboratory (VIPER), Purdue University; West Lafayette
2 shared publicationsSteven Barcelo
HP Labs, HP Inc
2 shared publicationsViktor Shkolnikov
HP Labs, HP Inc
2 shared publicationsYang Lei
HP Labs, HP Inc
2 shared publications
Latest Publications
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 61-69
Diffusion Model with Clustering-based Conditioning for Food Image Generation
Image-based dietary assessment serves as an efficient and accurate solution for recording and analyzing nutrition intake using eating occasion images as input. Deep learning-based techniques are commonly used to perform image analysis such as food classification, segmentation, and portion size estimation, which rely on large amounts of food images with annotations for training. However, such data dependency poses significant barriers to real-world applications, because acquiring a substantial, diverse, and balanced set of food images can be challenging. One potential solution is to use synthetic food images for data augmentation. Although existing work has explored the use of generative adversarial networks (GAN) based structures for generation, the quality of synthetic food images still remains subpar. In addition, while diffusion-based generative models have shown promising results for general image generation tasks, the generation of food images can be challenging due to the substantial intra-class variance. In this paper, we investigate the generation of synthetic food images based on the conditional diffusion model and propose an effective clustering-based training framework, named ClusDiff, for generating high-quality and representative food images. The proposed method is evaluated on the Food-101 dataset and shows improved performance when compared with existing image generation works. We also demonstrate that the synthetic food images generated by ClusDiff can help address the severe class imbalance issue in long-tailed food classification using the VFN-LT dataset.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 61-69
Open AccessDiffusion Model with Clustering-based Conditioning for Food Image Generation
Image-based dietary assessment serves as an efficient and accurate solution for recording and analyzing nutrition intake using eating occasion images as input. Deep learning-based techniques are commonly used to perform image analysis such as food classification, segmentation, and portion size estimation, which rely on large amounts of food images with annotations for training. However, such data dependency poses significant barriers to real-world applications, because acquiring a substantial, diverse, and balanced set of food images can be challenging. One potential solution is to use synthetic food images for data augmentation. Although existing work has explored the use of generative adversarial networks (GAN) based structures for generation, the quality of synthetic food images still remains subpar. In addition, while diffusion-based generative models have shown promising results for general image generation tasks, the generation of food images can be challenging due to the substantial intra-class variance. In this paper, we investigate the generation of synthetic food images based on the conditional diffusion model and propose an effective clustering-based training framework, named ClusDiff, for generating high-quality and representative food images. The proposed method is evaluated on the Food-101 dataset and shows improved performance when compared with existing image generation works. We also demonstrate that the synthetic food images generated by ClusDiff can help address the severe class imbalance issue in long-tailed food classification using the VFN-LT dataset.
- Open Access
Label-Free Mammalian Cell Tracking Enhanced by Precomputed Velocity Fields
Label-free cell imaging, where the cell is not “labeled” or modified by fluorescent chemicals, is an important research area in the field of biology. It avoids altering the cell’s properties which typically happens in the process of chemical labeling. However, without the contrast enhancement from the label, the analysis of label-free imaging is more challenging than label-based imaging. In addition, it provides few human interpretable features, and thus needs machine learning approaches to help with the identification and tracking of specific cells. We are interested in label-free phase contrast imaging to track cells flowing in a cell sorting device where images are acquired at 500 frames/s. Existing Multiple Object Tracking (MOT) methods face four major challenges when used for tracking cells in a microfluidic sorting device: (i) most of the cells have large displacements between frames without any overlap; (ii) it is difficult to distinguish between cells as they are visually similar to each other; (iii) the velocities of cells vary with the location in the device; (iv) the appearance of cells may change as they move in and out of the focal plane of the imaging sensor that observes the isolation process. In this paper, we introduce a method for tracking cells in a predefined flow in the sorting device via phase contrast microscopy. Our proposed method is based on DeepSORT and YOLOv4 and exploits prior knowledge of a cell’s velocity to assist tracking. We modify the Kalman filter in DeepSORT to accommodate a non-constant velocity motion model and integrate a representative velocity field obtained from fluid dynamics into the Kalman filter. The experimental results show that our proposed method outperforms several MOT methods for tracking cells in the sorting device.
Open AccessLabel-Free Mammalian Cell Tracking Enhanced by Precomputed Velocity Fields
Label-free cell imaging, where the cell is not “labeled” or modified by fluorescent chemicals, is an important research area in the field of biology. It avoids altering the cell’s properties which typically happens in the process of chemical labeling. However, without the contrast enhancement from the label, the analysis of label-free imaging is more challenging than label-based imaging. In addition, it provides few human interpretable features, and thus needs machine learning approaches to help with the identification and tracking of specific cells. We are interested in label-free phase contrast imaging to track cells flowing in a cell sorting device where images are acquired at 500 frames/s. Existing Multiple Object Tracking (MOT) methods face four major challenges when used for tracking cells in a microfluidic sorting device: (i) most of the cells have large displacements between frames without any overlap; (ii) it is difficult to distinguish between cells as they are visually similar to each other; (iii) the velocities of cells vary with the location in the device; (iv) the appearance of cells may change as they move in and out of the focal plane of the imaging sensor that observes the isolation process. In this paper, we introduce a method for tracking cells in a predefined flow in the sorting device via phase contrast microscopy. Our proposed method is based on DeepSORT and YOLOv4 and exploits prior knowledge of a cell’s velocity to assist tracking. We modify the Kalman filter in DeepSORT to accommodate a non-constant velocity motion model and integrate a representative velocity field obtained from fluid dynamics into the Kalman filter. The experimental results show that our proposed method outperforms several MOT methods for tracking cells in the sorting device.
- Open Access
Ensemble Processing and Synthetic Image Generation for Abnormally Shaped Nuclei Segmentation
Abnormalities in biological cell nuclei morphology are correlated with cell cycle stages, disease states, and various external stimuli. There have been many deep learning approaches that have described nuclei segmentation and analysis of nuclear morphology. One problem with many deep learning methods is acquiring large amounts of annotated nuclei data, which is generally expensive to obtain. In this paper, we propose a system to segment abnormally shaped nuclei with a limited amount of training data. We first generate specific shapes of synthetic nuclei groundtruth. We randomly sample these synthetic groundtruth images into training sets to train several Mask R-CNNs. We design an ensemble strategy to combine or fuse segmentation results from the Mask R-CNNs. We also design an oval nuclei removal by StarDist to reduce the false positives and improve the overall segmentation performance. Our experiments indicate that our method outperforms other methods in segmenting abnormally shaped nuclei.
Open AccessEnsemble Processing and Synthetic Image Generation for Abnormally Shaped Nuclei Segmentation
Abnormalities in biological cell nuclei morphology are correlated with cell cycle stages, disease states, and various external stimuli. There have been many deep learning approaches that have described nuclei segmentation and analysis of nuclear morphology. One problem with many deep learning methods is acquiring large amounts of annotated nuclei data, which is generally expensive to obtain. In this paper, we propose a system to segment abnormally shaped nuclei with a limited amount of training data. We first generate specific shapes of synthetic nuclei groundtruth. We randomly sample these synthetic groundtruth images into training sets to train several Mask R-CNNs. We design an ensemble strategy to combine or fuse segmentation results from the Mask R-CNNs. We also design an oval nuclei removal by StarDist to reduce the false positives and improve the overall segmentation performance. Our experiments indicate that our method outperforms other methods in segmenting abnormally shaped nuclei.
- Open Access
- 1 January 2021
- Published by Taylor & Francis in Drug Design, Development and Therapy
- Vol. ume 15, 323-330
CircNRIP1 Modulates the miR-515-5p/IL-25 Axis to Control 5-Fu and Cisplatin Resistance in Nasopharyngeal Carcinoma
Background: The development of drug resistance leads many NPC patients to experience disease relapse following the completion of chemotherapy. It is thus essential that the mechanistic basis for such chemoresistance be clarified in an effort to identify approaches to sensitizing NPC tumors to treatment with cisplatin and related agents. Methods: A qRT-PCR approach was used to measure the expression of circNRIP1 in NPC, while luciferase assays were used to identify interactions with downstream targets of circNRIP1 activity including miR-515-5p and IL-25. CCK8 assays were also utilized to detect IC50 values for cisplatin and 5-Fu. Results: The expression of circNRIP1 was significantly increased in the serum of chemoresistant NPC patients. At a functional level, we determined that circNRIP1 is able to sequester miR-515-5p, thereby inhibiting its ability to post-transcriptionally suppress IL-25 expression. We observed a significant negative correlation between the expression of miR-515-5p and circNRIP1 in serum samples from chemoresistant NPC patients, consistent with a functional interaction between these two factors. We further found that 5-Fu and CDDP IC50 values in NPC cells in which circNRIP1 had been knocked down were restored following miR-515-5p inhibitor transfection. Similarly, changes in these IC50 values were reversed in NPC cells transfected with miR-515-5p mimics following the overexpression of IL-25 in these same cells. Conclusion: These data highlight the circNRIP1/miR-515-5p/IL-25 as a novel regulator of 5-Fu and cisplatin resistance in NPC, suggesting that this pathway may be amenable to therapeutic targeting as an approach to treating this cancer type.
- 1 January 2021
- Published by Taylor & Francis in Drug Design, Development and Therapy
- Vol. ume 15, 323-330
Open AccessCircNRIP1 Modulates the miR-515-5p/IL-25 Axis to Control 5-Fu and Cisplatin Resistance in Nasopharyngeal Carcinoma
Background: The development of drug resistance leads many NPC patients to experience disease relapse following the completion of chemotherapy. It is thus essential that the mechanistic basis for such chemoresistance be clarified in an effort to identify approaches to sensitizing NPC tumors to treatment with cisplatin and related agents. Methods: A qRT-PCR approach was used to measure the expression of circNRIP1 in NPC, while luciferase assays were used to identify interactions with downstream targets of circNRIP1 activity including miR-515-5p and IL-25. CCK8 assays were also utilized to detect IC50 values for cisplatin and 5-Fu. Results: The expression of circNRIP1 was significantly increased in the serum of chemoresistant NPC patients. At a functional level, we determined that circNRIP1 is able to sequester miR-515-5p, thereby inhibiting its ability to post-transcriptionally suppress IL-25 expression. We observed a significant negative correlation between the expression of miR-515-5p and circNRIP1 in serum samples from chemoresistant NPC patients, consistent with a functional interaction between these two factors. We further found that 5-Fu and CDDP IC50 values in NPC cells in which circNRIP1 had been knocked down were restored following miR-515-5p inhibitor transfection. Similarly, changes in these IC50 values were reversed in NPC cells transfected with miR-515-5p mimics following the overexpression of IL-25 in these same cells. Conclusion: These data highlight the circNRIP1/miR-515-5p/IL-25 as a novel regulator of 5-Fu and cisplatin resistance in NPC, suggesting that this pathway may be amenable to therapeutic targeting as an approach to treating this cancer type.
- Open Access
- 9 July 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (7) , 1092
A Novel Object-Based Supervised Classification Method with Active Learning and Random Forest for PolSAR Imagery
Most of the traditional supervised classification methods using full-polarimetric synthetic aperture radar (PolSAR) imagery are dependent on sufficient training samples, whereas the results of pixel-based supervised classification methods show a high false alarm rate due to the influence of speckle noise. In this paper, to solve these problems, an object-based supervised classification method with an active learning (AL) method and random forest (RF) classifier is presented, which can enhance the classification performance for PolSAR imagery. The first step of the proposed method is used to reduce the influence of speckle noise through the generalized statistical region merging (GSRM) algorithm. A reliable training set is then selected from the different polarimetric features of the PolSAR imagery by the AL method. Finally, the RF classifier is applied to identify the different types of land cover in the three PolSAR images acquired by different sensors. The experimental results demonstrate that the proposed method can not only better suppress the influence of speckle noise, but can also significantly improve the overall accuracy and Kappa coefficient of the classification results, when compared with the traditional supervised classification methods.
- 9 July 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (7) , 1092
Open AccessA Novel Object-Based Supervised Classification Method with Active Learning and Random Forest for PolSAR Imagery
Most of the traditional supervised classification methods using full-polarimetric synthetic aperture radar (PolSAR) imagery are dependent on sufficient training samples, whereas the results of pixel-based supervised classification methods show a high false alarm rate due to the influence of speckle noise. In this paper, to solve these problems, an object-based supervised classification method with an active learning (AL) method and random forest (RF) classifier is presented, which can enhance the classification performance for PolSAR imagery. The first step of the proposed method is used to reduce the influence of speckle noise through the generalized statistical region merging (GSRM) algorithm. A reliable training set is then selected from the different polarimetric features of the PolSAR imagery by the AL method. Finally, the RF classifier is applied to identify the different types of land cover in the three PolSAR images acquired by different sensors. The experimental results demonstrate that the proposed method can not only better suppress the influence of speckle noise, but can also significantly improve the overall accuracy and Kappa coefficient of the classification results, when compared with the traditional supervised classification methods.