Tzu-Hsi Song
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
Research Subjects
Tzu-Hsi Song has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
Hesham Eidaly
Addenbrookes Hospital
2 shared publicationsNasir M. Rajpoot
2 shared publicationsVictor Sanchez
University of Warwick
2 shared publicationsAnat O. Stemmer‐Rachamimov
Department of Pathology Massachusetts General Hospital and Harvard Medical School Boston Massachusetts USA
1 shared publicationCaleb Hallinan
Vascular Biology Program Boston Children's Hospital Boston Massachusetts USA
1 shared publication- Gabriel Landini
School of Dentistry, College of Medical and Dental Sciences, University of Birmingham, 5 Mill Pool Way, Edgbaston, Birmingham B5 7EG, UK
1 shared publication
Latest Publications
- Open Access
- 23 July 2025
- Published by AIP Publishing in APL Bioengineering
- Vol. 9 (3) , 036107
Diffraction-informed deep learning for molecular-specific holograms of breast cancer cells
Lens-free digital in-line holography (LDIH) provides a large field-of-view at micrometer-scale resolution, making it a promising tool for high-throughput cellular analysis. However, the complexity of diffraction images (holograms) produced by LDIH presents challenges for human interpretation and requires time-consuming computational reconstruction, often leading to artifacts and information loss. To address these issues, we present HoloNet, a novel deep learning architecture specifically designed for direct analysis of diffraction images in cellular diagnostics. Tailored to the unique characteristics of diffraction images, HoloNet captures multi-scale features, enabling it to outperform conventional convolutional neural networks in recognizing well-defined regions within complex holograms. HoloNet classifies breast cancer cell types with high precision and quantifies molecular marker intensities using raw diffraction images of cells stained with ER/PR and HER2. Additionally, HoloNet has proven effective in transfer learning applications, accurately classifying breast cancer cell lines and discovering previously unidentified subtypes through unsupervised learning. By integrating computational imaging with deep learning, HoloNet offers a robust solution to the challenges of holographic data analysis, significantly improving the accuracy and explainability of cellular diagnostics.
- 23 July 2025
- Published by AIP Publishing in APL Bioengineering
- Vol. 9 (3) , 036107
Open AccessDiffraction-informed deep learning for molecular-specific holograms of breast cancer cells
Lens-free digital in-line holography (LDIH) provides a large field-of-view at micrometer-scale resolution, making it a promising tool for high-throughput cellular analysis. However, the complexity of diffraction images (holograms) produced by LDIH presents challenges for human interpretation and requires time-consuming computational reconstruction, often leading to artifacts and information loss. To address these issues, we present HoloNet, a novel deep learning architecture specifically designed for direct analysis of diffraction images in cellular diagnostics. Tailored to the unique characteristics of diffraction images, HoloNet captures multi-scale features, enabling it to outperform conventional convolutional neural networks in recognizing well-defined regions within complex holograms. HoloNet classifies breast cancer cell types with high precision and quantifies molecular marker intensities using raw diffraction images of cells stained with ER/PR and HER2. Additionally, HoloNet has proven effective in transfer learning applications, accurately classifying breast cancer cell lines and discovering previously unidentified subtypes through unsupervised learning. By integrating computational imaging with deep learning, HoloNet offers a robust solution to the challenges of holographic data analysis, significantly improving the accuracy and explainability of cellular diagnostics.
- Open Access
- 27 January 2025
- Published by Wiley in Journal of Extracellular Vesicles
- Vol. 14 (1) , e70038
Breast Cancer‐Derived Extracellular Vesicles Modulate the Cytoplasmic and Cytoskeletal Dynamics of Blood‐Brain Barrier Endothelial Cells
Extracellular vesicles (EVs) from brain‐seeking breast cancer cells (Br‐EVs) breach the blood‐brain barrier (BBB) via transcytosis and promote brain metastasis. Here, we defined the mechanisms by which Br‐EVs modulate brain endothelial cell (BEC) dynamics to facilitate their BBB transcytosis. BEC treated with Br‐EVs show significant downregulation of Rab11fip2, known to promote vesicle recycling to the plasma membrane and significant upregulation of Rab11fip3 and Rab11fip5, which support structural stability of the endosomal compartment and facilitate vesicle recycling and transcytosis, respectively. Using machine learning and quantitative global proteomic, we identified novel Br‐EV‐induced changes in BECs morphology, motility, and proteome that correlate with decreased BEC cytoplasm and cytoskeletal organization and dynamics. These results define early steps leading to breast‐to‐brain metastasis and identify molecules that could serve as targets for therapeutic strategies for brain metastasis.
- 27 January 2025
- Published by Wiley in Journal of Extracellular Vesicles
- Vol. 14 (1) , e70038
Open AccessBreast Cancer‐Derived Extracellular Vesicles Modulate the Cytoplasmic and Cytoskeletal Dynamics of Blood‐Brain Barrier Endothelial Cells
Extracellular vesicles (EVs) from brain‐seeking breast cancer cells (Br‐EVs) breach the blood‐brain barrier (BBB) via transcytosis and promote brain metastasis. Here, we defined the mechanisms by which Br‐EVs modulate brain endothelial cell (BEC) dynamics to facilitate their BBB transcytosis. BEC treated with Br‐EVs show significant downregulation of Rab11fip2, known to promote vesicle recycling to the plasma membrane and significant upregulation of Rab11fip3 and Rab11fip5, which support structural stability of the endosomal compartment and facilitate vesicle recycling and transcytosis, respectively. Using machine learning and quantitative global proteomic, we identified novel Br‐EV‐induced changes in BECs morphology, motility, and proteome that correlate with decreased BEC cytoplasm and cytoskeletal organization and dynamics. These results define early steps leading to breast‐to‐brain metastasis and identify molecules that could serve as targets for therapeutic strategies for brain metastasis.
- 31 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 23 (4) , 1469-1476
Simultaneous Cell Detection and Classification in Bone Marrow Histology Images
Recently, deep learning frameworks have been shown to be successful and efficient in processing digital histology images for various detection and classification tasks. Among these tasks, cell detection and classification are key steps in many computer-assisted diagnosis systems. Traditionally, cell detection and classification is performed as a sequence of two consecutive steps by using two separate deep learning networks: one for detection and the other for classification. This strategy inevitably increases the computational complexity of the training stage. In this paper, we propose a synchronized deep autoencoder network for simultaneous detection and classification of cells in bone marrow histology images. The proposed network uses a single architecture to detect the positions of cells and classify the detected cells, in parallel. It uses a curve-support Gaussian model to compute probability maps that allow detecting irregularly shape cells precisely. Moreover, the network includes a novel neighborhood selection mechanism to boost the classification accuracy. We show that the performance of the proposed network is superior than traditional deep learning detection methods and very competitive compared to traditional deep learning classification networks. Runtime comparison also shows that our network requires less time to be trained.
- 31 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 23 (4) , 1469-1476
Simultaneous Cell Detection and Classification in Bone Marrow Histology Images
Recently, deep learning frameworks have been shown to be successful and efficient in processing digital histology images for various detection and classification tasks. Among these tasks, cell detection and classification are key steps in many computer-assisted diagnosis systems. Traditionally, cell detection and classification is performed as a sequence of two consecutive steps by using two separate deep learning networks: one for detection and the other for classification. This strategy inevitably increases the computational complexity of the training stage. In this paper, we propose a synchronized deep autoencoder network for simultaneous detection and classification of cells in bone marrow histology images. The proposed network uses a single architecture to detect the positions of cells and classify the detected cells, in parallel. It uses a curve-support Gaussian model to compute probability maps that allow detecting irregularly shape cells precisely. Moreover, the network includes a novel neighborhood selection mechanism to boost the classification accuracy. We show that the performance of the proposed network is superior than traditional deep learning detection methods and very competitive compared to traditional deep learning classification networks. Runtime comparison also shows that our network requires less time to be trained.
- 22 June 2017
- Published by Springer Nature
- p. 829-838
Simultaneous Cell Detection and Classification with an Asymmetric Deep Autoencoder in Bone Marrow Histology Images
- 22 June 2017
- Published by Springer Nature
- p. 829-838
Simultaneous Cell Detection and Classification with an Asymmetric Deep Autoencoder in Bone Marrow Histology Images
- 4 April 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 64 (12) , 2913-2923
Dual-Channel Active Contour Model for Megakaryocytic Cell Segmentation in Bone Marrow Trephine Histology Images
Assessment of morphological features of megakaryocytes (MKs) (special kind of cells) in bone marrow trephine biopsies play an important role in the classification of different subtypes of Philadelphia-chromosome-negative myeloproliferative neoplasms (Ph-negative MPNs). In order to aid hematopathologists in the study of MKs, we propose a novel framework that can efficiently delineate the nuclei and cytoplasm of these cells in digitized images of bone marrow trephine biopsies. The framework first employs a supervised machine learning approach that utilizes color and texture features to delineate megakaryocytic nuclei. It then employs a novel dual-channel active contour model to delineate the boundary of megakaryocytic cytoplasm by using different deconvolved stain channels. Compared to other recent models, the proposed framework achieves accurate results for both megakaryocytic nuclear and cytoplasmic delineation.
- 4 April 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 64 (12) , 2913-2923
Dual-Channel Active Contour Model for Megakaryocytic Cell Segmentation in Bone Marrow Trephine Histology Images
Assessment of morphological features of megakaryocytes (MKs) (special kind of cells) in bone marrow trephine biopsies play an important role in the classification of different subtypes of Philadelphia-chromosome-negative myeloproliferative neoplasms (Ph-negative MPNs). In order to aid hematopathologists in the study of MKs, we propose a novel framework that can efficiently delineate the nuclei and cytoplasm of these cells in digitized images of bone marrow trephine biopsies. The framework first employs a supervised machine learning approach that utilizes color and texture features to delineate megakaryocytic nuclei. It then employs a novel dual-channel active contour model to delineate the boundary of megakaryocytic cytoplasm by using different deconvolved stain channels. Compared to other recent models, the proposed framework achieves accurate results for both megakaryocytic nuclear and cytoplasmic delineation.