Search

Your search keyword '"Chan, Ronald"' showing total 144 results
Start Over Author "Chan, Ronald" Publication Year Range Last 3 years
144 results on '"Chan, Ronald"'

1. Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation

Author

Ma, Jiabo, Guo, Zhengrui, Zhou, Fengtao, Wang, Yihui, Xu, Yingxue, Cai, Yu, Zhu, Zhengjie, Jin, Cheng, Lin, Yi, Jiang, Xinrui, Han, Anjia, Liang, Li, Chan, Ronald Cheong Kin, Wang, Jiguang, Cheng, Kwang-Ting, and Chen, Hao

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath). The generalization ability of foundation models is crucial for the success in various downstream clinical tasks. However, current foundation models have only been evaluated on a limited type and number of tasks, leaving their generalization ability and overall performance unclear. To address this gap, we established a most comprehensive benchmark to evaluate the performance of off-the-shelf foundation models across six distinct clinical task types, encompassing a total of 39 specific tasks. Our findings reveal that existing foundation models excel at certain task types but struggle to effectively handle the full breadth of clinical tasks. To improve the generalization of pathology foundation models, we propose a unified knowledge distillation framework consisting of both expert and self knowledge distillation, where the former allows the model to learn from the knowledge of multiple expert models, while the latter leverages self-distillation to enable image representation learning via local-global alignment. Based on this framework, a Generalizable Pathology Foundation Model (GPFM) is pretrained on a large-scale dataset consisting of 190 million images from around 86,000 public H&E whole slides across 34 major tissue types. Evaluated on the established benchmark, GPFM achieves an impressive average rank of 1.36, with 29 tasks ranked 1st, while the the second-best model, UNI, attains an average rank of 2.96, with only 4 tasks ranked 1st. The superior generalization of GPFM demonstrates its exceptional modeling capabilities across a wide range of clinical tasks, positioning it as a new cornerstone for feature representation in CPath.

Published
2024

2. A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model

Author

Xu, Yingxue, Wang, Yihui, Zhou, Fengtao, Ma, Jiabo, Yang, Shu, Lin, Huangjing, Wang, Xin, Wang, Jiguang, Liang, Li, Han, Anjia, Chan, Ronald Cheong Kin, and Chen, Hao

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Remarkable strides in computational pathology have been made in the task-agnostic foundation model that advances the performance of a wide array of downstream clinical tasks. Despite the promising performance, there are still several challenges. First, prior works have resorted to either vision-only or vision-captions data, disregarding invaluable pathology reports and gene expression profiles which respectively offer distinct knowledge for versatile clinical applications. Second, the current progress in pathology FMs predominantly concentrates on the patch level, where the restricted context of patch-level pretraining fails to capture whole-slide patterns. Here we curated the largest multimodal dataset consisting of H\&E diagnostic whole slide images and their associated pathology reports and RNA-Seq data, resulting in 26,169 slide-level modality pairs from 10,275 patients across 32 cancer types. To leverage these data for CPath, we propose a novel whole-slide pretraining paradigm which injects multimodal knowledge at the whole-slide context into the pathology FM, called Multimodal Self-TAught PRetraining (mSTAR). The proposed paradigm revolutionizes the workflow of pretraining for CPath, which enables the pathology FM to acquire the whole-slide context. To our knowledge, this is the first attempt to incorporate multimodal knowledge at the slide level for enhancing pathology FMs, expanding the modelling context from unimodal to multimodal knowledge and from patch-level to slide-level. To systematically evaluate the capabilities of mSTAR, extensive experiments including slide-level unimodal and multimodal applications, are conducted across 7 diverse types of tasks on 43 subtasks, resulting in the largest spectrum of downstream tasks. The average performance in various slide-level applications consistently demonstrates significant performance enhancements for mSTAR compared to SOTA FMs., Comment: 45 pages, 9 figures

Published
2024

3. GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration

Author

He, Sunan, Nie, Yuxiang, Wang, Hongmei, Yang, Shu, Wang, Yihui, Cai, Zhiyuan, Chen, Zhixuan, Xu, Yingxue, Luo, Luyang, Xiang, Huiling, Lin, Xi, Wu, Mingxiang, Peng, Yifan, Shih, George, Xu, Ziyang, Wu, Xian, Wang, Qiong, Chan, Ronald Cheong Kin, Vardhanabhuti, Varut, Chu, Winnie Chiu Wing, Zheng, Yefeng, Rajpurkar, Pranav, Zhang, Kang, and Chen, Hao

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Computation and Language
Abstract

Generalist foundation models (GFMs) are renowned for their exceptional capability and flexibility in effectively generalizing across diverse tasks and modalities. In the field of medicine, while GFMs exhibit superior generalizability based on their extensive intrinsic knowledge as well as proficiency in instruction following and in-context learning, specialist models excel in precision due to their domain knowledge. In this work, for the first time, we explore the synergy between the GFM and specialist models, to enable precise medical image analysis on a broader scope. Specifically, we propose a cooperative framework, Generalist-Specialist Collaboration (GSCo), which consists of two stages, namely the construction of GFM and specialists, and collaborative inference on downstream tasks. In the construction stage, we develop MedDr, the largest open-source GFM tailored for medicine, showcasing exceptional instruction-following and in-context learning capabilities. Meanwhile, a series of lightweight specialists are crafted for downstream tasks with low computational cost. In the collaborative inference stage, we introduce two cooperative mechanisms, Mixture-of-Expert Diagnosis and Retrieval-Augmented Diagnosis, to harvest the generalist's in-context learning abilities alongside the specialists' domain expertise. For a comprehensive evaluation, we curate a large-scale benchmark featuring 28 datasets and about 250,000 images. Extensive results demonstrate that MedDr consistently outperforms state-of-the-art GFMs on downstream datasets. Furthermore, GSCo exceeds both GFMs and specialists across all out-of-domain disease diagnosis datasets. These findings indicate a significant paradigm shift in the application of GFMs, transitioning from separate models for specific tasks to a collaborative approach between GFMs and specialists, thereby advancing the frontiers of generalizable AI in medicine.

Published
2024

4. iMD4GC: Incomplete Multimodal Data Integration to Advance Precise Treatment Response Prediction and Survival Analysis for Gastric Cancer

Author

Zhou, Fengtao, Xu, Yingxue, Cui, Yanfen, Zhang, Shenyan, Zhu, Yun, He, Weiyang, Wang, Jiguang, Wang, Xin, Chan, Ronald, Lau, Louis Ho Shing, Han, Chu, Zhang, Dafu, Li, Zhenhui, and Chen, Hao

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Gastric cancer (GC) is a prevalent malignancy worldwide, ranking as the fifth most common cancer with over 1 million new cases and 700 thousand deaths in 2020. Locally advanced gastric cancer (LAGC) accounts for approximately two-thirds of GC diagnoses, and neoadjuvant chemotherapy (NACT) has emerged as the standard treatment for LAGC. However, the effectiveness of NACT varies significantly among patients, with a considerable subset displaying treatment resistance. Ineffective NACT not only leads to adverse effects but also misses the optimal therapeutic window, resulting in lower survival rate. However, existing multimodal learning methods assume the availability of all modalities for each patient, which does not align with the reality of clinical practice. The limited availability of modalities for each patient would cause information loss, adversely affecting predictive accuracy. In this study, we propose an incomplete multimodal data integration framework for GC (iMD4GC) to address the challenges posed by incomplete multimodal data, enabling precise response prediction and survival analysis. Specifically, iMD4GC incorporates unimodal attention layers for each modality to capture intra-modal information. Subsequently, the cross-modal interaction layers explore potential inter-modal interactions and capture complementary information across modalities, thereby enabling information compensation for missing modalities. To evaluate iMD4GC, we collected three multimodal datasets for GC study: GastricRes (698 cases) for response prediction, GastricSur (801 cases) for survival analysis, and TCGA-STAD (400 cases) for survival analysis. The scale of our datasets is significantly larger than previous studies. The iMD4GC achieved impressive performance with an 80.2% AUC on GastricRes, 71.4% C-index on GastricSur, and 66.1% C-index on TCGA-STAD, significantly surpassing other compared methods., Comment: 27 pages, 9 figures, 3 tables (under review)

Published
2024

5. Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions

Author

Luo, Luyang, Wang, Xi, Lin, Yi, Ma, Xiaoqi, Tan, Andong, Chan, Ronald, Vardhanabhuti, Varut, Chu, Winnie CW, Cheng, Kwang-Ting, and Chen, Hao

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Breast cancer has reached the highest incidence rate worldwide among all malignancies since 2020. Breast imaging plays a significant role in early diagnosis and intervention to improve the outcome of breast cancer patients. In the past decade, deep learning has shown remarkable progress in breast cancer imaging analysis, holding great promise in interpreting the rich information and complex context of breast imaging modalities. Considering the rapid improvement in deep learning technology and the increasing severity of breast cancer, it is critical to summarize past progress and identify future challenges to be addressed. This paper provides an extensive review of deep learning-based breast cancer imaging research, covering studies on mammogram, ultrasound, magnetic resonance imaging, and digital pathology images over the past decade. The major deep learning methods and applications on imaging-based screening, diagnosis, treatment response prediction, and prognosis are elaborated and discussed. Drawn from the findings of this survey, we present a comprehensive discussion of the challenges and potential avenues for future research in deep learning-based breast cancer imaging., Comment: IEEE RBME 2024

Published
2023

6. Deep Learning for Computational Cytology: A Survey

Author

Jiang, Hao, Zhou, Yanning, Lin, Yi, Chan, Ronald CK, Liu, Jiang, and Chen, Hao

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Computational cytology is a critical, rapid-developing, yet challenging topic in the field of medical image computing which analyzes the digitized cytology image by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) algorithms have made significant progress in medical image analysis, leading to the boosting publications of cytological studies. To investigate the advanced methods and comprehensive applications, we survey more than 120 publications of DL-based cytology image analysis in this article. We first introduce various deep learning methods, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize the public datasets, evaluation metrics, versatile cytology image analysis applications including classification, detection, segmentation, and other related tasks. Finally, we discuss current challenges and potential research directions of computational cytology.

Published
2022
Full Text
View/download PDF

7. Transurethral En Bloc Resection Versus Standard Resection of Bladder Tumour: A Randomised, Multicentre, Phase 3 Trial

Author

Yuen-Chun Teoh, Jeremy, Cheng, Cheung-Hing, Tsang, Chiu-Fung, Kai-Man Li, Joseph, Kwun-Chung Cheng, Bryan, Hoi-Chak Chan, Wilson, Kwun-Wai Chan, Wayne, Churk-Fai Li, Trevor, Chiu, Yi, Law, Man-Chung, Lok-Hei Leung, Clarence, Sze-Ho Ho, Brian, Yue-Kit Lee, Chris, Cheong-Kin Chan, Ronald, Shu-Yin Chan, Eddie, Chan, Marco Tsz-Yeung, Hok-Leung Tsu, James, Tam, Ho-Man, Lam, Kin-Man, So, Hing-Shing, Cho, Chak-Lam, Ng, Chi-Man, Chan, Chun-Ki, Liu, Pak-Ling, Wing-Hong Chu, Ringo, Tsui-Lin Ng, Ada, Chu, Sau-Kwan, Yee, Chi-Hang, Yiu, Ming-Kwong, Lo, Ka-Lun, Au, Wing-Hang, Ma, Wai-Kit, Ka-Fung Chiu, Peter, Sze-Wan Kwok, Hilda, Yip, Siu-Ying, Leung, Chi-Ho, and Ng, Chi-Fai

Published
2024
Full Text
View/download PDF

13. Using brain cell-type-specific protein interactomes to interpret neurodevelopmental genetic signals in schizophrenia

Author

Ripke, Stephan, Neale, Benjamin M., Corvin, Aiden, Walters, James T.R., Farh, Kai-How, Holmans, Peter A., Lee, Phil, Bulik-Sullivan, Brendan, Collier, David A., Huang, Hailiang, Pers, Tune H., Agartz, Ingrid, Agerbo, Esben, Albus, Margot, Alexander, Madeline, Amin, Farooq, Bacanu, Silviu A., Begemann, Martin, Belliveau, Richard A., Jr., Bene, Judit, Bergen, Sarah E., Bevilacqua, Elizabeth, Bigdeli, Tim B., Black, Donald W., Bruggeman, Richard, Buccola, Nancy G., Buckner, Randy L., Byerley, William, Cahn, Wiepke, Cai, Guiqing, Campion, Dominique, Cantor, Rita M., Carr, Vaughan J., Carrera, Noa, Catts, Stanley V., Chambert, Kimberley D., Chan, Raymond C.K., Chan, Ronald Y.L., Chen, Eric Y.H., Cheng, Wei, Cheung, Eric FC., Chong, Siow Ann, Cloninger, C. Robert, Cohen, David, Cohen, Nadine, Cormican, Paul, Craddock, Nick, Crowley, James J., Curtis, David, Davidson, Michael, Davis, Kenneth L., Degenhardt, Franziska, Del Favero, Jurgen, Demontis, Ditte, Dikeos, Dimitris, Dinan, Timothy, Djurovic, Srdjan, Donohoe, Gary, Drapeau, Elodie, Duan, Jubao, Dudbridge, Frank, Durmishi, Naser, Eichhammer, Peter, Eriksson, Johan, Escott-Price, Valentina, Essioux, Laurent, Fanous, Ayman H., Farrell, Martilias S., Frank, Josef, Franke, Lude, Freedman, Robert, Freimer, Nelson B., Friedl, Marion, Friedman, Joseph I., Fromer, Menachem, Genovese, Giulio, Georgieva, Lyudmila, Giegling, Ina, Giusti-Rodríguez, Paola, Godard, Stephanie, Goldstein, Jacqueline I., Golimbet, Vera, Gopal, Srihari, Gratten, Jacob, de Haan, Lieuwe, Hammer, Christian, Hamshere, Marian L., Hansen, Mark, Hansen, Thomas, Haroutunian, Vahram, Hartmann, Annette M., Henskens, Frans A., Herms, Stefan, Hirschhorn, Joel N., Hoffmann, Per, Hofman, Andrea, Hollegaard, Mads V., Hougaard, David M., Ikeda, Masashi, Joa, Inge, Julià, Antonio, Kahn, René S., Kalaydjieva, Luba, Karachanak-Yankova, Sena, Karjalainen, Juha, Kavanagh, David, Keller, Matthew C., Kennedy, James L., Khrunin, Andrey, Kim, Yunjung, Klovins, Janis, Knowles, James A., Konte, Bettina, Kucinskas, Vaidutis, Kucinskiene, Zita Ausrele, Kuzelova-Ptackova, Hana, Kähler, Anna K., Laurent, Claudine, Lee, Jimmy, Lee, S. Hong, Legge, Sophie E., Lerer, Bernard, Li, Miaoxin, Li, Tao, Liang, Kung-Yee, Lieberman, Jeffrey, Limborska, Svetlana, Loughland, Carmel M., Lubinski, Jan, Lönnqvist, Jouko, Macek, Milan, Magnusson, Patrik K.E., Maher, Brion S., Maier, Wolfgang, Mallet, Jacques, Marsal, Sara, Mattheisen, Manuel, Mattingsdal, Morten, McCarley, Robert W., McDonald, Colm, McIntosh, Andrew M., Meier, Sandra, Meijer, Carin J., Melegh, Bela, Melle, Ingrid, Mesholam-Gately, Raquelle I., Metspalu, Andres, Michie, Patricia T., Milani, Lili, Milanova, Vihra, Mokrab, Younes, Morris, Derek W., Mors, Ole, Murphy, Kieran C., Murray, Robin M., Myin-Germeys, Inez, Müller-Myhsok, Bertram, Nelis, Mari, Nenadic, Igor, Nertney, Deborah A., Nestadt, Gerald, Nicodemus, Kristin K., Nikitina-Zake, Liene, Nisenbaum, Laura, Nordin, Annelie, O'Callaghan, Eadbhard, O'Dushlaine, Colm, O'Neill, F. Anthony, Oh, Sang-Yun, Olincy, Ann, Olsen, Line, Van Os, Jim, Pantelis, Christos, Papadimitriou, George N., Papiol, Sergi, Parkhomenko, Elena, Pato, Michele T., Paunio, Tiina, Pejovic-Milovancevic, Milica, Perkins, Diana O., Pietiläinen, Olli, Pimm, Jonathan, Pocklington, Andrew J., Powell, John, Price, Alkes, Pulver, Ann E., Purcell, Shaun M., Quested, Digby, Rasmussen, Henrik B., Reichenberg, Abraham, Reimers, Mark A., Richards, Alexander L., Roffman, Joshua L., Roussos, Panos, Ruderfer, Douglas M., Salomaa, Veikko, Sanders, Alan R., Schall, Ulrich, Schubert, Christian R., Schulze, Thomas G., Schwab, Sibylle G., Scolnick, Edward M., Scott, Rodney J., Seidman, Larry J., Shi, Jianxin, Sigurdsson, Engilbert, Silagadze, Teimuraz, Silverman, Jeremy M., Sim, Kang, Slominsky, Petr, Smoller, Jordan W., So, Hon-Cheong, Spencer, Chris C.A., Stahl, Eli A., Stefansson, Hreinn, Steinberg, Stacy, Stogmann, Elisabeth, Straub, Richard E., Strengman, Eric, Strohmaier, Jana, Stroup, T Scott, Subramaniam, Mythily, Suvisaari, Jaana, Svrakic, Dragan M., Szatkiewicz, Jin P., Söderman, Erik, Thirumalai, Srinivas, Toncheva, Draga, Tosato, Sarah, Veijola, Juha, Waddington, John, Walsh, Dermot, Wang, Dai, Wang, Qiang, Webb, Bradley T., Weiser, Mark, Wildenauer, Dieter B., Williams, Nigel M., Williams, Stephanie, Witt, Stephanie H., Wolen, Aaron R., Wong, Emily H.M., Wormley, Brandon K., Xi, Hualin Simon, Zai, Clement C., Zheng, Xuebin, Zimprich, Fritz, Wray, Naomi R., Stefansson, Kari, Visscher, Peter M., Adolfsson, Rolf, Andreassen, Ole A., Blackwood, Douglas H.R., Bramon, Elvira, Buxbaum, Joseph D., Børglum, Anders D., Cichon, Sven, Darvasi, Ariel, Domenici, Enrico, Ehrenreich, Hannelore, Esko, Tõnu, Gejman, Pablo V., Gill, Michael, Gurling, Hugh, Hultman, Christina M., Iwata, Nakao, Jablensky, Assen V., Jönsson, Erik G., Kendler, Kenneth S., Kirov, George, Knight, Jo, Lencz, Todd, Levinson, Douglas F., Li, Qingqin S., Liu, Jianjun, Malhotra, Anil K., McCarroll, Steven A., McQuillin, Andrew, Moran, Jennifer L., Mortensen, Preben B., Mowry, Bryan J., Nöthen, Markus M., Ophoff, Roel A., Owen, Michael J., Palotie, Aarno, Pato, Carlos N., Petryshen, Tracey L., Posthuma, Danielle, Rietschel, Marcella, Riley, Brien P., Rujescu, Dan, Sham, Pak C., Sklar, Pamela, St Clair, David, Weinberger, Daniel R., Wendland, Jens R., Werge, Thomas, Daly, Mark J., Sullivan, Patrick F., O'Donovan, Michael C., Qin, Shengying, Sawa, Akira, Kahn, Rene, Hong, Kyung Sue, Shi, Wenzhao, Tsuang, Ming, Itokawa, Masanari, Feng, Gang, Glatt, Stephen J., Ma, Xiancang, Tang, Jinsong, Ruan, Yunfeng, Liu, Ruize, Zhu, Feng, Horiuchi, Yasue, Lee, Byung Dae, Joo, Eun-Jeong, Myung, Woojae, Ha, Kyooseob, Won, Hong-Hee, Baek, Ji Hyung, Chung, Young Chul, Kim, Sung-Wan, Kusumawardhani, Agung, Chen, Wei J., Hwu, Hai-Gwo, Hishimoto, Akitoyo, Otsuka, Ikuo, Sora, Ichiro, Toyota, Tomoko, Yoshikawa, Takeo, Kunugi, Hiroshi, Hattori, Kotaro, Ishiwata, Sayuri, Numata, Shusuke, Ohmori, Tetsuro, Arai, Makoto, Ozeki, Yuji, Fujii, Kumiko, Kim, Se Joo, Lee, Heon-Jeong, Ahn, Yong Min, Kim, Se Hyun, Akiyama, Kazufumi, Shimoda, Kazutaka, Kinoshita, Makoto, Hsu, Yu-Han H., Pintacuda, Greta, Nacu, Eugeniu, Kim, April, Tsafou, Kalliopi, Petrossian, Natalie, Crotty, William, Suh, Jung Min, Riseman, Jackson, Martin, Jacqueline M., Biagini, Julia C., Mena, Daya, Ching, Joshua K.T., Malolepsza, Edyta, Li, Taibo, Singh, Tarjinder, Ge, Tian, Egri, Shawn B., Tanenbaum, Benjamin, Stanclift, Caroline R., Apffel, Annie M., Carr, Steven A., Schenone, Monica, Jaffe, Jake, Fornelos, Nadine, Eggan, Kevin C., and Lage, Kasper

Published
2023
Full Text
View/download PDF

22. Evaluation of breast‐specific marker expression in metastatic breast cancers: Correlation with subtype switch.

Author

Chan, Ronald, Leung, Howard, Li, Joshua, Poon, Ivan, Tsang, Julia Y, Ko, Chun‐Wai, Wong, Ngou‐Men, and Tse, Gary M

Subjects
*METASTATIC breast cancer, *TRANSCRIPTION factors, *SOX transcription factors, *BREAST cancer, *FORKHEAD transcription factors, *METASTASIS, *BREAST
Abstract

Aims Materials and methods Results Conclusions This study evaluates the utility of breast specific markers in identifying breast cancer subtypes within metastatic settings. The subtype alteration in metastatic disease and its consequent impact on breast‐specific marker expression is also examined.GATA‐binding protein 3 (GATA3), mammaglobin (MMG), transcriptional repressor GATA binding 1 (TRSP1) and SRY‐box transcription factor 10 (SOX10) expression were assessed in a large cohort of metastatic breast cancer (MBC) cases and correlated with the characteristics of both MBC and primary breast cancer (PBC).GATA3 was the most sensitive in MBC (83.1%), followed by TRPS1 (77.0%), MMG (58.5%) and SOX10 (7.1%). This trend was consistent in hormonal receptor (HR)+ and HR− MBC. Combining GATA3/TRPS1 yielded the highest detection rates in the overall cohort (90.1%) and HR+ MBC (97.1%), while TRSP1/MMG was most effective in HR− (76.2%) and TN (71.1%) MBC. Marker expression did not correlate with metastatic site, except SOX10 in lung metastases (P = 0.031). Subtype discordance between MBC and PBC occurred in 43 cases (24.4%), with GATA3 expression in HR− MBC significantly linked to subtype discordance (P = 0.005). Conversely, SOX10 expression was significantly associated with subtype concordance in HR− and TNBC (P ≤ 0.003). Despite a higher expression of GATA3 in all HR− cases, TRSP1 outperformed GATA3 in detecting concordant HR− cases (64.0% versus 38.5%). TRPS1 and SOX10 were expressed in more than 50% of concordant TNBC cases.The expression of breast‐specific markers is mainly determined by the PBC subtype. GATA3 retains high sensitivity in HR+ cancers, even after HR loss during metastasis. TRPS1 and SOX10 are identified as valuable markers in TNBC metastasis. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

24. Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions

Author

Luo, Luyang, Wang, Xi, Lin, Yi, Ma, Xiaoqi, Tan, Andong, Chan, Ronald, Vardhanabhuti, Varut, Chu, Winnie CW, Cheng, Kwang Ting, Chen, Hao, Luo, Luyang, Wang, Xi, Lin, Yi, Ma, Xiaoqi, Tan, Andong, Chan, Ronald, Vardhanabhuti, Varut, Chu, Winnie CW, Cheng, Kwang Ting, and Chen, Hao

Abstract

Breast cancer has reached the highest incidence rate worldwide among all malignancies since 2020. Breast imaging plays a significant role in early diagnosis and intervention to improve the outcome of breast cancer patients. In the past decade, deep learning has shown remarkable progress in breast cancer imaging analysis, holding great promise in interpreting the rich information and complex context of breast imaging modalities. Considering the rapid improvement in deep learning technology and the increasing severity of breast cancer, it is critical to summarize past progress and identify future challenges to be addressed. This paper provides an extensive review of deep learning-based breast cancer imaging research, covering studies on mammograms, ultrasound, magnetic resonance imaging, and digital pathology images over the past decade. The major deep learning methods and applications on imaging-based screening, diagnosis, treatment response prediction, and prognosis are elaborated and discussed. Drawn from the findings of this survey, we present a comprehensive discussion of the challenges and potential avenues for future research in deep learning-based breast cancer imaging.

Published
2024

26. The establishment of kidney cancer organoid line in drug testing.

Author

Tse, Ryan Tsz‐Hei, Wong, Christine Yim‐Ping, Ding, Xiaofan, Cheng, Carol Ka‐Lo, Chow, Chit, Chan, Ronald Cheong‐Kin, Ng, Joshua Hoi‐Yan, Tang, Victor Wai‐Lun, Chiu, Peter Ka‐Fung, Teoh, Jeremy Yuen‐Chun, Wong, Nathalie, To, Ka‐Fai, and Ng, Chi‐Fai

Subjects
RENAL cancer, DRUG use testing, MICROPHYSIOLOGICAL systems, RENAL cell carcinoma, XENOGRAFTS, KIDNEY tumors
Abstract

Introduction: Kidney cancer is a common urological malignancy worldwide with an increasing incidence in recent years. Among all subtypes, renal cell carcinoma (RCC) represents the most predominant malignancy in kidney. Clinicians faced a major challenge to select the most effective and suitable treatment regime for patients from a wide range of modalities, despite improved understanding and diagnosis of RCC. Objective: Recently, organoid culture gained more interest as the 3D model is shown to be highly patient specific which is hypothetically beneficial to the investigation of precision medicine. Nonetheless, the development and application of organotypic culture in RCC is still immature, therefore, the primary objective of this study was to establish an organoid model for RCC. Materials and Methods: Patients diagnosed with renal tumor and underwent surgical intervention were recruited. RCC specimen was collected and derived into organoids. Derived organoids were validated by histological examminations, sequencing and xenograft. Drug response of organoids were compared with resistance cell line and patients' clinical outcomes. Results: Our results demonstrated that organoids could be successfully derived from renal tumor and they exhibited high concordance in terms of immunoexpressional patterns. Sequencing results also depicted concordant mutations of driver genes in both organoids and parental tumor tissues. Critical and novel growth factors were discovered during the establishment of organoid model. Besides, organoids derived from renal tumor exhibited tumorigenic properties in vivo. In addition, organoids recapitulated patient's in vivo drug resistance and served as a platform to predict responsiveness of other therapeutic agents. Conclusion: Our RCC organoid model recaptiluated histological and genetic features observed in primary tumors. It also served as a potential platform in drug screening for RCC patients, though future studies are necessary before translating the outcomes into clinical practices. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

27. Spatial Distribution and Densities of CD103+ and FoxP3+ Tumor Infiltrating Lymphocytes by Digital Analysis for Outcome Prediction in Breast Cancer.

Author

Chan, Ronald, Aphivatanasiri, Chaiwat, Poon, Ivan K, Tsang, Julia Y, Ni, Yunbi, Lacambra, Maribel, Li, Joshua, Lee, Conrad, and Tse, Gary M

Subjects
BREAST cancer prognosis, STAINS & staining (Microscopy), BREAST physiology, MULTIVARIATE analysis, REGULATORY T cells, LYMPHOCYTES, SURVIVAL analysis (Biometry), RESEARCH funding, T cells, IMMUNOLOGIC memory
Abstract

Background The evaluation of tumor-infiltrating lymphocytes (TILs) for breast cancer prognosis is now established. However, the clinical value for their spatial distributions of specific immune subsets, namely CD103+ tissue-resident memory T cells FoxP3+ regulatory T ells, have not been thoroughly examined. Method Representative whole sections of breast cancers were subjected to CD103 and FoxP3 double staining. Their density, ratio, and spatial features were analyzed in tumor area and tumor-stromal interface. Their associations with clinicopathological parameters and patient's prognosis were analyzed. Results CD103 TILs were closer to tumor nests than FoxP3 TILs in the tumor-stromal interface. Their densities were associated with high-grade disease, TNBC, and stromal TILs. High stromal FoxP3 (sFoxP3) TILs and close proximity of sCD103 TILs to tumor were independently associated with better survival at multivariate analysis. Subgroup analysis showed the high FoxP3 TILs density associated better survival was seen in HER2-OE and TNBC subtypes while the proximity of CD103 TILs to tumor nests associated better survival was seen in luminal cancers. Conclusion The prognostic impact of CD103 and FoxP3 TILs in breast cancer depends on their spatial localization. High sFoxP3 TIL density and the lower distance of CD103 TILs from the tumor nests had independent favorable prognostic values. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

31. Deep learning for computational cytology: A survey

Author

Jiang, Hao, Zhou, Yanning, Lin, Yi, Chan, Ronald C.K., Liu, Jiang, Chen, Hao, Jiang, Hao, Zhou, Yanning, Lin, Yi, Chan, Ronald C.K., Liu, Jiang, and Chen, Hao

Abstract

Computational cytology is a critical, rapid-developing, yet challenging topic in medical image computing concerned with analyzing digitized cytology images by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) approaches have made significant achievements in medical image analysis, leading to boosting publications of cytological studies. In this article, we survey more than 120 publications of DL-based cytology image analysis to investigate the advanced methods and comprehensive applications. We first introduce various deep learning schemes, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize public datasets, evaluation metrics, versatile cytology image analysis applications including cell classification, slide-level cancer screening, nuclei or cell detection and segmentation. Finally, we discuss current challenges and potential research directions of computational cytology. © 2022 Elsevier B.V.

Published
2023

32. Number needed to diagnose in malignant ascites – effects of volume, repeating collection, and primary malignancy on diagnostic performance in peritoneal fluid cytology

Author

Ng, Joanna K. M., primary, Chow, Lok Hang, additional, Ngai, Annabelle M. Y., additional, Chan, Ronald C. K., additional, Lee, Jacqueline H. S., additional, Lee, Alfred L. H., additional, Li, Joshua J.X., additional, To, Curtis C. K., additional, and Tse, Gary M., additional

Published
2023
Full Text
View/download PDF

34. Additional file 1 of Plasma vaspin levels and clinical outcome in incident peritoneal dialysis patients

Author

Than, Win Hlaing, Chan, Gordon Chun-Kau, Kwan, Bonnie Ching-Ha, Lai, Ka-Bik, Chan, Ronald Cheong-Kin, Teoh, Jeromy Yuen Chun, Ng, Jack Kit-Chung, Fung, Winston Wing-Shing, Chow, Kai-Ming, Cheng, Phyllis Mei-Shan, Li, Philip Kam-Tao, and Szeto, Cheuk-Chun

Abstract

Additional file 1: Supplementary Table 1. Correlation between plasma vaspin level and baseline clinical and biochemical parameters according to diabetic status. PDE, peritoneal dialysis effluent; LDL, low-density lipoprotein; HDL, high-density lipoprotein; PTH, parathyroid hormone; SGA, subjective global assessment overall score; MIS, malnutrition inflammation score; E: I ratio, extra-cellular to intracellular volume ratio; D/P4, dialysate-to-plasma creatinine concentration at 4 hours; MTAC, mass transfer areas coefficient of creatinine; GFR, glomerular filtration rate; FEBM, fat-free edema-free body mass, NAPA for normalized protein nitrogen appearance; PWV, pulse wave velocity. Data are compared by Spearman’s rank correlation coefficient. Supplementary Table 2. Correlation between plasma vaspin level and insulin resistance. HbA1C, Hemoglobin A1C; HOMA, Homeostatic Model Assessment; IR, Insulin resistance; 2B, beta 2 cell function. Data are compared by Spearman’s rank correlation coefficient. Supplementary Table 3. Cox regression analysis for patient survival (all patients). HR, hazards ratio; AHR, adjusted hazards ratio; CI, confidence interval; GFR, glomerular filtration rate; CCI, Charlson’s comorbidity index; SGA, subjective global assessment overall score; MIS, malnutrition inflammation score; CR_PWV, carotid to radial pulse wave velocity; CF_PWV, carotid to femoral pulse wave velocity, BMI, body mass index; hsCRP, high sensitivity C-reactive protein; MTAC, mass transfer areas coefficient of creatinine; NPNA, normalized protein nitrogen appearance; E: I ratio, extra-cellular to intracellular volume ratio; HDL, high-density lipoprotein; LDL, Low-density lipoprotein; PTH, parathyroid hormone. *interaction between plasma vaspin level quartile and diabetic status. **male as compared to female

Published
2023
Full Text
View/download PDF

36. Reply to: A comparative study of diagnostic accuracy in 3026 pleural biopsies and matched pleural effusion cytology with clinical correlation: A methodological issue

Author

Poon, Ivan K., primary, Chan, Ronald C. K., additional, Choi, Joseph S. H., additional, Ng, Joanna K. M., additional, Tang, Katsie T., additional, Wong, Yolanda Y. H., additional, Chan, Ka Pang, additional, Yip, Wing Ho, additional, Tse, Gary M., additional, and Li, Joshua J. X., additional

Published
2022
Full Text
View/download PDF

37. Adipose and Plasma microRNAs miR-221 and 222 Associate with Obesity, Insulin Resistance, and New Onset Diabetes after Peritoneal Dialysis

Author

Chan, Gordon Chun Kau, primary, Than, Win Hlaing, additional, Kwan, Bonnie Ching Ha, additional, Lai, Ka Bik, additional, Chan, Ronald Cheong Kin, additional, Teoh, Jeremy Yuen Chun, additional, Ng, Jack Kit Chung, additional, Chow, Kai Ming, additional, Cheng, Phyllis Mei Shan, additional, Law, Man Ching, additional, Leung, Chi Bon, additional, Li, Philip Kam Tao, additional, and Szeto, Cheuk Chun, additional

Published
2022
Full Text
View/download PDF

40. High-Throughput, Label-Free and Slide-Free Histological Imaging by Computational Microscopy and Unsupervised Learning

Author

Zhang, Yan, Kang, Lei, Wong, Hei Man, Dai, Weixing, Li, Xiufeng, Chan, Ronald C. K., Hsin, Michael K. Y., Wong, Tsz Wai, Zhang, Yan, Kang, Lei, Wong, Hei Man, Dai, Weixing, Li, Xiufeng, Chan, Ronald C. K., Hsin, Michael K. Y., and Wong, Tsz Wai

Abstract

Rapid and high-resolution histological imaging with minimal tissue preparation has long been a challenging and yet captivating medical pursuit. Here, the authors propose a promising and transformative histological imaging method, termed computational high-throughput autofluorescence microscopy by pattern illumination (CHAMP). With the assistance of computational microscopy, CHAMP enables high-throughput and label-free imaging of thick and unprocessed tissues with large surface irregularity at an acquisition speed of 10 mm2/10 s with 1.1-µm lateral resolution. Moreover, the CHAMP image can be transformed into a virtually stained histological image (Deep-CHAMP) through unsupervised learning within 15 s, where significant cellular features are quantitatively extracted with high accuracy. The versatility of CHAMP is experimentally demonstrated using mouse brain/kidney and human lung tissues prepared with various clinical protocols, which enables a rapid and accurate intraoperative/postoperative pathological examination without tissue processing or staining, demonstrating its great potential as an assistive imaging platform for surgeons and pathologists to provide optimal adjuvant treatment.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results