Bo Lin
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
Bo Lin has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
- Jianwei Yin
School of Software Technology, Zhejiang University, Ningbo, China
4 shared publications - Xuanwen Bao
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
4 shared publications Jinlin Cheng
State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
3 shared publicationsChuan Liu
Department of Medical Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
2 shared publicationsJie Mei
Department of Liver Surgery, Sun Yat-sen University Cancer Center, Guangzhou, China; State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
2 shared publicationsJingping Yun
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, China
2 shared publications
Latest Publications
- Open Access
- 17 October 2026
- Published by MDPI AG in Automation
- Vol. 7 (5) , 165
Text-Guided Semantic Enhancement for Personal Protective Equipment Detection in Chemical Industry Environments
The automated detection of personal protective equipment (PPE) is crucial for ensuring operational safety in hazardous environments. However, background interference and target semantic ambiguity caused by dramatic illumination changes and occlusions pose severe challenges to traditional deep learning models. To address these challenges, we present TGF-ChD, a detection model based on the text-guided fusion (TGF) module, which enhances feature representation by introducing category semantic priors. TGF-ChD first employs text-guided attention to spatially capture significant regions based on semantic constraints; subsequently, through semantic feature modulation, which calibrates channel gains and shifts according to semantic relevance, high-level semantic information is deeply embedded into multi-scale visual features. On the Chemical Industry PPE dataset, the model achieved an mAP of 54.3% and an mAP50 of 84.9%, exceeding TOOD by 2.0 and 6.0 percentage points, respectively. Furthermore, the model achieves improved performance on challenging categories, such as ‘blurred clothing’ and ‘blurred heads’ caused by severe reflections. These results indicate that jointly applying spatial and channel-level semantic conditioning can improve PPE detection under the evaluated complex industrial conditions.
- 17 October 2026
- Published by MDPI AG in Automation
- Vol. 7 (5) , 165
Open AccessText-Guided Semantic Enhancement for Personal Protective Equipment Detection in Chemical Industry Environments
The automated detection of personal protective equipment (PPE) is crucial for ensuring operational safety in hazardous environments. However, background interference and target semantic ambiguity caused by dramatic illumination changes and occlusions pose severe challenges to traditional deep learning models. To address these challenges, we present TGF-ChD, a detection model based on the text-guided fusion (TGF) module, which enhances feature representation by introducing category semantic priors. TGF-ChD first employs text-guided attention to spatially capture significant regions based on semantic constraints; subsequently, through semantic feature modulation, which calibrates channel gains and shifts according to semantic relevance, high-level semantic information is deeply embedded into multi-scale visual features. On the Chemical Industry PPE dataset, the model achieved an mAP of 54.3% and an mAP50 of 84.9%, exceeding TOOD by 2.0 and 6.0 percentage points, respectively. Furthermore, the model achieves improved performance on challenging categories, such as ‘blurred clothing’ and ‘blurred heads’ caused by severe reflections. These results indicate that jointly applying spatial and channel-level semantic conditioning can improve PPE detection under the evaluated complex industrial conditions.
- 11 September 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (37)
Spatiotemporal mapping of tertiary lymphoid structure heterogeneity shapes immune niches and clinical outcomes in intrahepatic cholangiocarcinoma
Intrahepatic cholangiocarcinoma (iCCA) is a highly lethal malignancy with limited therapeutic options. The spatial architecture and functional diversity of tertiary lymphoid structures (TLSs) in iCCA remain unclear. Here, we present a multimodal spatial atlas of TLSs and identified intratumoral TLSs (iTLSs) as independent prognostic markers. Bulk proteomic profiling of 214 discovery and 155 validation cases identified a four-tier TLS-based tumor microenvironment classification system and supported development of a TLS-predictive random forest classifier. Imaging mass cytometry revealed that iTLS + tumors harbor structured immune architectures, where M1-like tissue-resident macrophages (RTMs), dendritic cells, and CXCL13 + CD4 + T cells colocalize to form antigen-presenting neighborhoods (apc-CNs) spatially coupled to TLS core regions (TLScore-CNs). Single-cell spatial transcriptomics further resolved 61 TLSs into 14 spatial niches and defined a pseudotemporal maturation continuum: aggregated, activated, and postactivated. Intraniche communication, primarily mediated by ifnCAFs, iCAFs, and CXCL12 + macrophages, evolved dynamically with maturation. Single-nucleus RNA sequencing combined with Tangram-based spatial mapping revealed CXCL12 + macrophages and iCAFs forming a peripheral band in aggregated TLSs, whereas ifnCAFs infiltrated TLS interiors during activation. These findings define TLS heterogeneity and provide insights for stroma-directed immunotherapy.
- 11 September 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (37)
Spatiotemporal mapping of tertiary lymphoid structure heterogeneity shapes immune niches and clinical outcomes in intrahepatic cholangiocarcinoma
Intrahepatic cholangiocarcinoma (iCCA) is a highly lethal malignancy with limited therapeutic options. The spatial architecture and functional diversity of tertiary lymphoid structures (TLSs) in iCCA remain unclear. Here, we present a multimodal spatial atlas of TLSs and identified intratumoral TLSs (iTLSs) as independent prognostic markers. Bulk proteomic profiling of 214 discovery and 155 validation cases identified a four-tier TLS-based tumor microenvironment classification system and supported development of a TLS-predictive random forest classifier. Imaging mass cytometry revealed that iTLS + tumors harbor structured immune architectures, where M1-like tissue-resident macrophages (RTMs), dendritic cells, and CXCL13 + CD4 + T cells colocalize to form antigen-presenting neighborhoods (apc-CNs) spatially coupled to TLS core regions (TLScore-CNs). Single-cell spatial transcriptomics further resolved 61 TLSs into 14 spatial niches and defined a pseudotemporal maturation continuum: aggregated, activated, and postactivated. Intraniche communication, primarily mediated by ifnCAFs, iCAFs, and CXCL12 + macrophages, evolved dynamically with maturation. Single-nucleus RNA sequencing combined with Tangram-based spatial mapping revealed CXCL12 + macrophages and iCAFs forming a peripheral band in aggregated TLSs, whereas ifnCAFs infiltrated TLS interiors during activation. These findings define TLS heterogeneity and provide insights for stroma-directed immunotherapy.
- 18 February 2026
- Published by Elsevier in Molecular Therapy
- Vol. 34 (6) , 3616-3635
High-resolution spatial multi-omics enables prognostic scoring in intrahepatic cholangiocarcinoma
- 18 February 2026
- Published by Elsevier in Molecular Therapy
- Vol. 34 (6) , 3616-3635
High-resolution spatial multi-omics enables prognostic scoring in intrahepatic cholangiocarcinoma
- Open Access
pFedSAM: Personalized Federated Learning of Segment Anything Model for Medical Image Segmentation
Medical image segmentation is crucial for computer-aided diagnosis, yet privacy constraints hinder data sharing across institutions. Federated learning addresses this limitation, but existing approaches often rely on lightweight architectures that struggle with complex, heterogeneous data. Recently, the Segment Anything Model (SAM) has shown outstanding segmentation capabilities; however, its massive encoder poses significant challenges in federated settings. In this work, we present the first personalized federated SAM framework tailored for heterogeneous data scenarios in medical image segmentation. Our framework integrates two key innovations: (1) a personalized strategy that aggregates only the global parameters to capture cross-client commonalities while retaining the designed L-MoE (Localized Mixture-of-Experts) component to preserve domain-specific features; and (2) a decoupled global-local fine-tuning mechanism that leverages a teacher-student paradigm via knowledge distillation to bridge the gap between the global shared model and the personalized local models, thereby mitigating overgeneralization. Extensive experiments on two public datasets validate that our approach significantly improves segmentation performance, achieves robust cross-domain adaptation, and reduces communication overhead.
Open AccesspFedSAM: Personalized Federated Learning of Segment Anything Model for Medical Image Segmentation
Medical image segmentation is crucial for computer-aided diagnosis, yet privacy constraints hinder data sharing across institutions. Federated learning addresses this limitation, but existing approaches often rely on lightweight architectures that struggle with complex, heterogeneous data. Recently, the Segment Anything Model (SAM) has shown outstanding segmentation capabilities; however, its massive encoder poses significant challenges in federated settings. In this work, we present the first personalized federated SAM framework tailored for heterogeneous data scenarios in medical image segmentation. Our framework integrates two key innovations: (1) a personalized strategy that aggregates only the global parameters to capture cross-client commonalities while retaining the designed L-MoE (Localized Mixture-of-Experts) component to preserve domain-specific features; and (2) a decoupled global-local fine-tuning mechanism that leverages a teacher-student paradigm via knowledge distillation to bridge the gap between the global shared model and the personalized local models, thereby mitigating overgeneralization. Extensive experiments on two public datasets validate that our approach significantly improves segmentation performance, achieves robust cross-domain adaptation, and reduces communication overhead.
- Open Access
- 28 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 240-248
Tropical Fréchet Means
- 28 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 240-248
Open AccessTropical Fréchet Means
- 24 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Low-rank and synergy prompts for efficient multimodal glioma segmentation with missing modalities
- 24 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Low-rank and synergy prompts for efficient multimodal glioma segmentation with missing modalities
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
"Break the Mask Barrier": An AU-based Rehabilitation Training System for Parkinson's Hypomimia
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open Access"Break the Mask Barrier": An AU-based Rehabilitation Training System for Parkinson's Hypomimia
- Open Access
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1287-1296
SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models
- 24 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1287-1296
Open AccessSkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models
- Top Cited Papers
- 25 February 2025
- Published by Wolters Kluwer Health in Hepatology
- Vol. 83 (1) , 57-74
Spatial single-cell proteomics landscape decodes the tumor microenvironmental ecosystem of intrahepatic cholangiocarcinoma
Background and Aims: The prognoses and therapeutic responses of patients with intrahepatic cholangiocarcinoma (iCCA) depend on spatial interactions among tumor microenvironment (TME) components. However, the spatial TME characteristics of iCCA remain poorly understood. The aim of this study was to generate a comprehensive spatial atlas of iCCA using artificial intelligence-assisted spatial multiomics patterns and to identify spatial features associated with prognosis and immunotherapy. Approach and Results: Spatial multiomics, including imaging mass cytometry (n=155 in-house), spatial proteomics (n=155 in-house), spatial transcriptomics (n=4 in-house), multiplex immunofluorescence (n=20 in-house), single-cell RNA sequencing (scRNA-seq, n=9 in-house and n=34 public), bulk RNA-seq (n=244 public), and bulk proteomics (n=110 in-house and n=214 public), were employed to elucidate the spatial TME of iCCA. More than 1.06 million cells were resolved, and the findings revealed that spatial topology, including cellular deposition patterns, cellular communities, and intercellular communications, profoundly correlates with the prognosis of patients with iCCA. Specifically, CD163 hi M2-like resident-tissue macrophages suppress antitumor immunity by directly interacting with CD8 + T cells, resulting in poorer patient survival. Additionally, 5 spatial subtypes with distinct prognoses were identified, and potential therapeutic options were generated for these subtypes. Furthermore, a spatial TME deep learning system was developed to predict the prognosis of patients with iCCA with high accuracy from a single 1-mm 2 tumor sample. Conclusions: This study offers preliminary insights into the spatial TME ecosystem of iCCA, providing valuable foundations for precise patient classification and the development of personalized treatment strategies.
- 25 February 2025
- Published by Wolters Kluwer Health in Hepatology
- Vol. 83 (1) , 57-74
Top Cited PapersSpatial single-cell proteomics landscape decodes the tumor microenvironmental ecosystem of intrahepatic cholangiocarcinoma
Background and Aims: The prognoses and therapeutic responses of patients with intrahepatic cholangiocarcinoma (iCCA) depend on spatial interactions among tumor microenvironment (TME) components. However, the spatial TME characteristics of iCCA remain poorly understood. The aim of this study was to generate a comprehensive spatial atlas of iCCA using artificial intelligence-assisted spatial multiomics patterns and to identify spatial features associated with prognosis and immunotherapy. Approach and Results: Spatial multiomics, including imaging mass cytometry (n=155 in-house), spatial proteomics (n=155 in-house), spatial transcriptomics (n=4 in-house), multiplex immunofluorescence (n=20 in-house), single-cell RNA sequencing (scRNA-seq, n=9 in-house and n=34 public), bulk RNA-seq (n=244 public), and bulk proteomics (n=110 in-house and n=214 public), were employed to elucidate the spatial TME of iCCA. More than 1.06 million cells were resolved, and the findings revealed that spatial topology, including cellular deposition patterns, cellular communities, and intercellular communications, profoundly correlates with the prognosis of patients with iCCA. Specifically, CD163 hi M2-like resident-tissue macrophages suppress antitumor immunity by directly interacting with CD8 + T cells, resulting in poorer patient survival. Additionally, 5 spatial subtypes with distinct prognoses were identified, and potential therapeutic options were generated for these subtypes. Furthermore, a spatial TME deep learning system was developed to predict the prognosis of patients with iCCA with high accuracy from a single 1-mm 2 tumor sample. Conclusions: This study offers preliminary insights into the spatial TME ecosystem of iCCA, providing valuable foundations for precise patient classification and the development of personalized treatment strategies.
- Open Access
- 17 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8350
A Framework for Agricultural Intelligent Analysis Based on a Visual Language Large Model
Smart agriculture has become an inevitable trend in the development of modern agriculture, especially promoted by the continuous progress of large language models like chat generative pre-trained transformer (ChatGPT) and general language model (ChatGLM). Although these large models perform well in general knowledge learning, they still have certain limitations and errors when facing agricultural professional knowledge about crop disease identification, growth stage judgment, and so on. Agricultural data involves images and texts and other modalities, which play an important role in agricultural production and management. In order to better learn the characteristics of different modal data in agriculture, realize cross-modal data fusion, and thus understand complex application scenarios, we propose a framework AgriVLM that uses a large amount of agricultural data to fine-tune the visual language model to analyze agricultural data. It can fuse multimodal data and provide more comprehensive agricultural decision support. Specifically, it utilizes Q-former as a bridge between an image encoder and a language model to achieve a cross-modal fusion of agricultural images and text data. Then, we apply a Low-Rank adaptive to fine-tune the language model to achieve an alignment between agricultural image features and a pre-trained language model. The experimental results prove that AgriVLM demonstrates great performance in crop disease recognition and growth stage recognition, with recognition accuracy exceeding 90%, demonstrating its capability to analyze different modalities of agricultural data.
- 17 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8350
Open AccessA Framework for Agricultural Intelligent Analysis Based on a Visual Language Large Model
Smart agriculture has become an inevitable trend in the development of modern agriculture, especially promoted by the continuous progress of large language models like chat generative pre-trained transformer (ChatGPT) and general language model (ChatGLM). Although these large models perform well in general knowledge learning, they still have certain limitations and errors when facing agricultural professional knowledge about crop disease identification, growth stage judgment, and so on. Agricultural data involves images and texts and other modalities, which play an important role in agricultural production and management. In order to better learn the characteristics of different modal data in agriculture, realize cross-modal data fusion, and thus understand complex application scenarios, we propose a framework AgriVLM that uses a large amount of agricultural data to fine-tune the visual language model to analyze agricultural data. It can fuse multimodal data and provide more comprehensive agricultural decision support. Specifically, it utilizes Q-former as a bridge between an image encoder and a language model to achieve a cross-modal fusion of agricultural images and text data. Then, we apply a Low-Rank adaptive to fine-tune the language model to achieve an alignment between agricultural image features and a pre-trained language model. The experimental results prove that AgriVLM demonstrates great performance in crop disease recognition and growth stage recognition, with recognition accuracy exceeding 90%, demonstrating its capability to analyze different modalities of agricultural data.