Jiancong Hu
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
Jiancong Hu has a total of 167 co-authors. Here are the top co-authors by number of shared publications:
- Xiaosheng He
Department of General Surgery (Colorectal Surgery), The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
12 shared publications - Ping Lan
Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
11 shared publications Junguo Chen
Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China
10 shared publications- Chen Liu
Department of General Surgery (Colorectal Surgery), The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
9 shared publications - Danling Liu
Department of General Surgery (Colorectal Surgery), The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
9 shared publications - Dayi Liang
Department of General Surgery (Colorectal Surgery), The Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China
9 shared publications
Latest Publications
- Open Access
- 6 August 2026
- Published by Springer Nature in npj Digital Medicine
An explainable generative AI system for video-to-report generation in capsule endoscopy
Gastrointestinal (GI) diseases remain a significant global health burden due to elevated morbidity and mortality. Accurate and timely diagnosis, especially for small-bowel conditions, remains challenging because capsule endoscopy (CE) videos last 6–12 hours and require prolonged manual review. While artificial intelligence has advanced CE analysis, integrated video-to-report generation remains largely unexplored. We introduce CE Reporter, an explainable system transforming full-length CE videos into evidence-supported diagnostic reports through multi-task keyframe detection and time-aware vision-language alignment. CE Reporter was trained on MICS-CE, a multicenter, multi-device dataset comprising 1002 video-report pairs, 109 million frames, 11,028 video hours, and 29,338 expert-annotated keyframe-text pairs. The model performed strongly across three dimensions: (1) Report quality: exceeding existing multimodal large language models in linguistic coherence and diagnostic agreement (BLEU-ave: 0.572 vs. 0.523; small intestine lesion F1-score: 0.79 vs. 0.58); (2) Clinician evaluation: achieving high correctness, completeness, and conciseness ratings, outperforming resident clinicians while reducing reporting time by 91.9%; (3) Clinical utility: generating explainable reports supported by visual keyframes and maintaining competitive performance across centers and capsule devices (F1 score: 0.72–0.81). These findings establish a foundation for automated CE video-to-report generation and highlight its potential for efficient and transparent clinical workflows.
- 6 August 2026
- Published by Springer Nature in npj Digital Medicine
Open AccessAn explainable generative AI system for video-to-report generation in capsule endoscopy
Gastrointestinal (GI) diseases remain a significant global health burden due to elevated morbidity and mortality. Accurate and timely diagnosis, especially for small-bowel conditions, remains challenging because capsule endoscopy (CE) videos last 6–12 hours and require prolonged manual review. While artificial intelligence has advanced CE analysis, integrated video-to-report generation remains largely unexplored. We introduce CE Reporter, an explainable system transforming full-length CE videos into evidence-supported diagnostic reports through multi-task keyframe detection and time-aware vision-language alignment. CE Reporter was trained on MICS-CE, a multicenter, multi-device dataset comprising 1002 video-report pairs, 109 million frames, 11,028 video hours, and 29,338 expert-annotated keyframe-text pairs. The model performed strongly across three dimensions: (1) Report quality: exceeding existing multimodal large language models in linguistic coherence and diagnostic agreement (BLEU-ave: 0.572 vs. 0.523; small intestine lesion F1-score: 0.79 vs. 0.58); (2) Clinician evaluation: achieving high correctness, completeness, and conciseness ratings, outperforming resident clinicians while reducing reporting time by 91.9%; (3) Clinical utility: generating explainable reports supported by visual keyframes and maintaining competitive performance across centers and capsule devices (F1 score: 0.72–0.81). These findings establish a foundation for automated CE video-to-report generation and highlight its potential for efficient and transparent clinical workflows.
- Open Access
- 9 April 2026
- Published by Springer Nature in BMC Gastroenterology
- Vol. 26 (1)
DeepSeek-R1 vs. OpenAI o1 in colorectal cancer screening: a binational evaluation
Large language models (LLMs), such as OpenAI o1 and DeepSeek-R1, demonstrate promising applications in healthcare through structured reasoning and decision
- 9 April 2026
- Published by Springer Nature in BMC Gastroenterology
- Vol. 26 (1)
Open AccessDeepSeek-R1 vs. OpenAI o1 in colorectal cancer screening: a binational evaluation
Large language models (LLMs), such as OpenAI o1 and DeepSeek-R1, demonstrate promising applications in healthcare through structured reasoning and decision
- 19 March 2026
- Published by Elsevier in Clinical Gastroenterology and Hepatology
- Vol. 24 (9) , 2571-2583
INTELCAPE: A Deep Learning-Powered System for Automated, High-Accuracy Crohn’s Disease Diagnosis via Capsule Endoscopy
- 19 March 2026
- Published by Elsevier in Clinical Gastroenterology and Hepatology
- Vol. 24 (9) , 2571-2583
INTELCAPE: A Deep Learning-Powered System for Automated, High-Accuracy Crohn’s Disease Diagnosis via Capsule Endoscopy
- Open Access
- 21 January 2026
- Published by Springer Nature in Research Square
An Adaptive Foundation Model with Evidence-based Clinical Reasoning for Gastroenterology
Gastrointestinal diseases affect 2.86 billion people globally, with capsule endoscopy (CE) providing crucial diagnostics but requiring manual review of over 60,000 frames per examination, a process associated with 17.4% disease miss rates. While artificial intelligence shows promise for CE analysis, existing endoscopic vision-language models (VLMs) lack multi-video understanding capability and cannot replicate the systematic multi-evidence reasoning that gastroenterologists integrate findings across anatomical regions to synthesize cohesive diagnoses. Here we introduce CE-R1, an adaptive foundation model with evidence-based clinical reasoning capabilities specifically designed for gastroenterology. CE-R1 incorporates a dynamic router that assesses query complexity and selectively routes cases to either a lightweight model for straightforward questions or a deep reasoning model that generates transparent, step-by-step diagnostic thought processes. To enable this capability, we construct CE-Bench, the first large-scale multimodal CE dataset comprising 502,066 visual question-answering pairs with chain-of-thought reasoning annotations, spanning 70 fine-grained clinical sub-tasks across five core diagnostic categories: anatomy identification, endoscopic findings recognition, disease diagnosis, treatment planning, and medical report generation. Comprehensive evaluation on both in-distribution and out-of-distribution datasets from four independent hospitals demonstrates that CE-R1 achieves 86.7% overall accuracy, substantially outperforming state-of-the-art VLMs (best baseline: 24.6%) and surpassing average physician performance (39.9%) by 21.1%. CE-R1 maintains superior generalization across external validation sets (65.1–81.9% accuracy). Critically, the multi-evidence clinical reasoning capability delivers substantial performance gains in complex diagnostic tasks: CE-R1 surpasses the model without reasoning by 8.5% in disease diagnosis, demonstrating the clinical value of transparent, step-by-step diagnostic processes. These results establish CE-R1 as a robust foundation model for comprehensive CE analysis with immediate applications in clinical decision support and medical education.
- 21 January 2026
- Published by Springer Nature in Research Square
Open AccessAn Adaptive Foundation Model with Evidence-based Clinical Reasoning for Gastroenterology
Gastrointestinal diseases affect 2.86 billion people globally, with capsule endoscopy (CE) providing crucial diagnostics but requiring manual review of over 60,000 frames per examination, a process associated with 17.4% disease miss rates. While artificial intelligence shows promise for CE analysis, existing endoscopic vision-language models (VLMs) lack multi-video understanding capability and cannot replicate the systematic multi-evidence reasoning that gastroenterologists integrate findings across anatomical regions to synthesize cohesive diagnoses. Here we introduce CE-R1, an adaptive foundation model with evidence-based clinical reasoning capabilities specifically designed for gastroenterology. CE-R1 incorporates a dynamic router that assesses query complexity and selectively routes cases to either a lightweight model for straightforward questions or a deep reasoning model that generates transparent, step-by-step diagnostic thought processes. To enable this capability, we construct CE-Bench, the first large-scale multimodal CE dataset comprising 502,066 visual question-answering pairs with chain-of-thought reasoning annotations, spanning 70 fine-grained clinical sub-tasks across five core diagnostic categories: anatomy identification, endoscopic findings recognition, disease diagnosis, treatment planning, and medical report generation. Comprehensive evaluation on both in-distribution and out-of-distribution datasets from four independent hospitals demonstrates that CE-R1 achieves 86.7% overall accuracy, substantially outperforming state-of-the-art VLMs (best baseline: 24.6%) and surpassing average physician performance (39.9%) by 21.1%. CE-R1 maintains superior generalization across external validation sets (65.1–81.9% accuracy). Critically, the multi-evidence clinical reasoning capability delivers substantial performance gains in complex diagnostic tasks: CE-R1 surpasses the model without reasoning by 8.5% in disease diagnosis, demonstrating the clinical value of transparent, step-by-step diagnostic processes. These results establish CE-R1 as a robust foundation model for comprehensive CE analysis with immediate applications in clinical decision support and medical education.
- Open Access
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Ext. Figure 4 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
CDCA inhibits CRC organoid growth and induces apoptosis beyond the activation of FXR
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessExt. Figure 4 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
CDCA inhibits CRC organoid growth and induces apoptosis beyond the activation of FXR
- Open Access
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Ext. Figure 3 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
CDCA does not affect proliferation, apoptosis, or ROS levels in normal colonic organoids
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessExt. Figure 3 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
CDCA does not affect proliferation, apoptosis, or ROS levels in normal colonic organoids
- Open Access
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Ext. Figure 2 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
Correlation between microbial genera and CDCA or LCA
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessExt. Figure 2 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
Correlation between microbial genera and CDCA or LCA
- Open Access
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Ext. Figure 1 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
Correlation between bile acids and gut microbiota genera
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessExt. Figure 1 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
Correlation between bile acids and gut microbiota genera
- Open Access
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Ext. Figure 6 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
L. johnsonii supernatant inhibits CRC organoid growth and induces apoptosis
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessExt. Figure 6 from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
L. johnsonii supernatant inhibits CRC organoid growth and induces apoptosis
- Open Access
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Data from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
High-fat diet (HFD) is positively correlated with colorectal cancer, but there are notable interindividual differences in susceptibility to the tumor-promoting effects of HFD. A better understanding of the mechanisms that modulate the outcomes of HFD could help inform precision prevention strategies for colorectal cancer. In this study, we found a key role for the gut microbiota in the individual differences observed in the tumor-promoting effects of HFD. Analysis of the gut bacteria enriched in mice resistant to HFD-induced cancer identified Lactobacillus johnsonii as an effective protector. Colonization of L. johnsonii increased intestinal chenodeoxycholic acid (CDCA) concentrations in HFD-exposed mice, which decelerated HFD-induced colorectal cancer progression. Mechanistically, L. johnsonii converted conjugated bile acid to CDCA via bile salt hydrolase, and CDCA induced mitochondrial dysfunction and oxidative stress to promote apoptosis, effectively suppressing tumor development. These results establish the gut microbiota as a mediator of interindividual differences in cancer susceptibility induced by HFD and reveal a probiotic strategy with the ability to inhibit tumorigenesis, suggesting a possible route to reduce HFD-induced colorectal cancer progression.Significance:Investigation of bacteria–host interactions that alter cancer susceptibility uncovers suppression of high-fat diet–induced colorectal cancer by Lactobacillus johnsonii, offering a translational approach to improve cancer prevention.See related commentary by Dalal and Shah, p. 4579
- 1 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessData from Lactobacillus johnsonii Synthesizes Chenodeoxycholic Acid to Reduce Susceptibility to High-Fat Diet–Induced Colorectal Cancer
High-fat diet (HFD) is positively correlated with colorectal cancer, but there are notable interindividual differences in susceptibility to the tumor-promoting effects of HFD. A better understanding of the mechanisms that modulate the outcomes of HFD could help inform precision prevention strategies for colorectal cancer. In this study, we found a key role for the gut microbiota in the individual differences observed in the tumor-promoting effects of HFD. Analysis of the gut bacteria enriched in mice resistant to HFD-induced cancer identified Lactobacillus johnsonii as an effective protector. Colonization of L. johnsonii increased intestinal chenodeoxycholic acid (CDCA) concentrations in HFD-exposed mice, which decelerated HFD-induced colorectal cancer progression. Mechanistically, L. johnsonii converted conjugated bile acid to CDCA via bile salt hydrolase, and CDCA induced mitochondrial dysfunction and oxidative stress to promote apoptosis, effectively suppressing tumor development. These results establish the gut microbiota as a mediator of interindividual differences in cancer susceptibility induced by HFD and reveal a probiotic strategy with the ability to inhibit tumorigenesis, suggesting a possible route to reduce HFD-induced colorectal cancer progression.Significance:Investigation of bacteria–host interactions that alter cancer susceptibility uncovers suppression of high-fat diet–induced colorectal cancer by Lactobacillus johnsonii, offering a translational approach to improve cancer prevention.See related commentary by Dalal and Shah, p. 4579