Related Experiment Video
Updated: Dec 24, 2025
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Emerging role of deep learning-based artificial intelligence in tumor pathology
Yahui Jiang1, Meng Yang2, Shuhao Wang3
1Department of Pathology, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Cancer Institute and Hospital, Tianjin Medical University, Tianjin, 300060, P. R. China.
Artificial intelligence (AI), particularly deep learning (DL), is revolutionizing tumor pathology with applications in diagnosis, grading, and prediction. Challenges remain in implementation, validation, and acceptance by professionals and patients.
Area of Science:
- Oncology
- Pathology
- Computer Science
- Artificial Intelligence
Background:
- Digital pathology and advanced computer vision algorithms fuel interest in AI for tumor pathology.
- Deep learning (DL)-based AI algorithms are being developed for diverse tasks including diagnosis, grading, staging, and prognostic prediction.
- AI enhances diagnostic accuracy, objectivity, and efficiency, supporting precision oncology.
Purpose of the Study:
- To provide an overview of AI integration in pathologists' workflows.
- To discuss the challenges and future perspectives of AI implementation in tumor pathology.
Main Methods:
- Review of current AI applications in tumor pathology.
- Discussion of challenges including algorithm validation, interpretability, computing infrastructure, and acceptance.
- Exploration of AI's role in precision oncology.
Main Results:
- AI algorithms are capable of performing numerous tasks in tumor pathology, from diagnosis to biomarker identification.
- AI improves diagnostic accuracy and reduces pathologist workload, allowing focus on complex decision-making.
- AI facilitates the adoption of precision oncology.
Conclusions:
- AI offers significant potential to transform tumor pathology, improving efficiency and accuracy.
- Addressing challenges in validation, interpretability, and acceptance is crucial for successful AI integration.
- Future perspectives involve overcoming implementation hurdles for widespread AI adoption in pathology.
