From fragile pipelines to reliable systems: error-correctable cascades in medical AI.
Authors
Affiliations (6)
Affiliations (6)
- Department of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat- sen University Cancer Center, Guangzhou, 510060, China.
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
- Department of Cellular and Molecular Diagnostics Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
- School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510006, China. [email protected].
- Department of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat- sen University Cancer Center, Guangzhou, 510060, China. [email protected].
- Department of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat- sen University Cancer Center, Guangzhou, 510060, China. [email protected].
Abstract
Artificial intelligence (AI) has achieved expert-level performance in medical imaging, but its clinical translation requires a reliable and interpretable system design. Decision-level hierarchical cascaded pipelines are widely used in medical AI, yet their benefits and limitations require further investigation. We compared decision-level hierarchical cascaded and parallel architectures in medical imaging and revealed a trade-off between error vulnerability and diagnostic transparency. Based on these observations, we developed an error-aware framework integrating automated error detection, adaptive correction, and confidence-guided human-AI collaboration. The framework was evaluated on over 10,000 patient cases, including 6,103 colorectal pathology and 7,164 cervical cytology samples, with additional validation in endoscopic and ophthalmological imaging. Decision-level hierarchical cascaded systems, although susceptible to error amplification, were more aligned with hierarchical clinical reasoning and enabled more transparent decision pathways. The proposed framework mitigated error propagation through automated detection and correction. Combined with confidence-guided human-AI collaboration, it achieved absolute accuracy gains of 16.12 and 10.11 percentage points in colorectal pathology and cervical cytology, respectively, compared with parallel systems, with consistent gains across other imaging tasks. Our study highlights the trade-off between error propagation and interpretability in hierarchical cascaded AI systems and demonstrates that error-aware design can improve their robustness and clinical applicability, contributing to the development of more reliable and human-centered medical AI.