Multi-Adapter SAM-Inspired Bronchoscopic Image Segmentation for Lung Cancer Diagnosis

Qian Li¹Xinbo Liu²Chao Ye³Sen Cui⁴Jinze Zhang⁵Xuanyu Meng⁶Jin Guo^7*Xianjun Min^1*

• ¹China Aerospace Science and Industry Corporation 731 Hospital, Beijing, China
• ²Fourth Hospital of Hebei Medical University, Shijiazhuang, China
• ³Hebei Medical University, Shijiazhuang, China
• ⁴Hunan University of Technology and Business, Changsha, China
• ⁵The Fourth Affiliated Hospital of Hebei Medical University, Shijiazhuang, China
• ⁶Genertec Digital Technology Co. Ltd, Beijing, China
• ⁷Beijing Institute of Technology, Beijing, China

Introduction:Lung cancer remains the leading cause of cancer-related mortality. Although bronchoscopy allows direct visualization and tissue sampling, detecting subtle lesions is still challenging due to limited resolution, variable imaging conditions, and the complex structure of the airway. Most existing approaches treat lesion segmentation and cancer diagnosis as separate tasks, which can reduce diagnostic coherence and limit clinical applicability. Method: We propose a novel Multi-Adapter-based Segment Any Bronchoscope Model (MASA), an end-to-end framework with an encoder that fuses spatial, frequency, and positional information and a dual-decoder that performs simultaneous lesion segmentation and lung cancer diagnosis. MASA was trained/evaluated on the public BM-BronchoLC dataset. Results: On BM-BronchoLC, MASA improved lesion segmentation over the strongest baseline (ESFPNet), raising mDice by +3.01\% and mIoU by +1.24\%. For diagnosis, MASA increased Macro-F1 by +8.1 points and AUPRC by +14.1\%. Conclusion: MASA provides a unified and interpretable pipeline for automated bronchoscopic image analysis, generating pixel-level lesion maps alongside case-level diagnostic predictions. The framework shows strong promise for improving early lung cancer detection and enhancing the efficiency of bronchoscopic workflows in clinical practice.