Search papers, labs, and topics across Lattice.
The paper introduces FOCUS, a foundation model-driven framework for end-to-end automation of 3D OCT retinal disease diagnosis, addressing limitations of conventional single-slice, single-task AI models. FOCUS employs EfficientNetV2-S for image quality assessment and a fine-tuned Vision Foundation Model for abnormality detection and multi-disease classification, integrating 2D slice predictions into 3D patient-level diagnoses using a unified adaptive aggregation method. Validated on a large dataset and compared against expert performance, FOCUS demonstrates high F1 scores and improved efficiency, showcasing its potential for autonomous retinal disease screening.
Automating 3D OCT retinal disease diagnosis with a foundation model-driven framework, FOCUS matches expert performance while significantly boosting efficiency, promising a leap towards unmanned ophthalmology.
Optical coherence tomography (OCT) has revolutionized retinal disease diagnosis with its high-resolution and three-dimensional imaging nature, yet its full diagnostic automation in clinical practices remains constrained by multi-stage workflows and conventional single-slice single-task AI models. We present Full-process OCT-based Clinical Utility System (FOCUS), a foundation model-driven framework enabling end-to-end automation of 3D OCT retinal disease diagnosis. FOCUS sequentially performs image quality assessment with EfficientNetV2-S, followed by abnormality detection and multi-disease classification using a fine-tuned Vision Foundation Model. Crucially, FOCUS leverages a unified adaptive aggregation method to intelligently integrate 2D slices-level predictions into comprehensive 3D patient-level diagnosis. Trained and tested on 3,300 patients (40,672 slices), and externally validated on 1,345 patients (18,498 slices) across four different-tier centers and diverse OCT devices, FOCUS achieved high F1 scores for quality assessment (99.01%), abnormally detection (97.46%), and patient-level diagnosis (94.39%). Real-world validation across centers also showed stable performance (F1: 90.22%-95.24%). In human-machine comparisons, FOCUS matched expert performance in abnormality detection (F1: 95.47% vs 90.91%) and multi-disease diagnosis (F1: 93.49% vs 91.35%), while demonstrating better efficiency. FOCUS automates the image-to-diagnosis pipeline, representing a critical advance towards unmanned ophthalmology with a validated blueprint for autonomous screening to enhance population scale retinal care accessibility and efficiency.
