UltraFlwr -- An Efficient Federated Surgical Object Detection Framework

TL;DR

UltraFlwr is a federated learning framework that enables efficient, privacy-preserving surgical object detection using YOLO, addressing data heterogeneity and communication challenges in multi-institutional laparoscopic video analysis.

Contribution

We introduce UltraFlwr, supporting native Partial Aggregation of YOLO components, and provide a systematic empirical study of federated YOLO training under diverse clinical scenarios.

Findings

Aggregating backbone and neck components yields performance close to full aggregation.

Standard FL methods reduce inter-client performance variability.

Improving data consistency within clients benefits federated learning despite increased distribution shift.

Abstract

Surgical object detection in laparoscopic videos enables real-time instrument identification for workflow analysis and skills assessment, but training robust models such as You Only Look Once (YOLO) is challenged by limited data, privacy constraints, and inter-institutional variability. Federated learning (FL) enables collaborative training without sharing raw data, yet practical support for modern YOLO pipelines under heterogeneous surgical data remains limited. We present UltraFlwr, an open-source, communication-efficient, and edge-deployable framework that integrates Ultralytics YOLO with the Flower FL platform and supports native Partial Aggregation (PA) of YOLO components (backbone, neck, head). Using two public laparoscopic surgical tool detection datasets, we conduct a systematic empirical study of federated YOLO training under Independent and Identically Distributed (IID) and multiple clinically motivated heterogeneous scenarios, including differences in data curation, video length, and label availability. Results show that standard FL aggregators (e.g., FedAvg) do not consistently match centralized training per client, but reduce inter-client performance variability. Aggregating both backbone and neck components achieves performance comparable to full aggregation with lower communication costs. Also, improving within-client data consistency can benefit FL even when it increases distribution shift across clients. These findings provide practical guidance for deploying federated YOLO-based object detection in heterogeneous surgical environments. UltraFlwr is publicly available at https://github.com/KCL-BMEIS/UltraFlwr.