Longitudinal Vestibular Schwannoma Dataset with Consensus-based Human-in-the-loop Annotations

TL;DR

This paper introduces a large, consensus-annotated MRI dataset for vestibular schwannoma, and presents a human-in-the-loop deep learning framework that improves segmentation accuracy and efficiency across diverse clinical datasets.

Contribution

It provides a publicly accessible, consensus-based longitudinal MRI dataset and develops a novel iterative, human-in-the-loop deep learning approach for robust vestibular schwannoma segmentation.

Findings

Segmentation accuracy improved from DSC 0.9125 to 0.9670.

Model generalizes well across multiple datasets.

Efficiency increased by approximately 37.4%.

Abstract

Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62).