ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2404.02614
82
1
v1v2 (latest)

Vestibular schwannoma growth_prediction from longitudinal MRI by time conditioned neural fields

3 April 2024
Yunjie Chen
J. Wolterink
O. M. Neve
Stephan R. Romeijn
Berit M. Verbist
Erik F. Hensen
Qian Tao
Marius Staring
ArXiv (abs)PDFHTMLGithub (4★)
Abstract

Vestibular schwannomas (VS) are benign tumors that are generally managed by active surveillance with MRI examination. To further assist clinical decision-making and avoid overtreatment, an accurate prediction of tumor growth based on longitudinal imaging is highly desirable. In this paper, we introduce DeepGrowth, a deep learning method that incorporates neural fields and recurrent neural networks for prospective tumor growth prediction. In the proposed method, each tumor is represented as a signed distance function (SDF) conditioned on a low-dimensional latent code. Unlike previous studies that perform tumor shape prediction directly in the image space, we predict the latent codes instead and then reconstruct future shapes from it. To deal with irregular time intervals, we introduce a time-conditioned recurrent module based on a ConvLSTM and a novel temporal encoding strategy, which enables the proposed model to output varying tumor shapes over time. The experiments on an in-house longitudinal VS dataset showed that the proposed model significantly improved the performance (≥1.6%\ge 1.6\%≥1.6% Dice score and ≥0.20\ge0.20≥0.20 mm 95\% Hausdorff distance), in particular for top 20\% tumors that grow or shrink the most (≥4.6%\ge 4.6\%≥4.6% Dice score and ≥0.73\ge 0.73≥0.73 mm 95\% Hausdorff distance). Our code is available at ~\burl{https://github.com/cyjdswx/DeepGrowth}

View on arXiv
Comments on this paper