PuSH - Publication Server of Helmholtz Zentrum München

Erdur, A.C.* ; Scholz, D.* ; Buchner, J.A.* ; Combs, S.E. ; Rueckert, D.* ; Peeken, J.C.

All Sizes Matter: Improving volumetric brain segmentation on small lesions.

In: (Brain Tumor Segmentation, and Cross-Modality Domain Adaptation for Medical Image Segmentation). Berlin [u.a.]: Springer, 2024. 177-189 (Lect. Notes Comput. Sc. ; 14669 LNCS)
DOI
Open Access Green as soon as Postprint is submitted to ZB.
Brain metastases (BMs) are the most frequently occurring brain tumors. The treatment of patients having multiple BMs with stereotactic radiosurgery necessitates accurate localization of the metastases. Neural networks can assist in this time-consuming and costly task that is typically performed by human experts. Particularly challenging is the detection of small lesions since they are often underrepresented in existing approaches. Yet, lesion detection is equally important for all sizes. In this work, we develop an ensemble of neural networks explicitly focused on detecting and segmenting small BMs. To accomplish this task, we trained several neural networks focusing on individual aspects of the BM segmentation problem: We use blob loss that specifically addresses the imbalance of lesion instances in terms of size and texture and is, therefore, not biased towards larger lesions. In addition, a model using a subtraction sequence between the T1 and T1 contrast-enhanced sequence focuses on low-contrast lesions. Furthermore, we train additional models only on small lesions. Our experiments demonstrate the utility of the additional blob loss and the subtraction sequence. However, including the specialized small lesion models in the ensemble deteriorates segmentation results. We also find domain-knowledge-inspired postprocessing steps to drastically increase our performance in most experiments. Our approach enables us to submit a challenge entry to the ASNR-MICCAI BraTS Brain Metastasis Challenge 2023.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Keywords Blob Loss ; Brain Mri ; Metastasis Segmentation ; Small Lesion Detection
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Conference Title Brain Tumor Segmentation, and Cross-Modality Domain Adaptation for Medical Image Segmentation
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 14669 LNCS, Issue: , Pages: 177-189 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Non-patent literature Publications
Institute(s) Institute of Radiation Medicine (IRM)