ZebRA, an open-source software tool for analyzing single cancer cells injected into zebrafish models: architecture and cell radiomics.

Mamaani Mamaan, Wafa (2026) ZebRA, an open-source software tool for analyzing single cancer cells injected into zebrafish models: architecture and cell radiomics. [Laurea magistrale], Università di Bologna, Corso di Studio in Physics [LM-DM270], Documento full-text non disponibile
Il full-text non è disponibile per scelta dell'autore. (Contatta l'autore)

Abstract

Zebrafish (*Danio rerio*) xenograft models are widely used in cancer research because their optical transparency enables *in vivo* observation of fluorescently labelled tumor cells and acquisition of 3D multichannel microscopy data. This thesis presents *ZebRA* (*Zebrafish Radiomic Analysis*), an open-source *MATLAB*-based platform for analysing single cancer cells in zebrafish models. It focuses on software architecture and object-level radiomic analysis. The platform supports “.ND2” and “.TIFF” files and integrates visualization, segmentation masks, 3D reconstruction, and radiomic feature extraction. Segmentation is treated as an upstream component, while the main contribution concerns software architecture, data management, object organization, and quantitative feature extraction. The radiomics module extracts object, intensity, shape, and texture features for visualization and export. The workflow was evaluated using zebrafish xenograft microscopy data and a manually segmented reference dataset. Object correspondence was established using 3D spatial overlap and reciprocal mutual-best matching. From 95 matched pairs, 30 were randomly selected with a fixed seed to validate six morphological features. Mean Absolute Percentage Error ranged from 11.95% for Equivalent Sphere Diameter to 32.61% for Volume, and all six features showed significant positive correlations between manual and *ZebRA*-derived measurements. Higher segmentation overlap was associated with lower error for Volume, Surface Area, and Equivalent Sphere Diameter. These results show that *ZebRA* provides an integrated framework for volumetric microscopy and object-level radiomics while highlighting the influence of segmentation agreement on downstream measurements. Its modular architecture supports future extensions in radiomics, 3D visualization, validation, and machine-learning analysis.

Abstract
Tipologia del documento
Tesi di laurea (Laurea magistrale)
Autore della tesi
Mamaani Mamaan, Wafa
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Indirizzo
Applied Physics
Ordinamento Cds
DM270
Parole chiave
Zebrafish,Microscopy,Image Processing,Software Design,Radiomics
Data di discussione della Tesi
29 Ottobre 2026
URI

Altri metadati

Gestione del documento: Visualizza il documento

^