Spatial–Texture Hybrid MRI Model for Orbital Lymphoma Typing
The ability to distinguish between mucosa‐associated lymphoid tissue (MALT) and non‐MALT orbital lymphomas aids ophthalmologists in opting for either conservative or aggressive treatment strategies. Radiographic assessment is a noninvasive approach to diagnose orbital lesions. This study aims to develop a hybrid model leveraging magnetic resonance imaging scans to discern between MALT and non‐MALT orbital lymphomas. The occupation of the tumor alters the relative positions of structures in the orbit. Hence, for the first time, the relative spatial positional features are extracted between different orbital structures and the tumor, complemented by the texture characteristics of the tumor area, to perform hybrid modeling. To validate this idea, 114 orbital lymphoma patients were are included. Statistical analysis reveals significant differences between the two groups in terms of four spatial features (lymphoma lesion, eyeball, inferior rectus, and optic nerve) and two texture features (angular second moment and contrast). The accuracy of the classifier based on spatial, texture, and hybrid features is 84.7, 83.1, and 88.3%, respectively. The innovative hybrid model offers a supportive approach for the differentiation of MALT and non‐MALT orbital lymphomas, enhancing the clinical decision‐making process. To facilitate the use of this hybrid model, a web‐based diagnostic tool has been launched at https://ads.testop.top.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Spatial–Texture Hybrid MRI Model for Orbital Lymphoma Typing ; day:02 ; month:03 ; year:2025 ; extent:13
Advanced intelligent systems ; (02.03.2025) (gesamt 13)
- Urheber
-
Li, Lunhao
Wei, Lai
Shi, Jiahao
Zhai, Guangtao
Hu, Menghan
Zhou, Yixiong
- DOI
-
10.1002/aisy.202400595
- URN
-
urn:nbn:de:101:1-2503031306169.343609485292
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:33 MESZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Li, Lunhao
- Wei, Lai
- Shi, Jiahao
- Zhai, Guangtao
- Hu, Menghan
- Zhou, Yixiong