Szczegóły publikacji
Opis bibliograficzny
Glioma classification using multimodal radiology and histology data / Azam Hamidinekoo, Tomasz PIĘCIAK, Maryam Afzali, Otar Akanyeti, Yinyin Yuan // W: Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries : 6th international workshop, BrainLes 2020 : held in conjunction with MICCAI 2020 : Lima, Peru, October 4, 2020 : selected papers, Pt. 2 / eds. Alessandro Crimi, Spyridon Bakas. — Cham : Springer Nature Switzerland AG, cop. 2021. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12659. Image Processing, Computer Vision, Pattern Recognition, and Graphics). — ISBN: 978-3-030-72086-5; e-ISBN: 978-3-030-72087-2. — S. 508–518. — Bibliogr. s. 517-518, Abstr. — T. Pięciak - dod. afiliacja: Universidad de Valladolid, Spain
Autorzy (5)
- Hamidinekoo Azam
- AGHPięciak Tomasz
- Afzali Maryam
- Akanyeti Otar
- Yuan Y.
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 133237 |
---|---|
Data dodania do BaDAP | 2021-04-01 |
DOI | 10.1007/978-3-030-72087-2_45 |
Rok publikacji | 2021 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Springer |
Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Gliomas are brain tumours with a high mortality rate. There are various grades and sub-types of this tumour, and the treatment procedure varies accordingly. Clinicians and oncologists diagnose and categorise these tumours based on visual inspection of radiology and histology data. However, this process can be time-consuming and subjective. The computer-assisted methods can help clinicians to make better and faster decisions. In this paper, we propose a pipeline for automatic classification of gliomas into three sub-types: oligodendroglioma, astrocytoma, and glioblastoma, using both radiology and histopathology images. The proposed approach implements distinct classification models for radiographic and histologic modalities and combines them through an ensemble method. The classification algorithm initially carries out tile-level (for histology) and slice-level (for radiology) classification via a deep learning method, then tile/slice-level latent features are combined for a whole-slide and whole-volume sub-type prediction. The classification algorithm was evaluated using the data set provided in the CPM-RadPath 2020 challenge. The proposed pipeline achieved the F1-Score of 0.886, Cohen’s Kappa score of 0.811 and Balance accuracy of 0.860. The ability of the proposed model for end-to-end learning of diverse features enables it to give a comparable prediction of glioma tumour sub-types.