Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices-A Feasibility Study.

Sager, Philipp; Näf, Lukas; Vu, Erwin; Fischer, Tim; Putora, Paul M.; Ehret, Felix; Fürweger, Christoph; Schröder, Christina; Förster, Robert; Zwahlen, Daniel R.; Muacevic, Alexander; Windisch, Paul (2021). Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices-A Feasibility Study. Diagnostics, 11(9) MDPI 10.3390/diagnostics11091676

[img]
Preview
Text
diagnostics-11-01676.pdf - Published Version
Available under License Creative Commons: Attribution (CC-BY).

Download (3MB) | Preview

Introduction: Many proposed algorithms for tumor detection rely on 2.5/3D convolutional neural networks (CNNs) and the input of segmentations for training. The purpose of this study is therefore to assess the performance of tumor detection on single MRI slices containing vestibular schwannomas (VS) as a computationally inexpensive alternative that does not require the creation of segmentations. Methods: A total of 2992 T1-weighted contrast-enhanced axial slices containing VS from the MRIs of 633 patients were labeled according to tumor location, of which 2538 slices from 539 patients were used for training a CNN (ResNet-34) to classify them according to the side of the tumor as a surrogate for detection and 454 slices from 94 patients were used for internal validation. The model was then externally validated on contrast-enhanced and non-contrast-enhanced slices from a different institution. Categorical accuracy was noted, and the results of the predictions for the validation set are provided with confusion matrices. Results: The model achieved an accuracy of 0.928 (95% CI: 0.869-0.987) on contrast-enhanced slices and 0.795 (95% CI: 0.702-0.888) on non-contrast-enhanced slices from the external validation cohorts. The implementation of Gradient-weighted Class Activation Mapping (Grad-CAM) revealed that the focus of the model was not limited to the contrast-enhancing tumor but to a larger area of the cerebellum and the cerebellopontine angle. Conclusions: Single-slice predictions might constitute a computationally inexpensive alternative to training 2.5/3D-CNNs for certain detection tasks in medical imaging even without the use of segmentations. Head-to-head comparisons between 2D and more sophisticated architectures could help to determine the difference in accuracy, especially for more difficult tasks.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Haematology, Oncology, Infectious Diseases, Laboratory Medicine and Hospital Pharmacy (DOLS) > Clinic of Radiation Oncology

UniBE Contributor:

Putora, Paul Martin

Subjects:

600 Technology > 610 Medicine & health

ISSN:

2075-4418

Publisher:

MDPI

Language:

English

Submitter:

Beatrice Scheidegger

Date Deposited:

09 Nov 2021 09:37

Last Modified:

09 Nov 2021 09:45

Publisher DOI:

10.3390/diagnostics11091676

PubMed ID:

34574017

Uncontrolled Keywords:

artificial intelligence deep learning machine learning neuro-oncology schwannoma vestibular

BORIS DOI:

10.48350/160332

URI:

https://boris.unibe.ch/id/eprint/160332

Actions (login required)

Edit item Edit item
Provide Feedback