Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Apr 20;14(9):2069.
doi: 10.3390/cancers14092069.

Convolutional Neural Networks to Detect Vestibular Schwannomas on Single MRI Slices: A Feasibility Study

Carole Koechli  1 , Erwin Vu  2 , Philipp Sager  1 , Lukas Näf  3 , Tim Fischer  3 , Paul M Putora  2   4 , Felix Ehret  5   6   7 , Christoph Fürweger  7   8 , Christina Schröder  1 , Robert Förster  1 , Daniel R Zwahlen  1 , Alexander Muacevic  7 , Paul Windisch  1   7
Affiliations

Convolutional Neural Networks to Detect Vestibular Schwannomas on Single MRI Slices: A Feasibility Study

Carole Koechli et al. Cancers (Basel). .

Abstract

In this study. we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. A pretrained CNN (ResNet-34) was retrained and internally validated using contrast-enhanced T1-weighted (T1c) MRI slices from one institution. In a second step, the model was externally validated using T1c- and T1-weighted (T1) slices from a different institution. As a substitute, bisected slices were used with and without tumors originating from whole transversal slices that contained part of the unilateral VS. The model predictions were assessed based on the categorical accuracy and confusion matrices. A total of 539, 94, and 74 patients were included for training, internal validation, and external T1c validation, respectively. This resulted in an accuracy of 0.949 (95% CI 0.935-0.963) for the internal validation and 0.912 (95% CI 0.866-0.958) for the external T1c validation. We suggest that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased demand for computational power and the fact that there is no need for segmentations. However, further research is needed on the difference between 2D-CNNs and more complex architectures.

Keywords: artificial intelligence; deep learning; machine learning; neuro-oncology; schwannoma; vestibular.

PubMed Disclaimer

Conflict of interest statement

P.W. has a patent application titled ‘Method for detection of neurological abnormalities’. C.F. and F.E. received speaker honoraria from Accuray outside of the submitted work. The remaining authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Workflow of the training, internal validation, and external validation. ERC: European Radiosurgery Center in Munich; KSSG: Kantonsspital St. Gallen; n: number of slices; T1c: contrast-enhanced T1-weighted; T1: T1-weighted.
Figure 2
Figure 2
Workflow of splitting the magnetic resonance imaging (MRI) slices into a left and right image, resulting in a hemisphere with and without a tumor.
Figure 3
Figure 3
Flattened cross-entropy loss of the training (blue) and internal validation (orange) data set across the 15 unfrozen epochs.
Figure 4
Figure 4
(a) Confusion matrix of the external validation with T1c MRI slices; (b) confusion matrix of the external validation with T1 MRI slices. VS: vestibular schwannoma.
Figure 5
Figure 5
All MRI slices of the external validation data set with the T1c sequence. The images are sorted based on whether they contained a VS and whether they were correctly classified.
Figure 6
Figure 6
All MRI slices of the external validation data set with the T1 sequence. The images are sorted based on whether they contained a VS and whether they were correctly classified.
Figure 7
Figure 7
Sample MRI slices of the T1c data set with and without gradient-weighted class activation mapping (Grad-CAM). (a) The correctly classified images are shown above; (b) the incorrectly classified slices are shown below. Bright yellow and purple correspond with high and low activation, respectively.
See this image and copyright information in PMC

References

    1. Angra S., Ahuja S. Machine Learning and Its Applications: A Review; Proceedings of the 2017 International Conference on Big Data Analytics and Computational Intelligence (ICBDAC); Chirala, India. 23–25 March 2017; pp. 57–60.
    1. Valliani A.A.-A., Ranti D., Oermann E.K. Deep Learning and Neurology: A Systematic Review. Neurol. Ther. 2019;8:351–365. doi: 10.1007/s40120-019-00153-8. - DOI - PMC - PubMed
    1. Tiwari A., Srivastava S., Pant M. Brain Tumor Segmentation and Classification from Magnetic Resonance Images: Review of Selected Methods from 2014 to 2019. Pattern Recognit. Lett. 2020;131:244–260. doi: 10.1016/j.patrec.2019.11.020. - DOI
    1. Ehret F., Kaul D., Clusmann H., Delev D., Kernbach J.M. Machine Learning-Based Radiomics in Neuro-Oncology. Acta Neurochir. Suppl. 2022;134:139–151. - PubMed
    1. Abd-Ellah M.K., Awad A.I., Khalaf A.A.M., Hamed H.F.A. A Review on Brain Tumor Diagnosis from MRI Images: Practical Implications, Key Achievements, and Lessons Learned. Magn. Reson. Imaging. 2019;61:300–318. doi: 10.1016/j.mri.2019.05.028. - DOI - PubMed