Background Brain extraction is a common preprocessing step when working with intracranial medical imaging data. While several tools exist to automate the preprocessing of magnetic resonance imaging (MRI) of the human brain, none are available for canine MRIs. We present a pipeline mapping separate 2D scans to a 3D image, and a neural network for canine brain extraction. Methodology The training dataset consisted of T1-weighted and contrast-enhanced images from 68 dogs of different breeds, all cranial conformations (mesaticephalic, dolichocephalic, brachycephalic), with several pathological conditions, taken at three institutions. Testing was performed on a similarly diverse group of 10 dogs with images from a 4th institution. Results The model achieved excellent results in terms of Dice (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12917_2025_5003_Article_IEq1.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="80" /> </InlineMediaObject> <EquationSource Format="TEX">\(0.95\pm 0.01\)</EquationSource> </InlineEquation>) and Jaccard (<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12917_2025_5003_Article_IEq2.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="80" /> </InlineMediaObject> <EquationSource Format="TEX">\(0.90\pm 0.01\)</EquationSource> </InlineEquation>) metrics and generalised well across different MRI scanners, the three aforementioned skull types, and variations in head size and breed. The pipeline was effective for a combination of one to three acquisition planes (i.e., transversal, dorsal, and sagittal). Aside from the T1 weighted imaging training datasets, the model also performed well on other MRI sequences with Jaccardian indices and median Dice scores ranging from 0.86 to 0.89 and 0.92 to 0.94, respectively. Conclusions Our approach was robust for automated brain extraction. Variations in canine anatomy and performance degradation in multi-scanner data can largely be mitigated through normalisation and augmentation techniques. Brain extraction, as a preprocessing step, can improve the accuracy of an algorithm for abnormality classification in MRI image slices.

Automated brain extraction for canine magnetic resonance images

期刊论文
出版模式：

开放获取
发表日期：

2025年9月16日

查看全文

Gloria D. Lesta,
Thomas M. Deserno,
Samira Abani,
Jörg Janisch,
Alexej Hänsch,
Merlin Laue,
Stefanie Winzer,
Peter J. Dickinson,
Steven De Decker,
Rodrigo Gutierrez-Quintana,
Aleksandr Subbotin,
Kseniia Bocharova,
Ehren McLarty,
Laura Lemke,
Adriano Wang-Leandro,
Franziska Spohn,
Holger A. Volk,
Jasmin N. Nessler

摘要

Background

Brain extraction is a common preprocessing step when working with intracranial medical imaging data. While several tools exist to automate the preprocessing of magnetic resonance imaging (MRI) of the human brain, none are available for canine MRIs. We present a pipeline mapping separate 2D scans to a 3D image, and a neural network for canine brain extraction.

Methodology

The training dataset consisted of T1-weighted and contrast-enhanced images from 68 dogs of different breeds, all cranial conformations (mesaticephalic, dolichocephalic, brachycephalic), with several pathological conditions, taken at three institutions. Testing was performed on a similarly diverse group of 10 dogs with images from a 4th institution.

Results

The model achieved excellent results in terms of Dice ( \(0.95\pm 0.01\) ) and Jaccard ( \(0.90\pm 0.01\) ) metrics and generalised well across different MRI scanners, the three aforementioned skull types, and variations in head size and breed. The pipeline was effective for a combination of one to three acquisition planes (i.e., transversal, dorsal, and sagittal). Aside from the T1 weighted imaging training datasets, the model also performed well on other MRI sequences with Jaccardian indices and median Dice scores ranging from 0.86 to 0.89 and 0.92 to 0.94, respectively.

Conclusions

Our approach was robust for automated brain extraction. Variations in canine anatomy and performance degradation in multi-scanner data can largely be mitigated through normalisation and augmentation techniques. Brain extraction, as a preprocessing step, can improve the accuracy of an algorithm for abnormality classification in MRI image slices.