Abstract
Purpose
The estimated incidence of pituitary adenomas in the general population is 10–30%, yet radiographic diagnosis remains a challenge. Diagnosis is complicated by the heterogeneity of radiographic features in both normal (e.g. complex anatomy, pregnancy) and pathologic states (e.g. primary endocrinopathy, hypophysitis). Clinical symptoms and laboratory testing are often equivocal, which can result in misdiagnosis or unnecessary specialist referrals. Computer vision models can aid in pituitary adenoma diagnosis; however, a major challenge to model development is the lack of dedicated pituitary imaging datasets. We hypothesized that deep volumetric segmentation models trained to extract the sellar and parasellar region from existing whole-brain MRI scans could be used to generate a novel dataset of pituitary imaging.
Methods
Six open-source whole-brain MRI datasets, created for research purposes, were included for model development. Deep learning-based volumetric segmentation models were trained using 318 manually annotated MRI scans from a single open-source MRI dataset. Out-of-distribution volumetric segmentation performance was then tested on 418 MRIs from five held-out research datasets.
Results
On our annotated images, agreement between manual and model volumetric segmentations was high. Dice scores (a measure of overlap) ranged 0.76–0.82 for both in-distribution and out-of-distribution model testing. In total, 6,755 MRIs from six data sources were included in the final generated pituitary dataset.
Conclusions
We present the first and largest dataset of pituitary imaging constructed using existing MRI data and deep volumetric segmentation models trained to identify sellar and parasellar anatomy. The model generalizes well across patient populations and MRI scanner types. We hope our pituitary dataset will be an integral part of future machine learning research on pituitary pathologies.
Similar content being viewed by others
References
Ezzat S, Asa SL, Couldwell WT, Barr CE, Dodge WE, Vance ML, McCutcheon IE (2004) The prevalence of pituitary adenomas: a systematic review. Cancer 101(3):613–619. https://doi.org/10.1002/cncr.20412
Choi SH, Kwon BJ, Na DG, Kim JH, Han MH, Chang KH (2007) Pituitary adenoma, craniopharyngioma, and Rathke cleft cyst involving both intrasellar and suprasellar regions: differentiation using MRI. Clin Radiol 62(5):453–462. https://doi.org/10.1016/j.crad.2006.12.001
Heck A, Ringstad G, Fougner SL, Casar-Borota O, Nome T, Ramm-Pettersen J, Bollerslev J (2012) Intensity of pituitary adenoma on T2-weighted magnetic resonance imaging predicts the response to octreotide treatment in newly diagnosed acromegaly. Clin Endocrinol (Oxf) 77(1):72–78. https://doi.org/10.1111/j.1365-2265.2011.04286.x
Altshuler DB, Andrews CA, Parmar HA, Sullivan SE, Trobe JD (2021) Imaging errors in distinguishing pituitary adenomas from other sellar lesions. J Neuroophthalmol 41(4):512–518. https://doi.org/10.1097/WNO.0000000000001164
Chandler WF, Barkan AL, Hollon T, Sakharova A, Sack J, Brahma B, Schteingart DE (2016) Outcome of transsphenoidal surgery for Cushing disease: A single-center experience over 32 years. Neurosurgery 78(2):216–223. https://doi.org/10.1227/NEU.0000000000001011
Fan Y, Jiang S, Hua M, Feng S, Feng M, Wang R (2019) Machine learning-based radiomics predicts radiotherapeutic response in patients with acromegaly. Front Endocrinol (Lausanne) 10:588. https://doi.org/10.3389/fendo.2019.00588
Swinburne NC, Schefflein J, Sakai Y, Oermann EK, Titano JJ, Chen I, Tadayon S, Aggarwal A, Doshi A, Nael K (2019) Machine learning for semi-automated classification of glioblastoma, brain metastasis and central nervous system lymphoma using magnetic resonance advanced imaging. Ann Transl Med 7(11):232. https://doi.org/10.21037/atm.2018.08.05
Titano JJ, Badgeley M, Schefflein J, Pain M, Su A, Cai M, Swinburne N, Zech J, Kim J, Bederson J, Mocco J, Drayer B et al (2018) Automated deep-neural-network surveillance of cranial images for acute neurologic events. Nat Med 24(9):1337–1341. https://doi.org/10.1038/s41591-018-0147-y
Rajkomar A, Dean J, Kohane I (2019) Machine learning in medicine. N Engl J Med 380(14):1347–1358. https://doi.org/10.1056/NEJMra1814259
Crawford KL, Neu SC, Toga AW (2016) The Image and Data Archive at the Laboratory of Neuro Imaging. NeuroImage 124(Pt B):1080–1083. https://doi.org/10.1016/j.neuroimage.2015.04.067
Di Martino A, Yan CG, Li Q, Denio E, Castellanos FX, Alaerts K, Anderson JS, Assaf M, Bookheimer SY, Dapretto M, Deen B, Delmonte S et al (2014) The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry 19(6):659–667. https://doi.org/10.1038/mp.2013.78
Petersen RC, Aisen PS, Beckett LA, Donohue MC, Gamst AC, Harvey DJ, Jack CR Jr, Jagust WJ, Shaw LM, Toga AW, Trojanowski JQ, Weiner MW (2010) Alzheimer’s Disease Neuroimaging Initiative (ADNI): clinical characterization. Neurology 74(3):201–209. https://doi.org/10.1212/WNL.0b013e3181cb3e25
Ellis KA, Bush AI, Darby D, De Fazio D, Foster J, Hudson P, Lautenschlager NT, Lenzo N, Martins RN, Maruff P, Masters C, Milner A et al (2009) The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging: methodology and baseline characteristics of 1112 individuals recruited for a longitudinal study of Alzheimer’s disease. Int Psychogeriatr 21(4):672–687. https://doi.org/10.1017/S1041610209009405
Marek K, Jennings D, Lasch S, Siderowf A, Tanner C, Simuni T, Coffey C et al (2011) The Parkinson Progression Marker Initiative (PPMI). Prog Neurobiol 95(4):629–635. https://doi.org/10.1016/j.pneurobio.2011.09.005
Mazziotta J, Toga A, Evans A, Fox P, Lancaster J, Zilles K, Woods R, Paus T, Simpson G, Pike B, Holmes C, Collins L et al (2001) A probabilistic atlas and reference system for the human brain: International Consortium for Brain Mapping (ICBM). Philos Trans R Soc Lond B Biol Sci 356(1412):1293–1322. https://doi.org/10.1098/rstb.2001.0915
Pieper S, Halle M, Kikinis R (2004) 3D slicer. 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro, ISBI 2004, April 15–18. Vol IEEE Cat No. 04EX821. Washington, DC. IEEE; 2004:632–635
MONAI Consortium (2020) Project MONAI. Zenodo. https://doi.org/10.5281/zenodo.4323059
Huang H, Lin L, Tong R, Hu H, Zhang Q, Iwamoto Y, Han X, Chen Y-W, Wu J UNet 3+: A full-scale connected UNet for medical image segmentation. IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP(2020) 2020, May 4. Barcelona, Spain. IEEE; 2020:1055–1059
Luo Z, Zhang Y, Zhou L, Zhang B, Luo J, Wu H (2019) Micro-vessel image segmentation based on the AD-UNet model. IEEE Access 7:143402–143411. https://doi.org/10.1109/ACCESS.2019.2945556
Qiang Z, Tu S, Xu L(2019) A k-Dense-UNet for biomedical image segmentation. In: Cui Z, Pan J, Zhang S, Xiao L, Yang J, eds. Intelligence Science and Big Data Engineering. Visual Data Engineering. Proceedings of the 9th International Conference, IScIDE 2019, October 17–20. Nanjing, China. Springer; 2019:552–562
Shi T, Jiang H, Zheng B (2020) A stacked generalization U-shape network based on zoom strategy and its application in biomedical image segmentation. Comput Methods Programs Biomed 197:105678. https://doi.org/10.1016/j.cmpb.2020.105678
Weng Y, Zhou T, Li Y, Qiu X (2019) NAS-Unet: Neural architecture search for medical image segmentation. IEEE Access 7:44247–44257. https://doi.org/10.1109/ACCESS.2019.2908991
Kerfoot E, Clough J, Oksuz I, Lee J, King AP, Schnabel JA(2019) Left-ventricle quantification using residual U-Net. In: Pop M, Sermesant M, Zhao J, et al., eds. Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. 9th International Workshop, STACOM 2018, September 16. Granada, Spain. Springer; 2019:371–380
Milletari F, Navab N, Ahmadi S(2016) V-Net: Fully convolutional neural networks for volumetric medical image segmentation. 2016 Fourth International Conference on 3D Vision (3DV), October 25–28. Stanford University. IEEE; 2016:565–571
Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, Roth H, Xu D(2021) UNETR: Transformers for 3D medical image segmentation. arXiv:2103.10504 [eess.IV]
Heinrich MP, Oktay O, Bouteldja N (2019) OBELISK-Net: Fewer layers to solve 3D multi-organ segmentation with sparse deformable convolutions. Med Image Anal 54:1–9. https://doi.org/10.1016/j.media.2019.02.006
Hu Y, Gibson E, Barratt DC, Emberton M, Alison Noble J, Vercauteren T(2019) Conditional segmentation in lieu of image registration. arXiv:1907.00438 [eess.IV].
Lowekamp BC, Chen DT, Ibanez L, Blezek D (2013) The design of SimpleITK. Front Neuroinform 7:45. https://doi.org/10.3389/fninf.2013.00045
Yaniv Z, Lowekamp BC, Johnson HJ, Beare R (2018) SimpleITK image-analysis notebooks: a collaborative environment for education and reproducible research. J Digit Imaging 31(3):290–303
Paterno V, Fahlbusch R (2014) High-field iMRI in transsphenoidal pituitary adenoma surgery with special respect to typical localization of residual tumor. Acta Neurochir (Wien) 156(3):463–474 discussion 474. https://doi.org/10.1007/s00701-013-1978-4
Li H, Zhao Q, Zhang Y, Sai K, Xu L, Mou Y, Xie Y, Ren J, Jiang X (2021) Image-driven classification of functioning and nonfunctioning pituitary adenoma by deep convolutional neural networks. Comput Struct Biotechnol J 19:3077–3086. https://doi.org/10.1016/j.csbj.2021.05.023
Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK (2018) Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med 15(11):e1002683. https://doi.org/10.1371/journal.pmed.1002683
Funding
This work was supported by the Neurosurgery Research & Education Foundation (2021 Medical Student Summer Research Fellowship to R. Gologorsky).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors report no relevant conflicts of interest.
Compliance with ethical standards
While our research was done using human MRI data, these data were anonymized and are publicly available. No informed consent was required to complete the study.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Gologorsky, R., Harake, E., von Oiste, G. et al. Generating novel pituitary datasets from open-source imaging data and deep volumetric segmentation. Pituitary 25, 842–853 (2022). https://doi.org/10.1007/s11102-022-01255-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11102-022-01255-7