Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas
Yıl: 2022 Cilt: 37 Sayı: 1 Sayfa Aralığı: 36 - 43 Metin Dili: İngilizce DOI: 10.4274/MMJ.galenos.2022.58538 İndeks Tarihi: 23-06-2022
Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas
Öz: Objective: This study aims to develop neural networks to detect hormone
secretion profiles in the pituitary adenomas based on T2 weighted
magnetic resonance imaging (MRI) radiomics.
Methods: This retrospective model-development study included a
cohort of patients with pituitary adenomas (n=130) from January 2015 to
January 2020 in one tertiary center. The mean age was 46.49±13.69 years,
and 76/130 (58.46%) were women. Three observers segmented lesions on
coronal T2 weighted MRI, and an interrater agreement was evaluated using
the Dice coefficient. Predictors were determined as radiomics features
(n=851). Feature selection was based on intraclass correlation coefficient,
coefficient variance, variance inflation factor, and LASSO regression
analysis. Outcomes were identified as 7 hormone secretion profiles [non-
functioning pituitary adenoma, growth hormone-secreting adenomas,
prolactinomas, adrenocorticotropic hormone-secreting adenomas,
pluri-hormonal secreting adenomas (PHA), follicle-stimulating hormone
and luteinizing hormone-secreting adenomas, and thyroid-stimulating
hormone adenomas]. A multivariable diagnostic prediction model was
developed with artificial neural networks (ANN) for 7 outcomes. ANN
performance was presented as an area under the receiver operating
characteristic curve (AUC) and accepted as successful if the AUC was
>0.85 and p-value was <0.01.
Results: The performance of the ANN distinguishing prolactinomas from
other adenomas was validated (AUC=0.95, p<0.001, sensitivity: 91%, and
specificity: 98%). The model distinguishing PHA had the lowest AUC
(AUC=0.74 and p<0.001). The AUC values for the other five ANN were
>0.85 and p values were <0.001.
Conclusions: This study was successful in training neural networks that
could differentiate the hormone secretion profile of pituitary adenomas.
Anahtar Kelime: Hipofiz Makroadenomlarında T2-MRG Tabanlı Radyomiks ve Sinir Ağları ile Hormon Salgılama Profilinin Tahmini
Öz: Amaç: Bu çalışma, T2 ağırlıklı manyetik rezonans görüntüleme (MRG)
radyomikslerine dayalı olarak hipofiz adenomlarında hormon salgılama
profillerini tespit etmek için sinir ağları geliştirmeyi amaçlamaktadır.
Yöntemler: Bu retrospektif model geliştirme çalışması, üçüncü
basamak bir merkezde Ocak 2015 ile Ocak 2020 arasında hipofiz
adenomu olan hastalardan oluşan bir kohortu içermektedir (n=130).
Ortalama hasta yaşı 46,49±13,69 yıldır ve 76/130’u (%58,46) kadındır.
Üç gözlemci, koronal T2 ağırlıklı MRG’de lezyonları segmente etti ve
Dice katsayısı kullanılarak gözlemciler arası uyum değerlendirildi.
Prediktörler radyomiks parametreleri olarak belirlendi (n=851).
Parametre seçimi, sınıf içi korelasyon katsayısına, katsayı varyansına,
varyans inflasyon faktörüne ve LASSO regresyon analizine
dayanmaktadır. Sonuçlar yedi farklı hormon salgılama profili olarak
tanımlandı [non-fonksiyone hipofiz adenomu, büyüme hormonu
salgılayan adenomlar, prolaktinomalar, adrenokortikotropik hormon
salgılayan adenomlar, pluri-hormonal adenomlar (PLSA), folikül uyarıcı
hormon ve luteinize edici hormon salgılayan adenomlar ile tiroid
uyarıcı hormon salgılayan adenomlar]. Yedi hormon için yapay sinir
ağları (YSA) ile çok değişkenli bir tanısal tahmin modeli geliştirildi. YSA
performansı, alıcı işletim karakteristik eğrisinin altındaki alan (AUC)
olarak sunuldu ve AUC >0,85 ve p değeri <0,01 başarılı kabul edildi.
Bulgular: YSA, AUC=0,95, p<0,001, duyarlılık: %91, özgüllük: %98
değerleri ile prolaktinomaları diğer adenomlardan ayırabildi. PLSA için
AUC=0,74 ve p<0,001’di. Diğer beş YSA için ise AUC değerleri >0,85 ve
p<0,001 idi.
Sonuçlar: Bu çalışma, hipofiz adenomlarının hormon salgılama
profilini ayırt edebilen sinir ağlarının eğitiminde başarılı olmuştur.
Anahtar Kelime: Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
- 1. Dolecek TA, Propp JM, Stroup NE, Kruchko C. CBTRUS Statistical Report: Primary Brain and Central Nervous System Tumors Diagnosed in the United States in 2005-2009. Neuro Oncol. 2012;14(Suppl 5):1-49.
- 2. Ezzat S, Asa SL, Couldwell WT, et al. The prevalence of pituitary adenomas: A systematic review. Cancer. 2004;101:613-9.
- 3. Guo S, Wang Z, Kang X, Xin W, Li X. A Meta-Analysis of Endoscopic vs. Microscopic Transsphenoidal Surgery for Non-functioning and Functioning Pituitary Adenomas: Comparisons of Efficacy and Safety. Front Neurol. 2021;12:614382.
- 4. Agustsson TT, Baldvinsdottir T, Jonasson JG, et al. The epidemiology of pituitary adenomas in Iceland, 1955-2012: a nationwide population-based study. Eur J Endocrinol. 2015;173:655-64.
- 5. Raappana A, Koivukangas J, Ebeling T, Pirilä T. Incidence of pituitary adenomas in Northern Finland in 1992-2007. J Clin Endocrinol Metab. 2010;95:4268-75.
- 6. Tjörnstrand A, Gunnarsson K, Evert M, et al. The incidence rate of pituitary adenomas in western Sweden for the period 2001-2011. Eur J Endocrinol. 2014;171:519-26.
- 7. Sivakumar W, Chamoun R, Nguyen V, Couldwell WT. Incidental pituitary adenomas. Neurosurg Focus. 2011;31:18.
- 8. Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: Extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48:441-6.
- 9. Lu CF, Hsu FT, Hsieh KL, et al. Machine Learning-Based Radiomics for Molecular Subtyping of Gliomas. Clin Cancer Res. 2018;24:4429-36.
- 10. Huang YQ, Liang CH, He L, et al. Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer. J Clin Oncol. 2016;34:2157- 64.
- 11. Cuocolo R, Ugga L, Solari D, et al. Prediction of pituitary adenoma surgical consistency: radiomic data mining and machine learning on T2-weighted MRI. Neuroradiology. 2020;62:1649-56.
- 12. Peng A, Dai H, Duan H, et al. A machine learning model to precisely immunohistochemically classify pituitary adenoma subtypes with radiomics based on preoperative magnetic resonance imaging. Eur J Radiol. 2020;125:108892.
- 13. Zeynalova A, Kocak B, Durmaz ES, et al. Preoperative evaluation of tumour consistency in pituitary macroadenomas: a machine learning-based histogram analysis on conventional T2-weighted MRI. Neuroradiology. 2019;61:767-74.
- 14. Fan Y, Hua M, Mou A, et al. Preoperative noninvasive radiomics approach predicts tumor consistency in patients with acromegaly: Development and multicenter prospective validation. Front Endocrinol (Lausanne). 2019;10:403.
- 15. Rui W, Wu Y, Ma Z, et al. MR textural analysis on contrast enhanced 3D-SPACE images in assessment of consistency of pituitary macroadenoma. Eur J Radiol. 2019;110:219-24.
- 16. European Society of Radiology (ESR). ESR Statement on the Validation of Imaging Biomarkers. Insights Imaging. 2020;11:76.
- 17. Park JE, Kim D, Kim HS, et al. Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement. Eur Radiol. 2020;30:523-36.
- 18. Bossuyt PM, Reitsma JB, Bruns DE, et al. STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies. Radiology. 2015;277:826-32.
- 19. Jaremko JL, Azar M, Bromwich R, et al. Canadian Association of Radiologists White Paper on Ethical and Legal Issues Related to Artificial Intelligence in Radiology. Can Assoc Radiol J. 2019;70:107-18.
- 20. Geis JR, Brady AP, Wu CC, et al. Ethics of artificial intelligence in radiology: Summary of the joint European and North American multisociety statement. Radiology. 2019;293:436-40.
- 21. European Society of Radiology (ESR). What the radiologist should know about artificial intelligence - an ESR white paper. Insights Imaging. 2019;10:44.
- 22. Koo TK, Li MY. A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. J Chiropr Med. 2016;15:155-63.
- 23. Kim JH. Multicollinearity and misleading statistical results. Korean J Anesthesiol. 2019;72:558-69
APA | BAYSAL B, Eser M, Dogan M, KURSUN M (2022). Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. , 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
Chicago | BAYSAL Begumhan,Eser Mehmet Bilgin,Dogan Mahmut Bilal,KURSUN Muhammet Arif Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. (2022): 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
MLA | BAYSAL Begumhan,Eser Mehmet Bilgin,Dogan Mahmut Bilal,KURSUN Muhammet Arif Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. , 2022, ss.36 - 43. 10.4274/MMJ.galenos.2022.58538 |
AMA | BAYSAL B,Eser M,Dogan M,KURSUN M Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. . 2022; 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
Vancouver | BAYSAL B,Eser M,Dogan M,KURSUN M Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. . 2022; 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
IEEE | BAYSAL B,Eser M,Dogan M,KURSUN M "Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas." , ss.36 - 43, 2022. 10.4274/MMJ.galenos.2022.58538 |
ISNAD | BAYSAL, Begumhan vd. "Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas". (2022), 36-43. https://doi.org/10.4274/MMJ.galenos.2022.58538 |
APA | BAYSAL B, Eser M, Dogan M, KURSUN M (2022). Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. Medeniyet Medical Journal, 37(1), 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
Chicago | BAYSAL Begumhan,Eser Mehmet Bilgin,Dogan Mahmut Bilal,KURSUN Muhammet Arif Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. Medeniyet Medical Journal 37, no.1 (2022): 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
MLA | BAYSAL Begumhan,Eser Mehmet Bilgin,Dogan Mahmut Bilal,KURSUN Muhammet Arif Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. Medeniyet Medical Journal, vol.37, no.1, 2022, ss.36 - 43. 10.4274/MMJ.galenos.2022.58538 |
AMA | BAYSAL B,Eser M,Dogan M,KURSUN M Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. Medeniyet Medical Journal. 2022; 37(1): 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
Vancouver | BAYSAL B,Eser M,Dogan M,KURSUN M Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas. Medeniyet Medical Journal. 2022; 37(1): 36 - 43. 10.4274/MMJ.galenos.2022.58538 |
IEEE | BAYSAL B,Eser M,Dogan M,KURSUN M "Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas." Medeniyet Medical Journal, 37, ss.36 - 43, 2022. 10.4274/MMJ.galenos.2022.58538 |
ISNAD | BAYSAL, Begumhan vd. "Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas". Medeniyet Medical Journal 37/1 (2022), 36-43. https://doi.org/10.4274/MMJ.galenos.2022.58538 |