MRI texture analysis as a predictor of tumor recurrence or progression in patients with clinically non-functioning pituitary adenomas

Galm, Brandon; Martinez-Salazar, Edgar L; Swearingen, Brooke; Torriani, Martin; Klibanski, Anne; Bredella, Miriam A.; Tritos, Nicholas A.

doi:10.1530/eje-18-0291

Cited by 30 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In regard to the application in NFPAs, radiomics has been used in the evaluation of tumor subtypes, consistency, ki-67 proliferation indices, and cavernous sinus invasion (18)(19)(20)(21)(22), but rarely for the prediction of clinical outcomes (23). The purpose of this study was to investigate the role of radiomics features extracted from segmented tumor sampling for the prediction of P/R in NFPAs.…”

Section: Introductionmentioning

confidence: 99%

Radiomics Approach for Prediction of Recurrence in Non-Functioning Pituitary Macroadenomas

Zhang

Chen

et al. 2020

Front. Oncol.

View full text Add to dashboard Cite

ObjectivesA subset of non-functioning pituitary macroadenomas (NFPAs) may exhibit early progression/recurrence (P/R) after surgical resection. The purpose of this study was to apply radiomics in predicting P/R in NFPAs.MethodsOnly patients who had undergone preoperative MRI and postoperative MRI follow-ups for more than 1 year were included in this study. From September 2010 to December 2017, 50 eligible patients diagnosed with pathologically confirmed NFPAs were identified. Preoperative coronal T2WI and contrast-enhanced (CE) T1WI imaging were analyzed by computer algorithms. For each imaging sequence, 32 first-order features and 75 texture features were extracted. Support vector machine (SVM) classifier was utilized to evaluate the importance of extracted parameters, and the most significant three parameters were used to build the prediction model. The SVM score was calculated based on the three selected features.ResultsTwenty-eight patients exhibited P/R (28/50, 56%) after surgery. The median follow-up time was 38 months, and the median time to P/R was 20 months. Visual disturbance, hypopituitarism, extrasellar extension, compression of the third ventricle, large tumor height and volume, failed optic chiasmatic decompression, and high SVM score were more frequently encountered in the P/R group (p < 0.05). In multivariate Cox hazards analysis, symptoms of sex hormones, hypopituitarism, and SVM score were high risk factors for P/R (p < 0.05) with hazard ratios of 10.71, 2.68, and 6.88. The three selected radiomics features were T1 surface-to-volume radio, T1 GLCM-informational measure of correlation, and T2 NGTDM-coarseness. The radiomics predictive model shows 25 true positive, 16 true negative, 6 false positive, and 3 false negative cases, with an accuracy of 82% and AUC of 0.78 in differentiating P/R from non-P/R NFPAs. For SVM score, optimal cut-off value of 0.537 and AUC of 0.87 were obtained for differentiation of P/R. Higher SVM scores were associated with shorter progression-free survival (p < 0.001).ConclusionsOur preliminary results showed that objective and quantitative MR radiomic features can be extracted from NFPAs. Pending more studies and evidence to support the findings, radiomics analysis of preoperative MRI may have the potential to offer valuable information in treatment planning for NFPAs.

show abstract

Section: Introductionmentioning

confidence: 99%

Radiomics Approach for Prediction of Recurrence in Non-Functioning Pituitary Macroadenomas

Zhang

Chen

et al. 2020

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…In more recent studies, the Trouillas classification of tumor grading based on invasion and proliferation was found to predict recurrence with the highest-grade lesions (2b invasive and proliferative) harboring an almost 9 times higher risk of recurrence than the lowest grade lesions (1a invasive) (33). In other reports, MRI texture analysis parameters enabled the prediction of recurrence even after adjusting for other factors like age, Ki67, and completeness of resection (34). The tumor subtype has been reported to be associated with higher recurrence in some studies but not in others (35)(36)(37).…”

Section: Discussionmentioning

confidence: 96%

Phosphorylated EGFR (pEGFR T693) as a Novel Predictor of Recurrence in Non-Functioning Pituitary Adenomas

et al. 2021

View full text Add to dashboard Cite

PurposeNon-functioning pituitary adenomas (NFPAs) exhibit high recurrence rates after surgery. However, the determinants of recurrence are inconsistent in the available literature. The present study sought to investigate the association between nuclear phosphorylated EGFR (pEGFR) levels and recurrence of NFPAs.MethodsTissue microarrays from patients undergoing adenomectomy for NFPAs at our tertiary care center from 2003 to 2015 and having a minimum of 60 months of follow-up (n=102) were accessed. Immunohistochemical analysis (IHC) was performed to determine the expression of nuclear pEGFR T693. h-score was calculated as the product of staining intensity and the number of positively staining cells. Radiological surveillance (MRI) was performed to categorize NFPAs as recurrent or non-recurrent on follow-up.ResultsThe mean age of the cohort was 50 ± 11 years with a male preponderance (61.1%). Recurrence was observed in 46.1% of the patients at a median of 123 months (IQR 72-159) of follow-up. pEGFR T693 positivity was higher in a significantly greater number of recurrent NFPAs as compared to non-recurrent NFPAs (95.7% vs 81%, p=0.02). h-scores were also significantly higher in recurrent NFPAs (122.1 ± 6 vs 81.54 ± 3.3, p<0.0001). pEGFR T693 positivity significantly predicted recurrence in NFPAs (HR=4.9, CI 2.8-8.8, p<0.0001). ROC analysis revealed an h-score cutoff of 89.8 as being associated significantly with recurrence (sensitivity 80%, specificity 78%, AUC 0.84, p<0.0001).ConclusionpEGFR T693 was expressed in significantly higher number of recurrent NFPAs. The h-scores were also higher in recurrent NFPAs. Nuclear pEGFR T693 may serve as a predictor of recurrence in NFPAs.

show abstract

“…In addition, a recent study observed that MRI texture analysis on T1-weighted images could predict the risk of tumour recurrence or progression after surgery, and this clearly requires further study (Galm et al 2018). Long-term mortality in these patients also appears to be higher than that of the general population (Pagesy et al 1991, Tomlinson et al 2001, Nielsen et al 2007, Olsson et al 2015, Ntali et al 2016, although an improvement has been reported in the last decade, highlighting the efficacy of recent advances in the diagnosis and treatment of PitNETs.…”

Section: Natural Historymentioning

confidence: 99%

The natural history and treatment of non-functioning pituitary adenomas (non-functioning PitNETs)

Yavropoulou

Tsoli

Barkas

et al. 2020

Endocrine-Related Cancer

View full text Add to dashboard Cite

Non-functioning pituitary adenomas, recently alternatively-termed pituitary neuroendocrine tumours (NFpitNETs), are mostly benign neoplasms that are not associated with a hormonal hypersecretory syndrome. The clinical spectrum of NFpitNETs varies from completely asymptomatic to the development of panhypopituitarism and manifestations attributed to mass effects on nearby structures. NFpitNETs follow generally an indolent course, but in 5%-10% of cases they exhibit more aggressive behavior, characterised by rapid growth, invasiveness and early recurrence. The initial size of the adenoma, the presence of symptoms and the histological subtype are related to the natural course of NFpitNETs. Active surveillance is usually the strategy of choice in the case of an asymptomatic NFpitNET, while surgical resection is recommended in case of visual and/or neurological abnormalities or rapid tumour growth. Based on previous and emerging data, approximately 50% of patients show tumour growth while 20% of patients with NF-macroadenomas on active surveillance may require further intervention during a follow-up period of 7 years. Adjuvant radiotherapy is usually considered for large residual tumours or recurrent and/or aggressive adenomas, but there is evidence that medical therapy, especially with cabergoline, can occasionally be beneficial, whereas newer molecular agents are under investigation. Thus, while highly effective medical therapy is awaited, a move towards a more conservative approach seems appropriate, at least until we have better molecular markers of progressiveness.

show abstract

MRI texture analysis as a predictor of tumor recurrence or progression in patients with clinically non-functioning pituitary adenomas

Abstract: Our data suggest that MRI texture analysis can predict the risk of tumor recurrence or progression in patients with NFPAs.

Cited by 30 publications

References 31 publications

Radiomics Approach for Prediction of Recurrence in Non-Functioning Pituitary Macroadenomas

Radiomics Approach for Prediction of Recurrence in Non-Functioning Pituitary Macroadenomas

Phosphorylated EGFR (pEGFR T693) as a Novel Predictor of Recurrence in Non-Functioning Pituitary Adenomas

The natural history and treatment of non-functioning pituitary adenomas (non-functioning PitNETs)

Contact Info

Product

Resources

About