Assessment of Amide proton transfer weighted (APTw) MRI for pre-surgical prediction of final diagnosis in gliomas

Abstract

Purpose: Radiological assessment of primary brain neoplasms, both high (HGG) and low grade tumors (LGG), based on contrast-enhancement alone can be inaccurate. We evaluated the radiological value of amide proton transfer weighted (APTw) MRI as an imaging complement for pre-surgical radiological diagnosis of brain tumors.

Methods: Twenty-six patients were evaluated prospectively; (22 males, 4 females, mean age 55 years, range 26-76 years) underwent MRI at 3T using T1-MPRAGE pre- and post-contrast administration, conventional T2w, FLAIR, and APTw imaging pre-surgically for suspected primary/secondary brain tumor. Assessment of the additional value of APTw imaging compared to conventional MRI for correct pre-surgical brain tumor diagnosis. The initial radiological pre-operative diagnosis was based on the conventional contrast-enhanced MR images. The range, minimum, maximum, and mean APTw signals were evaluated. Conventional normality testing was performed; with boxplots/outliers/skewness/kurtosis and a Shapiro-Wilk's test. Mann-Whitney U for analysis of significance for mean/max/min and range APTw signal. A logistic regression model was constructed for mean, max, range and Receiver Operating Characteristic (ROC) curves calculated for individual and combined APTw signals.

Results: Conventional radiological diagnosis prior to surgery/biopsy was HGG (8 patients), LGG (12 patients), and metastasis (6 patients). Using the mean and maximum: APTw signal would have changed the pre-operative evaluation the diagnosis in 8 of 22 patients (two LGGs excluded, two METs excluded). Using a cut off value of >2.0% for mean APTw signal integral, 4 of the 12 radiologically suspected LGG would have been diagnosed as high grade glioma, which was confirmed by histopathological diagnosis. APTw mean of >2.0% and max >2.48% outperformed four separate clinical radiological assessments of tumor type, P-values = .004 and = .002, respectively.

Conclusions: Using APTw-images as part of the daily clinical pre-operative radiological evaluation may improve diagnostic precision in differentiating LGGs from HGGs, with potential improvement of patient management and treatment.

Fig 1

Conventional MRI; T1-MPRAGE without contrast, T1-MPRAGE with Gadolinium and APTw in color for subject 25 (MET; top) and subject 17 (LGG; middle) and subject 18 (HGG; bottom). The ROI placement for each subject is depicted. The APTw signal intensity for the high grade glioma and metastasis subject is distinctly higher than for the low grade glioma subject in the middle. Subject 25 MET (misdiagnosed by reader 2 and reader 3 as HGG, correctly diagnosed by APTw), Subject 17 LGG (correctly diagnosed by all). Subject 18 HGG (misdiagnosed by the initial radiological assessment as LGG, correctly diagnosed by APTw and all readers)”.

Fig 2. Enlargement of Fig 1 for visualization of ROI-placement.

T1-MPRAGE without contrast, T1-MPRAGE with Gadolinium and APTw in color for subject 25 (MET; top) and subject 17 (LGG; middle) and subject 18 (HGG; bottom).

Fig 3

Conventional MRI; T1-MPRAGE without contrast, T1-MPRAGE with Gadolinium, FLAIR and APTw in color for subject one (HGG; top) and subject 3 (LGG; bottom) The APTw signal intensity for the high grade glioma subject at the top is distinctly higher than for the low grade glioma subject at the bottom. Also notice the increased APTw signal in blood vessel regions. Subject 1 HGG (misdiagnosed by reader 1 and 3 as MET, correctly diagnosed by APTw) and subject 3 LGG (correctly diagnosed by all)”.

Fig 4. Four slices through the lesion of subject 5 with a high grade glioma (HGG).

Notice the coherence between the increasing hypointensity on T1-MPRAGE (a-d), hyperintensity on FLAIR (e-h), increased hyperintensity on T2w MRI (i-l) and increased APTw signal (m-p). Also notice the increased APTw signal in blood vessel regions. Gd-enhancement was studied with T1w; T1-MPRAGE. Hyperintensities on T2 FLAIR and T2 turbo spin-echo of conventional pre-contrast protocols were correlated to T1w-Gd enhancement where possible, otherwise hypointensity.

Fig 5

T1-MPRAGE without contrast, T1-MPRAGE with Gadolinium, FLAIR, T2w and APTw in subject 9 with a low grade glioma (a-e) and subject 10 with a high grade glioma (f-j). Of note is the increased APTw signal in the high grade glioma (j) compared to the low grade glioma (e). on APTw. Also notice the increased APTw signal in blood vessel regions of all patients. Subject 9 LGG (correctly diagnosed by all) and subject 10 HGG (misdiagnosed by the initial radiological classification as MET, correctly diagnosed by APTw).

Fig 6. Z-spectra and magnetization transfer ratio asymmetry spectra for subjects; subject 13 (HGG) and 9 (LGG) within tumor and in contralateral normal appearing white matter.

Fig 7. AUC, 95% CI, sensitivity and specificity with cut off values reported in Table 4.

Fig 8. Mean, max and range APTw signal combined with logistic regression.

AUC, 95% CI, Sensitivity and specificity with cut off values reported in Table 4. The combined model mislabelled subjects 3 and 17 as they were labelled HGG in the model but are histologically verified LGG, also subject 7 was mislabelled as a LGG whereas it is histologically a Glioblastoma, Table 1.