Prediction of high proliferative index in pituitary macroadenomas using MRI-based radiomics and machine learning

A Preoperative MRI-Based Radiomics-Clinicopathological Classifier to Predict the Recurrence of Pituitary Macroadenoma Within 5 Years

Objective: To investigate the ability of a MRI-based radiomics-clinicopathological model to predict pituitary macroadenoma (PMA) recurrence within 5 years. Materials and Methods: We recruited 74 recurrent and 94 non-recurrent subjects, following first surgery with 5-year follow-up data. Univariate and multivariate analyses were conducted to identify independent clinicopathological risk factors. Two independent and blinded neuroradiologists used 3D-Slicer software to manually delineate whole tumors using preoperative axial contrast-enhanced T1WI (CE-T1WI) images. 3D-Slicer was then used to extract radiomics features from segmented tumors. Dimensionality reduction was carried out by the least absolute shrinkage and selection operator (LASSO). Two multilayer perceptron (MLP) models were established, including independent clinicopathological risk factors (Model 1) and a combination of screened radiomics features and independent clinicopathological markers (Model 2). The predictive performance of these models was evaluated by receiver operator characteristic (ROC) curve analysis. Results: In total, 1,130 features were identified, and 4 of these were selected by LASSO. In the test set, the area under the curve (AUC) of Model 2 was superior to Model 1 {0.783, [95% confidence interval (CI): 0.718-.860] vs. 0.739, (95% CI: 0.665-0.818)}. Model 2 also yielded the higher accuracy (0.808 vs. 0.692), sensitivity (0.826 vs. 0.652), and specificity (0.793 vs. 0.724) than Model 1. Conclusions: The integrated classifier was superior to a clinical classifier and may facilitate the prediction of individualized prognosis and therapy.

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

Objectives

A 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.

Methods

Only 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.

Results

Twenty-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).

Conclusions

Our 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.

Radiomics model predicts granulation pattern in growth hormone-secreting pituitary adenomas

PURPOSE

To investigate whether radiomic features from magnetic resonance image (MRI) can predict the granulation pattern of growth hormone (GH)-secreting pituitary adenoma patients.

METHODS

Sixty-nine pathologically proven acromegaly patients (densely granulated [DG] = 50, sparsely granulated [SG] = 19) were included. Radiomic features (n = 214) were extracted from contrast-enhancing and total tumor portions from T2-weighted (T2) MRIs. Imaging features were selected using a least absolute shrinkage and selection operator (LASSO) logistic regression model with fivefold cross-validation. Diagnostic performance for predicting granulation pattern was compared with that for qualitative T2 signal intensity assessment and T2 relative signal intensity (rSI) using the area under the receiver operating characteristics curve (AUC).

RESULTS

Four significant radiomic features from the contrast-enhancing tumor (1 from shape, 1 from first order feature, and 2 from second order features) were selected by LASSO for model construction. The radiomics model showed an AUC, accuracy, sensitivity, and specificity of 0.834 (95% confidence interval [CI] 0.738-0.930), 73.7%, 74.0%, and 73.9%, respectively. The radiomics model showed significantly better performance than the model using qualitative T2 signal intensity assessment (AUC 0.597 [95% CI 0.447-0.747], P = 0.009) and T2 rSI (AUC 0.647 [95% CI 0.523-0.759], P = 0.037).

CONCLUSION

Radiomic features may be useful biomarkers to differentiate granulation pattern of GH-secreting pituitary adenoma patients, and showed better performance than qualitative assessment or rSI evaluation.

Supervised machine learning tools: a tutorial for clinicians

In an increasingly data-driven world, artificial intelligence is expected to be a key tool for converting big data into tangible benefits and the healthcare domain is no exception to this. Machine learning aims to identify complex patterns in multi-dimensional data and use these uncovered patterns to classify new unseen cases or make data-driven predictions. In recent years, deep neural networks have shown to be capable of producing results that considerably exceed those of conventional machine learning methods for various classification and regression tasks. In this paper, we provide an accessible tutorial of the most important supervised machine learning concepts and methods, including deep learning, which are potentially the most relevant for the medical domain. We aim to take some of the mystery out of machine learning and depict how machine learning models can be useful for medical applications. Finally, this tutorial provides a few practical suggestions for how to properly design a machine learning model for a generic medical problem.

Advances in the Imaging of Pituitary Tumors

In most patients with pituitary adenomas magnetic resonance imaging (MRI) is essential to guide effective decision-making. T1- and T2-weighted sequences allow the majority of adenomas to be readily identified. Supplementary MR sequences (e.g. FLAIR; MR angiography) may also help inform surgery. However, in some patients MRI findings are 'negative' or equivocal (e.g. with failure to reliably identify a microadenoma or to distinguish postoperative change from residual/recurrent disease). Molecular imaging [e.g. ¹¹C-methionine PET/CT coregistered with volumetric MRI (Met-PET/MR^CR)] may allow accurate localisation of the site of de novo or persistent disease to guide definitive treatment (e.g. surgery or radiosurgery).

Artificial intelligence and pituitary adenomas: A review

The aim of this review was to provide an overview of the main concepts in machine learning (ML) and to analyze the ML applications in the imaging of pituitary adenomas. After describing the clinical, pathological and imaging features of pituitary tumors, we defined the difference between ML and classical rule-based algorithms, we illustrated the fundamental ML techniques: supervised, unsupervised and reinforcement learning and explained the characteristic of deep learning, a ML approach employing networks inspired by brain’s structure. Pre-treatment assessment and neurosurgical outcome prediction were the potential ML applications using magnetic resonance imaging. Regarding pre-treatment assessment, ML methods were used to have information about tumor consistency, predict cavernous sinus invasion and high proliferative index, discriminate null cell adenomas, which respond to neo-adjuvant radiotherapy from other subtypes, predict somatostatin analogues response and visual pathway injury. Regarding neurosurgical outcome prediction, the following applications were discussed: Gross total resection prediction, evaluation of Cushing disease recurrence after transsphenoidal surgery and prediction of cerebrospinal fluid fistula’s formation after surgery. Although clinical applicability requires more replicability, generalizability and validation, results are promising, and ML software can be a potential power to facilitate better clinical decision making in pituitary tumor patients.

Prediction of pituitary adenoma surgical consistency: radiomic data mining and machine learning on T2-weighted MRI

Purpose

Pituitary macroadenoma consistency can influence the ease of lesion removal during surgery, especially when using a transsphenoidal approach. Unfortunately, it is not assessable on standard qualitative MRI. Radiomic texture analysis could help in extracting mineable quantitative tissue characteristics. We aimed to assess the accuracy of texture analysis combined with machine learning in the preoperative evaluation of pituitary macroadenoma consistency in patients undergoing endoscopic endonasal surgery.

Methods

Data of 89 patients (68 soft and 21 fibrous macroadenomas) who underwent MRI and transsphenoidal surgery at our institution were retrospectively reviewed. After manual segmentation, radiomic texture features were extracted from original and filtered MR images. Feature stability analysis and a multistep feature selection were performed. After oversampling to balance the classes, 80% of the data was used for hyperparameter tuning via stratified 5-fold cross-validation, while a 20% hold-out set was employed for its final testing, using an Extra Trees ensemble meta-algorithm. The reference standard was based on surgical findings.

Results

A total of 1118 texture features were extracted, of which 741 were stable. After removal of low variance (n = 4) and highly intercorrelated (n = 625) parameters, recursive feature elimination identified a subset of 14 features. After hyperparameter tuning, the Extra Trees classifier obtained an accuracy of 93%, sensitivity of 100%, and specificity of 87%. The area under the receiver operating characteristic and precision-recall curves was 0.99.

Conclusion

Preoperative T2-weighted MRI texture analysis and machine learning could predict pituitary macroadenoma consistency.

Electronic supplementary material

The online version of this article (10.1007/s00234-020-02502-z) contains supplementary material, which is available to authorized users.

Pituitary Tumors in the Computational Era, Exploring Novel Approaches to Diagnosis, and Outcome Prediction with Machine Learning

BACKGROUND

Machine learning has emerged as a viable asset in the setting of pituitary surgery. In the past decade, the number of machine learning models developed to aid in the diagnosis of pituitary lesions and predict intraoperative and postoperative complications following transsphenoidal surgery has increased exponentially. As computational processing power continues to increase, big data sets continue to expand, and learning algorithms continue to surpass gold standard predictive tools, machine learning will serve to become an important component in improving patient care and outcomes.

METHODS

Relevant studies were identified based on a literature search in PubMed and MEDLINE databases, as well as from other sources including reference lists of published articles.

RESULTS

Radiomics and artificial neural networks comprise the majority of machine learning-based applications in pituitary surgery. Radiomics serves to quantify specific imaging features, which can then be used to noninvasively identify tumor characteristics and make definitive diagnoses, circumventing presurgical biopsy altogether. Neural networks can be adapted to predict intraoperative changes in visual evoked potentials or cerebral spinal fluid leak. In addition, these algorithms may be combined with others to predict tumor aggressiveness, gross total resection, recurrence and remission, and even total cost burden.

CONCLUSIONS

The field of machine learning is broad, with radiomics and artificial neural networks comprising 2 commonly used supervised learning methods in pituitary surgery. Given the large heterogeneity of pituitary and sellar lesions, the promise of machine learning lies in its ability to identify relationships and patterns that are otherwise hidden from standard statistical methods. While machine learning has great potential as a clinical adjunct during the surgical preplanning process and in predicting complications and outcomes, challenges moving forward include standardization and validation of these paradigms.

Biomarkers of pituitary macroadenomas aggressive behaviour: a conventional MRI and DWI 3T study

OBJECTIVE

Pituitary macroadenomas (PAs) are usually defined as benign intracranial tumors. However, they may present local aggressive course. High Ki67 labelling index (LI) values have been related to an aggressive tumor behavior. A recent clinicopathological classification of PA based on local invasiveness and proliferation indexes, divided them in groups with different prognosis. We evaluated the utility of conventional MRI (cMRI) and diffusion-weighted imaging (DWI), in predicting the Ki67- LI according the clinicopathological classification.

METHODS

17 patients (12 M and 5 F) who underwent surgical removal of a PA were studied. cMRI features, quantification of T₁W and T₂W signal intensity, degree of contrast uptake (enhancement ratio, ER) and apparent diffusion coefficient (ADC) values were evaluated by using a 3 T scan. Statistics included Mann-Whitney test, Spearman's test, and receiver operating characteristic analysis. A value of p ≤ 0.05 was considered significant for all the tests.

RESULTS

Negative correlations were observed between Ki-67 LI, ADCm (ρ = - 0.67, p value = 0.005) and ER values (ρ = -0.62; p = 0.008). ER values were significantly lower in the proliferative PA group (p = 0.028; p = 0.017). ADCm showed sensitivity and specificity of 90 and 85% respectively into predict Ki67-LI value. A value of ADCm ≤0, 711 x 10-6 mm² emerged as a cut-off of a value of Ki67-LI ≥ 3%.

CONCLUSION

Adding quantitative measures of ADC values to cMRI could be used routinely as a non-invasive marker of specific predictive biomarker of the proliferative activity of PA.

ADVANCES IN KNOWLEDGE

Routinely use of DWI on diagnostic work-up of pituitary adenomas may help in establish the likely biological aggressive lesions.

Machine learning applications in imaging analysis for patients with pituitary tumors: a review of the current literature and future directions

PURPOSE

To provide an overview of fundamental concepts in machine learning (ML), review the literature on ML applications in imaging analysis of pituitary tumors for the last 10 years, and highlight the future directions on potential applications of ML for pituitary tumor patients.

METHOD

We presented an overview of the fundamental concepts in ML, its various stages used in healthcare, and highlighted the key components typically present in an imaging-based tumor analysis pipeline. A search was conducted across four databases (PubMed, Ovid, Embase, and Google Scholar) to gather research articles from the past 10 years (2009-2019) involving imaging related to pituitary tumor and ML. We grouped the studies by imaging modalities and analyzed the ML tasks in terms of the data inputs, reference standards, methodologies, and limitations.

RESULTS

Of the 16 studies included in our analysis, 10 appeared in 2018-2019. Most of the studies utilized retrospective data and followed a semi-automatic ML pipeline. The studies included use of magnetic resonance imaging (MRI), facial photographs, surgical microscopic video, spectrometry, and spectroscopy imaging. The objectives of the studies covered 14 distinct applications and majority of the studies addressed a binary classification problem. Only five of the 11 MRI-based studies had an external validation or a holdout set to test the performance of a final trained model.

CONCLUSION

Through our concise evaluation and comparison of the studies using the concepts presented, we highlight future directions so that potential ML applications using different imaging modalities can be developed to benefit the clinical care of pituitary tumor patients.

Non-invasive and real-time proliferative activity estimation based on a quantitative radiomics approach for patients with acromegaly: a multicenter study

BACKGROUND

Proliferative activity prediction is important for determining individual treatment strategies for patients with acromegaly, and tumor proliferative activity is usually measured by the expression of Ki-67.

OBJECTIVE

This study aimed to assess the value of a magnetic resonance imaging (MRI)-based radiomics approach in predicting the Ki-67 index of acromegaly patients.

METHODS

A total of 138 patients with acromegaly were retrospectively reviewed and randomly assigned to primary and validation cohorts. Radiomics features were extracted from MR images, and then the elastic net and recursive feature elimination algorithms were applied to determine critical radiomics features for constructing a radiomics signature. Subsequently, multivariable logistic regression analysis was used to select the most informative clinical features, and a radiomics nomogram incorporating a radiomics signature and selected clinical features was constructed for individual predictions. Twenty-five acromegaly patients were enrolled for multicenter model validation.

RESULTS

Seventeen radiomics features were selected to construct a radiomics signature that achieved an area under the curve (AUC) value of 0.96 and 0.89 in the primary cohort and the validation cohort, respectively. A radiomics nomogram that incorporated the radiomics signature and eight selected clinical features was constructed and showed good discrimination and calibration, with an AUC of 0.94 in the primary cohort and 0.91 in the validation cohort. The radiomics signature in the multicenter validation achieved an accuracy of 88.2%. The analysis of the decision curve showed that the radiomics signature and radiomics nomogram were clinically useful for patients with acromegaly.

CONCLUSIONS

The radiomics signature developed in this study could aid neurosurgeons in predicting the Ki-67 index of patients with acromegaly and could contribute to non-invasive measurement of proliferative activity, affecting individual treatment strategies.

MRI radiomics-based machine-learning classification of bone chondrosarcoma

PURPOSE

To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI).

METHODS

We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensional regions of interest, which were used for first order and texture feature extraction. A Random Forest wrapper was employed for feature selection. The resulting dataset was used to train a locally weighted ensemble classifier (AdaboostM1). Its performance was assessed via 10-fold cross-validation on the training data and then on the previously unseen test set. Thereafter, an experienced musculoskeletal radiologist blinded to histological and radiomic data qualitatively evaluated the cartilaginous tumors in the test group.

RESULTS

After feature selection, the dataset was reduced to 4 features extracted from T1-weighted images. AdaboostM1 correctly classified 85.7 % and 75 % of the lesions in the training and test groups, respectively. The corresponding areas under the receiver operating characteristic curve were 0.85 and 0.78. The radiologist correctly graded 81.3 % of the lesions. There was no significant difference in performance between the radiologist and machine learning classifier (P = 0.453).

CONCLUSIONS

Our machine learning approach showed good diagnostic performance for classification of low-to-high grade cartilaginous bone tumors and could prove a valuable aid in preoperative tumor characterization.

UPDATES IN AGGRESSIVE PITUITARY TUMORS

Aggressive pituitary tumors lie between pituitary adenomas and carcinomas, displaying a particular behavior, with invasion, resistance to conventional therapy and early recurrence. The radiological grading, along with prognostic markers such as Ki-67 proliferation index, p53, MGMT and transcription factors are important factors in establishing the benign, aggressive, or malignant nature of pituitary tumors, with a more accurate treatment strategy. In this article, we report the novelties in defining, classifying, and managing aggressive pituitary tumors and their malignant potential, focusing on clinicopathological, histological, molecular and radiological data.