Predicting response to somatostatin analogues in acromegaly: machine learning-based high-dimensional quantitative texture analysis on T2-weighted MRI

The current state of MRI-based radiomics in pituitary adenoma: promising but challenging

In the clinical diagnosis and treatment of pituitary adenomas, MRI plays a crucial role. However, traditional manual interpretations are plagued by inter-observer variability and limitations in recognizing details. Radiomics, based on MRI, facilitates quantitative analysis by extracting high-throughput data from images. This approach elucidates correlations between imaging features and pituitary tumor characteristics, thereby establishing imaging biomarkers. Recent studies have demonstrated the extensive application of radiomics in differential diagnosis, subtype identification, consistency evaluation, invasiveness assessment, and treatment response in pituitary adenomas. This review succinctly presents the general workflow of radiomics, reviews pertinent literature with a summary table, and provides a comparative analysis with traditional methods. We further elucidate the connections between radiological features and biological findings in the field of pituitary adenoma. While promising, the clinical application of radiomics still has a considerable distance to traverse, considering the issues with reproducibility of imaging features and the significant heterogeneity in pituitary adenoma patients.

Radiomics of pituitary adenoma using computer vision: a review

Pituitary adenomas (PA) represent the most common type of sellar neoplasm. Extracting relevant information from radiological images is essential for decision support in addressing various objectives related to PA. Given the critical need for an accurate assessment of the natural progression of PA, computer vision (CV) and artificial intelligence (AI) play a pivotal role in automatically extracting features from radiological images. The field of "Radiomics" involves the extraction of high-dimensional features, often referred to as "Radiomic features," from digital radiological images. This survey offers an analysis of the current state of research in PA radiomics. Our work comprises a systematic review of 34 publications focused on PA radiomics and other automated information mining pertaining to PA through the analysis of radiological data using computer vision methods. We begin with a theoretical exploration essential for understanding the theoretical background of radionmics, encompassing traditional approaches from computer vision and machine learning, as well as the latest methodologies in deep radiomics utilizing deep learning (DL). Thirty-four research works under examination are comprehensively compared and evaluated. The overall results achieved in the analyzed papers are high, e.g., the best accuracy is up to 96% and the best achieved AUC is up to 0.99, which establishes optimism for the successful use of radiomic features. Methods based on deep learning seem to be the most promising for the future. In relation to this perspective DL methods, several challenges are remarkable: It is important to create high-quality and sufficiently extensive datasets necessary for training deep neural networks. Interpretability of deep radiomics is also a big open challenge. It is necessary to develop and verify methods that will explain to us how deep radiomic features reflect various physics-explainable aspects.

Current role of pasireotide in the treatment of acromegaly

"First-generation" somatostatin receptor agonists (SSTRAs) octreotide and lanreotide are the most commonly used first-line pharmacological therapy for patients with acromegaly. A subset of patients respond only partially or not at all to the first-generation SSTRA, necessitating the use of additional pharmacological agents or other modes of therapy. Pasireotide is a "second-generation" SSTRA that has multi-receptor activity. Prospective studies have shown promise in the use of pasireotide in patients with poor response to first-generation SSTRA. Here we elucidate the molecular pathways of resistance to first-generation SSTRA, the mechanism of action, pre-clinical and clinical evidence of the use of pasireotide in patients having incomplete / lack of response to first-generation SSTRA. We also discuss the clinical, pathological, and radiological markers predicting response to pasireotide, and the difference in side-effect profiles of pasireotide, compared to first-generation SSTRA.

Predictors of biochemical response to somatostatin receptor ligands in acromegaly

Although predictors of response to first-generation somatostatin receptor ligands (fg-SRLs), and to a lesser extent to pasireotide, have been studied in acromegaly for many years, their use is still not recommended in clinical guidelines. Is there insufficient evidence to use them? Numerous biomarkers including various clinical, functional, radiological and molecular markers have been identified. The first ones are applicable pre-surgery, while the molecular predictors are utilized for patients not cured after surgery. In this regard, factors predicting a good response to fg-SRLs are specifically: low basal GH, a low GH nadir in the acute octreotide test, T2 MRI hypointensity, a densely granulated pattern, high immunohistochemistry staining for somatostatin receptor 2 (SSTR2), and E-cadherin. However, there is still a lack of consensus regarding which of these biomarkers is more useful or how to integrate them into clinical practice. With classical statistical methods, it is complex to define reliable and generalizable cut-off values for a single biomarker. The potential solution to the limitations of traditional methods involves combining systems biology with artificial intelligence, which is currently providing answers to such long-standing questions that may eventually be finally included into the clinical guidelines and make personalized medicine a reality. The aim of this review is to describe the current knowledge of the main fg-SRLs and pasireotide response predictors, discuss their current usefulness, and point to future directions in the research of this field.

Radiomic Analysis in Pituitary Tumors: Current Knowledge and Future Perspectives

Radiomic analysis has emerged as a valuable tool for extracting quantitative features from medical imaging data, providing in-depth insights into various contexts and diseases. By employing methods derived from advanced computational techniques, radiomics quantifies textural information through the evaluation of the spatial distribution of signal intensities and inter-voxel relationships. In recent years, these techniques have gained considerable attention also in the field of pituitary tumors, with promising results. Indeed, the extraction of radiomic features from pituitary magnetic resonance imaging (MRI) images has been shown to provide useful information on various relevant aspects of these diseases. Some of the key topics that have been explored in the existing literature include the association of radiomic parameters with histopathological and clinical data and their correlation with tumor invasiveness and aggressive behavior. Their prognostic value has also been evaluated, assessing their role in the prediction of post-surgical recurrence, response to medical treatments, and long-term outcomes. This review provides a comprehensive overview of the current knowledge and application of radiomics in pituitary tumors. It also examines the current limitations and future directions of radiomic analysis, highlighting the major challenges that need to be addressed before a consistent integration of these techniques into routine clinical practice.

Biomarkers of response to treatment in acromegaly

INTRODUCTION

Medical treatment of acromegaly is based in a `trial and error` approach. First-generation somatostatin receptor ligands (fg-SRL) are prescribed as first-line medical therapy to the vast majority of patients, despite lack of disease control in approximately 60% of patients. However, other drugs used in acromegaly treatment are available (cabergoline, pasireotide and pegvisomant).

AREAS COVERED

In this article, we review and discuss the biomarkers of response to medical treatment in acromegaly.

EXPERT OPINION

Biomarkers for fg-SRL that can already be applied in clinical practice are: gender, age, pretreatment GH and IGF-I levels, cytokeratin granulation pattern, and the expression of somatostatin receptor type 2. Using biomarkers of response could guide treatment towards precision medicine with greater efficacy and lower costs.

Predictors of Response to Treatment with First-Generation Somatostatin Receptor Ligands in Patients with Acromegaly

BACKGROUND AND AIMS

Predictors of first-generation somatostatin receptor ligands (fgSRLs) response in acromegaly have been studied for over 30 years, but they are still not recommended in clinical guidelines. Is there not enough evidence to support their use? This systematic review aims to describe the current knowledge of the main predictors of fgSRLs response and discuss their current usefulness, as well as future research directions.

METHODS

A systematic search was performed in the Scopus and PubMed databases for functional, imaging, and molecular predictive factors.

RESULTS

A total of 282 articles were detected, of which 64 were included. Most of them are retrospective studies performed between 1990 and 2023 focused on the predictive response to fgSRLs in acromegaly. The usefulness of the predictive factors is confirmed, with good response identified by the most replicated factors, specifically low GH nadir in the acute octreotide test, T2 MRI hypointensity, high Somatostatin receptor 2 (SSTR2) and E-cadherin expression, and a densely granulated pattern. Even if these biomarkers are interrelated, the association is quite heterogeneous. With classical statistical methods, it is complex to define reliable and generalizable cut-off values worth recommending in clinical guidelines. Machine-learning models involving omics are a promising approach to achieve the highest accuracy values to date.

CONCLUSIONS

This survey confirms a sufficiently robust level of evidence to apply knowledge of predictive factors for greater efficiency in the treatment decision process. The irruption of artificial intelligence in this field is providing definitive answers to such long-standing questions that may change clinical guidelines and make personalized medicine a reality.

Magnetic resonance imaging as a predictor of therapeutic response to pasireotide in acromegaly

OBJECTIVE

Hyperintensity signal in T2-weighted magnetic resonance imaging (MRI) has been related to better therapeutic response during pasireotide treatment in acromegaly. The aim of the study was to evaluate T2 MRI signal intensity and its relation with pasireotide therapeutic effectiveness in real-life clinical practice.

DESIGN, PATIENTS AND MEASUREMENTS

Retrospective multicentre study including acromegaly patients treated with pasireotide. Adenoma T2-weighted MRI signal at diagnosis was qualitatively classified as iso-hyperintense or hypointense. Insulin-like growth factor (IGF-I), growth hormone (GH) and tumour volume reduction were assessed after 6 and 12 months of treatment and its effectiveness evaluated according to baseline MRI signal. Hormonal response was considered 'complete' when normalization of IGF-I levels was achieved. Significant tumour shrinkage was defined as a volume reduction of ≥25% from baseline.

RESULTS

Eighty-one patients were included (48% women, 50 ± 1.5 years); 93% had previously received somatostatin receptor ligands (SRLs) treatment. MRI signal was hypointense in 25 (31%) and hyperintense in 56 (69%) cases. At 12 months of follow-up, 42/73 cases (58%) showed normalization of IGF-I and 37% both GH and IGF-I. MRI signal intensity was not associated with hormonal control. 19/51 cases (37%) presented a significant tumour volume shrinkage, 16 (41%) from the hyperintense group and 3 (25%) from the hypointense.

CONCLUSIONS

T2-signal hyperintensity was more frequently observed in pasireotide treated patients. Almost 60% of SRLs resistant patients showed a complete normalization of IGF-I after 1 year of pasireotide treatment, regardless of the MRI signal. There was also no difference in the percentage tumour shrinkage over basal residual volume between the two groups.

Current and Future Advances in Surgical Therapy for Pituitary Adenoma

The vital physiological role of the pituitary gland, alongside its proximity to critical neurovascular structures, means that pituitary adenomas can cause significant morbidity or mortality. While enormous advancements have been made in the surgical care of pituitary adenomas, numerous challenges remain, such as treatment failure and recurrence. To meet these clinical challenges, there has been an enormous expansion of novel medical technologies (eg, endoscopy, advanced imaging, artificial intelligence). These innovations have the potential to benefit each step of the patient's journey, and ultimately, drive improved outcomes. Earlier and more accurate diagnosis addresses this in part. Analysis of novel patient data sets, such as automated facial analysis or natural language processing of medical records holds potential in achieving an earlier diagnosis. After diagnosis, treatment decision-making and planning will benefit from radiomics and multimodal machine learning models. Surgical safety and effectiveness will be transformed by smart simulation methods for trainees. Next-generation imaging techniques and augmented reality will enhance surgical planning and intraoperative navigation. Similarly, surgical abilities will be augmented by the future operative armamentarium, including advanced optical devices, smart instruments, and surgical robotics. Intraoperative support to surgical team members will benefit from a data science approach, utilizing machine learning analysis of operative videos to improve patient safety and orientate team members to a common workflow. Postoperatively, neural networks leveraging multimodal datasets will allow early detection of individuals at risk of complications and assist in the prediction of treatment failure, thus supporting patient-specific discharge and monitoring protocols. While these advancements in pituitary surgery hold promise to enhance the quality of care, clinicians must be the gatekeepers of the translation of such technologies, ensuring systematic assessment of risk and benefit prior to clinical implementation. In doing so, the synergy between these innovations can be leveraged to drive improved outcomes for patients of the future.

Machine Learning Models to Forecast Outcomes of Pituitary Surgery: A Systematic Review in Quality of Reporting and Current Evidence

Background: The complex nature and heterogeneity involving pituitary surgery results have increased interest in machine learning (ML) applications for prediction of outcomes over the last decade. This study aims to systematically review the characteristics of ML models involving pituitary surgery outcome prediction and assess their reporting quality. Methods: We searched the PubMed, Scopus, and Web of Knowledge databases for publications on the use of ML to predict pituitary surgery outcomes. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to assess report quality. Our search strategy was based on the terms “artificial intelligence”, “machine learning”, and “pituitary”. Results: 20 studies were included in this review. The principal models reported in each article were post-surgical endocrine outcomes (n = 10), tumor management (n = 3), and intra- and postoperative complications (n = 7). Overall, the included studies adhered to a median of 65% (IQR = 60–72%) of TRIPOD criteria, ranging from 43% to 83%. The median reported AUC was 0.84 (IQR = 0.80–0.91). The most popular algorithms were support vector machine (n = 5) and random forest (n = 5). Only two studies reported external validation and adherence to any reporting guideline. Calibration methods were not reported in 15 studies. No model achieved the phase of actual clinical applicability. Conclusion: Applications of ML in the prediction of pituitary outcomes are still nascent, as evidenced by the lack of any model validated for clinical practice. Although studies have demonstrated promising results, greater transparency in model development and reporting is needed to enable their use in clinical practice. Further adherence to reporting guidelines can help increase AI’s real-world utility and improve clinical practice.

Development of MRI-based radiomics predictive model for classifying endometrial lesions

An unbiased and accurate diagnosis of benign and malignant endometrial lesions is essential for the gynecologist, as each type might require distinct treatment. Radiomics is a quantitative method that could facilitate deep mining of information and quantification of the heterogeneity in images, thereby aiding clinicians in proper lesion diagnosis. The aim of this study is to develop an appropriate predictive model for the classification of benign and malignant endometrial lesions, and evaluate potential clinical applicability of the model. 139 patients with pathologically-confirmed endometrial lesions from January 2018 to July 2020 in two independent centers (center A and B) were finally analyzed. Center A was used for training set, while center B was used for test set. The lesions were manually drawn on the largest slice based on the lesion area by two radiologists. After feature extraction and feature selection, the possible associations between radiomics features and clinical parameters were assessed by Uni- and multi- variable logistic regression. The receiver operator characteristic (ROC) curve and DeLong validation were employed to evaluate the possible predictive performance of the models. Decision curve analysis (DCA) was used to evaluate the net benefit of the radiomics nomogram. A radiomics prediction model was established from the 15 selected features, and were found to be relatively high discriminative on the basis of the area under the ROC curve (AUC) for both the training and the test cohorts (AUC = 0.90 and 0.85, respectively). The radiomics nomogram also showed good performance of discrimination for both the training and test cohorts (AUC = 0.91 and 0.86, respectively), and the DeLong test shows that AUCs were significantly different between clinical parameters and nomogram. The result of DCA demonstrated the clinical usefulness of this novel nomogram method. The predictive model constructed based on MRI radiomics and clinical parameters indicated a highly diagnostic efficiency, thereby implying its potential clinical usefulness for the precise identification and prediction of endometrial lesions.

A current perspective of pituitary adenoma MRI characteristics: a review

INTRODUCTION

MR imaging is an essential and fundamental tool in the diagnosis, management, and follow-up of patients with pituitary adenomas (PAs). Recent advances have continued to enhance the usefulness of this imaging modality.

AREAS COVERED

This article focuses on signal intensity patterns of PAs and associated clinical characteristics, vertical extension patterns, and cavernous sinus invasion with a special focus on the clinical implications that arise. A search using Medline and Google Scholar was conducted using different combinations of relevant keywords, giving preference to recent publications.

EXPERT OPINION

A higher proportion of GH-secreting PAs are hypointense on T2 weighted images compared to other tumor subtypes. Hypointense tumors are generally smaller compared to hyperintense ones, and among the GH-secreting subgroup, a better response to somatostatin analogue treatment was noted together with an association for a densely granulated pattern. Nonfunctional PAs show a predilection to extend upwards while GH-secreting PAs and prolactinomas show a predominantly inferior extension growth pattern. Further studies to better understand the mechanisms responsible for this behavior are anticipated. Further development, refining and validation of predictive scoring systems for tumor behavior might be useful adjuncts in the management of patients with PAs.

Quality reporting of radiomics analysis in pituitary adenomas: promoting clinical translation

OBJECTIVE

To evaluate the quality of radiomics studies on pituitary adenoma according to the radiomics quality score (RQS) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD).

METHODS

PubMed MEDLINE and EMBASE were searched to identify radiomics studies on pituitary adenomas. From 138 articles, 20 relevant original research articles were included. Studies were scored based on RQS and TRIPOD guidelines.

RESULTS

Most included studies did not perform pre-processing; isovoxel resampling, signal intensity normalization, and N4 bias field correction were performed in only five (25%), eight (40%), and four (20%) studies, respectively. Only two (10%) studies performed external validation. The mean RQS and basic adherence rate were 2.8 (7.6%) and 26.6%, respectively. There was a low adherence rate for conducting comparison to "gold-standard" (20%), multiple segmentation (25%), and stating potential clinical utility (25%). No study stated the biological correlation, conducted a test-retest or phantom study, was a prospective study, conducted cost-effectiveness analysis, or provided open-source code and data, which resulted in low-level evidence. The overall adherence rate for TRIPOD was 54.6%, and it was low for reporting the title (5%), abstract (0%), explaining the sample size (10%), and suggesting a full prediction model (5%).

CONCLUSION

The radiomics reporting quality for pituitary adenoma is insufficient. Pre-processing is required for feature reproducibility and external validation is necessary. Feature reproducibility, clinical utility demonstration, higher evidence levels, and open science are required. Titles, abstracts, and full prediction model suggestions should be improved for transparent reporting.

ADVANCES IN KNOWLEDGE

Despite the rapidly increasing number of radiomics researches on pituitary adenoma, the quality of science in these researches is unknown. Our study indicates that the overall quality needs to be significantly improved in radiomics studies on pituitary adenoma, and since the concept of RQS and IBSI is still unfamiliar to clinicians and radiologist researchers, our study may help to reach higher technical and clinical impact in the future study.

Discrimination between non-functioning pituitary adenomas and hypophysitis using machine learning methods based on magnetic resonance imaging‑derived texture features

PURPOSE

Hypophysitis is a heterogeneous condition that includes inflammation of the pituitary gland and infundibulum, and it can cause symptoms related to mass effects and hormonal deficiencies. We aimed to evaluate the potential role of machine learning methods in differentiating hypophysitis from non-functioning pituitary adenomas.

METHODS

The radiomic parameters obtained from T1A-C images were used. Among the radiomic parameters, parameters capable of distinguishing between hypophysitis and non-functioning pituitary adenomas were selected. In order to avoid the effects of confounding factors and to improve the performance of the classifiers, parameters with high correlation with each other were eliminated. Machine learning algorithms were performed with the combination of gray-level run-length matrix-low gray level run emphasis, gray-level co-occurrence matrix-correlation, and gray-level co-occurrence entropy.

RESULTS

A total of 34 patients were included, 17 of whom had hypophysitis and 17 had non-functioning pituitary adenomas. Among the 38 radiomics parameters obtained from post-contrast T1-weighted images, 10 tissue features that could differentiate the lesions were selected. Machine learning algorithms were performed using three selected parameters; gray level run length matrix-low gray level run emphasis, gray-level co-occurrence matrix-correlation, and gray level co-occurrence entropy. Error matrices were calculated by using the machine learning algorithm and it was seen that support vector machines showed the best performance in distinguishing the two lesion types.

CONCLUSIONS

Our analysis reported that support vector machines showed the best performance in distinguishing hypophysitis from non-functioning pituitary adenomas, emphasizing the importance of machine learning in differentiating the two lesions.

Personalized Medical Treatment in Patients with Acromegaly: A Review

Acromegaly is associated with significant morbidity and mortality if not appropriately treated. In addition to insulin-like growth factor 1 (IGF-1) and growth hormone (GH) normalization, and tumor shrinkage, treatment goals include symptom relief, managing complications and improving quality of life. Surgical resection is a first-line treatment in most patients, with few being pretreated pre-operatively with medications. Somatostatin receptor ligands (SRLs), injectable and more recently oral capsules, have been the cornerstone of first-line medical therapy for persistent disease. However, several factors, including sparsely granulated adenomas, absent/low somatostatin receptor (SSTR2) status, imaging T2-hyperintensity, young age and aryl hydrocarbon receptor interacting protein mutations could predict first-generation SRL resistance. Patients with these characteristics may be better candidates for the GH receptor antagonist, pegvisomant, or in cases of large tumors the second-generation SRL, pasireotide. Combination therapy should be further pursued in patients who remain biochemically uncontrolled or have high remnant tumor after monotherapy. An efficacious and cost-effective pegvisomant dose-sparing effect of SRLs when used in combination has been demonstrated. With such a wide array of medical treatment options, it is increasingly important to tailor treatment to patients' unique characteristics as well as preferences, with a goal of personalizing management to achieve high quality outcomes.

The Application of Artificial Intelligence and Machine Learning in Pituitary Adenomas

Pituitary adenomas (PAs) are a group of tumors with complex and heterogeneous clinical manifestations. Early accurate diagnosis, individualized management, and precise prediction of the treatment response and prognosis of patients with PA are urgently needed. Artificial intelligence (AI) and machine learning (ML) have garnered increasing attention to quantitatively analyze complex medical data to improve individualized care for patients with PAs. Therefore, we critically examined the current use of AI and ML in the management of patients with PAs, and we propose improvements for future uses of AI and ML in patients with PAs. AI and ML can automatically extract many quantitative features based on massive medical data; moreover, related diagnosis and prediction models can be developed through quantitative analysis. Previous studies have suggested that AI and ML have wide applications in early accurate diagnosis; individualized treatment; predicting the response to treatments, including surgery, medications, and radiotherapy; and predicting the outcomes of patients with PAs. In addition, facial imaging-based AI and ML, pathological picture-based AI and ML, and surgical microscopic video-based AI and ML have also been reported to be useful in assisting the management of patients with PAs. In conclusion, the current use of AI and ML models has the potential to assist doctors and patients in making crucial surgical decisions by providing an accurate diagnosis, response to treatment, and prognosis of PAs. These AI and ML models can improve the quality and safety of medical services for patients with PAs and reduce the complication rates of neurosurgery. Further work is needed to obtain more reliable algorithms with high accuracy, sensitivity, and specificity for the management of PA patients.

Machine Learning in Pituitary Surgery

Machine learning applications in neurosurgery are increasingly reported for diverse tasks such as faster and more accurate preoperative diagnosis, enhanced lesion characterization, as well as surgical outcome, complications and healthcare cost prediction. Even though the pertinent literature in pituitary surgery is less extensive with respect to other neurosurgical diseases, past research attempted to answer clinically relevant questions to better assist surgeons and clinicians. In the present chapter we review reported ML applications in pituitary surgery including differential diagnosis, preoperative lesion characterization (immunohistochemistry, cavernous sinus invasion, tumor consistency), surgical outcome and complication predictions (gross total resection, tumor recurrence, and endocrinological remission, cerebrospinal fluid leak, postoperative hyponatremia). Moreover, we briefly discuss from a practical standpoint the current barriers to clinical translation of machine learning research. On the topic of pituitary surgery, published reports can be considered mostly preliminary, requiring larger training populations and strong external validation. Thoughtful selection of clinically relevant outcomes of interest and transversal application of model development pipeline-together with accurate methodological planning and multicenter collaborations-have the potential to overcome current limitations and ultimately provide additional tools for more informed patient management.

Application of artificial intelligence and radiomics in pituitary neuroendocrine and sellar tumors: a quantitative and qualitative synthesis

PURPOSE

To systematically review the literature regarding the application of machine learning (ML) of magnetic resonance imaging (MRI) radiomics in common sellar tumors. To identify future directions for application of ML in sellar tumor MRI.

METHODS

PubMed, Medline, Embase, Google Scholar, Scopus, ArxIV, and bioRxiv were searched to identify relevant studies published between 2010 and September 2021. Studies were included if they specifically involved ML of MRI radiomics in the analysis of sellar masses. Risk of bias assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) Tool.

RESULTS

Fifty-eight articles were identified for review. All papers utilized retrospective data, and a quantitative systematic review was performed for thirty-one studies utilizing a public dataset which compared pituitary adenomas, meningiomas, and gliomas. One of the analyzed architectures yielded the highest classification accuracy of 0.996. The remaining twenty-seven articles were qualitatively reviewed and showed promising findings in predicting specific tumor characteristics such as tumor consistency, Ki-67 proliferative index, and post-surgical recurrence.

CONCLUSION

This review highlights the potential clinical application of ML using MRI radiomic data of the sellar region in diagnosis and predicting treatment outcomes. We describe future directions for practical application in the clinical care of patients with pituitary neuroendocrine and other sellar tumors.

MRI-Based Machine Learning in Differentiation Between Benign and Malignant Breast Lesions

Background

Differential diagnosis between benign and malignant breast lesions is of crucial importance relating to follow-up treatment. Recent development in texture analysis and machine learning may lead to a new solution to this problem.

Method

This current study enrolled a total number of 265 patients (benign breast lesions:malignant breast lesions = 71:194) diagnosed in our hospital and received magnetic resonance imaging between January 2014 and August 2017. Patients were randomly divided into the training group and validation group (4:1), and two radiologists extracted their texture features from the contrast-enhanced T1-weighted images. We performed five different feature selection methods including Distance correlation, Gradient Boosting Decision Tree (GBDT), least absolute shrinkage and selection operator (LASSO), random forest (RF), eXtreme gradient boosting (Xgboost) and five independent classification models were built based on Linear discriminant analysis (LDA) algorithm.

Results

All five models showed promising results to discriminate malignant breast lesions from benign breast lesions, and the areas under the curve (AUCs) of receiver operating characteristic (ROC) were all above 0.830 in both training and validation groups. The model with a better discriminating ability was the combination of LDA + gradient boosting decision tree (GBDT). The sensitivity, specificity, AUC, and accuracy in the training group were 0.814, 0.883, 0.922, and 0.868, respectively; LDA + random forest (RF) also suggests promising results with the AUC of 0.906 in the training group.

Conclusion

The evidence of this study, while preliminary, suggested that a combination of MRI texture analysis and LDA algorithm could discriminate benign breast lesions from malignant breast lesions. Further multicenter researches in this field would be of great help in the validation of the result.

Usefulness of the Texture Signatures Based on Multiparametric MRI in Predicting Growth Hormone Pituitary Adenoma Subtypes

Objective

To explore the usefulness of texture signatures based on multiparametric magnetic resonance imaging (MRI) in predicting the subtypes of growth hormone (GH) pituitary adenoma (PA).

Methods

Forty-nine patients with GH-secreting PA confirmed by the pathological analysis were included in this retrospective study. Texture parameters based on T1-, T2-, and contrast-enhanced T1-weighted images (T1C) were extracted and compared for differences between densely granulated (DG) and sparsely granulated (SG) somatotroph adenoma by using two segmentation methods [region of interest 1 (ROI₁), excluding the cystic/necrotic portion, and ROI₂, containing the whole tumor]. Receiver operating characteristic (ROC) curve analysis was performed to determine the differentiating efficacy.

Results

Among 49 included patients, 24 were DG and 25 were SG adenomas. Nine optimal texture features with significant differences between two groups were obtained from ROI₁. Based on the ROC analyses, T1WI signatures from ROI₁ achieved the highest diagnostic efficacy with an AUC of 0.918, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 85.7, 72.0, 100.0, 100.0, and 77.4%, respectively, for differentiating DG from SG. Comparing with the T1WI signature, the T1C signature obtained relatively high efficacy with an AUC of 0.893. When combining the texture features of T1WI and T1C, the radiomics signature also had a good performance in differentiating the two groups with an AUC of 0.908. In addition, the performance got in all the signatures from ROI₂ was lower than those in the corresponding signature from ROI_1.

Conclusion

Texture signatures based on MR images may be useful biomarkers to differentiate subtypes of GH-secreting PA patients.

Machine Learning-based Prediction Model for Treatment of Acromegaly With First-generation Somatostatin Receptor Ligands

CONTEXT

Artificial intelligence (AI), in particular machine learning (ML), may be used to deeply analyze biomarkers of response to first-generation somatostatin receptor ligands (fg-SRLs) in the treatment of acromegaly.

OBJECTIVE

To develop a prediction model of therapeutic response of acromegaly to fg-SRL.

METHODS

Patients with acromegaly not cured by primary surgical treatment and who had adjuvant therapy with fg-SRL for at least 6 months after surgery were included. Patients were considered controlled if they presented growth hormone (GH) <1.0 ng/mL and normal age-adjusted insulin-like growth factor (IGF)-I levels. Six AI models were evaluated: logistic regression, k-nearest neighbor classifier, support vector machine, gradient-boosted classifier, random forest, and multilayer perceptron. The features included in the analysis were age at diagnosis, sex, GH, and IGF-I levels at diagnosis and at pretreatment, somatostatin receptor subtype 2 and 5 (SST2 and SST5) protein expression and cytokeratin granulation pattern (GP).

RESULTS

A total of 153 patients were analyzed. Controlled patients were older (P = .002), had lower GH at diagnosis (P = .01), had lower pretreatment GH and IGF-I (P < .001), and more frequently harbored tumors that were densely granulated (P = .014) or highly expressed SST2 (P < .001). The model that performed best was the support vector machine with the features SST2, SST5, GP, sex, age, and pretreatment GH and IGF-I levels. It had an accuracy of 86.3%, positive predictive value of 83.3% and negative predictive value of 87.5%.

CONCLUSION

We developed a ML-based prediction model with high accuracy that has the potential to improve medical management of acromegaly, optimize biochemical control, decrease long-term morbidities and mortality, and reduce health services costs.

Deep Myometrial Infiltration of Endometrial Cancer on MRI: A Radiomics-Powered Machine Learning Pilot Study

RATIONALE AND OBJECTIVES

To evaluate an MRI radiomics-powered machine learning (ML) model's performance for the identification of deep myometrial invasion (DMI) in endometrial cancer (EC) patients and explore its clinical applicability.

MATERIALS AND METHODS

Preoperative MRI scans of EC patients were retrospectively selected. Three radiologists performed whole-lesion segmentation on T2-weighted images for feature extraction. Feature robustness was tested before randomly splitting the population in training and test sets (80/20% proportion). A multistep feature selection was applied to the first, excluding noninformative, low variance features and redundant, highly-intercorrelated ones. A Random Forest wrapper was used to identify the most informative among the remaining. An ensemble of J48 decision trees was tuned and finalized in the training set using 10-fold cross-validation, and then assessed on the test set. A radiologist evaluated all MRI scans without and with the aid of ML to detect the presence of DMI. McNemars's test was employed to compare the two readings.

RESULTS

Of the 54 patients included, 17 had DMI. In all, 1132 features were extracted. After feature selection, the Random Forest wrapper identified the three most informative which were used for ML training. The classifier reached an accuracy of 86% and 91% and areas under the Receiver Operating Characteristic curve of 0.92 and 0.94 in the cross-validation and final testing, respectively. The radiologist performance increased from 82% to 100% when using ML (p = 0.48).

CONCLUSION

We proved the feasibility of a radiomics-powered ML model for DMI detection on MR T2-w images that might help radiologists to increase their performance.

Machine Learning in Preoperative Prediction of Postoperative Immediate Remission of Histology-Positive Cushing's Disease

BACKGROUND

There are no established accurate models that use machine learning (ML) methods to preoperatively predict immediate remission after transsphenoidal surgery (TSS) in patients diagnosed with histology-positive Cushing's disease (CD).

PURPOSE

Our current study aims to devise and assess an ML-based model to preoperatively predict immediate remission after TSS in patients with CD.

METHODS

A total of 1,045 participants with CD who received TSS at Peking Union Medical College Hospital in a 20-year period (between February 2000 and September 2019) were enrolled in the present study. In total nine ML classifiers were applied to construct models for the preoperative prediction of immediate remission with preoperative factors. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate the performance of the models. The performance of each ML-based model was evaluated in terms of AUC.

RESULTS

The overall immediate remission rate was 73.3% (766/1045). First operation (p<0.001), cavernous sinus invasion on preoperative MRI(p<0.001), tumour size (p<0.001), preoperative ACTH (p=0.008), and disease duration (p=0.010) were significantly related to immediate remission on logistic univariate analysis. The AUCs of the models ranged between 0.664 and 0.743. The highest AUC, i.e., the best performance, was 0.743, which was achieved by stacking ensemble method with four factors: first operation, cavernous sinus invasion on preoperative MRI, tumour size and preoperative ACTH.

CONCLUSION

We developed a readily available ML-based model for the preoperative prediction of immediate remission in patients with CD.

Pasireotide in the Personalized Treatment of Acromegaly

The delay in controlling the disease in patients who do not respond to first-line treatment with first generation somatostatin receptor ligands (first-generation SRLs) can be quantified in years, as every modification in the medical therapy requires some months to be fully evaluated. Considering this, acromegaly treatment should benefit from personalized medicine therapeutic approach by using biomarkers identifying drug response. Pasireotide has been positioned mostly as a compound to be used in first-generation SRLs resistant patients and after surgical failure, but sufficient data are now available to indicate it is a first line therapy for patients with certain characteristics. Pasireotide has been proved to be useful in patients in which hyperintensity T2 MRI signal is shown and in those depicting low SST2 and high expression of SST5, low or mutated AIP condition and sparsely granulated immunohistochemical pattern. This combination of clinical and pathological characteristics is unique for certain patients and seems to cluster in the same cases, strongly suggesting an etiopathogenic link. Thus, in this paper we propose to include this clinico-pathologic phenotype in the therapeutic algorithm, which would allow us to use as first line medical treatment those compounds with the highest potential for achieving the fastest control of GH hypersecretion as well as a positive effect upon tumor shrinkage, therefore accelerating the implementation of precision medicine for acromegaly. Moreover, we suggest the development, validation and clinical use of a pasireotide acute test, able to identify patients responsive to pasireotide LAR as the acute octreotide test is able to do for SRLs.

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.

Distinguishing brain inflammation from grade II glioma in population without contrast enhancement: a radiomics analysis based on conventional MRI

PURPOSE

In populations without contrast enhancement, the imaging features of atypical brain parenchyma inflammations can mimic those of grade II gliomas. The aim of this study was to assess the value of the conventional MR-based radiomics signature in differentiating brain inflammation from grade II glioma.

METHODS

Fifty-seven patients (39 patients with grade II glioma and 18 patients with inflammation) were divided into primary (n = 44) and validation cohorts (n = 13). Radiomics features were extracted from T₁-weighted images (T₁WI) and T₂-weighted images (T₂WI). Two-sample t-test and least absolute shrinkage and selection operator (LASSO) regression were adopted to select features and build radiomics signature models for discriminating inflammation from glioma. The predictive performance of the models was evaluated via area under the receiver operating characteristic curve (AUC) and compared with the radiologists' assessments.

RESULTS

Based on the primary cohort, we developed T₁WI, T₂WI and combination (T₁WI + T₂WI) models for differentiating inflammation from glioma with 4, 8, and 5 radiomics features, respectively. Among these models, T₂WI and combination models achieved better diagnostic efficacy, with AUC of 0.980, 0.988 in primary cohort and that of 0.950, 0.925 in validation cohort, respectively. The AUCs of radiologist 1's and 2's assessments were 0.661 and 0.722, respectively.

CONCLUSION

The signature based on radiomics features helps to differentiate inflammation from grade II glioma and improved performance compared with experienced radiologists, which could potentially be useful in clinical practice.

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.

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.

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.

Radiomics with artificial intelligence: a practical guide for beginners

Radiomics is a relatively new word for the field of radiology, meaning the extraction of a high number of quantitative features from medical images. Artificial intelligence (AI) is broadly a set of advanced computational algorithms that basically learn the patterns in the data provided to make predictions on unseen data sets. Radiomics can be coupled with AI because of its better capability of handling a massive amount of data compared with the traditional statistical methods. Together, the primary purpose of these fields is to extract and analyze as much and meaningful hidden quantitative data as possible to be used in decision support. Nowadays, both radiomics and AI have been getting attention for their remarkable success in various radiological tasks, which has been met with anxiety by most of the radiologists due to the fear of replacement by intelligent machines. Considering ever-developing advances in computational power and availability of large data sets, the marriage of humans and machines in future clinical practice seems inevitable. Therefore, regardless of their feelings, the radiologists should be familiar with these concepts. Our goal in this paper was three-fold: first, to familiarize radiologists with the radiomics and AI; second, to encourage the radiologists to get involved in these ever-developing fields; and, third, to provide a set of recommendations for good practice in design and assessment of future works.

A machine learning model to precisely immunohistochemically classify pituitary adenoma subtypes with radiomics based on preoperative magnetic resonance imaging

PURPOSE

The type of pituitary adenoma (PA) cannot be clearly recognized with preoperative magnetic resonance imaging (MRI) but can be classified with immunohistochemical staining after surgery. In this study, a model to precisely immunohistochemically classify the PA subtypes by radiomic features based on preoperative MR images was developed.

METHODS

Two hundred thirty-five pathologically diagnosed PAs, including t-box pituitary transcription factor (Tpit) family tumors (n = 55), pituitary transcription factor 1 (Pit-1) family tumors (n = 110), and steroidogenic factor 1 (SF-1) family tumors (n = 70), were retrospectively studied. T1-weighted, T2-weighted and contrast-enhanced T1-weighted images were obtained from all patients. Through imaging acquisition, feature extraction and radiomic data processing, 18 radiomic features were used to train support vector machine (SVM), k-nearest neighbors (KNN) and Naïve Bayes (NBs) models. Ten-fold cross-validation was applied to evaluate the performance of these models.

RESULTS

The SVM model showed high performance (balanced accuracy 0.89, AUC 0.9549) whereas the KNN (balanced accuracy 0.83, AUC 0.9266) and NBs (balanced accuracy 0.80, AUC 0.9324) models displayed low performance based on the T2-weighted images. The performance of the T2-weighted images was better than that of the other two MR sequences. Additionally, significant sensitivity (P = 0.031) and specificity (P = 0.012) differences were observed when classifying the PA subtypes by T2-weighted images.

CONCLUSIONS

The SVM model was superior to the KNN and NBs models and can potentially precisely immunohistochemically classify PA subtypes with an MR-based radiomic analysis. The developed model exhibited good performance using T2-weighted images and might offer potential guidance to neurosurgeons in clinical decision-making before surgery.

Acromegaly in the elderly patient

Acromegaly is an insidious disease, usually resulting from growth hormone hypersecretion by a pituitary adenoma. It is most often diagnosed during the 3rd to 4th decade of life. However, recent studies have shown an increase in the incidence and prevalence of acromegaly in the elderly, probably due to increasing life expectancy. As in the younger population with acromegaly, there is a delay in diagnosis, aggravated by the similarities of the aging process with some of the characteristics of the disease. As can be expected elderly patients with acromegaly have a higher prevalence of comorbidities than younger ones. The diagnostic criteria are the same as for younger patients. Surgical treatment of the pituitary adenoma is the primary therapy of choice unless contraindicated. Somatostatin receptor ligands are generally effective as both primary and postoperative treatment. The prognosis correlates inversely with the patient's age, disease duration and last GH level. Arch Endocrinol Metab. 2019;63(6):638-45.

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

PURPOSE

Pituitary adenomas are among the most frequent intracranial tumors. They may exhibit clinically aggressive behavior, with recurrent disease and resistance to multimodal therapy. The ki-67 labeling index represents a proliferative marker which correlates with pituitary adenoma aggressiveness. Aim of our study was to assess the accuracy of machine learning analysis of texture-derived parameters from pituitary adenomas preoperative MRI for the prediction of ki-67 proliferation index class.

METHODS

A total of 89 patients who underwent an endoscopic endonasal procedure for pituitary adenoma removal with available ki-67 labeling index were included. From T2w MR images, 1128 quantitative imaging features were extracted. To select the most informative features, different supervised feature selection methods were employed. Subsequently, a k-nearest neighbors (k-NN) classifier was employed to predict macroadenoma high or low proliferation index. Algorithm validation was performed with a train-test approach.

RESULTS

Of the 12 subsets derived from feature selection, the best performing one was constituted by the 4 highest correlating parameters at Pearson's test. These all showed very good (ICC ≥ 0.85) inter-observer reproducibility. The overall accuracy of the k-NN in the test group was of 91.67% (33/36) of correctly classified patients.

CONCLUSIONS

Machine learning analysis of texture-derived parameters from preoperative T2 MRI has proven to be effective for the prediction of pituitary macroadenomas ki-67 proliferation index class. This might aid the surgical strategy making a more accurate preoperative lesion classification and allow for a more focused and cost-effective follow-up and long-term management.

A systematic review on machine learning in sellar region diseases: quality and reporting items

INTRODUCTION

Machine learning methods in sellar region diseases present a particular challenge because of the complexity and the necessity for reproducibility. This systematic review aims to compile the current literature on sellar region diseases that utilized machine learning methods and to propose a quality assessment tool and reporting checklist for future studies.

METHODS

PubMed and Web of Science were searched to identify relevant studies. The quality assessment included five categories: unmet needs, reproducibility, robustness, generalizability and clinical significance.

RESULTS

Seventeen studies were included with the diagnosis of general pituitary neoplasms, acromegaly, Cushing's disease, craniopharyngioma and growth hormone deficiency. 87.5% of the studies arbitrarily chose one or two machine learning models. One study chose ensemble models, and one study compared several models. 43.8% of studies did not provide the platform for model training, and roughly half did not offer parameters or hyperparameters. 62.5% of the studies provided a valid method to avoid over-fitting, but only five reported variations in the validation statistics. Only one study validated the algorithm in a different external database. Four studies reported how to interpret the predictors, and most studies (68.8%) suggested possible clinical applications of the developed algorithm. The workflow of a machine-learning study and the recommended reporting items were also provided based on the results.

CONCLUSIONS

Machine learning methods were used to predict diagnosis and posttreatment outcomes in sellar region diseases. Though most studies had substantial unmet need and proposed possible clinical application, replicability, robustness and generalizability were major limits in current studies.

Preoperative evaluation of tumour consistency in pituitary macroadenomas: a machine learning-based histogram analysis on conventional T2-weighted MRI

PURPOSE

To evaluate the potential value of machine learning (ML)-based histogram analysis (or first-order texture analysis) on T2-weighted magnetic resonance imaging (MRI) for predicting consistency of pituitary macroadenomas (PMA) and to compare it with that of signal intensity ratio (SIR) evaluation.

METHODS

Fifty-five patients with 13 hard and 42 soft PMAs were included in this retrospective study. Histogram features were extracted from coronal T2-weighted original, filtered and transformed MRI images by manual segmentation. To achieve balanced classes (38 hard vs 42 soft), multiple samples were obtained from different slices of the PMAs with hard consistency. Dimension reduction was done with reproducibility analysis, collinearity analysis and feature selection. ML classifier was artificial neural network (ANN). Reference standard for the classifications was based on surgical and histopathological findings. Predictive performance of histogram analysis was compared with that of SIR evaluation. The main metric for comparisons was the area under the receiver operating characteristic curve (AUC).

RESULTS

Only 137 of 162 features had excellent reproducibility. Collinearity analysis yielded 20 features. Feature selection algorithm provided six texture features. For histogram analysis, the ANN correctly classified 72.5% of the PMAs regarding consistency with an AUC value of 0.710. For SIR evaluation, accuracy and AUC values were 74.5% and 0.551, respectively. Considering AUC values, ML-based histogram analysis performed better than SIR evaluation (z = 2.312, p = 0.021).

CONCLUSION

ML-based T2-weighted MRI histogram analysis might be a useful technique in predicting the consistency of PMAs, with a better predictive performance than that of SIR evaluation.