Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation

A physics-informed deep learning framework for dynamic susceptibility contrast perfusion MRI

BACKGROUND

Perfusion magnetic resonance imaging (MRI)s plays a central role in the diagnosis and monitoring of neurovascular or neurooncological disease. However, conventional processing techniques are limited in their ability to capture relevant characteristics of the perfusion dynamics and suffer from a lack of standardization.

PURPOSE

We propose a physics-informed deep learning framework which is capable of analyzing dynamic susceptibility contrast perfusion MRI data and recovering the dynamic tissue response with high accuracy.

METHODS

The framework uses physics-informed neural networks (PINNs) to learn the voxel-wise TRF, which represents the dynamic response of the local vascular network to the contrast agent bolus. The network output is stabilized by total variation and elastic net regularization. Parameter maps of normalized cerebral blood flow (nCBF) and volume (nCBV) are then calculated from the predicted residue functions. The results are validated using extensive comparisons to values derived by conventional Tikhonov-regularized singular value decomposition (TiSVD), in silico simulations and an in vivo dataset of perfusion MRI exams of patients with high-grade gliomas.

RESULTS

The simulation results demonstrate that PINN-derived residue functions show a high concordance with the true functions and that the calculated values of nCBF and nCBV converge towards the true values for higher contrast-to-noise ratios. In the in vivo dataset, we find high correlations between conventionally derived and PINN-predicted perfusion parameters (Pearson's rho for nCBF:0.84 ± 0.03 $0.84 \pm 0.03$ and nCBV:0.92 ± 0.03 $0.92 \pm 0.03$ ) and very high indices of image similarity (structural similarity index for nCBF:0.91 ± 0.03 $0.91 \pm 0.03$ and for nCBV:0.98 ± 0.00 $0.98 \pm 0.00$ ).

CONCLUSIONS

PINNs can be used to analyze perfusion MRI data and stably recover the response functions of the local vasculature with high accuracy.

Differentiation between multifocal CNS lymphoma and glioblastoma based on MRI criteria

PURPOSE

Differentiating between glioblastoma (GB) with multiple foci (mGB) and multifocal central nervous system lymphoma (mCNSL) can be challenging because these cancers share several features at first appearance on magnetic resonance imaging (MRI). The aim of this study was to explore morphological differences in MRI findings for mGB versus mCNSL and to develop an interpretation algorithm with high diagnostic accuracy.

METHODS

In this retrospective study, MRI characteristics were compared between 50 patients with mGB and 50 patients with mCNSL treated between 2015 and 2020. The following parameters were evaluated: size, morphology, lesion location and distribution, connections between the lesions on the fluid-attenuated inversion recovery sequence, patterns of contrast enhancement, and apparent diffusion coefficient (ADC) values within the tumor and the surrounding edema, as well as MR perfusion and susceptibility weighted imaging (SWI) whenever available.

RESULTS

A total of 187 mCNSL lesions and 181 mGB lesions were analyzed. The mCNSL lesions demonstrated frequently a solid morphology compared to mGB lesions, which showed more often a cystic, mixed cystic/solid morphology and a cortical infiltration. The mean measured diameter was significantly smaller for mCNSL than mGB lesions (p < 0.001). Tumor ADC ratios were significantly smaller in mCNSL than in mGB (0.89 ± 0.36 vs. 1.05 ± 0.35, p < 0.001). The ADC ratio of perilesional edema was significantly higher (p < 0.001) in mCNSL than in mGB. In SWI / T2*-weighted imaging, tumor-associated susceptibility artifacts were more often found in mCNSL than in mGB (p < 0.001).

CONCLUSION

The lesion size, ADC ratios of the lesions and the adjacent tissue as well as the vascularization of the lesions in the MR-perfusion were found to be significant distinctive patterns of mCNSL and mGB allowing a radiological differentiation of these two entities on initial MRI. A diagnostic algorithm based on these parameters merits a prospective validation.

An accessible deep learning tool for voxel-wise classification of brain malignancies from perfusion MRI

Noninvasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging (MRI) coupled with dynamic susceptibility contrast (DSC). However, a definitive diagnosis often requires neurosurgical interventions that compromise patients' quality of life. We apply deep learning on DSC images from histology-confirmed patients with glioblastoma, metastasis, or lymphoma. The convolutional neural network trained on ∼50,000 voxels from 40 patients provides intratumor probability maps that yield clinical-grade diagnosis. Performance is tested in 400 additional cases and an external validation cohort of 128 patients. The tool reaches a three-way accuracy of 0.78, superior to the conventional MRI metrics cerebral blood volume (0.55) and percentage of signal recovery (0.59), showing high value as a support diagnostic tool. Our open-access software, Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), demonstrates its potential in aiding medical decisions for brain tumor diagnosis using standard-of-care MRI.

Deep learning aided preoperative diagnosis of primary central nervous system lymphoma

The preoperative distinction between glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) can be difficult, even for experts, but is highly relevant. We aimed to develop an easy-to-use algorithm, based on a convolutional neural network (CNN) to preoperatively discern PCNSL from GBM and systematically compare its performance to experienced neurosurgeons and radiologists. To this end, a CNN-based on DenseNet169 was trained with the magnetic resonance (MR)-imaging data of 68 PCNSL and 69 GBM patients and its performance compared to six trained experts on an external test set of 10 PCNSL and 10 GBM. Our neural network predicted PCNSL with an accuracy of 80% and a negative predictive value (NPV) of 0.8, exceeding the accuracy achieved by clinicians (73%, NPV 0.77). Combining expert rating with automated diagnosis in those cases where experts dissented yielded an accuracy of 95%. Our approach has the potential to significantly augment the preoperative radiological diagnosis of PCNSL.

Radiomic-Based MRI for Classification of Solitary Brain Metastases Subtypes From Primary Lymphoma of the Central Nervous System

BACKGROUND

Differential diagnosis of brain metastases subtype and primary central nervous system lymphoma (PCNSL) is necessary for treatment decisions. The application of machine learning facilitates the classification of brain tumors, but prior investigations into primary lymphoma and brain metastases subtype classification have been limited.

PURPOSE

To develop a machine-learning model to classify PCNSL, brain metastases with primary lung and non-lung origin.

STUDY TYPE

Retrospective.

POPULATION

A total of 211 subjects with pathologically confirmed PCNSL or brain metastases (training cohort 168 and testing cohort 43).

FIELD STRENGTH/SEQUENCE

A 3.0 T axial contrast-enhanced T1-weighted spin-echo inversion recovery sequence (T1WI-CE), axial T2-weighted fluid-attenuation inversion recovery sequence (T2FLAIR) ASSESSMENT: Several machine-learning models (support vector machine, random forest, and K-nearest neighbors) were built with least absolute shrinkage and selection operator (LASSO) using features from T1WI-CE, T2FLAIR, and clinical. The model with the highest performance in the training cohort was selected to differentiate lesions in the testing cohort. Then, three radiologists conducted a two-round classification (with and without model reference) using images and clinical information from testing cohorts.

STATISTICAL TESTS

Five-fold cross-validation was used for model evaluation and calibration. Model performance was assessed based on sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC).

RESULTS

Twenty-five image features were selected by LASSO analysis. Random forest classifier was selected for its highest performance on the training set with an AUC of 0.73. After calibration, this model achieved an accuracy of 0.70 on the testing set. Accuracies of all three radiologists improved under model reference (0.49 vs. 0.70, 0.60 vs. 0.77, 0.58 vs. 0.72, respectively).

DATA CONCLUSION

The random forest model based on conventional MRI and clinical data can diagnose PCNSL and brain metastases subtypes (lung and non-lung origin). Model classification can help foster the diagnostic accuracy of specialists and streamline prognostication workflow.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Progress of radiological‑pathological workflows in the differential diagnosis between primary central nervous system lymphoma and high‑grade glioma (Review)

Primary central nervous system lymphoma (PCNSL) and high‑grade glioma (HGG) are distinct entities of the CNS with completely distinct treatments. The treatment of PCNSL is chemotherapy‑based, while surgery is the first choice for HGG. However, the clinical features of the two entities often overlap, and a clear pathological diagnosis is important for subsequent management, especially for the management of PCNSL. Stereotactic biopsy is recognized as one of the minimally invasive alternatives for evaluating the involvement of the CNS. However, in the case of limited tissue materials, the differential diagnosis between the two entities is still difficult. In addition, some patients are too ill to tolerate a needle biopsy. Therefore, combining imaging, histopathology and laboratory examinations is essential in order to make a clear diagnosis as soon as possible. The present study reviews the progress of comparative research on both imaging and laboratory tests based on the pathophysiological changes of the two entities, and proposes an integrative and optimized diagnostic process, with the purpose of building a better understanding for neurologists, hematologists, radiologists and pathologists.

Classifying primary central nervous system lymphoma from glioblastoma using deep learning and radiomics based machine learning approach - a systematic review and meta-analysis

Background

Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common in elderly yet difficult to differentiate on MRI. Their management and prognosis are quite different. Recent surge of interest in predictive analytics, using machine learning (ML) from radiomic features and deep learning (DL) for diagnosing, predicting response and prognosticating disease has evinced interest among radiologists and clinicians. The objective of this systematic review and meta-analysis was to evaluate the deep learning &amp; ML algorithms in classifying PCNSL from GBM.

Methods

The authors performed a systematic review of the literature from MEDLINE, EMBASE and the Cochrane central trials register for the search strategy in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML, DL, AI, GBM, PCNSL. All studies reporting on ML algorithms or DL that for differentiating PCNSL from GBM on MR imaging were included. These studies were further narrowed down to focus on works published between 2018 and 2021. Two researchers independently conducted the literature screening, database extraction and risk bias assessment. The extracted data was synthesised and analysed by forest plots. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity and balanced accuracy.

Results

Ten articles meeting the eligibility criteria were identified addressing use of ML and DL in training and validation classifiers to distinguish PCNSL from GBM on MR imaging. The total sample size was 1311 in the included studies. ML approach was used in 6 studies while DL in 4 studies. The lowest reported sensitivity was 80%, while the highest reported sensitivity was 99% in studies in which ML and DL was directly compared with the gold standard histopathology. The lowest reported specificity was 87% while the highest reported specificity was 100%. The highest reported balanced accuracy was 100% and the lowest was 84%.

Conclusions

Extensive search of the database revealed a limited number of studies that have applied ML or DL to differentiate PCNSL from GBM. Of the currently published studies, Both DL &amp; ML algorithms have demonstrated encouraging results and certainly have the potential to aid neurooncologists in taking preoperative decisions in the future leading to not only reduction in morbidities but also be cost effective.

Machine Learning in Differentiating Gliomas from Primary CNS Lymphomas: A Systematic Review, Reporting Quality, and Risk of Bias Assessment

BACKGROUND

Differentiating gliomas and primary CNS lymphoma represents a diagnostic challenge with important therapeutic ramifications. Biopsy is the preferred method of diagnosis, while MR imaging in conjunction with machine learning has shown promising results in differentiating these tumors.

PURPOSE

Our aim was to evaluate the quality of reporting and risk of bias, assess data bases with which the machine learning classification algorithms were developed, the algorithms themselves, and their performance.

DATA SOURCES

Ovid EMBASE, Ovid MEDLINE, Cochrane Central Register of Controlled Trials, and the Web of Science Core Collection were searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines.

STUDY SELECTION

From 11,727 studies, 23 peer-reviewed studies used machine learning to differentiate primary CNS lymphoma from gliomas in 2276 patients.

DATA ANALYSIS

Characteristics of data sets and machine learning algorithms were extracted. A meta-analysis on a subset of studies was performed. Reporting quality and risk of bias were assessed using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) and Prediction Model Study Risk Of Bias Assessment Tool.

DATA SYNTHESIS

The highest area under the receiver operating characteristic curve (0.961) and accuracy (91.2%) in external validation were achieved by logistic regression and support vector machines models using conventional radiomic features. Meta-analysis of machine learning classifiers using these features yielded a mean area under the receiver operating characteristic curve of 0.944 (95% CI, 0.898-0.99). The median TRIPOD score was 51.7%. The risk of bias was high for 16 studies.

LIMITATIONS

Exclusion of abstracts decreased the sensitivity in evaluating all published studies. Meta-analysis had high heterogeneity.

CONCLUSIONS

Machine learning-based methods of differentiating primary CNS lymphoma from gliomas have shown great potential, but most studies lack large, balanced data sets and external validation. Assessment of the studies identified multiple deficiencies in reporting quality and risk of bias. These factors reduce the generalizability and reproducibility of the findings.

MUC21 induces the viability and migration of glioblastoma via the STAT3/AKT pathway

Glioblastoma (GBM) is a malignant tumor with one of the fastest increasing morbidity and mortality rates. As such, more therapeutic targets need to be developed to combat this disease. Mucin 21 (MUC21) is a human counterpart of mouse epiglycanin and mediates multiple cellular functions. However, its possible effects on GBM and its possible mechanism remain unclear. The current study aimed to clarify the role or MUC21 in the progression of GBM by performing a series of in vitro assays, including Cell Counting Kit-8, colony formation, wound closure, transwell, and in vivo assays. In the present study, the aberrantly high expression of MUC21 in human GBM tissues and cell lines was observed and it was revealed that it was associated with the clinicopathological feature, tumor recurrence, in patients with GBM. MUC21 promoted the viability and motility of GBM cells in vitro and stimulated tumor growth in vivo. It was further confirmed that MUC21 promoted the progression of GBM via the STAT3/AKT pathway and it was considered that MUC21 could serve as a promising target for the treatment of GBM.

Machine Learning Applications for Differentiation of Glioma from Brain Metastasis-A Systematic Review

Simple Summary

We present a systematic review of published reports on machine learning (ML) applications for the differentiation of gliomas from brain metastases by summarizing study characteristics, strengths, and pitfalls. Based on these findings, we present recommendations for future research in this field.

Abstract

Glioma and brain metastasis can be difficult to distinguish on conventional magnetic resonance imaging (MRI) due to the similarity of imaging features in specific clinical circumstances. Multiple studies have investigated the use of machine learning (ML) models for non-invasive differentiation of glioma from brain metastasis. Many of the studies report promising classification results, however, to date, none have been implemented into clinical practice. After a screening of 12,470 studies, we included 29 eligible studies in our systematic review. From each study, we aggregated data on model design, development, and best classifiers, as well as quality of reporting according to the TRIPOD statement. In a subset of eligible studies, we conducted a meta-analysis of the reported AUC. It was found that data predominantly originated from single-center institutions (n = 25/29) and only two studies performed external validation. The median TRIPOD adherence was 0.48, indicating insufficient quality of reporting among surveyed studies. Our findings illustrate that despite promising classification results, reliable model assessment is limited by poor reporting of study design and lack of algorithm validation and generalizability. Therefore, adherence to quality guidelines and validation on outside datasets is critical for the clinical translation of ML for the differentiation of glioma and brain metastasis.

Differentiating Glioblastomas from Solitary Brain Metastases: An Update on the Current Literature of Advanced Imaging Modalities

Differentiating between glioblastomas and solitary brain metastases proves to be a challenging diagnosis for neuroradiologists, as both present with imaging patterns consisting of peritumoral hyperintensities with similar intratumoral texture on traditional magnetic resonance imaging sequences. Early diagnosis is paramount, as each pathology has completely different methods of clinical assessment. In the past decade, recent developments in advanced imaging modalities enabled providers to acquire a more accurate diagnosis earlier in the patient's clinical assessment, thus optimizing clinical outcome. Dynamic susceptibility contrast has been optimized for detecting relative cerebral blood flow and relative cerebral blood volume. Diffusion tensor imaging can be used to detect changes in mean diffusivity. Neurite orientation dispersion and density imaging is an innovative modality detecting changes in intracellular volume fraction, isotropic volume fraction, and extracellular volume fraction. Magnetic resonance spectroscopy is able to assist by providing a metabolic descriptor while detecting variable ratios of choline/N-acetylaspartate, choline/creatine, and N-acetylaspartate/creatine. Finally, radiomics and machine learning algorithms have been devised to assist in improving diagnostic accuracy while often utilizing more than one advanced imaging protocol per patient. In this review, we provide an update on all the current evidence regarding the identification and differentiation of glioblastomas from solitary brain metastases.