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

Park, Ji Eun; Kim, Ho Sung; Lee, Junkyu; Cheong, E-Nae; Shin, In Sik; Ahn, Sung Soo; Shim, Woo Hyun

doi:10.1038/s41598-020-78485-x

Cited by 11 publications

(31 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Outside of the framework of TRIPOD, we investigated the reporting on data availability. While six studies [14,32,34,37,38,40] explicitly mentioned data availability upon request, among all twenty-nine examined studies, only Liu et al [39] provided the algorithm code and radiomics data on an open-source platform.…”

Section: Quality Of Reportingmentioning

confidence: 99%

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

Jekel

Brim

Reppert

et al. 2022

Cancers

View full text Add to dashboard Cite

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.

show abstract

Section: Quality Of Reportingmentioning

confidence: 99%

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

Jekel

Brim

Reppert

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…This edema is additionally suggested to provide local compression of blood flow, further decreasing rCBV when compared with glioblastoma [44,45]. Park et al describe an autoencoder used for DSC that is found to be helpful in differentiating the two diseases by using perfusion patterns [46]. Increased rCBV is additionally suggested to be associated with worse clinical outcomes and shorter overall survivability due to its correlation with aggressive tumor growth in glioblastoma [30,47,48].…”

Section: Dynamic Susceptibility Contrast-enhanced Perfusionmentioning

confidence: 99%

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

Fordham

Hacherl

Patel

et al. 2021

Cancers

View full text Add to dashboard Cite

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.

show abstract

“…The total sample size in the 10 studies was 1311 and the overall accuracy (9 studies), sensitivity, and specificity values of each study was documented. There was no available accuracy value in one of the studies ( 21 ), nor were we able to reverse calculate it with the given information. 5 studies used a 3T MRI scanner, while 3 studies used both 3T and 1.5 T. Two studies ( 22 , 23 ) did not provide details on the scanner used or the scanning protocol.…”

Section: Resultsmentioning

confidence: 99%

“…Hence, the authors decided to evaluate only the results of validation/test data set to conduct the statistical analysis in this study. Only one study was externally validated ( 21 ), therefore, all the other included studies were assigned a high risk of bias. As noted previously, future studies of ML should attempt to remove this risk of bias as much as possible, ideally by utilizing a prospective design and external validation.…”

Section: Resultsmentioning

confidence: 99%

“…Significant heterogeneity was present amongst the included studies regarding their scanning protocols, image sequences selected for analysis, methods of drawing ROI, feature engineering, and methodology of using ML/DL algorithms. The forest plots for balanced accuracy, sensitivity, and specificity were plotted based on the total sample size, and the forest plot for accuracy was plotted based on 1051 samples (excluding the study conducted by Park JE ( 21 ) as accuracy data was not available). The I ( 2 ) was estimated to test the level of heterogeneity; and since this was greater than 50%, random effect model for meta-analysis was used.…”

Section: Subgroup Analysismentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2022

View full text Add to dashboard Cite

BackgroundGlioblastoma (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 & ML algorithms in classifying PCNSL from GBM.MethodsThe 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.ResultsTen 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%.ConclusionsExtensive 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 & 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.

show abstract

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

Cited by 11 publications

References 37 publications

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

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

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

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

Contact Info

Product

Resources

About