Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features

Bo, Linlin; Zhang, Zijian; Jiang, Zekun; Yang, Chia-Han; Huang, Pu; Chen, Tingyin; Wang, Yifan; Yu, Gang; Tan, Xiao Jian; Cheng, Quan; Li, Dengwang; Liu, Zhixiong

doi:10.3389/fmed.2021.748144

Cited by 21 publications

(21 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Their findings were promising, with models’ AUCs superior to 92% and their performances superior to those from experienced radiologists. Finally, the remaining two studies investigated the ability of radiomics to differentiate between gliomas (in particular, necrotic glioblastomas [ 60 ] and cystic gliomas [ 61 ]) and brain abscess.…”

Section: Resultsmentioning

confidence: 99%

A Systematic Review of the Current Status and Quality of Radiomics for Glioma Differential Diagnosis

Brancato¹,

Cerrone²,

Lavitrano

et al. 2022

Cancers

View full text Add to dashboard Cite

Radiomics is a promising tool that may increase the value of imaging in differential diagnosis (DDx) of glioma. However, implementation in clinical practice is still distant and concerns have been raised regarding the methodological quality of radiomic studies. Therefore, we aimed to systematically review the current status of radiomic studies concerning glioma DDx, also using the radiomics quality score (RQS) to assess the quality of the methodology used in each study. A systematic literature search was performed to identify original articles focused on the use of radiomics for glioma DDx from 2015. Methodological quality was assessed using the RQS tool. Spearman’s correlation (ρ) analysis was performed to explore whether RQS was correlated with journal metrics and the characteristics of the studies. Finally, 42 articles were selected for the systematic qualitative analysis. Selected articles were grouped and summarized in terms of those on DDx between glioma and primary central nervous system lymphoma, those aiming at differentiating glioma from brain metastases, and those based on DDx of glioma and other brain diseases. Median RQS was 8.71 out 36, with a mean RQS of all studies of 24.21%. Our study revealed that, despite promising and encouraging results, current studies on radiomics for glioma DDx still lack the quality required to allow its introduction into clinical practice. This work could provide new insights and help to reach a consensus on the use of the radiomic approach for glioma DDx.

show abstract

Section: Resultsmentioning

confidence: 99%

A Systematic Review of the Current Status and Quality of Radiomics for Glioma Differential Diagnosis

Brancato¹,

Cerrone²,

Lavitrano

et al. 2022

Cancers

View full text Add to dashboard Cite

show abstract

“…The parameters of several deep learning networks were trained by maximal rectangular slice ROIs of EGC, including Resnet152, Resnet101, Resnet50, Resnet34, Resnet18, Wide_resnet101_2, Wide_resnet50_2, and Inception v3. Then, convolution neural networks based on pre-trained TL networks were used to extract DTL features, which followed the following steps: the slices of ROIs were fed to the pre-trained network; the average probability from all slices was used to generate TL features; and the penultimate FC layer output was used as TL features ( 21 ). Based on these pre-trained deep learning networks, we extracted 512–2,048 transfer learning features, respectively ( Supplementary Table 6 ).…”

Section: Methodsmentioning

confidence: 99%

“…However, acquiring a large number of medical images is difficult ( 20 ). Due to a pre-trained CNN known as “transfer learning (TL)” can be used to minimize overfitting with a small training size, TL has gradually been used in various medical image analysis domains in recent years ( 21 , 22 ). TL increases model performance in target tasks by transferring previously learned features from source tasks.…”

Section: Introductionmentioning

confidence: 99%

“…A previous study found that a TL radiomics nomogram based on gastric whole slide images can assist in distinguishing primary gastric lymphoma from Borrmann type IV GC ( 22 ). In addition, Linlin et al ( 21 ) developed a convenient model based on deep learning-based radiomics characteristics to differentiate brain abscess from cystic glioma. Therefore, it suggests that building a TL radiomics model may be beneficial in improving the accuracy of LNM prediction in EGC.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of a predictive model combining clinical, radiomics, and deep transfer learning features for lymph node metastasis in early gastric cancer

Zeng

Zhu

et al. 2022

Front. Med.

View full text Add to dashboard Cite

BackgroundThis study aims to develop and validate a predictive model combining deep transfer learning, radiomics, and clinical features for lymph node metastasis (LNM) in early gastric cancer (EGC).Materials and methodsThis study retrospectively collected 555 patients with EGC, and randomly divided them into two cohorts with a ratio of 7:3 (training cohort, n = 388; internal validation cohort, n = 167). A total of 79 patients with EGC collected from the Second Affiliated Hospital of Soochow University were used as external validation cohort. Pre-trained deep learning networks were used to extract deep transfer learning (DTL) features, and radiomics features were extracted based on hand-crafted features. We employed the Spearman rank correlation test and least absolute shrinkage and selection operator regression for feature selection from the combined features of clinical, radiomics, and DTL features, and then, machine learning classification models including support vector machine, K-nearest neighbor, random decision forests (RF), and XGBoost were trained, and their performance by determining the area under the curve (AUC) were compared.ResultsWe constructed eight pre-trained transfer learning networks and extracted DTL features, respectively. The results showed that 1,048 DTL features extracted based on the pre-trained Resnet152 network combined in the predictive model had the best performance in discriminating the LNM status of EGC, with an AUC of 0.901 (95% CI: 0.847–0.956) and 0.915 (95% CI: 0.850–0.981) in the internal validation and external validation cohorts, respectively.ConclusionWe first utilized comprehensive multidimensional data based on deep transfer learning, radiomics, and clinical features with a good predictive ability for discriminating the LNM status in EGC, which could provide favorable information when choosing therapy options for individuals with EGC.

show abstract

“…Radiomics has recently emerged as a promising field of research based on the hypothesis that quantitative analysis of medical images can capture additional information that helps infer phenotypes and gene-protein signatures and provide prognostic information [ 11 , 12 ]. More recently, radiomics has been used to identify brain abscess from cystic gliomas [ 13 ], predict the molecular subtypes of HGGs (such as IDH [ 14 , 15 ] and MGMT [ 16 ] status), assess the antiangiogenic treatment response of recurrent glioblastomas (GBMs) [ 17 ], and stratify the risk of patients with GBMs [ 18 ]. Previous radiomics analysis of GBMs has shown that the radiomics signature holds better prognostic value than clinical and radiological risk models in predicting survival [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

Radiomics Profiling Identifies the Incremental Value of MRI Features beyond Key Molecular Biomarkers for the Risk Stratification of High‐Grade Gliomas

Yang

Sha

Wang

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Objective. To identify the incremental value of magnetic resonance imaging (MRI) features beyond key molecular biomarkers for the risk stratification of high-grade gliomas (HGGs). Methods. A total of 241 patients with preoperative magnetic resonance (MR) images and clinical and genetic data were retrospectively collected from our institution and The Cancer Genome Atlas/The Cancer Imaging Archive (TCGA/TCIA) dataset. Radiomic features (n = 1702) were extracted from both postcontrast T1-weighted (CE-T1) and T2-weighted fluid attenuation inversion recovery (T2FLAIR) MR images. The least absolute shrinkage and selection operator (LASSO) method was used to select effective features. A multivariate Cox proportional risk regression model was established to explore the prognostic value of clinical features, molecular biomarkers, and radiomic features. Kaplan–Meier survival analysis and the log-rank test were used to evaluate the prognostic model, and a stratified analysis was conducted to demonstrate the incremental value of the radiomics signature. A nomogram was developed to predict the 1-year, 2-year, and 3-year overall survival (OS) probabilities of the patients with HGGs. Results. The radiomics signature provided significant prognostic value for the risk stratification of patients with HGGs. The combined model integrating the radiomics signature with clinical data (age) and O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status had the best prognostic value, with C-index values of 0.752 and 0.792 in the training set and external validation set, respectively. Stratified Kaplan–Meier survival analysis showed that the radiomics signature could identify the risk subgroups in different clinical and molecular subgroups. Conclusion. This radiomics signature can be used for the risk stratification of patients with HGGs and has incremental value beyond key molecular biomarkers, providing a preoperative basis for individualized diagnosis and treatment decision-making.

show abstract

Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features

Cited by 21 publications

References 39 publications

A Systematic Review of the Current Status and Quality of Radiomics for Glioma Differential Diagnosis

A Systematic Review of the Current Status and Quality of Radiomics for Glioma Differential Diagnosis

Development and validation of a predictive model combining clinical, radiomics, and deep transfer learning features for lymph node metastasis in early gastric cancer

Radiomics Profiling Identifies the Incremental Value of MRI Features beyond Key Molecular Biomarkers for the Risk Stratification of High‐Grade Gliomas

Contact Info

Product

Resources

About