scholarly journals Sequential implementation of DSC-MR perfusion and dynamic [18F]FET PET allows efficient differentiation of glioma progression from treatment-related changes

2020 ◽  
Author(s):  
Eike Steidl ◽  
Karl-Josef Langen ◽  
Sarah Abu Hmeidan ◽  
Nenad Polomac ◽  
Christian P. Filss ◽  
...  
Keyword(s):  
Area Under The Curve ◽  
Diagnostic Methods ◽  
Superior Performance ◽  
Dynamic Susceptibility ◽  
Dynamic Susceptibility Contrast ◽  
Clinical Value ◽  
Who Grade ◽  
Fet Pet ◽  
The Impact ◽  
Sequential Implementation

Abstract Purpose Perfusion-weighted MRI (PWI) and O-(2-[18F]fluoroethyl-)-l-tyrosine ([18F]FET) PET are both applied to discriminate tumor progression (TP) from treatment-related changes (TRC) in patients with suspected recurrent glioma. While the combination of both methods has been reported to improve the diagnostic accuracy, the performance of a sequential implementation has not been further investigated. Therefore, we retrospectively analyzed the diagnostic value of consecutive PWI and [18F]FET PET. Methods We evaluated 104 patients with WHO grade II–IV glioma and suspected TP on conventional MRI using PWI and dynamic [18F]FET PET. Leakage corrected maximum relative cerebral blood volumes (rCBVmax) were obtained from dynamic susceptibility contrast PWI. Furthermore, we calculated static (i.e., maximum tumor to brain ratios; TBRmax) and dynamic [18F]FET PET parameters (i.e., Slope). Definitive diagnoses were based on histopathology (n = 42) or clinico-radiological follow-up (n = 62). The diagnostic performance of PWI and [18F]FET PET parameters to differentiate TP from TRC was evaluated by analyzing receiver operating characteristic and area under the curve (AUC). Results Across all patients, the differentiation of TP from TRC using rCBVmax or [18F]FET PET parameters was moderate (AUC = 0.69–0.75; p < 0.01). A rCBVmax cutoff > 2.85 had a positive predictive value for TP of 100%, enabling a correct TP diagnosis in 44 patients. In the remaining 60 patients, combined static and dynamic [18F]FET PET parameters (TBRmax, Slope) correctly discriminated TP and TRC in a significant 78% of patients, increasing the overall accuracy to 87%. A subgroup analysis of isocitrate dehydrogenase (IDH) mutant tumors indicated a superior performance of PWI to [18F]FET PET (AUC = 0.8/< 0.62, p < 0.01/≥ 0.3). Conclusion While marked hyperperfusion on PWI indicated TP, [18F]FET PET proved beneficial to discriminate TP from TRC when PWI remained inconclusive. Thus, our results highlight the clinical value of sequential use of PWI and [18F]FET PET, allowing an economical use of diagnostic methods. The impact of an IDH mutation needs further investigation.

scholarly journals Convolutional Neural Network for Breast and Thyroid Nodules Diagnosis in Ultrasound Imaging

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Xiaowen Liang ◽  
Jinsui Yu ◽  
Jianyi Liao ◽  
Zhiyi Chen
Keyword(s):  
Predictive Value ◽  
Area Under The Curve ◽  
Roc Curves ◽  
Diagnostic Efficiency ◽  
Clinical Value ◽  
Data Set ◽  
Multiple Organs ◽  
Significant Difference ◽  
Segmented Images ◽  
The Impact

Objective. The incidence of superficial organ diseases has increased rapidly in recent years. New methods such as computer-aided diagnosis (CAD) are widely used to improve diagnostic efficiency. Convolutional neural networks (CNNs) are one of the most popular methods, and further improvements of CNNs should be considered. This paper aims to develop a multiorgan CAD system based on CNNs for classifying both thyroid and breast nodules and investigate the impact of this system on the diagnostic efficiency of different preprocessing approaches. Methods. The training and validation sets comprised randomly selected thyroid and breast nodule images. The data were subgrouped into 4 models according to the different preprocessing methods (depending on segmentation and the classification method). A prospective data set was selected to verify the clinical value of the CNN model by comparison with ultrasound guidelines. Diagnostic efficiency was assessed based on receiver operating characteristic (ROC) curves. Results. Among the 4 models, the CNN model using segmented images for classification achieved the best result. For the validation set, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the curve (AUC) of our CNN model were 84.9%, 69.0%, 62.5%, 88.2%, 75.0%, and 0.769, respectively. There was no statistically significant difference between the CNN model and the ultrasound guidelines. The combination of the two methods achieved superior diagnostic efficiency compared with their use individually. Conclusions. The study demonstrates the probability, feasibility, and clinical value of CAD in the ultrasound diagnosis of multiple organs. The use of segmented images and classification by the nature of the disease are the main factors responsible for the improvement of the CNN model. Moreover, the combination of the CNN model and ultrasound guidelines results in better diagnostic performance, which will contribute to the improved diagnostic efficiency of CAD systems.

scholarly journals Genetic Abnormalities in Biliary Brush Samples for Distinguishing Cholangiocarcinoma from Benign Strictures in Primary Sclerosing Cholangitis

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Margriet R. Timmer ◽  
Chiu T. Lau ◽  
Sybren L. Meijer ◽  
Paul Fockens ◽  
Erik A. J. Rauws ◽  
...  
Keyword(s):  
Primary Sclerosing Cholangitis ◽  
Sclerosing Cholangitis ◽  
Area Under The Curve ◽  
Clonal Diversity ◽  
Diagnostic Value ◽  
Diagnostic Methods ◽  
Biliary Strictures ◽  
Clinical Value ◽  
Benign Biliary Strictures ◽  
Genetic Abnormalities

Background. Primary sclerosing cholangitis (PSC) is a chronic inflammatory liver disease and is strongly associated with cholangiocarcinoma (CCA). The lack of efficient diagnostic methods for CCA is a major problem. Testing for genetic abnormalities may increase the diagnostic value of cytology.Methods.We assessed genetic abnormalities forCDKN2A,TP53,ERBB2,20q,MYC, and chromosomes 7 and 17 and measures of genetic clonal diversity in brush samples from 29 PSC patients with benign biliary strictures and 12 patients with sporadic CCA or PSC-associated CCA. Diagnostic performance of cytology alone and in combination with genetic markers was evaluated by sensitivity, specificity, and area under the curve analysis.Results. The presence ofMYCgain andCDKN2Aloss as well as a higher clonal diversity was significantly associated with malignancy.MYCgain increased the sensitivity of cytology from 50% to 83%. However, the specificity decreased from 97% to 76%. The diagnostic accuracy of the best performing measures of clonal diversity was similar to the combination of cytology andMYC. AddingCDKN2Aloss to the panel had no additional benefit.Conclusion. Evaluation ofMYCabnormalities and measures of clonal diversity in brush cytology specimens may be of clinical value in distinguishing CCA from benign biliary strictures in PSC.

scholarly journals Contribution of advanced neuro-imaging (MR diffusion, perfusion and proton spectroscopy) in differentiation between low grade gliomas GII and MR morphologically similar non neoplastic lesions

2022 ◽  
Vol 53 (1) ◽  
Author(s):  
Mohamed Saied Abdelgawad ◽  
Mohamed Hamdy Kayed ◽  
Mohamed Ihab Samy Reda ◽  
Eman Abdelzaher ◽  
Ahmed Hafez Farhoud ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Cerebral Blood Volume ◽  
Area Under The Curve ◽  
Threshold Value ◽  
Low Grade ◽  
Dynamic Susceptibility ◽  
Who Grade ◽  
Low Grade Gliomas ◽  
Neoplastic Lesions ◽  
Neuro Imaging

Abstract Background Non-neoplastic brain lesions can be misdiagnosed as low-grade gliomas. Conventional magnetic resonance (MR) imaging may be non-specific. Additional imaging modalities such as spectroscopy (MRS), perfusion and diffusion imaging aid in diagnosis of such lesions. However, contradictory and overlapping results are still present. Hence, our purpose was to evaluate the role of advanced neuro-imaging in differentiation between low-grade gliomas (WHO grade II) and MR morphologically similar non-neoplastic lesions and to prove which modality has the most accurate results in differentiation. Results All patients were classified into two main groups: patients with low-grade glioma (n = 12; mean age, 38.8 ± 16; 8 males) and patients with non-neoplastic lesions (n = 27; mean age, 36.6 ± 15; 19 males) based on the histopathological and clinical–radiological diagnosis. Using ROC curve analysis, a threshold value of 0.93 for rCBV (AUC = 0.875, PPV = 92%, NPV = 71.4%) and a threshold value of 2.5 for Cho/NAA (AUC = 0.829, PPV = 92%, NPV = 71.4%) had 85.2% sensitivity and 83.3% specificity for predicting neoplastic lesions. The area under the curve (AUC) of ROC analysis was good for relative cerebral blood volume (rCBV) and Cho/NAA ratios (> 0.80) and fair for Cho/Cr and NAA/Cr ratios (0.70–0.80). When the rCBV measurements were combined with MRS ratios, significant improvement was observed in the area under the curve (AUC) (0.969) with improved diagnostic accuracy (89.7%) and sensitivity (88.9%). Conclusions Evaluation of rCBV and metabolite ratios at MRS, particularly Cho/NAA ratio, may be helpful in differentiating low-grade gliomas from non-neoplastic lesions. The combination of dynamic susceptibility contrast (DSC) perfusion and MRS can significantly improve the diagnostic accuracy and can help avoiding the need for an invasive biopsy.

scholarly journals Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network

2019 ◽  
Vol 21 (9) ◽  
pp. 1197-1209 ◽  
Author(s):  
Kyu Sung Choi ◽  
Seung Hong Choi ◽  
Bumseok Jeong
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Signal Intensity ◽  
Short Term Memory ◽  
Area Under The Curve ◽  
Perfusion Mri ◽  
Dynamic Susceptibility ◽  
Dynamic Susceptibility Contrast ◽  
Operating Characteristics ◽  
Susceptibility Contrast

Abstract Background The aim of this study was to predict isocitrate dehydrogenase (IDH) genotypes of gliomas using an interpretable deep learning application for dynamic susceptibility contrast (DSC) perfusion MRI. Methods Four hundred sixty-three patients with gliomas who underwent preoperative MRI were enrolled in the study. All the patients had immunohistopathologic diagnoses of either IDH-wildtype or IDH-mutant gliomas. Tumor subregions were segmented using a convolutional neural network followed by manual correction. DSC perfusion MRI was performed to obtain T2* susceptibility signal intensity-time curves from each subregion of the tumors: enhancing tumor, non-enhancing tumor, peritumoral edema, and whole tumor. These, with arterial input functions, were fed into a neural network as multidimensional inputs. A convolutional long short-term memory model with an attention mechanism was developed to predict IDH genotypes. Receiver operating characteristics analysis was performed to evaluate the model. Results The IDH genotype predictions had an accuracy, sensitivity, and specificity of 92.8%, 92.6%, and 93.1%, respectively, in the validation set (area under the curve [AUC], 0.98; 95% confidence interval [CI], 0.969–0.991) and 91.7%, 92.1%, and 91.5%, respectively, in the test set (AUC, 0.95; 95% CI, 0.898–0.982). In temporal feature analysis, T2* susceptibility signal intensity-time curves obtained from DSC perfusion MRI with attention weights demonstrated high attention on the combination of the end of the pre-contrast baseline, up/downslopes of signal drops, and/or post-bolus plateaus for the curves used to predict IDH genotype. Conclusions We developed an explainable recurrent neural network model based on DSC perfusion MRI to predict IDH genotypes in gliomas.

Sign in / Sign up

Export Citation Format

Share Document