scholarly journals MR-Based Radiomics for Differential Diagnosis between Cystic Pituitary Adenoma and Rathke Cleft Cyst

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Yanping Wang ◽  
Sixuan Chen ◽  
Feng Shi ◽  
Xiaoqing Cheng ◽  
Qiang Xu ◽  
...  
Keyword(s):  
Differential Diagnosis ◽  
Pituitary Adenoma ◽  
Diagnostic Performance ◽  
Characteristic Curve ◽  
Semantic Features ◽  
Imaging Features ◽  
Semantic Model ◽  
Imaging Data ◽  
Test Set ◽  
Rathke Cleft Cyst

Background. It is often tricky to differentiate cystic pituitary adenoma from Rathke cleft cyst with visual inspection because of similar MRI presentations between them. We aimed to design an MR-based radiomics model for improving differential diagnosis between them. Methods. Conventional diagnostic MRI data (T1-,T2-, and postcontrast T1-weighted MR images) were obtained from 215 pathologically confirmed patients (105 cases with cystic pituitary adenoma and the other 110 cases with Rathke cleft cyst) and were divided into training ( n = 172 ) and test sets ( n = 43 ). MRI radiomics features were extracted from the imaging data, and semantic imaging features ( n = 15 ) were visually estimated by two radiologists. Four classifiers were used to construct radiomics models through 5-fold crossvalidation after feature selection with least absolute shrinkage and selection operator. An integrated model by combining radiomics and semantic features was further constructed. The diagnostic performance was validated in the test set. Receiver operating characteristic curve was used to evaluate and compare the performance of the models at the background of diagnostic performance by radiologist. Results. In test set, the combined radiomics and semantic model using ANN classifier obtained the best classification performance with an AUC of 0.848 (95% CI: 0.750-0.946), accuracy of 76.7% (95% CI: 64.1-89.4%), sensitivity of 73.9% (95% CI: 56.0-91.9%), and specificity of 80.0% (95% CI: 62.5-97.5%) and performed better than multiparametric model ( AUC = 0.792 , 95% CI: 0.674-0.910) or semantic model ( AUC = 0.823 , 95% CI: 0.705-0.941). The two radiologists had an accuracy of 69.8% and 74.4%, respectively, sensitivity of 69.6% and 73.9%, and specificity of 70.0% and 75.0%. Conclusions. The MR-based radiomics model had technical feasibility and good diagnostic performance in the differential diagnosis between cystic pituitary adenoma and Rathke cleft cyst.

scholarly journals Contrast-Enhanced Ultrasound in the Differential Diagnosis of Primary Thyroid Lymphoma and Nodular Hashimoto’s Thyroiditis in a Background of Heterogeneous Parenchyma

2021 ◽  
Vol 10 ◽  
Author(s):  
Lulu Yang ◽  
Haina Zhao ◽  
Yushuang He ◽  
Xianglan Zhu ◽  
Can Yue ◽  
...  
Keyword(s):  
Differential Diagnosis ◽  
Hashimoto’S Thyroiditis ◽  
Diagnostic Performance ◽  
Roc Curves ◽  
Hashimoto's Thyroiditis ◽  
Imaging Features ◽  
Contrast Enhanced Ultrasound ◽  
Thyroid Lymphoma ◽  
Contrast Enhanced ◽  
Primary Thyroid Lymphoma

ObjectiveTo investigate the diagnostic performance of contrast-enhanced ultrasound (CEUS) in the differentiation of primary thyroid lymphoma (PTL) and nodular Hashimoto’s thyroiditis (NHT) in patients with background of heterogeneous diffuse Hashimoto’s thyroiditis (HT).MethodsSixty HT patients with 64 thyroid nodules (31 PTL and 33 NHT) who had undergone CEUS examination were included in this study. With histopathological results as the reference, we evaluated the imaging features of each nodule on both conventional ultrasonography (US) and CEUS. Quantitative CEUS parameters including peak intensity (PI), time to peak (TTP), and area under the time–intensity curve (AUC) were gathered in the nodule and background parenchyma. The ratio indexes of theses parameters were calculated by the ratio of the lesion and the corresponding thyroid parenchyma. Logistic regression and receiver operating characteristic (ROC) curves analyses of valuable US indicators were further preformed to evaluate the diagnostic capability of CEUS in discrimination of PTL and NHT.ResultsAmong all the observed US imaging features and CEUS parameters, 10 indicators showed significant differences between PTL and NHT (all P < 0.05). All the significant indicators were ranked according to the odds ratios (ORs). Eight of them were CEUS associated including imaging features of enhancement pattern, degree, homogeneity, and quantification parameters of PI, AUC, ratios of PI, AUC, and TTP, while indicators on conventional US, including vascularity and size ranked the last two with ORs less than 3. The five single CEUS parameters showed good diagnostic performance in diagnosis of PTL with areas under ROC curves of 0.72–0.83 and accuracies of 70.3–75.0%. The combination of CEUS imaging features and the ratios of PI, AUC, and TTP demonstrated excellent diagnostic efficiency and achieved area under ROC curve of 0.92, which was significantly higher than any of the five single parameters (all P < 0.05), with a sensitivity of 83.9%, specificity of 87.9%, and accuracy of 85.9%.ConclusionsCEUS is an efficient diagnostic tool in the differential diagnosis of PTL and NHT for patients with diffuse HT. Conjoint analysis of CEUS imaging features and quantification parameters could improve the diagnostic values.

Differential diagnosis of parkinsonian degenerative disorders in combination manual measurements with automated volumetry of the brain

2020 ◽  
Author(s):  
Yiwei Zhang ◽  
Han Wang ◽  
Dan Xu ◽  
Bo Hou ◽  
Tianye Lin ◽  
...  
Keyword(s):  
Differential Diagnosis ◽  
Diagnostic Performance ◽  
Characteristic Curve ◽  
Brain Regions ◽  
Relative Volume ◽  
Intracranial Volume ◽  
Degenerative Disorders ◽  
Automated Measurements ◽  
Morphological Differences ◽  
The Brain

Abstract Background: To compare brain morphological differences in progressive supranuclear palsy (PSP), multiple system atrophy with the parkinsonian variant (MSA-P), Parkinson’s disease (PD) and controls by manual and automated measurements and to explore the feasibility of these measurements in disease differentiation.Methods: Ninety-five PSP patients (48 males, mean age 67.9 y), 32 MSA-P patients (18 males, mean age 63.0 y), 136 PD patients (72 males, mean age 66.6 y) and 100 controls (50 males, mean age 66 y) were included. The 12 manual measurements were acquired. Relative brain structural volumes adjusted according to the intracranial volume (ICV) of different brain regions werealsoquantified. Differences among and between groups were evaluated. Receiver operating characteristic curve analysis was used to assess diagnostic performance and define cutoff values of these measures.Results: P/M area 2.0displayed the highest diagnostic performance (AUC: 0.801) for distinguishing PSP from MSA-P or PD (sensitivity69.5%, specificity 82.1%). Furthermore, the combination of morphological features in manual parameters (P/M area 2.0, MRPI and M/P diameter) and volume atrophy in the midbrain improved the PSP discrimination (AUC: 0.870, sensitivity 76.8%, specificity 83.9%). The relative volume of the putamen can better differentiate MSA-P from PSP and PD (AUC: 0.844, sensitivity 81.3%, specificity 75.3%). Similarly, the ability to differentially diagnose MSA-P increased most significantly (AUC: 0.927, sensitivity 87.5%, specificity 87.9%) when combing volume atrophy in the putamen with the caudate and manual parameter (M/P diameter).Conclusion: Manual and automated MR variables can reveal atrophy features of the brain and be helpful in the differential diagnosis.

scholarly journals In Silico Approach for the Definition of radiomiRNomic Signatures for Breast Cancer Differential Diagnosis

2019 ◽  
Vol 20 (23) ◽  
pp. 5825 ◽  
Author(s):  
Francesca Gallivanone ◽  
Claudia Cava ◽  
Fabio Corsi ◽  
Gloria Bertoli ◽  
Isabella Castiglioni
Keyword(s):  
Breast Cancer ◽  
Differential Diagnosis ◽  
Regulatory Networks ◽  
Tumor Imaging ◽  
Tumor Development ◽  
Computational Approach ◽  
Imaging Features ◽  
Imaging Data ◽  
Luminal A ◽  
Mirna Expression Data

Personalized medicine relies on the integration and consideration of specific characteristics of the patient, such as tumor phenotypic and genotypic profiling. Background: Radiogenomics aim to integrate phenotypes from tumor imaging data with genomic data to discover genetic mechanisms underlying tumor development and phenotype. Methods: We describe a computational approach that correlates phenotype from magnetic resonance imaging (MRI) of breast cancer (BC) lesions with microRNAs (miRNAs), mRNAs, and regulatory networks, developing a radiomiRNomic map. We validated our approach to the relationships between MRI and miRNA expression data derived from BC patients. We obtained 16 radiomic features quantifying the tumor phenotype. We integrated the features with miRNAs regulating a network of pathways specific for a distinct BC subtype. Results: We found six miRNAs correlated with imaging features in Luminal A (miR-1537, -205, -335, -337, -452, and -99a), seven miRNAs (miR-142, -155, -190, -190b, -1910, -3617, and -429) in HER2+, and two miRNAs (miR-135b and -365-2) in Basal subtype. We demonstrate that the combination of correlated miRNAs and imaging features have better classification power of Luminal A versus the different BC subtypes than using miRNAs or imaging alone. Conclusion: Our computational approach could be used to identify new radiomiRNomic profiles of multi-omics biomarkers for BC differential diagnosis and prognosis.

scholarly journals Can Additional Patient Information Improve the Diagnostic Performance of Deep Learning for the Interpretation of Knee Osteoarthritis Severity

2020 ◽  
Vol 9 (10) ◽  
pp. 3341
Author(s):  
Dong Hyun Kim ◽  
Kyong Joon Lee ◽  
Dongjun Choi ◽  
Jae Ik Lee ◽  
Han Gyeol Choi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Confidence Interval ◽  
Knee Osteoarthritis ◽  
Patient Information ◽  
Diagnostic Performance ◽  
Characteristic Curve ◽  
Image Data ◽  
Clinical Information ◽  
Additional Patient ◽  
Test Set

The study compares the diagnostic performance of deep learning (DL) with that of the former radiologist reading of the Kellgren–Lawrence (KL) grade and evaluates whether additional patient data can improve the diagnostic performance of DL. From March 2003 to February 2017, 3000 patients with 4366 knee AP radiographs were randomly selected. DL was trained using knee images and clinical information in two stages. In the first stage, DL was trained only with images and then in the second stage, it was trained with image data and clinical information. In the test set of image data, the areas under the receiver operating characteristic curve (AUC)s of the DL algorithm in diagnosing KL 0 to KL 4 were 0.91 (95% confidence interval (CI), 0.88–0.95), 0.80 (95% CI, 0.76–0.84), 0.69 (95% CI, 0.64–0.73), 0.86 (95% CI, 0.83–0.89), and 0.96 (95% CI, 0.94–0.98), respectively. In the test set with image data and additional patient information, the AUCs of the DL algorithm in diagnosing KL 0 to KL 4 were 0.97 (95% confidence interval (CI), 0.71–0.74), 0.85 (95% CI, 0.80–0.86), 0.75 (95% CI, 0.66–0.73), 0.86 (95% CI, 0.79–0.85), and 0.95 (95% CI, 0.91–0.97), respectively. The diagnostic performance of image data with additional patient information showed a statistically significantly higher AUC than image data alone in diagnosing KL 0, 1, and 2 (p-values were 0.008, 0.020, and 0.027, respectively).The diagnostic performance of DL was comparable to that of the former radiologist reading of the knee osteoarthritis KL grade. Additional patient information improved DL diagnosis in interpreting early knee osteoarthritis.

A Case of an Extraosseous Pretibial Ganglion Cyst

2019 ◽  
Vol 1 ◽  
pp. 114-116
Author(s):  
Catrin Wigley ◽  
Guy Morris ◽  
Scott Evans ◽  
Rajesh Botchu
Keyword(s):  
Differential Diagnosis ◽  
Ganglion Cyst ◽  
Imaging Features ◽  
Oncology Service ◽  
Orthopedic Oncology

Pretibial lesion can have a plethora of differential diagnosis. We report a case of extraosseous pretibial ganglion cyst which was referred to our orthopedic oncology service and described the imaging features.

scholarly journals Machine learning approach for differentiating cytomegalovirus esophagitis from herpes simplex virus esophagitis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jung Su Lee ◽  
Jihye Yun ◽  
Sungwon Ham ◽  
Hyunjung Park ◽  
Hyunsu Lee ◽  
...  
Keyword(s):  
Machine Learning ◽  
Differential Diagnosis ◽  
Herpes Simplex Virus ◽  
Herpes Simplex ◽  
Predictive Value ◽  
Characteristic Curve ◽  
Previous History ◽  
Clinical Factor ◽  
Endoscopic Images ◽  
Simplex Virus

AbstractThe endoscopic features between herpes simplex virus (HSV) and cytomegalovirus (CMV) esophagitis overlap significantly, and hence the differential diagnosis between HSV and CMV esophagitis is sometimes difficult. Therefore, we developed a machine-learning-based classifier to discriminate between CMV and HSV esophagitis. We analyzed 87 patients with HSV esophagitis and 63 patients with CMV esophagitis and developed a machine-learning-based artificial intelligence (AI) system using a total of 666 endoscopic images with HSV esophagitis and 416 endoscopic images with CMV esophagitis. In the five repeated five-fold cross-validations based on the hue–saturation–brightness color model, logistic regression with a least absolute shrinkage and selection operation showed the best performance (sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and area under the receiver operating characteristic curve: 100%, 100%, 100%, 100%, 100%, and 1.0, respectively). Previous history of transplantation was included in classifiers as a clinical factor; the lower the performance of these classifiers, the greater the effect of including this clinical factor. Our machine-learning-based AI system for differential diagnosis between HSV and CMV esophagitis showed high accuracy, which could help clinicians with diagnoses.

scholarly journals Predicting drug–target interactions Based on the Ensemble Models of Multiple Feature Pairs

2021 ◽  
Vol 22 (12) ◽  
pp. 6598
Author(s):  
Cheng Wang ◽  
Jun Zhang ◽  
Peng Chen ◽  
Bing Wang
Keyword(s):  
Drug Target ◽  
Essential Feature ◽  
Characteristic Curve ◽  
Prediction Method ◽  
New Drugs ◽  
Good Prediction ◽  
Ensemble Model ◽  
Test Set ◽  
Multiple Feature ◽  
Validation Set

Backgroud: The prediction of drug–target interactions (DTIs) is of great significance in drug development. It is time-consuming and expensive in traditional experimental methods. Machine learning can reduce the cost of prediction and is limited by the characteristics of imbalanced datasets and problems of essential feature selection. Methods: The prediction method based on the Ensemble model of Multiple Feature Pairs (Ensemble-MFP) is introduced. Firstly, three negative sets are generated according to the Euclidean distance of three feature pairs. Then, the negative samples of the validation set/test set are randomly selected from the union set of the three negative sets in the validation set/test set. At the same time, the ensemble model with weight is optimized and applied to the test set. Results: The area under the receiver operating characteristic curve (area under ROC, AUC) in three out of four sub-datasets in gold standard datasets was more than 94.0% in the prediction of new drugs. The effectiveness of the proposed method is also shown with the comparison of state-of-the-art methods and demonstration of predicted drug–target pairs. Conclusion: The Ensemble-MFP can weigh the existing feature pairs and has a good prediction effect for general prediction on new drugs.

scholarly journals Not all that glitters is COVID! Differential diagnosis of FDG-avid interstitial lung disease in low-prevalence regions

2020 ◽  
Vol 4 (1) ◽  
Author(s):  
Annalisa Papa ◽  
Chiara Pozzessere ◽  
Francesco Cicone ◽  
Fabiola Rizzuto ◽  
Giuseppe Lucio Cascini
Keyword(s):  
Differential Diagnosis ◽  
Interstitial Lung Diseases ◽  
Routine Activity ◽  
Imaging Features ◽  
Pet Ct ◽  
Oncologic Patients ◽  
The Many ◽  
Fdg Pet Ct ◽  
Low Prevalence ◽  
Similar Imaging

Abstract Coronavirus disease-19 (COVID-19) is only one of the many possible infectious and non-infectious diseases that may occur with similar imaging features in patients undergoing [18F]-fluorodeoxyglucose (18FDG) monitoring, particularly in the most fragile oncologic patients. We briefly summarise some key radiological elements of differential diagnosis of interstitial lung diseases which, in our opinion, could be extremely useful for physicians reporting 18FDG PET/CT scans, not only during the COVID-19 pandemic, but also for their normal routine activity.

scholarly journals Extraosseous Ewing’s Sarcoma: Pictorial Review of Imaging Findings, Differential Diagnosis, and Pathologic Correlation

2021 ◽  
Author(s):  
Alan Alexander ◽  
Kyle Hunter ◽  
Michael Rubin ◽  
Ambarish P. Bhat
Keyword(s):  
Differential Diagnosis ◽  
Ewing’S Sarcoma ◽  
Ewing's Sarcoma ◽  
Multimodality Imaging ◽  
Imaging Features ◽  
Older Children ◽  
Radiologic Findings ◽  
Pictorial Review ◽  
Malignant Mesenchymal Tumor ◽  
Extraosseous Ewing’S Sarcoma

AbstractExtraosseous Ewing’s sarcoma (EES), first described in 1969, is a malignant mesenchymal tumor just like its intraosseous counterpart. Although Ewing’s sarcomas are common bone tumors in young children, EESs are rarer and more commonly found in older children/adults, often carrying a poorer prognosis. We discuss the multimodality imaging features of EES and the differential diagnosis of an aggressive appearing mass in proximity to skeletal structures, with pathologic correlates. This review highlights the need to recognize the variability of radiologic findings in EES such as the presence of hemorrhage, rich vascularity, and cystic or necrotic regions and its imaging similarity to other neoplasms that are closely related pathologically.

scholarly journals Centered Kernel Alignment Enhancing Neural Network Pretraining for MRI-Based Dementia Diagnosis

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
David Cárdenas-Peña ◽  
Diego Collazos-Huertas ◽  
German Castellanos-Dominguez
Keyword(s):  
Neural Network ◽  
Characteristic Curve ◽  
Principal Component ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Dementia Diagnosis ◽  
Target Matrix ◽  
Computer Aided ◽  
Artificial Neural Network Ann ◽  
Aided Diagnosis

Dementia is a growing problem that affects elderly people worldwide. More accurate evaluation of dementia diagnosis can help during the medical examination. Several methods for computer-aided dementia diagnosis have been proposed using resonance imaging scans to discriminate between patients with Alzheimer’s disease (AD) or mild cognitive impairment (MCI) and healthy controls (NC). Nonetheless, the computer-aided diagnosis is especially challenging because of the heterogeneous and intermediate nature of MCI. We address the automated dementia diagnosis by introducing a novel supervised pretraining approach that takes advantage of the artificial neural network (ANN) for complex classification tasks. The proposal initializes an ANN based on linear projections to achieve more discriminating spaces. Such projections are estimated by maximizing the centered kernel alignment criterion that assesses the affinity between the resonance imaging data kernel matrix and the label target matrix. As a result, the performed linear embedding allows accounting for features that contribute the most to the MCI class discrimination. We compare the supervised pretraining approach to two unsupervised initialization methods (autoencoders and Principal Component Analysis) and against the best four performing classification methods of the 2014CADDementiachallenge. As a result, our proposal outperforms all the baselines (7% of classification accuracy and area under the receiver-operating-characteristic curve) at the time it reduces the class biasing.

Sign in / Sign up

Export Citation Format

Share Document