scholarly journals Predicting Infarct Core From Computed Tomography Perfusion in Acute Ischemia With Machine Learning

Stroke ◽  
2021 ◽  
Author(s):  
Arsany Hakim ◽  
Søren Christensen ◽  
Stefan Winzeck ◽  
Maarten G. Lansberg ◽  
Mark W. Parsons ◽  
...  
Keyword(s):  
Machine Learning ◽  
Diffusion Weighted Imaging ◽  
Interquartile Range ◽  
Reference Standard ◽  
Lesion Segmentation ◽  
Diffusion Weighted ◽  
Absolute Volume ◽  
Stroke Lesion ◽  
Infarcted Tissue ◽  
Volume Difference

Background and Purpose: The ISLES challenge (Ischemic Stroke Lesion Segmentation) enables globally diverse teams to compete to develop advanced tools for stroke lesion analysis with machine learning. Detection of irreversibly damaged tissue on computed tomography perfusion (CTP) is often necessary to determine eligibility for late-time-window thrombectomy. Therefore, the aim of ISLES-2018 was to segment infarcted tissue on CTP based on diffusion-weighted imaging as a reference standard. Methods: The data, from 4 centers, consisted of 103 cases of acute anterior circulation large artery occlusion stroke who underwent diffusion-weighted imaging rapidly after CTP. Diffusion-weighted imaging lesion segmentation was performed manually and acted as a reference standard. The data were separated into 63 cases for training and 40 for testing, upon which quality metrics (dice score coefficient, Hausdorff distance, absolute lesion volume difference, etc) were computed to rank methods based on their overall performance. Results: Twenty-four different teams participated in the challenge. Median time to CTP was 185 minutes (interquartile range, 180–238), the time between CTP and magnetic resonance imaging was 36 minutes (interquartile range, 25–79), and the median infarct lesion size was 15.2 mL (interquartile range, 5.7–45). The best performance for Dice score coefficient and absolute volume difference were 0.51 and 10.1 mL, respectively, from different teams. Based on the ranking criteria, the top team’s algorithm demonstrated for average Dice score coefficient and average absolute volume difference 0.51 and 10.2 mL, respectively, outperforming the conventional threshold-based method (dice score coefficient, 0.3; volume difference, 15.3). Diverse algorithms were used, almost all based on deep learning, with top-ranked approaches making use of the raw perfusion data as well as methods to synthetically generate complementary information to boost prediction performance. Conclusions: Machine learning methods may predict infarcted tissue from CTP with improved accuracy compared with threshold-based methods used in clinical routine. This dataset will remain public and can be used to test improvement in algorithms over time.

Machine Learning of Diffusion Weighted Imaging for Prediction of Seizure Susceptibility Following Traumatic Brain Injury

2021 ◽  
Author(s):  
Akul Sharma ◽  
Rachael Garner ◽  
Marianna La Rocca ◽  
Celina Alba ◽  
Yenlin Lee ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Diffusion Weighted Imaging ◽  
Seizure Susceptibility ◽  
Diffusion Weighted

Texture and shape analysis of diffusion‐weighted imaging for thyroid nodules classification using machine learning

2021 ◽  
Author(s):  
Ahmed Sharafeldeen ◽  
Mohamed Elsharkawy ◽  
Reem Khaled ◽  
Ahmed Shaffie ◽  
Fahmi Khalifa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Shape Analysis ◽  
Diffusion Weighted Imaging ◽  
Thyroid Nodules ◽  
Diffusion Weighted

scholarly journals A machine learning model for the prediction of survival and tumor subtype in pancreatic ductal adenocarcinoma from preoperative diffusion-weighted imaging

2019 ◽  
Vol 3 (1) ◽  
Author(s):  
Georgios Kaissis ◽  
Sebastian Ziegelmayer ◽  
Fabian Lohöfer ◽  
Hana Algül ◽  
Matthias Eiber ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Diffusion Weighted Imaging ◽  
Area Under The Curve ◽  
Supervised Machine Learning ◽  
Ductal Adenocarcinoma ◽  
Recursive Feature Elimination ◽  
Training Cohort ◽  
Diffusion Weighted ◽  
Histopathological Subtype

Abstract Background To develop a supervised machine learning (ML) algorithm predicting above- versus below-median overall survival (OS) from diffusion-weighted imaging-derived radiomic features in patients with pancreatic ductal adenocarcinoma (PDAC). Methods One hundred two patients with histopathologically proven PDAC were retrospectively assessed as training cohort, and 30 prospectively accrued and retrospectively enrolled patients served as independent validation cohort (IVC). Tumors were segmented on preoperative apparent diffusion coefficient (ADC) maps, and radiomic features were extracted. A random forest ML algorithm was fit to the training cohort and tested in the IVC. Histopathological subtype of tumor samples was assessed by immunohistochemistry in 21 IVC patients. Individual radiomic feature importance was evaluated by assessment of tree node Gini impurity decrease and recursive feature elimination. Fisher’s exact test, 95% confidence intervals (CI), and receiver operating characteristic area under the curve (ROC-AUC) were used. Results The ML algorithm achieved 87% sensitivity (95% IC 67.3–92.7), 80% specificity (95% CI 74.0–86.7), and ROC-AUC 90% for the prediction of above- versus below-median OS in the IVC. Heterogeneity-related features were highly ranked by the model. Of the 21 patients with determined histopathological subtype, 8/9 patients predicted to experience below-median OS exhibited the quasi-mesenchymal subtype, whilst 11/12 patients predicted to experience above-median OS exhibited a non-quasi-mesenchymal subtype (p < 0.001). Conclusion ML application to ADC radiomics allowed OS prediction with a high diagnostic accuracy in an IVC. The high overlap of clinically relevant histopathological subtypes with model predictions underlines the potential of quantitative imaging in PDAC pre-operative subtyping and prognosis.

scholarly journals LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-Weighted MR Images

2021 ◽  
pp. 731-741
Author(s):  
Yanglan Ou ◽  
Ye Yuan ◽  
Xiaolei Huang ◽  
Kelvin Wong ◽  
John Volpi ◽  
...  
Keyword(s):  
Lesion Segmentation ◽  
Mr Images ◽  
Diffusion Weighted ◽  
Stroke Lesion

Internal comparison standard for abdominal diffusion-weighted imaging

2016 ◽  
Vol 58 (9) ◽  
pp. 1029-1036 ◽  
Author(s):  
Zafer Koc ◽  
Gurcan Erbay ◽  
Elif Karadeli
Keyword(s):  
Diffusion Weighted Imaging ◽  
Area Under The Curve ◽  
Body Parts ◽  
Reference Standard ◽  
Comparison Standard ◽  
Diffusion Weighted ◽  
Abdominal Disease ◽  
Comparison Standards ◽  
Abdominal Lesions ◽  
Internal Comparison

Background Standards for abdominal diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) measurements, and analysis are required for reproducibility. Purpose To identify optimal internal comparison standards for DWI to normalize the measured ADC for increased accuracy of differentiating malignant and benign abdominal lesions. Material and Methods We retrospectively studied 97 lesions (89 patients; age, 57 ± 13 years) with histopathologically confirmed abdominal disease. Seven normal body parts/contents (normal parenchyma, spleen, kidney, gallbladder bile, paraspinal muscle, spinal cord, and cerebrospinal fluid [CSF]) were assessed as internal references for possible use as comparison standards. Three observers performed ADC measurements. Statistical analyses included interclass correlation coefficients (ICCs), Mann–Whitney and Kruskal–Wallis tests, and coefficient of variation (CV). ROC analyses were performed to assess diagnostic accuracy of lesion ADC and normalized ADC for differentiating lesions. Pathology results were the reference standard. Results Mean and normalized ADCs were significantly lower for malignant lesions than for benign lesions ( P < 0.001). ICC was excellent for all internal references. Gallbladder had the lowest CV. Receiver operating characteristic (ROC) analyses showed that normalized ADCs obtained using normal parenchyma were better than lesion ADCs for differentiating malignant and benign abdominal lesions (area under the curve [AUC], 0.808 and 0.756, respectively). The normalized ADCs obtained using CSF shows higher accuracy than lesion ADCs (0.80 and 0.76, respectively) for differentiating between malignant and benign abdominal lesions. Conclusion The normal parenchyma from a lesion-detected organ can be used as an internal comparison standard for DWI. CSF can be used as a generalizable in plane reference standard.

scholarly journals Computer-Aided Segmentation and Machine Learning of Integrated Clinical and Diffusion-Weighted Imaging Parameters for Predicting Lymph Node Metastasis in Endometrial Cancer

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1406
Author(s):  
Lan-Yan Yang ◽  
Tiing Yee Siow ◽  
Yu-Chun Lin ◽  
Ren-Chin Wu ◽  
Hsin-Ying Lu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Endometrial Cancer ◽  
Lymph Node ◽  
Decision Tree ◽  
Diffusion Weighted Imaging ◽  
Short Axis ◽  
Adc Value ◽  
Diffusion Weighted ◽  
Computer Aided ◽  
And Diffusion

Precise risk stratification in lymphadenectomy is important for patients with endometrial cancer (EC), to balance the therapeutic benefit against the operation-related morbidity and mortality. We aimed to investigate added values of computer-aided segmentation and machine learning based on clinical parameters and diffusion-weighted imaging radiomics for predicting lymph node (LN) metastasis in EC. This prospective observational study included 236 women with EC (mean age ± standard deviation, 51.2 ± 11.6 years) who underwent magnetic resonance (MR) imaging before surgery during July 2010–July 2018, randomly split into training (n = 165) and test sets (n = 71). A decision-tree model was constructed based on mean apparent diffusion coefficient (ADC) value of the tumor (cutoff, 1.1 × 10−3 mm2/s), skewness of the relative ADC value (cutoff, 1.2), short-axis diameter of LN (cutoff, 1.7 mm) and skewness ADC value of the LN (cutoff, 7.2 × 10−2), as well as tumor grade (1 vs. 2 and 3), and clinical tumor size (cutoff, 20 mm). The sensitivity and specificity of the model were 94% and 80% for the training set and 86%, 78% for the independent testing set, respectively. The areas under the receiver operating characteristics curve (AUCs) of the decision-tree was 0.85—significantly higher than the mean ADC model (AUC = 0.54) and LN short-axis diameter criteria (AUC = 0.62) (both p < 0.0001). We concluded that a combination of clinical and MR radiomics generates a prediction model for LN metastasis in EC, with diagnostic performance surpassing the conventional ADC and size criteria.

MRT des Prostatakarzinoms: Diffusion Weighted Imaging im Vergleich mit der Histologie

2009 ◽  
Vol 181 (S 01) ◽  
Author(s):  
J Yamamura ◽  
G Salomon ◽  
J Graessner ◽  
A Hohenstein ◽  
M Graefen ◽  
...  
Keyword(s):  
Diffusion Weighted Imaging ◽  
Diffusion Weighted

Diffusion-weighted imaging in pancreatic tumours

2011 ◽  
Vol 49 (05) ◽  
Author(s):  
T Puskás
Keyword(s):  
Diffusion Weighted Imaging ◽  
Pancreatic Tumours ◽  
Diffusion Weighted
Sign in / Sign up

Export Citation Format

Share Document