scholarly journals Pseudoprogression in Patients with Glioblastoma: Assessment by Using Volume-weighted Voxel-based Multiparametric Clustering of MR Imaging Data in an Independent Test Set

Radiology ◽  
2015 ◽  
Vol 275 (3) ◽  
pp. 792-802 ◽  
Author(s):  
Ji Eun Park ◽  
Ho Sung Kim ◽  
Myeong Ju Goh ◽  
Sang Joon Kim ◽  
Jeong Hoon Kim
2020 ◽  
Author(s):  
Md. Kamrul Hasan ◽  
Md. Ashraful Alam ◽  
Lavsen Dahal ◽  
Md. Toufick E Elahi ◽  
Shidhartho Roy ◽  
...  

ABSTRACTA large number of studies in the past months have proposed deep learning-based Artificial Intelligence (AI) tools for automated detection of COVID-19 using publicly available datasets of Chest X-rays (CXRs) or CT scans for training and evaluation. Most of these studies report high accuracy when classifying COVID-19 patients from normal or other commonly occurring pneumonia cases. However, these results are often obtained on cross-validation studies without an independent test set coming from a separate dataset and have biases such as the two classes to be predicted come from two completely different datasets. In this work, we investigate potential overfitting and biases in such studies by designing different experimental setups within the available public data constraints and highlight the challenges and limitations of developing deep learning models with such datasets. We propose a deep learning architecture for COVID-19 classification that combines two very popular classification networks, ResNet and Xception, and use it to carry out the experiments to investigate challenges and limitations. The results show that the deep learning models can overestimate their performance due to biases in the experimental design and overfitting to the training dataset. We compare the proposed architecture to state-of-the-art methods utilizing an independent test set for evaluation, where some of the identified bias and overfitting issues are reduced. Although our proposed deep learning architecture gives the best performance with our best possible setup, we highlight the challenges in comparing and interpreting various deep learning algorithms’ results. While the deep learning-based methods using chest imaging data show promise in being helpful for clinical management and triage of COVID-19 patients, our experiments suggest that a larger, more comprehensive database with less bias is necessary for developing tools applicable in real clinical settings.


1990 ◽  
Vol 29 (03) ◽  
pp. 167-181 ◽  
Author(s):  
G. Hripcsak

AbstractA connectionist model for decision support was constructed out of several back-propagation modules. Manifestations serve as input to the model; they may be real-valued, and the confidence in their measurement may be specified. The model produces as its output the posterior probability of disease. The model was trained on 1,000 cases taken from a simulated underlying population with three conditionally independent manifestations. The first manifestation had a linear relationship between value and posterior probability of disease, the second had a stepped relationship, and the third was normally distributed. An independent test set of 30,000 cases showed that the model was better able to estimate the posterior probability of disease (the standard deviation of residuals was 0.046, with a 95% confidence interval of 0.046-0.047) than a model constructed using logistic regression (with a standard deviation of residuals of 0.062, with a 95% confidence interval of 0.062-0.063). The model fitted the normal and stepped manifestations better than the linear one. It accommodated intermediate levels of confidence well.


1981 ◽  
Vol 5 (2) ◽  
pp. 92-96 ◽  
Author(s):  
James L. Smith ◽  
Roy A. Mead

Abstract Two aerial photo volume prediction models, Avery's Composite Aerial Volume Table, and Mead's Quadratic Model, were compared using graphs and a small independent test set. The graphs indicated that Mead's model predicted higher merchantable volumes for pine stands in central Mississippi than did Avery's model. Both models tended to underpredict ground merchantable volume. However, only Avery's model underpredicted in a statistically significant manner. Even though the possibility of negative volume predictions exists when using Mead's Quadratic Model, it was deemed the superior model of the two investigated.


2011 ◽  
Vol 32 (11) ◽  
pp. 2098-2102 ◽  
Author(s):  
K. Kac̆ar ◽  
M.A. Rocca ◽  
M. Copetti ◽  
S. Sala ◽  
Š. Mesaroš ◽  
...  

2011 ◽  
Vol 114 (2) ◽  
pp. 329-335 ◽  
Author(s):  
Paula Eboli ◽  
Bob Shafa ◽  
Marc Mayberg

Object The authors assessed the feasibility, anatomical accuracy, and cost effectiveness of frameless electromagnetic (EM) neuronavigation in conjunction with portable intraoperative CT (iCT) registration for transsphenoidal adenomectomy (TSA). Methods A prospective database was established for data obtained in 208 consecutive patients who underwent TSA in which the iCT/EM navigation technique was used. Data were compared with those acquired in a retrospective cohort of 65 consecutive patients in whom fluoroscope-assisted TSA had been performed by the same surgeon. All patients in both groups underwent transnasal removal of pituitary adenomas or neuroepithelial cysts, using identical surgical techniques with an operating microscope. In the iCT/EM technique–treated cases, a portable iCT scan was obtained immediately prior to surgery for registration to the EM navigation system, which did not require rigid head fixation. Preexisting (nonnavigation protocol) MR imaging studies were fused with the iCT scans to enable 3D navigation based on MR imaging data. The accuracy of the navigation system was determined in the first 50 iCT/EM cases by visual concordance of the navigation probe location to 5 preselected bony landmarks. For all patients in both cohorts, total operating room time, incision-to-closure time, and relative costs of imaging and surgical procedures were determined from hospital records. Results In every case, iCT registration was successful and preoperative MR images were fused to iCT scans without affecting navigation accuracy. There was 100% concordance between probe tip location and predetermined bony loci in the first 50 cases involving the iCT/EM technique. Total operating room time was significantly less in the iCT/EM cases (mean 108.9 ± 24.3 minutes [208 patients]) compared with the fluoroscopy group (mean 121.1 ± 30.7 minutes [65 patients]; p < 0.001). Similarly, incision-to-closure time was significantly less for the iCT/EM cases (mean 61.3 ± 18.2 minutes) than for the fluoroscopy cases (mean 71.75 ± 19.0 minutes; p < 0.001). Relative overall costs for iCT/EM technique and intraoperative C-arm fluoroscopy were comparable; increased costs for navigation equipment were offset by savings in operating room costs for shorter procedures. Conclusions The use of iCT/MR imaging–guided neuronavigation for transsphenoidal surgery is a time-effective, cost-efficient, safe, and technically beneficial technique.


Radiology ◽  
1996 ◽  
Vol 199 (1) ◽  
pp. 37-40 ◽  
Author(s):  
C P Davis ◽  
M E Ladd ◽  
B J Romanowski ◽  
S Wildermuth ◽  
J F Knoplioch ◽  
...  

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 8536-8536
Author(s):  
Gouji Toyokawa ◽  
Fahdi Kanavati ◽  
Seiya Momosaki ◽  
Kengo Tateishi ◽  
Hiroaki Takeoka ◽  
...  

8536 Background: Lung cancer is the leading cause of cancer-related death in many countries, and its prognosis remains unsatisfactory. Since treatment approaches differ substantially based on the subtype, such as adenocarcinoma (ADC), squamous cell carcinoma (SCC) and small cell lung cancer (SCLC), an accurate histopathological diagnosis is of great importance. However, if the specimen is solely composed of poorly differentiated cancer cells, distinguishing between histological subtypes can be difficult. The present study developed a deep learning model to classify lung cancer subtypes from whole slide images (WSIs) of transbronchial lung biopsy (TBLB) specimens, in particular with the aim of using this model to evaluate a challenging test set of indeterminate cases. Methods: Our deep learning model consisted of two separately trained components: a convolutional neural network tile classifier and a recurrent neural network tile aggregator for the WSI diagnosis. We used a training set consisting of 638 WSIs of TBLB specimens to train a deep learning model to classify lung cancer subtypes (ADC, SCC and SCLC) and non-neoplastic lesions. The training set consisted of 593 WSIs for which the diagnosis had been determined by pathologists based on the visual inspection of Hematoxylin-Eosin (HE) slides and of 45 WSIs of indeterminate cases (64 ADCs and 19 SCCs). We then evaluated the models using five independent test sets. For each test set, we computed the receiver operator curve (ROC) area under the curve (AUC). Results: We applied the model to an indeterminate test set of WSIs obtained from TBLB specimens that pathologists had not been able to conclusively diagnose by examining the HE-stained specimens alone. Overall, the model achieved ROC AUCs of 0.993 (confidence interval [CI] 0.971-1.0) and 0.996 (0.981-1.0) for ADC and SCC, respectively. We further evaluated the model using five independent test sets consisting of both TBLB and surgically resected lung specimens (combined total of 2490 WSIs) and obtained highly promising results with ROC AUCs ranging from 0.94 to 0.99. Conclusions: In this study, we demonstrated that a deep learning model could be trained to predict lung cancer subtypes in indeterminate TBLB specimens. The extremely promising results obtained show that if deployed in clinical practice, a deep learning model that is capable of aiding pathologists in diagnosing indeterminate cases would be extremely beneficial as it would allow a diagnosis to be obtained sooner and reduce costs that would result from further investigations.


2021 ◽  
Author(s):  
Mudan zhang ◽  
Xuntao Yin ◽  
Wuchao Li ◽  
Yan Zha ◽  
Xianchun Zeng ◽  
...  

Abstract Background: Endocrine system plays an important role in infectious disease prognosis. Our goal is to assess the value of radiomics features extracted from adrenal gland and periadrenal fat CT images in predicting disease prognosis in patients with COVID-19. Methods: A total of 1,325 patients (765 moderate and 560 severe patients) from three centers were enrolled in the retrospective study. We proposed a 3D cascade V-Net to automatically segment adrenal glands in onset CT images. Periadrenal fat areas were obtained using inflation operations. Then, the radiomics features were automatically extracted. Five models were established to predict the disease prognosis in patients with COVID-19: a clinical model (CM), three radiomics models (adrenal gland model [AM], periadrenal fat model [PM], fusion of adrenal gland and periadrenal fat model [FM]), and a radiomics nomogram model (RN).Data from one center (1,183 patients) were utilized as training and validation sets. The remaining two (36 and 106 patients) were used as 2 independent test sets to evaluate the models’ performance. Results: The auto-segmentation framework achieved an average dice of 0.79 in the test set. CM, AM, PM, FM, and RN obtained AUCs of 0.716, 0.755, 0.796, 0.828, and 0.825, respectively in the training set, and the mean AUCs of 0.754, 0.709, 0.672, 0.706 and 0.778 for 2 independent test sets. Decision curve analysis showed that if the threshold probability was more than 0.3, 0.5, and 0.1 in the validation set, the independent-test set 1 and the independent-test set 2 could gain more net benefits using RN than FM and CM, respectively. Conclusion: Radiomics features extracted from CT images of adrenal glands and periadrenal fat are related to disease prognosis in patients with COVID-19 and have great potential for predicting its severity.


Sign in / Sign up

Export Citation Format

Share Document