scholarly journals Deep Learning With Data Enhancement for the Differentiation of Solitary and Multiple Cerebral Glioblastoma, Lymphoma, and Tumefactive Demyelinating Lesion

2021 ◽  
Vol 11 ◽  
Author(s):  
Yu Zhang ◽  
Kewei Liang ◽  
Jiaqi He ◽  
He Ma ◽  
Hongyan Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Area Under The Curve ◽  
Discrimination Performance ◽  
Central Nervous System Lymphoma ◽  
3D Segmentation ◽  
Accurate Identification ◽  
Tumefactive Demyelinating Lesion ◽  
Sensitivity Specificity ◽  
Better Than

ObjectivesTo explore the MRI-based differential diagnosis of deep learning with data enhancement for cerebral glioblastoma (GBM), primary central nervous system lymphoma (PCNSL), and tumefactive demyelinating lesion (TDL).Materials and MethodsThis retrospective study analyzed the MRI data of 261 patients with pathologically diagnosed solitary and multiple cerebral GBM (n = 97), PCNSL (n = 92), and TDL (n = 72). The 3D segmentation model was trained to capture the lesion. Different enhancement data were generated by changing the pixel ratio of the lesion and non-lesion areas. The 3D classification network was trained by using the enhancement data. The accuracy, sensitivity, specificity, and area under the curve (AUC) were used to assess the value of different enhancement data on the discrimination performance. These results were then compared with the neuroradiologists’ diagnoses.ResultsThe diagnostic performance fluctuated with the ratio of lesion to non-lesion area changed. The diagnostic performance was best when the ratio was 1.5. The AUCs of GBM, PCNSL, and TDL were 1.00 (95% confidence interval [CI]: 1.000–1.000), 0.96 (95% CI: 0.923–1.000), and 0.954 (95% CI: 0.904–1.000), respectively.ConclusionsDeep learning with data enhancement is useful for the accurate identification of GBM, PCNSL, and TDL, and its diagnostic performance is better than that of the neuroradiologists.

Glioblastoma and primary central nervous system lymphoma: differentiation using MRI derived first-order texture analysis – a machine learning study

2021 ◽  
pp. 197140092199897
Author(s):  
Sarv Priya ◽  
Caitlin Ward ◽  
Thomas Locke ◽  
Neetu Soni ◽  
Ravishankar Pillenahalli Maheshwarappa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Central Nervous System ◽  
Nervous System ◽  
Diagnostic Performance ◽  
Model Performance ◽  
Area Under The Curve ◽  
Central Nervous System Lymphoma ◽  
First Order ◽  
Single Slice ◽  
Contrast Enhanced

Objectives To evaluate the diagnostic performance of multiple machine learning classifier models derived from first-order histogram texture parameters extracted from T1-weighted contrast-enhanced images in differentiating glioblastoma and primary central nervous system lymphoma. Methods Retrospective study with 97 glioblastoma and 46 primary central nervous system lymphoma patients. Thirty-six different combinations of classifier models and feature selection techniques were evaluated. Five-fold nested cross-validation was performed. Model performance was assessed for whole tumour and largest single slice using receiver operating characteristic curve. Results The cross-validated model performance was relatively similar for the top performing models for both whole tumour and largest single slice (area under the curve 0.909–0.924). However, there was a considerable difference between the worst performing model (logistic regression with full feature set, area under the curve 0.737) and the highest performing model for whole tumour (least absolute shrinkage and selection operator model with correlation filter, area under the curve 0.924). For single slice, the multilayer perceptron model with correlation filter had the highest performance (area under the curve 0.914). No significant difference was seen between the diagnostic performance of the top performing model for both whole tumour and largest single slice. Conclusions T1 contrast-enhanced derived first-order texture analysis can differentiate between glioblastoma and primary central nervous system lymphoma with good diagnostic performance. The machine learning performance can vary significantly depending on the model and feature selection methods. Largest single slice and whole tumour analysis show comparable diagnostic performance.

Deep-learning for predicting C-shaped canals in mandibular second molars on panoramic radiographs

2021 ◽  
pp. 20200513
Author(s):  
Su-Jin Jeon ◽  
Jong-Pil Yun ◽  
Han-Gyeol Yeom ◽  
Woo-Sang Shin ◽  
Jong-Hyun Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cone Beam Ct ◽  
Area Under The Curve ◽  
Roc Curves ◽  
Learning System ◽  
Operating Characteristics ◽  
Panoramic Radiographs ◽  
Test Sets ◽  
Sensitivity Specificity ◽  
Deep Learning Model

Objective: The aim of this study was to evaluate the use of a convolutional neural network (CNN) system for predicting C-shaped canals in mandibular second molars on panoramic radiographs. Methods: Panoramic and cone beam CT (CBCT) images obtained from June 2018 to May 2020 were screened and 1020 patients were selected. Our dataset of 2040 sound mandibular second molars comprised 887 C-shaped canals and 1153 non-C-shaped canals. To confirm the presence of a C-shaped canal, CBCT images were analyzed by a radiologist and set as the gold standard. A CNN-based deep-learning model for predicting C-shaped canals was built using Xception. The training and test sets were set to 80 to 20%, respectively. Diagnostic performance was evaluated using accuracy, sensitivity, specificity, and precision. Receiver-operating characteristics (ROC) curves were drawn, and the area under the curve (AUC) values were calculated. Further, gradient-weighted class activation maps (Grad-CAM) were generated to localize the anatomy that contributed to the predictions. Results: The accuracy, sensitivity, specificity, and precision of the CNN model were 95.1, 92.7, 97.0, and 95.9%, respectively. Grad-CAM analysis showed that the CNN model mainly identified root canal shapes converging into the apex to predict the C-shaped canals, while the root furcation was predominantly used for predicting the non-C-shaped canals. Conclusions: The deep-learning system had significant accuracy in predicting C-shaped canals of mandibular second molars on panoramic radiographs.

scholarly journals Optimization of Classification Strategies of Acetowhite Temporal Patterns towards Improving Diagnostic Performance of Colposcopy

2017 ◽  
Vol 2017 ◽  
pp. 1-10
Author(s):  
Karina Gutiérrez-Fragoso ◽  
Héctor Gabriel Acosta-Mesa ◽  
Nicandro Cruz-Ramírez ◽  
Rodolfo Hernández-Jiménez
Keyword(s):  
Cervical Cancer ◽  
Diagnostic Performance ◽  
Precancerous Lesions ◽  
Temporal Patterns ◽  
Nearest Neighbors ◽  
High Grade ◽  
Classification Methods ◽  
Computing Systems ◽  
Sensitivity Specificity ◽  
Better Than

Efforts have been being made to improve the diagnostic performance of colposcopy, trying to help better diagnose cervical cancer, particularly in developing countries. However, improvements in a number of areas are still necessary, such as the time it takes to process the full digital image of the cervix, the performance of the computing systems used to identify different kinds of tissues, and biopsy sampling. In this paper, we explore three different, well-known automatic classification methods (k-Nearest Neighbors, Naïve Bayes, and C4.5), in addition to different data models that take full advantage of this information and improve the diagnostic performance of colposcopy based on acetowhite temporal patterns. Based on the ROC and PRC area scores, thek-Nearest Neighbors and discrete PLA representation performed better than other methods. The values of sensitivity, specificity, and accuracy reached using this method were 60% (95% CI 50–70), 79% (95% CI 71–86), and 70% (95% CI 60–80), respectively. The acetowhitening phenomenon is not exclusive to high-grade lesions, and we have found acetowhite temporal patterns of epithelial changes that are not precancerous lesions but that are similar to positive ones. These findings need to be considered when developing more robust computing systems in the future.

scholarly journals Validity and diagnostic performance of Fluorescence Optical Imaging measuring synovitis in hand osteoarthritis. Baseline results from the Nor-Hand cohort.

2020 ◽  
Author(s):  
Øystein Maugesten ◽  
Alexander Mathiessen ◽  
Hilde Berner Hammer ◽  
Sigrid Hestetun ◽  
Tore Kristian Kvien ◽  
...  
Keyword(s):  
Optical Imaging ◽  
Diagnostic Performance ◽  
Power Doppler ◽  
Area Under The Curve ◽  
Correlation Coefficients ◽  
Hand Osteoarthritis ◽  
Dominant Hand ◽  
Fluorescence Optical Imaging ◽  
Sum Scores ◽  
Sensitivity Specificity

Abstract Objective: Fluorescence Optical Imaging (FOI) demonstrates enhanced microcirculation in finger joints as a sign of inflammation. We wanted to assess the validity and diagnostic performance of FOI measuring synovitis in persons with hand OA, comparing it with magnetic resonance imaging (MRI)- and ultrasound-detected synovitis. Methods: 221 participants with hand OA underwent FOI and ultrasound (grey scale synovitis and power-Doppler activity) of the bilateral hands and contrast-enhanced MRI examination of the dominant hand. Fifteen joints in each hand were scored on semi-quantitative scales (grade 0-3) for all modalities. Four FOI images were evaluated: one composite image (Prima Vista Mode; PVM) and three images representing phases of fluorescent dye distribution. Spearman’s correlation coefficients were calculated between sum scores of FOI, MRI and ultrasound. Sensitivity, specificity and area under the curve (AUC) was calculated for FOI using MRI or ultrasound as reference. Results: FOI did not demonstrate enhancement in the thumb base, and the joint was excluded from further analyses. FOI sum scores showed poor to fair correlations with MRI (rho 0.01-0.24) and GS synovitis sum scores (rho 0.12-0.25). None of the FOI images demonstrated both good sensitivity and specificity, and the AUC ranged from 0.50-0.61 and 0.51-0.63 with MRI and GS synovitis as reference, respectively. FOI demonstrated similar diagnostic performance with PD activity and GS synovitis as reference. Conclusion: FOI enhancement correlated poorly with synovitis assessed by more established imaging modalities, questioning the value of FOI for the evaluation of synovitis in hand OA.

scholarly journals A Human-Algorithm Integration System for Hip Fracture Detection on Plain Radiography: System Development and Validation Study (Preprint)

2020 ◽  
Author(s):  
Chi-Tung Cheng ◽  
Chih-Chi Chen ◽  
Fu-Jen Cheng ◽  
Huan-Wu Chen ◽  
Yi-Siang Su ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hip Fracture ◽  
Emergency Departments ◽  
Diagnostic Performance ◽  
Learning Algorithm ◽  
Fracture Detection ◽  
Testing Dataset ◽  
Fracture Diagnosis ◽  
Sensitivity Specificity ◽  
Independent Testing Dataset

BACKGROUND Hip fracture is the most common type of fracture in elderly individuals. Numerous deep learning (DL) algorithms for plain pelvic radiographs (PXRs) have been applied to improve the accuracy of hip fracture diagnosis. However, their efficacy is still undetermined. OBJECTIVE The objective of this study is to develop and validate a human-algorithm integration (HAI) system to improve the accuracy of hip fracture diagnosis in a real clinical environment. METHODS The HAI system with hip fracture detection ability was developed using a deep learning algorithm trained on trauma registry data and 3605 PXRs from August 2008 to December 2016. To compare their diagnostic performance before and after HAI system assistance using an independent testing dataset, 34 physicians were recruited. We analyzed the physicians’ accuracy, sensitivity, specificity, and agreement with the algorithm; we also performed subgroup analyses according to physician specialty and experience. Furthermore, we applied the HAI system in the emergency departments of different hospitals to validate its value in the real world. RESULTS With the support of the algorithm, which achieved 91% accuracy, the diagnostic performance of physicians was significantly improved in the independent testing dataset, as was revealed by the sensitivity (physician alone, median 95%; HAI, median 99%; <i>P</i>&lt;.001), specificity (physician alone, median 90%; HAI, median 95%; <i>P</i>&lt;.001), accuracy (physician alone, median 90%; HAI, median 96%; <i>P</i>&lt;.001), and human-algorithm agreement [physician alone κ, median 0.69 (IQR 0.63-0.74); HAI κ, median 0.80 (IQR 0.76-0.82); <i>P</i>&lt;.001. With the help of the HAI system, the primary physicians showed significant improvement in their diagnostic performance to levels comparable to those of consulting physicians, and both the experienced and less-experienced physicians benefited from the HAI system. After the HAI system had been applied in 3 departments for 5 months, 587 images were examined. The sensitivity, specificity, and accuracy of the HAI system for detecting hip fractures were 97%, 95.7%, and 96.08%, respectively. CONCLUSIONS HAI currently impacts health care, and integrating this technology into emergency departments is feasible. The developed HAI system can enhance physicians’ hip fracture diagnostic performance.

scholarly journals Deep Learning in Prostate Cancer Diagnosis Using Multiparametric Magnetic Resonance Imaging With Whole-Mount Histopathology Referenced Delineations

2022 ◽  
Vol 8 ◽  
Author(s):  
Danyan Li ◽  
Xiaowei Han ◽  
Jie Gao ◽  
Qing Zhang ◽  
Haibo Yang ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Prostate Cancer ◽  
Deep Learning ◽  
Diagnostic Performance ◽  
Resonance Imaging ◽  
Test Dataset ◽  
Multiparametric Magnetic Resonance Imaging ◽  
Whole Mount ◽  
Precision And Accuracy ◽  
Sensitivity Specificity

Background: Multiparametric magnetic resonance imaging (mpMRI) plays an important role in the diagnosis of prostate cancer (PCa) in the current clinical setting. However, the performance of mpMRI usually varies based on the experience of the radiologists at different levels; thus, the demand for MRI interpretation warrants further analysis. In this study, we developed a deep learning (DL) model to improve PCa diagnostic ability using mpMRI and whole-mount histopathology data.Methods: A total of 739 patients, including 466 with PCa and 273 without PCa, were enrolled from January 2017 to December 2019. The mpMRI (T2 weighted imaging, diffusion weighted imaging, and apparent diffusion coefficient sequences) data were randomly divided into training (n = 659) and validation datasets (n = 80). According to the whole-mount histopathology, a DL model, including independent segmentation and classification networks, was developed to extract the gland and PCa area for PCa diagnosis. The area under the curve (AUC) were used to evaluate the performance of the prostate classification networks. The proposed DL model was subsequently used in clinical practice (independent test dataset; n = 200), and the PCa detective/diagnostic performance between the DL model and different level radiologists was evaluated based on the sensitivity, specificity, precision, and accuracy.Results: The AUC of the prostate classification network was 0.871 in the validation dataset, and it reached 0.797 using the DL model in the test dataset. Furthermore, the sensitivity, specificity, precision, and accuracy of the DL model for diagnosing PCa in the test dataset were 0.710, 0.690, 0.696, and 0.700, respectively. For the junior radiologist without and with DL model assistance, these values were 0.590, 0.700, 0.663, and 0.645 versus 0.790, 0.720, 0.738, and 0.755, respectively. For the senior radiologist, the values were 0.690, 0.770, 0.750, and 0.730 vs. 0.810, 0.840, 0.835, and 0.825, respectively. The diagnosis made with DL model assistance for radiologists were significantly higher than those without assistance (P &lt; 0.05).Conclusion: The diagnostic performance of DL model is higher than that of junior radiologists and can improve PCa diagnostic accuracy in both junior and senior radiologists.

scholarly journals Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Gang Yu ◽  
Kai Sun ◽  
Chao Xu ◽  
Xing-Hua Shi ◽  
Chong Wu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Colorectal Cancer ◽  
Deep Learning ◽  
Supervised Learning ◽  
Area Under The Curve ◽  
Patient Level ◽  
Significant Difference ◽  
The Mean ◽  
Whole Slide Images ◽  
Better Than

AbstractMachine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

scholarly journals Parasite-derived circulating microRNAs as biomarkers for the detection of human Schistosoma japonicum infection

Parasitology ◽  
2019 ◽  
Vol 147 (8) ◽  
pp. 889-896 ◽  
Author(s):  
Yi Mu ◽  
Pengfei Cai ◽  
Remigio M. Olveda ◽  
Allen G. Ross ◽  
David U. Olveda ◽  
...  
Keyword(s):  
Schistosoma Japonicum ◽  
Diagnostic Performance ◽  
Area Under The Curve ◽  
Infection Intensity ◽  
The Philippines ◽  
Pcr Analysis ◽  
Rt Pcr ◽  
Serum Samples ◽  
Sensitivity Specificity ◽  
Pcr Targeting

AbstractNovel tools for early diagnosis and monitoring of schistosomiasis are urgently needed. This study aimed to validate parasite-derived miRNAs as potential novel biomarkers for the detection of human Schistosoma japonicum infection. A total of 21 miRNAs were initially validated by real-time-polymerase chain reaction (RT-PCR) using serum samples of S. japonicum-infected BALB/c mice. Of these, 6 miRNAs were further validated with a human cohort of individuals from a schistosomiasis-endemic area of the Philippines. RT-PCR analysis showed that two parasite-derived miRNAs (sja-miR-2b-5p and sja-miR-2c-5p) could detect infected individuals with low infection intensity with moderate sensitivity/specificity values of 66%/68% and 55%/80%, respectively. Analysis of the combined data for the two parasite miRNAs revealed a specificity of 77.4% and a sensitivity of 60.0% with an area under the curve (AUC) value of 0.6906 (P = 0.0069); however, a duplex RT-PCR targeting both sja-miR-2b-5p and sja-miR-2c-5p did not result in an increased diagnostic performance compared with the singleplex assays. Furthermore, the serum level of sja-miR-2c-5p correlated significantly with faecal egg counts, whereas the other five miRNAs did not. Targeting S. japonicum-derived miRNAs in serum resulted in a moderate diagnostic performance when applied to a low schistosome infection intensity setting.

Diagnostic Performance of Risk of Ovarian Malignancy Algorithm Against CA125 and HE4 in Connection With Ovarian Cancer: A Meta-analysis

2016 ◽  
Vol 26 (9) ◽  
pp. 1586-1593 ◽  
Author(s):  
Farshid Dayyani ◽  
Steffen Uhlig ◽  
Bertrand Colson ◽  
Kirsten Simon ◽  
Vinzent Rolny ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Confidence Interval ◽  
Late Stage ◽  
Diagnostic Performance ◽  
Clinical Decision Making ◽  
Early Stage ◽  
Area Under The Curve ◽  
Ovarian Malignancy ◽  
Eligibility Criteria ◽  
Sensitivity Specificity

ObjectivesThe aim of this study was to determine whether the Risk of Ovarian Malignancy Algorithm (ROMA) is more accurate than the human epididymis 4 (HE4) or carbohydrate antigen 125 (CA125) biomarkers with respect to the differential diagnosis of women with a pelvic mass. The secondary objective is to assess the performance of ROMA in early-stage ovarian cancer (OC) and late-stage OC, as well as premenopausal and postmenopausal patient populations.Methods/MaterialsThe PubMed and Google Scholar databases were searched for relevant clinical studies. Eligibility criteria included comparison of ROMA with both HE4 and CA125 levels in OC (unspecified, epithelial, and borderline ovarian tumors), use of only validated ROMA assays, presentation of area under the curve and sensitivity/specificity data, and results from early-stage OC, late-stage OC and premenopausal and postmenopausal women. Area under the curve (AUC), sensitivity/specificity, and the diagnostic odds ratio (DOR) results were summarized.ResultsFive studies were selected comprising 1975 patients (premenopausal, n = 1033; postmenopausal, n = 925; benign, n = 1387; early stage, n = 192; and late stage, n = 313). On the basis of the AUC (95% confidence interval) data for all patients, ROMA (0.921 [0.855–0.960]) had a numerically greater diagnostic performance than CA125 (0.883 [0.771–0.950]) and HE4 (0.899 [0.835–0.943]). This was also observed in each of the subgroup populations, in particular, the postmenopausal patients and patients with early OC. The sensitivity and specificity (95% confidence interval) results showed ROMA (sensitivity, 0.873 [0.752–0.940]; specificity, 0.855 [0.719–0.932]) to be numerically superior to CA125 (sensitivity, 0.796 [0.663–0.885]; specificity, 0.825 [0.662–0.919]) and HE4 (sensitivity, 0.817 [0.683–0.902]; specificity, 0.851 [0.716–0.928]) in all patients and for the early- and late-stage OC subgroups. Finally, the ROMA log DOR results were better than HE4 and CA125 log DOR results especially for the early-stage patient group.ConclusionsThe results presented support the use of ROMA to improve clinical decision making, most notably in patients with early OC.

scholarly journals Review on Diagnosis of COVID-19 from Chest CT Images Using Artificial Intelligence

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Ilker Ozsahin ◽  
Boran Sekeroglu ◽  
Musa Sani Musa ◽  
Mubarak Taiwo Mustapha ◽  
Dilber Uzun Ozsahin
Keyword(s):  
Artificial Intelligence ◽  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Chest Radiography ◽  
Area Under The Curve ◽  
Chest Ct ◽  
Chest Computed Tomography ◽  
Classification Tasks ◽  
Sensitivity Specificity

The COVID-19 diagnostic approach is mainly divided into two broad categories, a laboratory-based and chest radiography approach. The last few months have witnessed a rapid increase in the number of studies use artificial intelligence (AI) techniques to diagnose COVID-19 with chest computed tomography (CT). In this study, we review the diagnosis of COVID-19 by using chest CT toward AI. We searched ArXiv, MedRxiv, and Google Scholar using the terms “deep learning”, “neural networks”, “COVID-19”, and “chest CT”. At the time of writing (August 24, 2020), there have been nearly 100 studies and 30 studies among them were selected for this review. We categorized the studies based on the classification tasks: COVID-19/normal, COVID-19/non-COVID-19, COVID-19/non-COVID-19 pneumonia, and severity. The sensitivity, specificity, precision, accuracy, area under the curve, and F1 score results were reported as high as 100%, 100%, 99.62, 99.87%, 100%, and 99.5%, respectively. However, the presented results should be carefully compared due to the different degrees of difficulty of different classification tasks.

Sign in / Sign up

Export Citation Format

Share Document