Improving positive predictive value in computer-aided diagnosis using mammographic mass and microcalcification confidence score fusion based on co-location information

Evaluation of the Quadri-Planes Method in Computer-Aided Diagnosis of Breast Lesions by Ultrasonography: Prospective Single-Center Study

JMIR Medical Informatics ◽

10.2196/18251 ◽

2020 ◽

Vol 8 (5) ◽

pp. e18251 ◽

Cited By ~ 3

Author(s):

Liang Yongping ◽

Zhang Juan ◽

Ping Zhou ◽

Zhao Yongfeng ◽

Wengang Liu ◽

...

Keyword(s):

Positive Predictive Value ◽

Predictive Value ◽

Characteristic Curve ◽

Computer Aided Diagnosis ◽

Breast Lesions ◽

Paired Data ◽

Optimal Method ◽

Experienced Reader ◽

Computer Aided ◽

Aided Diagnosis

Background Computer-aided diagnosis (CAD) is a tool that can help radiologists diagnose breast lesions by ultrasonography. Previous studies have demonstrated that CAD can help reduce the incidence of missed diagnoses by radiologists. However, the optimal method to apply CAD to breast lesions using diagnostic planes has not been assessed. Objective The aim of this study was to compare the performance of radiologists with different levels of experience when using CAD with the quadri-planes method to detect breast tumors. Methods From November 2018 to October 2019, we enrolled patients in the study who had a breast mass as their most prominent symptom. We assigned 2 ultrasound radiologists (with 1 and 5 years of experience, respectively) to read breast ultrasonography images without CAD and then to perform a second reading while applying CAD with the quadri-planes method. We then compared the diagnostic performance of the readers for the 2 readings (without and with CAD). The McNemar test for paired data was used for statistical analysis. Results A total of 331 patients were included in this study (mean age 43.88 years, range 17-70, SD 12.10), including 512 lesions (mean diameter 1.85 centimeters, SD 1.19; range 0.26-9.5); 200/512 (39.1%) were malignant, and 312/512 (60.9%) were benign. For CAD, the area under the receiver operating characteristic curve (AUC) improved significantly from 0.76 (95% CI 0.71-0.79) with the cross-planes method to 0.84 (95% CI 0.80-0.88; P<.001) with the quadri-planes method. For the novice reader, the AUC significantly improved from 0.73 (95% CI 0.69-0.78) for the without-CAD mode to 0.83 (95% CI 0.80-0.87; P<.001) for the combined-CAD mode with the quadri-planes method. For the experienced reader, the AUC improved from 0.85 (95% CI 0.81-0.88) to 0.87 (95% CI 0.84-0.91; P=.15). The kappa indicating consistency between the experienced reader and the novice reader for the combined-CAD mode was 0.63. For the novice reader, the sensitivity significantly improved from 60.0% for the without-CAD mode to 79.0% for the combined-CAD mode (P=.004). The specificity, negative predictive value, positive predictive value, and accuracy improved from 84.9% to 87.8% (P=.53), 76.8% to 86.7% (P=.07), 71.9% to 80.6% (P=.13), and 75.2% to 84.4% (P=.12), respectively. For the experienced reader, the sensitivity improved significantly from 76.0% for the without-CAD mode to 87.0% for the combined-CAD mode (P=.045). The NPV and accuracy moderately improved from 85.8% and 86.3% to 91.0% (P=.27) and 87.0% (P=.84), respectively. The specificity and positive predictive value decreased from 87.4% to 81.3% (P=.25) and from 87.2% to 93.0% (P=.16), respectively. Conclusions S-Detect is a feasible diagnostic tool that can improve the sensitivity, accuracy, and AUC of the quadri-planes method for both novice and experienced readers while also improving the specificity for the novice reader. It demonstrates important application value in the clinical diagnosis of breast cancer. Trial Registration ChiCTR.org.cn 1800019649; http://www.chictr.org.cn/showproj.aspx?proj=33094

Download Full-text

Evaluation of the Quadri-Planes Method in Computer-Aided Diagnosis of Breast Lesions by Ultrasonography: Prospective Single-Center Study (Preprint)

10.2196/preprints.18251 ◽

2020 ◽

Author(s):

Liang Yongping ◽

Zhang Juan ◽

Ping Zhou ◽

Zhao Yongfeng ◽

Wengang Liu ◽

...

Keyword(s):

Positive Predictive Value ◽

Predictive Value ◽

Characteristic Curve ◽

Computer Aided Diagnosis ◽

Breast Lesions ◽

Paired Data ◽

Optimal Method ◽

Experienced Reader ◽

Computer Aided ◽

Aided Diagnosis

BACKGROUND Computer-aided diagnosis (CAD) is a tool that can help radiologists diagnose breast lesions by ultrasonography. Previous studies have demonstrated that CAD can help reduce the incidence of missed diagnoses by radiologists. However, the optimal method to apply CAD to breast lesions using diagnostic planes has not been assessed. OBJECTIVE The aim of this study was to compare the performance of radiologists with different levels of experience when using CAD with the quadri-planes method to detect breast tumors. METHODS From November 2018 to October 2019, we enrolled patients in the study who had a breast mass as their most prominent symptom. We assigned 2 ultrasound radiologists (with 1 and 5 years of experience, respectively) to read breast ultrasonography images without CAD and then to perform a second reading while applying CAD with the quadri-planes method. We then compared the diagnostic performance of the readers for the 2 readings (without and with CAD). The McNemar test for paired data was used for statistical analysis. RESULTS A total of 331 patients were included in this study (mean age 43.88 years, range 17-70, SD 12.10), including 512 lesions (mean diameter 1.85 centimeters, SD 1.19; range 0.26-9.5); 200/512 (39.1%) were malignant, and 312/512 (60.9%) were benign. For CAD, the area under the receiver operating characteristic curve (AUC) improved significantly from 0.76 (95% CI 0.71-0.79) with the cross-planes method to 0.84 (95% CI 0.80-0.88; P<.001) with the quadri-planes method. For the novice reader, the AUC significantly improved from 0.73 (95% CI 0.69-0.78) for the without-CAD mode to 0.83 (95% CI 0.80-0.87; P<.001) for the combined-CAD mode with the quadri-planes method. For the experienced reader, the AUC improved from 0.85 (95% CI 0.81-0.88) to 0.87 (95% CI 0.84-0.91; P=.15). The kappa indicating consistency between the experienced reader and the novice reader for the combined-CAD mode was 0.63. For the novice reader, the sensitivity significantly improved from 60.0% for the without-CAD mode to 79.0% for the combined-CAD mode (P=.004). The specificity, negative predictive value, positive predictive value, and accuracy improved from 84.9% to 87.8% (P=.53), 76.8% to 86.7% (P=.07), 71.9% to 80.6% (P=.13), and 75.2% to 84.4% (P=.12), respectively. For the experienced reader, the sensitivity improved significantly from 76.0% for the without-CAD mode to 87.0% for the combined-CAD mode (P=.045). The NPV and accuracy moderately improved from 85.8% and 86.3% to 91.0% (P=.27) and 87.0% (P=.84), respectively. The specificity and positive predictive value decreased from 87.4% to 81.3% (P=.25) and from 87.2% to 93.0% (P=.16), respectively. CONCLUSIONS S-Detect is a feasible diagnostic tool that can improve the sensitivity, accuracy, and AUC of the quadri-planes method for both novice and experienced readers while also improving the specificity for the novice reader. It demonstrates important application value in the clinical diagnosis of breast cancer. CLINICALTRIAL ChiCTR.org.cn 1800019649; http://www.chictr.org.cn/showproj.aspx?proj=33094

Download Full-text

A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms

BioMed Research International ◽

10.1155/2020/7695207 ◽

2020 ◽

Vol 2020 ◽

pp. 1-17 ◽

Cited By ~ 1

Author(s):

Said Boumaraf ◽

Xiabi Liu ◽

Chokri Ferkous ◽

Xiaohong Ma

Keyword(s):

Feature Selection ◽

Predictive Value ◽

Breast Imaging ◽

Feature Selection Method ◽

Computer Aided Diagnosis ◽

Screening Mammography ◽

Breast Masses ◽

Computer Aided ◽

Aided Diagnosis

Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extracted from the shape, margin, and density of each mass, together with the mass size and the patient’s age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database for screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.

Download Full-text

Development and Validation of a Deep Learning Algorithm to Automatic Detection of Pituitary Microadenoma From MRI

Frontiers in Medicine ◽

10.3389/fmed.2021.758690 ◽

2021 ◽

Vol 8 ◽

Author(s):

Qingling Li ◽

Yanhua Zhu ◽

Minglin Chen ◽

Ruomi Guo ◽

Qingyong Hu ◽

...

Keyword(s):

Deep Learning ◽

Diagnostic Accuracy ◽

Roc Curve ◽

Predictive Value ◽

Computer Aided Diagnosis ◽

Validation Dataset ◽

Cad System ◽

Pituitary Microadenoma ◽

Computer Aided ◽

Aided Diagnosis

Background: It is often difficult to diagnose pituitary microadenoma (PM) by MRI alone, due to its relatively small size, variable anatomical structure, complex clinical symptoms, and signs among individuals. We develop and validate a deep learning -based system to diagnose PM from MRI.Methods: A total of 11,935 infertility participants were initially recruited for this project. After applying the exclusion criteria, 1,520 participants (556 PM patients and 964 controls subjects) were included for further stratified into 3 non-overlapping cohorts. The data used for the training set were derived from a retrospective study, and in the validation dataset, prospective temporal and geographical validation set were adopted. A total of 780 participants were used for training, 195 participants for testing, and 545 participants were used to validate the diagnosis performance. The PM-computer-aided diagnosis (PM-CAD) system consists of two parts: pituitary region detection and PM diagnosis. The diagnosis performance of the PM-CAD system was measured using the receiver operating characteristics (ROC) curve and area under the ROC curve (AUC), calibration curve, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score.Results: Pituitary microadenoma-computer-aided diagnosis system showed 94.36% diagnostic accuracy and 98.13% AUC score in the testing dataset. We confirm the robustness and generalization of our PM-CAD system, the diagnostic accuracy in the internal dataset was 96.50% and in the external dataset was 92.26 and 92.36%, the AUC was 95.5, 94.7, and 93.7%, respectively. In human-computer competition, the diagnosis performance of our PM-CAD system was comparable to radiologists with >10 years of professional expertise (diagnosis accuracy of 94.0% vs. 95.0%, AUC of 95.6% vs. 95.0%). For the misdiagnosis cases from radiologists, our system showed a 100% accurate diagnosis. A browser-based software was designed to assist the PM diagnosis.Conclusions: This is the first report showing that the PM-CAD system is a viable tool for detecting PM. Our results suggest that the PM-CAD system is applicable to radiology departments, especially in primary health care institutions.

Download Full-text

Detection of Mesial Temporal Lobe Epilepsy in MRI Sequence T2 Flair MRI Image Using Computer Aided Diagnosis (CAD)

E3S Web of Conferences ◽

10.1051/e3sconf/202020215010 ◽

2020 ◽

Vol 202 ◽

pp. 15010

Author(s):

Redha Okta Silfina ◽

Hermina Sukmaningtyas ◽

Rini Indrati

Keyword(s):

Temporal Lobe Epilepsy ◽

Temporal Lobe ◽

Predictive Value ◽

Hippocampal Sclerosis ◽

Mesial Temporal Lobe Epilepsy ◽

Computer Aided Diagnosis ◽

Mri Features ◽

Computer Aided ◽

Mesial Temporal Lobe ◽

Aided Diagnosis

Epilepsy is a serious disorder in the brain. One of the most frequently found is temporal lobe epilepsy. This type of epilepsy is mainly caused by hippocampal sclerosis and treatment is often refractory so it needs surgery, this epilepsy is called mesial temporal lobe epilepsy (MTLE). MRI features for hippocampal sclerosis seen visually are a decrease in T1-weighted intensity and an increase in T2-weighted intensity. T2WI and T2 FLAIR are the sequences most often assessed for the diagnosis of hippocampal sclerosis. The assessment carried out by the practitioner to see the increase in intensity of the sequence is done visually. Visual assessment has flaws because of the limited vision and subjectivity of the practitioner, thereby producing several opinions to determine the level of intensity of the sequence. In this study a Computer Aided Diagnosis (CAD) method is proposed to assess quantitatively by assessing the intensity that exists in the FLAIR T2 sequence. This research uses Computer Aided Diagnosis (CAD) with computer programming, Image processing as a tool to find the intensity value and get a cut-off point value > 825, from this result then conduct a test by measuring the sensitivity value (90%), specificity (69%), positive predictive value (80%), negative predictive value (83%) and accuracy (81%). The of area under the curve is 0.8119, with the average ability to determine the pain is not sick is 0.71 -0.91. The results of this study indicate that Computer Aided Diagnosis (CAD) is able to detect hippocampal sclerosis in ELTM well.

Download Full-text

Computer-aided Diagnosis and Medical Decision Support are not Synonymous

Methods of Information in Medicine ◽

10.1055/s-0038-1634612 ◽

1995 ◽

Vol 34 (04) ◽

pp. 369-370 ◽

Cited By ~ 2

Author(s):

F. T. de Dombal

Keyword(s):

Decision Support ◽

Computer Aided Diagnosis ◽

Medical Decision ◽

Medical Decision Support ◽

Computer Aided ◽

Aided Diagnosis

Download Full-text

Pattern-Recognition: A Comparison of the Performance of Clinicians and Non-Clinicians - with a Note on the Performance of a Computer-Based System

Methods of Information in Medicine ◽

10.1055/s-0038-1636061 ◽

1972 ◽

Vol 11 (01) ◽

pp. 32-37 ◽

Cited By ~ 10

Author(s):

F. T. DE DOMBAL ◽

J. C. HORROCKS ◽

J. R. STANILAND ◽

P. J. GUILLOU

Keyword(s):

Pattern Recognition ◽

Computer System ◽

Computer Aided Diagnosis ◽

Clinical Interview ◽

Computer Performance ◽

Pattern Size ◽

Computer Aided ◽

Computer Based ◽

Aided Diagnosis ◽

Better Than

This paper describes a series of 10,500 attempts at »pattern-recognition« by two groups of humans and a computer based system. There was little difference between the performances of 11 clinicians and 11 other persons of comparable intellectual capability. Both groups’ performances were related to the pattern-size, the accuracy diminishing rapidly as the patterns grew larger. By contrast the computer system increased its accuracy as the patterns increased in size.It is suggested (a) that clinicians are very little better than others at pattem-recognition, (b) that the clinician is incapable of analysing on a probabilistic basis the data he collects during a traditional clinical interview and examination and (c) that the study emphasises once again a major difference between human and computer performance. The implications as - regards human- and computer-aided diagnosis are discussed.

Download Full-text