scholarly journals Integrating Computer Aided Detection in Every Day Multiple Sclerosis Follow-up Preserves Lesion Detection Accuracy Between Radiology Trainees and Neuroradiologists

2020 ◽  
Author(s):  
Ariel Dahan ◽  
Frank Gaillard ◽  
Charles Malpas
Keyword(s):  
Multiple Sclerosis ◽  
Lesion Detection ◽  
Detection Accuracy ◽  
Computer Aided Detection ◽  
Computer Aided

scholarly journals Detection Accuracy and Latency of Colorectal Lesions with Computer-Aided Detection System Based on Low-Bias Evaluation

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1922
Author(s):  
Hiroaki Matsui ◽  
Shunsuke Kamba ◽  
Hideka Horiuchi ◽  
Sho Takahashi ◽  
Masako Nishikawa ◽  
...  
Keyword(s):  
Predictive Value ◽  
Detection System ◽  
Poor Quality ◽  
Lesion Detection ◽  
University Hospital ◽  
Detection Accuracy ◽  
Computer Aided Detection ◽  
Test Dataset ◽  
Computer Aided ◽  
Cade System

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for 69 colorectal lesions at the Jikei University Hospital between June 2017 and February 2018. First, we evaluated the diagnostic performances using still images randomly and automatically extracted from video recordings of the entire endoscopic procedure at intervals of 5 s, without eliminating poor quality images. Second, the latency of lesion detection by the CADe system from the initial appearance of lesions was investigated by reviewing the videos. A total of 6531 images, including 662 images with a lesion, were studied in the image-based analysis. The AUC, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.983, 94.6%, 95.2%, 68.8%, 99.4%, and 95.1%, respectively. The median time for detecting colorectal lesions measured in the lesion-based analysis was 0.67 s. In conclusion, we proved that the originally developed CADe system based on YOLO v3 could accurately and instantaneously detect colorectal lesions using the test dataset obtained from videos, mitigating operator selection biases.

A Comparison of Follow-Up Recommendations by Chest Radiologists, General Radiologists, and Pulmonologists Using Computer-Aided Detection to Assess Radiographs for Actionable Pulmonary Nodules

2011 ◽  
Vol 196 (5) ◽  
pp. W542-W549 ◽  
Author(s):  
Moulay Meziane ◽  
Nancy A. Obuchowski ◽  
Omar Lababede ◽  
Michael L. Lieber ◽  
Michael Philips ◽  
...  
Keyword(s):  
Pulmonary Nodules ◽  
Computer Aided Detection ◽  
Computer Aided

scholarly journals The value of computer aided detection system for mammography in the fatty breast: the results of the single-centered, prospective, randomized clinical trial

2021 ◽  
Vol 25 (4) ◽  
pp. 93-105
Author(s):  
D. V. Pasynkov ◽  
M. G. Tukhbatullin ◽  
R. Sh. Khasanov
Keyword(s):  
Detection System ◽  
Low Density ◽  
Breast Cancers ◽  
Computer Aided Detection ◽  
Initial Screening ◽  
Prospective Randomized Clinical Trial ◽  
Primary Screening ◽  
Targeted Ultrasound ◽  
Computer Aided

Aim. To assess the reasonability to use CAD added to mammography with subsequent targeted ultrasound (US) of CAD markings in patients with low-density (ACR A-В) breasts.Materials and methods. In the prospective study we included 2326 women with low breast density. They were randomized for CAD (MammCheck II of our own design) checking with subsequent targeted US (MMG + CAD group) or without CAD (MMG only group). After the initial screening we performed the 3-year follow-up phase.Results. Totally, during the primary screening in the MMG only group we found 77 breast cancers (BCs) (28,57% of them sized less than 1 cm), in the MMG + CAD group – 69 BCs (36,23% of them sized less than 1 cm), р > 0.05. The suspicious lesion was identified only during the targeted US of the CAD marking in 4 of 25 women in the MMG + CAD group, and all these BCs were below 1 cm in size. During the subsequent follow-up in the MMG only group we found 5 additional BCs, with no such cases in the MMG + CAD group (p < 0.05). Three of these five BCs were retrospectively marked by CAD. The only visible BC that was not marked by CAD was 3 mm in size.Discussion. The overall false positive marking rate was 0.31 и 0.28 per film-screen and digital image, respectively (р > 0.05).Conclusion. The CAD usage added to mammography with subsequent targeted US of markings in patients with low-density (ACR A-В) breast is reasonable due to the significant decrease of the BC rate diagnosed during the 3-year follow-up. This combination detected 77 of the 77 (100.00%) BCs compared to 69 of 74 (93.24%) BCs when only mammography used.

scholarly journals Computer-aided Detection Fidelity of Pulmonary Nodules in Chest Radiograph

2017 ◽  
Vol 7 ◽  
pp. 8 ◽  
Author(s):  
Nikolaos Dellios ◽  
Ulf Teichgraeber ◽  
Robert Chelaru ◽  
Ansgar Malich ◽  
Ismini E Papageorgiou
Keyword(s):  
Chest Radiograph ◽  
False Positive Rate ◽  
False Negative ◽  
Radiographic Finding ◽  
Pulmonary Nodules ◽  
Clinical Diagnostics ◽  
Lesion Detection ◽  
Chest Radiographs ◽  
Computer Aided Detection ◽  
Computer Aided

Aim: The most ubiquitous chest diagnostic method is the chest radiograph. A common radiographic finding, quite often incidental, is the nodular pulmonary lesion. The detection of small lesions out of complex parenchymal structure is a daily clinical challenge. In this study, we investigate the efficacy of the computer-aided detection (CAD) software package SoftView™ 2.4A for bone suppression and OnGuard™ 5.2 (Riverain Technologies, Miamisburg, OH, USA) for automated detection of pulmonary nodules in chest radiographs. Subjects and Methods: We retrospectively evaluated a dataset of 100 posteroanterior chest radiographs with pulmonary nodular lesions ranging from 5 to 85 mm. All nodules were confirmed with a consecutive computed tomography scan and histologically classified as 75% malignant. The number of detected lesions by observation in unprocessed images was compared to the number and dignity of CAD-detected lesions in bone-suppressed images (BSIs). Results: SoftView™ BSI does not affect the objective lesion-to-background contrast. OnGuard™ has a stand-alone sensitivity of 62% and specificity of 58% for nodular lesion detection in chest radiographs. The false positive rate is 0.88/image and the false negative (FN) rate is 0.35/image. From the true positive lesions, 20% were proven benign and 80% were malignant. FN lesions were 47% benign and 53% malignant. Conclusion: We conclude that CAD does not qualify for a stand-alone standard of diagnosis. The use of CAD accompanied with a critical radiological assessment of the software suggested pattern appears more realistic. Accordingly, it is essential to focus on studies assessing the quality-time-cost profile of real-time (as opposed to retrospective) CAD implementation in clinical diagnostics.

Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images

2012 ◽  
pp. 125-152
Author(s):  
Moi Hoon Yap ◽  
Eran Edirisinghe ◽  
Helmut Bez
Keyword(s):  
Pattern Recognition ◽  
Feature Selection ◽  
Standard Deviation ◽  
Performance Analysis ◽  
Comprehensive Analysis ◽  
Lesion Detection ◽  
Computer Aided Detection ◽  
Computer Aided ◽  
Overall Performance ◽  
Tool Set

The authors extend their previous work on Ultrasound (US) image lesion detection and segmentation, to classification, proposing a complete end-to-end solution for automatic Ultrasound Computer Aided Detection (US CAD). Carried out is a comprehensive analysis to determine the best classifier-feature set combination that works optimally in US imaging. In particular the use of nineteen features categorised into three groups (shape, texture and edge), ten classifiers and 22 feature selection approaches are used in the analysis. From the overall performance, the classifier RBFNetworks defined by the WEKA pattern recognition tool set, with a feature set comprising of the area to perimeter ratio, solidity, elongation, roundness, standard deviation, two Fourier related and a fractal related texture measures out-performed other combinations of feature-classifiers, with an achievement of predicted Az value of 0.948. Next analyzed is the use of a number of different metrics in performance analysis and provide an insight to future improvements and extension.

Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images

2010 ◽  
Vol 1 (2) ◽  
pp. 53-81
Author(s):  
Moi Hoon Yap ◽  
Eran Edirisinghe ◽  
Helmut Bez
Keyword(s):  
Pattern Recognition ◽  
Feature Selection ◽  
Standard Deviation ◽  
Comprehensive Analysis ◽  
Lesion Detection ◽  
Computer Aided Detection ◽  
Computer Aided ◽  
Overall Performance ◽  
Tool Set ◽  
Detection And Recognition

The authors extend their previous work on Ultrasound (US) image lesion detection and segmentation, to classification, proposing a complete end-to-end solution for automatic Ultrasound Computer Aided Detection (US CAD). Carried out is a comprehensive analysis to determine the best classifier-feature set combination that works optimally in US imaging. In particular the use of nineteen features categorised into three groups (shape, texture and edge), ten classifiers and 22 feature selection approaches are used in the analysis. From the overall performance, the classifier RBFNetworks defined by the WEKA pattern recognition tool set, with a feature set comprising of the area to perimeter ratio, solidity, elongation, roundness, standard deviation, two Fourier related and a fractal related texture measures out-performed other combinations of feature-classifiers, with an achievement of predicted Az value of 0.948. Next analyzed is the use of a number of different metrics in performance analysis and provide an insight to future improvements and extension.

Computer-aided Detection Output on 172 Subtle Findings on Normal Mammograms Previously Obtained in Women with Breast Cancer Detected at Follow-Up Screening Mammography

Radiology ◽  
2004 ◽  
Vol 230 (3) ◽  
pp. 811-819 ◽  
Author(s):  
Debra M. Ikeda ◽  
Robyn L. Birdwell ◽  
Kathryn F. O’Shaughnessy ◽  
Edward A. Sickles ◽  
R. James Brenner
Keyword(s):  
Breast Cancer ◽  
Screening Mammography ◽  
Computer Aided Detection ◽  
Computer Aided
Sign in / Sign up

Export Citation Format

Share Document