scholarly journals Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Diagnosis for Breast Microcalcification on Mammography

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1409
Author(s):  
Yoon Ah Do ◽  
Mijung Jang ◽  
Bo La Yun ◽  
Sung Ui Shin ◽  
Bohyoung Kim ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Diagnostic Performance ◽  
Computer Aided Diagnosis ◽  
Clinical Decisions ◽  
Pathological Analysis ◽  
Computer Aided ◽  
Breast Microcalcification ◽  
Aided Diagnosis

The present study evaluated the diagnostic performance of artificial intelligence-based computer-aided diagnosis (AI-CAD) compared to that of dedicated breast radiologists in characterizing suspicious microcalcification on mammography. We retrospectively analyzed 435 unilateral mammographies from 420 patients (286 benign; 149 malignant) undergoing biopsy for suspicious microcalcification from June 2003 to November 2019. Commercial AI-CAD was applied to the mammography images, and malignancy scores were calculated. Diagnostic performance was compared between radiologists and AI-CAD using the area under the receiving operator characteristics curve (AUC). The AUCs of radiologists and AI-CAD were not significantly different (0.722 vs. 0.745, p = 0.393). The AUCs of the adjusted category were 0.726, 0.744, and 0.756 with cutoffs of 2%, 10%, and 38.03% for AI-CAD, respectively, which were all significantly higher than those for radiologists alone (all p < 0.05). None of the 27 cases downgraded to category 3 with a cutoff of 2% were confirmed as malignant on pathological analysis, suggesting that unnecessary biopsies could be avoided. Our findings suggest that the diagnostic performance of AI-CAD in characterizing suspicious microcalcification on mammography was similar to that of the radiologists, indicating that it may aid in making clinical decisions regarding the treatment of breast microcalcification.

Clinical Application of Computer-Aided Diagnosis According to S-Detect in Category 4 Breast Lesions: Prospective Single-Center Study (Preprint)

2020 ◽  
Author(s):  
Pengfei Sun ◽  
Chen Chen ◽  
Weiqi Wang ◽  
Lei Liang ◽  
Dan Luo ◽  
...  
Keyword(s):  
Clinical Management ◽  
Diagnostic Performance ◽  
Breast Biopsy ◽  
Computer Aided Diagnosis ◽  
Breast Lesions ◽  
Breast Masses ◽  
Computer Aided ◽  
Conventional Ultrasound ◽  
Us Findings ◽  
Aided Diagnosis

BACKGROUND Computer-aided diagnosis (CAD) is a useful tool that can provide a reference for the differential diagnosis of benign and malignant breast lesion. Previous studies have demonstrated that CAD can improve the diagnostic performance. However, conventional ultrasound (US) combined with CAD were used to adjust the classification of category 4 lesions has been few assessed. OBJECTIVE The objective of our study was to evaluate the diagnosis performance of conventional ultrasound combined with a CAD system S-Detect in the category of BI-RADS 4 breast lesions. METHODS Between December 2018 and May 2020, we enrolled patients in this study who received conventional ultrasound and S-Detect before US-guided biopsy or surgical excision. The diagnostic performance was compared between US findings only and the combined use of US findings with S-Detect, which were correlated with pathology results. RESULTS A total of 98 patients (mean age 51.06 ±16.25 years, range 22-81) with 110 breast masses (mean size1.97±1.38cm, range0.6-8.5) were included in this study. Of the 110 breast masses, 64/110 (58.18%) were benign, 46/110 (41.82%) were malignant. Compared with conventional ultrasound, a significant increase in specificity (0% to 53.12%, P<.001), accuracy (41.81% to70.19%, P<.001) were noted, with no statistically significant decrease on sensitivity(100% to 95.65% ,P=.48). According to S-Detect-guided US BI-RADS re-classification, 30 out of 110 (27.27%) breast lesions underwent a correct change in clinical management, 74of 110 (67.27%) breast lesions underwent no change and 6 of 110 (5.45%) breast lesions underwent an incorrect change in clinical management. The biopsy rate decreased from 100% to 67.27 % (P<.001).Benign masses among subcategory 4a had higher rates of possibly benign assessment on S-Detect for the US only (60% to 0%, P<.001). CONCLUSIONS S-Detect can be used as an additional diagnostic tool to improve the specificity and accuracy in clinical practice. S-Detect have the potential to be used in downgrading benign masses misclassified as BI-RADS category 4 on US by radiologist, and may reduce unnecessary breast biopsy. CLINICALTRIAL none

scholarly journals Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions

2019 ◽  
Vol 4 (1) ◽  
pp. 71-80 ◽  
Author(s):  
Omer F Ahmad ◽  
Antonio S Soares ◽  
Evangelos Mazomenos ◽  
Patrick Brandao ◽  
Roser Vega ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Computer Aided Diagnosis ◽  
Current Evidence ◽  
Future Directions ◽  
Computer Aided ◽  
Aided Diagnosis

scholarly journals Computer-Aided Diagnosis for Spitzoid Lesions Classification Using Artificial Intelligence Techniques

2021 ◽  
Vol 16 (1) ◽  
pp. 16-37
Author(s):  
Abir Belaala ◽  
Labib Sadek Terrissa ◽  
Noureddine Zerhouni ◽  
Christine Devalland
Keyword(s):  
Artificial Intelligence ◽  
Phase 1 ◽  
Computer Aided Diagnosis ◽  
Machine Learning Algorithms ◽  
Spitz Nevus ◽  
Artificial Intelligence Techniques ◽  
System A ◽  
Three Phase ◽  
Computer Aided ◽  
Aided Diagnosis

Spitzoid lesions may be largely categorized into Spitz Nevus, Atypical Spitz Tumors, and Spitz Melanomas. Classifying a lesion precisely as Atypical Spitz Tumors or AST is challenging and often requires the integration of clinical, histological, and immunohistochemical features to differentiate AST from regular Spitz Nevus and malignant Spitz Melanomas. Specifically, this paper aims to test several artificial intelligence techniques so as to build a computer-aided diagnosis system. A proposed three-phase approach is being implemented. In Phase 1, collected data are preprocessed with an effective SMOTE-based method being implemented to treat the imbalance data problem. Then, a feature selection mechanism using genetic algorithm (GA) is applied in Phase 2. Finally, in Phase 3, a 10-fold cross-validation method is used to compare the performance of seven machine-learning algorithms for classification. Results obtained with SMOTE-Multilayer Perceptron with GA-based 14 features show the highest classification accuracy, specificity (0.98), and a sensitivity of 0.99.

scholarly journals Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine

2019 ◽  
Vol 52 (6) ◽  
pp. 387-396 ◽  
Author(s):  
Marcel Koenigkam Santos ◽  
José Raniery Ferreira Júnior ◽  
Danilo Tadao Wada ◽  
Ariane Priscilla Magalhães Tenório ◽  
Marcello Henrique Nogueira Barbosa ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Diagnostic Imaging ◽  
Precision Medicine ◽  
Quantitative Information ◽  
Computer Aided Diagnosis ◽  
Rapid Expansion ◽  
Computer Aided ◽  
The Impact ◽  
Aided Diagnosis

Abstract The discipline of radiology and diagnostic imaging has evolved greatly in recent years. We have observed an exponential increase in the number of exams performed, subspecialization of medical fields, and increases in accuracy of the various imaging methods, making it a challenge for the radiologist to “know everything about all exams and regions”. In addition, imaging exams are no longer only qualitative and diagnostic, providing now quantitative information on disease severity, as well as identifying biomarkers of prognosis and treatment response. In view of this, computer-aided diagnosis systems have been developed with the objective of complementing diagnostic imaging and helping the therapeutic decision-making process. With the advent of artificial intelligence, “big data”, and machine learning, we are moving toward the rapid expansion of the use of these tools in daily life of physicians, making each patient unique, as well as leading radiology toward the concept of multidisciplinary approach and precision medicine. In this article, we will present the main aspects of the computational tools currently available for analysis of images and the principles of such analysis, together with the main terms and concepts involved, as well as examining the impact that the development of artificial intelligence has had on radiology and diagnostic imaging.

Sign in / Sign up

Export Citation Format

Share Document