Diagnostic Performance of AI for Cancers Registered in A Mammography Screening Program: A Retrospective Analysis

Yırgın, İnci Kızıldağ; Koyluoglu, Yilmaz Onat; Seker, Mustafa Ege; Gürdal, Sibel Özkan; Özaydın, Ayşe; Özçınar, Beyza; Cabıoğlu, Neslihan; Özmen, Vahit; Arıbal, Erkin

doi:10.1177/15330338221075172

Cited by 8 publications

(3 citation statements)

References 48 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te maturing AI software may also increase our ability to capture cancer. A diagnostic study for AI in a retrospective simulated screening setting found the highest cancer detection rate by teaming up radiologists and AI [23]. A recently published retrospective study by Kim et al also found AI to be able to detect mammographically occult cancers in dense breasts [24].…”

Section: Discussionmentioning

confidence: 98%

Comparison of Characteristics of Breast Cancer Detected through Different Imaging Modalities in a Large Cohort of Hong Kong Chinese Women: Implication of Imaging Choice on Upcoming Local Screening Program

Chan

Hung²,

Yuen³

et al. 2022

The Breast Journal

View full text Add to dashboard Cite

Background. We compared the clinico-radio-pathological characteristics of breast cancer detected through mammogram (MMG) and ultrasound (USG) and discuss the implication of the choice of imaging as the future direction of our recently launched local screening program. Methods. Retrospective study of 14613 Hong Kong Chinese female patients with histologically confirmed breast cancer registered in the Hong Kong Breast Cancer Registry between January 2006 and February 2020. Patients were classified into four groups based on the mode of breast cancer detection (detectable by both mammogram and ultrasound (MMG+/USG+), mammogram only (MMG+/USG−), ultrasound only (MMG−/USG+), or not detectable by either (MMG−/USG−). Characteristics of breast cancer detected were compared, including patient demographics, breast density on MMG, mode of presentation, tumour size, histological type, and staging. Types of mammographic abnormalities were also evaluated for MMG+ subgroups. Results. 85% of the cancers were detectable by MMG, while USG detected an additional 9%. MMG+/USG+ cancers were larger, more advanced in stage, often of symptomatic presentation, and commonly manifested as mammographic mass. MMG+/USG− cancers were more likely of asymptomatic presentation, manifested as microcalcifications, and of earlier stage and to be ductal carcinoma in situ. MMG−/USG+ cancers were more likely seen in young patients and those with denser breasts and more likely of symptomatic presentation. MMG−/USG− cancers were often smaller and found in denser breasts. Conclusion. Mammogram has a good detection rate of cancers in our local population. It has superiority in detecting early cancers by detecting microcalcifications. Our current study agrees that ultrasound is one of the key adjunct tools of breast cancer detection.

show abstract

Section: Discussionmentioning

confidence: 98%

Comparison of Characteristics of Breast Cancer Detected through Different Imaging Modalities in a Large Cohort of Hong Kong Chinese Women: Implication of Imaging Choice on Upcoming Local Screening Program

Chan

Hung²,

Yuen³

et al. 2022

The Breast Journal

View full text Add to dashboard Cite

show abstract

“…AI framework using CNN has been employed for screening BC using DM. 34 AI enabled screening outperformed radiologist screening with an accuracy of 72.7%. Further combining AI and radiologist decision improved the detection performance of 83.6% accuracy with reduced false positive rates.…”

Section: Deep Learning-based Cad Approaches For Breast Cancer Diagnosismentioning

confidence: 99%

Review on Deep Learning-Based CAD Systems for Breast Cancer Diagnosis

Kumar¹,

Sasikala²

2023

Technol Cancer Res Treat

View full text Add to dashboard Cite

Breast Cancer (BC) is a major health issue in women of the age group above 45. Identification of BC at an earlier stage is important to reduce the mortality rate. Image-based noninvasive methods are used for early detection and for providing appropriate treatment. Computer-Aided Diagnosis (CAD) schemes can support radiologists in making correct decisions. Computational intelligence paradigms such as Machine Learning (ML) and Deep Learning (DL) have been used in the recent past in CAD systems to accelerate diagnosis. ML techniques are feature driven and require a high amount of domain expertise. However, DL approaches make decisions directly from the image. The current advancement in DL approaches for early diagnosis of BC is the motivation behind this review. This article throws light on various types of CAD approaches used in BC detection and diagnosis. A survey on DL, Transfer Learning, and DL-based CAD approaches for the diagnosis of BC is presented in detail. A comparative study on techniques, datasets, and performance metrics used in state-of-the-art literature in BC diagnosis is also summarized. The proposed work provides a review of recent advancements in DL techniques for enhancing BC diagnosis.

show abstract

“…Numerous applications of AI in breast imaging are currently under development, such as cancer detection for different imaging modalities [7][8][9][10], triage [11][12][13][14], optimization of acquisition protocols and individual risk prediction.…”

Section: Introductionmentioning

confidence: 99%

Impact of artificial intelligence in breast cancer screening with mammography

et al. 2022

View full text Add to dashboard Cite

Objectives To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time. Methods A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or “continuous BI-RADS 100”. Cohen’s kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed. Results On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95% CI (0.528–0.571) without AI and κ = 0.626, 95% CI (0.607–0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754). Conclusions When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.

show abstract

Diagnostic Performance of AI for Cancers Registered in A Mammography Screening Program: A Retrospective Analysis

Cited by 8 publications

References 48 publications

Comparison of Characteristics of Breast Cancer Detected through Different Imaging Modalities in a Large Cohort of Hong Kong Chinese Women: Implication of Imaging Choice on Upcoming Local Screening Program

Comparison of Characteristics of Breast Cancer Detected through Different Imaging Modalities in a Large Cohort of Hong Kong Chinese Women: Implication of Imaging Choice on Upcoming Local Screening Program

Review on Deep Learning-Based CAD Systems for Breast Cancer Diagnosis

Impact of artificial intelligence in breast cancer screening with mammography

Contact Info

Product

Resources

About