Cumulative Advanced Breast Cancer Risk Prediction Model Developed in a Screening Mammography Population

Kerlikowske, Karla; Chen, Shuai; Golmakani, Marzieh K; Sprague, Brian L.; Tice, Jeffrey A.; Rauscher, Garth H.; Henderson, Louise M.; Buist, Diana S.M.; Lee, Janie M.; Gard, Charlotte C.; Miglioretti, Diana L.

doi:10.1093/jnci/djac008

Cited by 27 publications

(54 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These risk estimates can be used by policy makers in conjunction with estimates of other breast cancer screening outcomes (such as cumulative risk of false-positive mammography results and advanced cancer) when evaluating the balance of screening benefits and harms by screening interval. 15 , 16 …”

Section: Discussionmentioning

confidence: 99%

“…Previous studies 13 , 15 , 27 , 42 have identified risk groups that can undergo biennial screening with little adverse change in risk of advanced cancer or life-years gained compared with annual mammography. Our results indicate that women who have low advanced cancer risk with biennial screening (eg, women with healthy weight and nondense breasts) 15 would also experience reduced cumulative DCIS detection with a biennial vs annual screening interval. Of note, risk of screen-detected DCIS on a single screening round was higher with increasing time since last mammography, reflecting the longer interval for DCIS to emerge.…”

Section: Discussionmentioning

confidence: 99%

“…Models were recently published for cumulative 6-year risk of advanced (prognostic stage II or higher) breast cancer and cumulative 10-year risk of a false-positive mammography result based on mammography screening frequency and readily available clinical risk factors. 15 , 16 Prediction models for screen-detected DCIS would further inform screening decisions and guidelines.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cumulative 6-Year Risk of Screen-Detected Ductal Carcinoma In Situ by Screening Frequency

et al. 2023

Self Cite

View full text Add to dashboard Cite

ImportanceDetection of ductal carcinoma in situ (DCIS) by mammography screening is a controversial outcome with potential benefits and harms. The association of mammography screening interval and woman’s risk factors with the likelihood of DCIS detection after multiple screening rounds is poorly understood.ObjectiveTo develop a 6-year risk prediction model for screen-detected DCIS according to mammography screening interval and women’s risk factors.Design, Setting, and ParticipantsThis Breast Cancer Surveillance Consortium cohort study assessed women aged 40 to 74 years undergoing mammography screening (digital mammography or digital breast tomosynthesis) from January 1, 2005, to December 31, 2020, at breast imaging facilities within 6 geographically diverse registries of the consortium. Data were analyzed between February and June 2022.ExposuresScreening interval (annual, biennial, or triennial), age, menopausal status, race and ethnicity, family history of breast cancer, benign breast biopsy history, breast density, body mass index, age at first birth, and false-positive mammography history.Main Outcomes and MeasuresScreen-detected DCIS defined as a DCIS diagnosis within 12 months after a positive screening mammography result, with no concurrent invasive disease.ResultsA total of 916 931 women (median [IQR] age at baseline, 54 [46-62] years; 12% Asian, 9% Black, 5% Hispanic/Latina, 69% White, 2% other or multiple races, and 4% missing) met the eligibility criteria, with 3757 screen-detected DCIS diagnoses. Screening round–specific risk estimates from multivariable logistic regression were well calibrated (expected-observed ratio, 1.00; 95% CI, 0.97-1.03) with a cross-validated area under the receiver operating characteristic curve of 0.639 (95% CI, 0.630-0.648). Cumulative 6-year risk of screen-detected DCIS estimated from screening round–specific risk estimates, accounting for competing risks of death and invasive cancer, varied widely by all included risk factors. Cumulative 6-year screen-detected DCIS risk increased with age and shorter screening interval. Among women aged 40 to 49 years, the mean 6-year screen-detected DCIS risk was 0.30% (IQR, 0.21%-0.37%) for annual screening, 0.21% (IQR, 0.14%-0.26%) for biennial screening, and 0.17% (IQR, 0.12%-0.22%) for triennial screening. Among women aged 70 to 74 years, the mean cumulative risks were 0.58% (IQR, 0.41%-0.69%) after 6 annual screens, 0.40% (IQR, 0.28%-0.48%) for 3 biennial screens, and 0.33% (IQR, 0.23%-0.39%) after 2 triennial screens.Conclusions and RelevanceIn this cohort study, 6-year screen-detected DCIS risk was higher with annual screening compared with biennial or triennial screening intervals. Estimates from the prediction model, along with risk estimates of other screening benefits and harms, could help inform policy makers’ discussions of screening strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cumulative 6-Year Risk of Screen-Detected Ductal Carcinoma In Situ by Screening Frequency

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is a major issue in healthcare. As a result, early identification of breast cancer can lower the risk of patient death [4].…”

Section: Introductionmentioning

confidence: 99%

A Novel CNN-Inception-V4-Based Hybrid Approach for Classification of Breast Cancer in Mammogram Images

Nazir

Khan

Mohiyuddin

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Breast cancer is the most frequent disease in women, with one in every 19 women at risk. Breast cancer is the fifth leading cause of cancer death in women around the world. The most effective and efficient technique of controlling cancer development is early identification. Mammography helps in the early detection of cancer, which saves lives. Many studies conducted various tests to categorize the tumor and obtained positive findings. However, there are certain limits. Mass categorization in mammography is still a problem, although it is critical in aiding radiologists in establishing correct diagnoses. The purpose of this study is to develop a unique hybrid technique to identify breast cancer mass pictures as benign or malignant. The combination of two networks helps accelerate the categorization process. This study proposes a novel-based hybrid approach, CNN-Inception-V4, based on the fusing of these two networks. Mass images are used in this research from the CBIS-DDSM dataset. 450 images are taken for benign, and 450 images are used for malignant. The images are first cleaned by removing pectoral muscles, labels, and white borders. Then, CLAHE is used to these images to improve their quality in order to produce promising classification results. Following preprocessing, our model classifies cancer in mammography pictures as benign or malignant abnormalities. Our proposed model’s accuracy is 99.2%, with sensitivity of 99.8%, specificity of 96.3%, and F1-score of 97%. We also compared our proposed model to CNN, Inception-V4, and ResNet-50. Our proposed model outperforms existing classification models, according to the results.

show abstract

“…The most widely used method for breast cancer diagnosis is breast imaging medical examination [3,4]. The widely used medical breast images are Mammography [5], Positron Emission Tomography (PET) [6], Magnetic Resonance Imaging (MRI) [7], Computed Tomography (CT) [8] and Ultrasound [9]. Mammography is one of the most widely used screening methods for breast cancer [10,11] due to its low cost, better sensitivity and specificity for breast lesions, and excellent ability to detect lesions of the breast in the early stage of breast cancer [12].…”

Section: Introductionmentioning

confidence: 99%

Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography

et al. 2022

View full text Add to dashboard Cite

Breast cancer accounts for the largest number of patients among all cancers in the world. Intervention treatment for early breast cancer can dramatically extend a woman's 5‐year survival rate. However, the lack of public available breast mammography databases in the field of Computer‐aided Diagnosis and the insufficient feature extraction ability from breast mammography limit the diagnostic performance of breast cancer. In this paper, A novel classification algorithm based on Convolutional Neural Network (CNN) is proposed to improve the diagnostic performance for breast cancer on mammography. A multi‐view network is designed to extract the complementary information between the Craniocaudal (CC) and Mediolateral Oblique (MLO) mammographic views of a breast mass. For the different predictions of the features extracted from the CC view and MLO view of the same breast mass, the proposed algorithm forces the network to extract the consistent features from the two views by the cross‐entropy function with an added consistent penalty term. To exploit the discriminative features from the insufficient mammographic images, the authors learnt an encoder in the classification model to learn the invariable representations from the mammographic breast mass by Supervised Contrastive Learning (SCL) to weaken the side effect of colour jitter and illumination of mammographic breast mass on image quality degradation. The experimental results of all the classification algorithms mentioned in this paper on Digital Database for Screening Mammography (DDSM) illustrate that the proposed algorithm greatly improves the classification performance and diagnostic speed of mammographic breast mass, which is of great significance for breast cancer diagnosis.

show abstract

Cumulative Advanced Breast Cancer Risk Prediction Model Developed in a Screening Mammography Population

Cited by 27 publications

References 54 publications

Cumulative 6-Year Risk of Screen-Detected Ductal Carcinoma In Situ by Screening Frequency

Cumulative 6-Year Risk of Screen-Detected Ductal Carcinoma In Situ by Screening Frequency

A Novel CNN-Inception-V4-Based Hybrid Approach for Classification of Breast Cancer in Mammogram Images

Breast mass classification based on supervised contrastive learning and multi‐view consistency penalty on mammography

Contact Info

Product

Resources

About