Digital versus screen film mammography: a clinical comparison

Estimated health outcomes of breast cancer screening in the national breast and cervical cancer early detection program by race/ethnicity

PURPOSE

To estimate the number of screenings received, life-years (LYs) saved, and number of screenings per LY saved per woman who participated in the National Breast and Cervical Cancer Early Detection Program (NBCCEDP) (Program) compared with those who did not participate (no Program).

METHODS

We developed a time-to-event simulation model to compare the outcomes of women participating in the Program vs. no Program, categorized by race/ethnicity. Model input parameters included data from the Program's minimum data elements, United States Cancer Statistics, National Health Interview Survey, and published literature. The Program's impact was calculated as the difference in LYs between the Program and no Program using data from 2010 to 2019.

RESULTS

Among 1 million women of all races/ethnicities who participated in the NBCCEDP in the last 10 years, 457,152 (standard deviation [SD]: 848) received more screenings than those who did not participate. These participants saved an average of 0.027 LYs per woman screened. In addition, we estimated that about 17 screenings would be required to save an additional 1 LY per woman screened in the Program compared with no Program. Per woman screened by race/ethnicity, non-Hispanic Black women had the highest estimated 0.075 LYs saved, followed by Hispanic women with 0.025 LYs, non-Hispanic White with 0.014 LYs, and non-Hispanic American Indian/Alaska Native and Asian/Pacific Islander had the least health outcome with 0.011 LYs.

CONCLUSION

The reported findings underscore the importance of providing preventive health services to populations that might not otherwise have access to these services.

Automated classification of fat-infiltrated axillary lymph nodes on screening mammograms

OBJECTIVE

Fat-infiltrated axillary lymph nodes (LNs) are unique sites for ectopic fat deposition. Early studies showed a strong correlation between fatty LNs and obesity-related diseases. Confirming this correlation requires large-scale studies, hindered by scarce labeled data. With the long-term goal of developing a rapid and generalizable tool to aid data labeling, we developed an automated deep learning (DL)-based pipeline to classify the status of fatty LNs on screening mammograms.

METHODS

Our internal data set included 886 mammograms from a tertiary academic medical institution, with a binary status of the fat-infiltrated LNs based on the size and morphology of the largest visible axillary LN. A two-stage DL model training and fine-tuning pipeline was developed to classify the fat-infiltrated LN status using the internal training and development data set. The model was evaluated on a held-out internal test set and a subset of the Digital Database for Screening Mammography.

RESULTS

Our model achieved 0.97 (95% CI: 0.94-0.99) accuracy and 1.00 (95% CI: 1.00-1.00) area under the receiver operator characteristic curve on 264 internal testing mammograms, and 0.82 (95% CI: 0.77-0.86) accuracy and 0.87 (95% CI: 0.82-0.91) area under the receiver operator characteristic curve on 70 external testing mammograms.

CONCLUSION

This study confirmed the feasibility of using a DL model for fat-infiltrated LN classification. The model provides a practical tool to identify fatty LNs on mammograms and to allow for future large-scale studies to evaluate the role of fatty LNs as an imaging biomarker of obesity-associated pathologies.

ADVANCES IN KNOWLEDGE

Our study is the first to classify fatty LNs using an automated DL approach.

Rapid Diagnosis of Ductal Carcinoma In Situ and Breast Cancer Based on Raman Spectroscopy of Serum Combined with Convolutional Neural Network

Ductal carcinoma in situ (DCIS) and breast cancer are common female breast diseases and pose a serious health threat to women. Early diagnosis of breast cancer and DCIS can help to develop targeted treatment plans in time. In this paper, we investigated the feasibility of using Raman spectroscopy combined with convolutional neural network (CNN) to discriminate between healthy volunteers, breast cancer and DCIS patients. Raman spectra were collected from the sera of 241 healthy volunteers, 463 breast cancer and 100 DCIS patients, and a total of 804 spectra were recorded. The pre-processed Raman spectra were used as the input of CNN to establish a model to classify the three different spectra. After using cross-validation to optimize its hyperparameters, the model's final classification performance was assessed using an unknown test set. For comparison with other machine learning algorithms, we additionally built models using support vector machine (SVM), random forest (RF) and k-nearest neighbor (KNN) methods. The final accuracies for CNN, SVM, RF and KNN were 98.76%, 94.63%, 80.99% and 78.93%, respectively. The values for area under curve (AUC) were 0.999, 0.994, 0.931 and 0.900, respectively. Therefore, our study results demonstrate that CNN outperforms three traditional algorithms in terms of classification performance for Raman spectral data and can be a useful auxiliary diagnostic tool of breast cancer and DCIS.

Breast cancer diagnosis using frequency decomposition of surface motion of actuated breast tissue

This paper presents a computationally simple diagnostic algorithm for breast cancer using a non-invasive Digital Image Elasto Tomography (DIET) system. N=14 women (28 breasts, 13 cancerous) underwent a clinical trial using the DIET system following mammography diagnosis. The screening involves steady state sinusoidal vibrations applied to the free hanging breast with cameras used to capture tissue motion. Image reconstruction methods provide surface displacement data for approximately 14,000 reference points on the breast surface. The breast surface was segmented into four radial and four vertical segments. Frequency decomposition of reference point motion in each segment were compared. Segments on the same vertical band were hypothesised to have similar frequency content in healthy breasts, with significant differences indicating a tumor, based on the stiffness dependence of frequency and tumors being 4~10 times stiffer than healthy tissue. Twelve breast configurations were used to test robustness of the method. Optimal breast configuration for the 26 breasts analysed (13 cancerous, 13 healthy) resulted in 85% sensitivity and 77% specificity. Combining two opposite configurations resulted in correct diagnosis of all cancerous breasts with 100% sensitivity and 69% specificity. Bootstrapping was used to fit a smooth receiver operator characteristic (ROC) curve to compare breast configuration performance with optimal area under the curve (AUC) of 0.85. Diagnostic results show diagnostic accuracy is comparable or better than mammography, with the added benefits of DIET screening, including portability, non-invasive screening, and no breast compression, with potential to increase screening participation and equity, improving outcomes for women.

An approach to dual-energy contrast-enhanced spectral mammography (DE-CESM) using a double layer filter: dosimetric and image quality assessment

Dual-energy contrast-enhanced spectral mammography (DE-CESM) is a recently developed advanced technique in digital mammography that uses an iodinated intravenous contrast agent to assess tumor angiogenesis. The aim of this study was to investigate the diagnostic potential of DE-CESM recombined images in terms of radiation dose and image quality. A 50% fibroglandular-50% adipose, custom-made phantom with iodine inserts of 1.0 mgI cm^-3, 2.0 mgI cm^-3, 4.0 mgI cm^-3was used for the estimation of mean glandular dose (MGD) and the image quality. Low-energy (LE) images were acquired with the W/Rh, W/Rh + 0.01 mm Cu and W/Rh + 0.5 mm Al while high energy images (HE) are acquired with the W/Rh, W/Rh + 0.06 mm Ba, W/Rh + 0.01 mm Cu, and W/Rh + 0.03 mm Ce anode filter combinations. The total MGD was reduced up to a maximum from 1.75 mGy to 1.45 mGy by using Rh + 0.01 mm Cu double-layer filter for both LE and HE imaging of 50 mm, standard 50% fibroglandular phantom compared to Rh single-layer filter with W target. The minimum total MGD reduction (1.69 mGy) was observed when Rh + 0.5 mm Al was used for LE and Rh + 0.06 mm Ba was used for HE exposure. The image quality was comparable with the single-layer filter. The use of W/Rh + 0.01 mm Cu or W/Rh + 0.5 mm Al as target/filter combination for LE exposure and W/Rh + 0.01 mm Cu for HE exposure can reduce the additional radiation dose delivered by DE-CESM without degrading the image quality.

Modeling viscous damping in actuated breast tissue to provide diagnostic insight for breast cancer: A proof-of-concept analysis

PURPOSE

This study develops a viscous damping model (VDM) based on Rayleigh Damping (RD) with potential use in low cost, non-invasive breast cancer diagnostics using Digital Image Elasto Tomography (DIET).

METHODS

A clinical trial involving 13 subjects, each with a tumor in one breast, resulted in 13 cancerous and 13 healthy breasts. Displacement data following actuator induced steady state vibration in the breast tissue were captured using the DIET system. Over 14 000 reference points on the breast surface were split into four segments and viscous damping constant calculated for each reference point. The VDM was fit to median-filtered data for each breast segment and VDM coefficients compared within each breast. One model coefficient, relating to stiffness, was hypothesized to differ in breast segments containing a tumor. Comparison of " b " coefficients in different breast segments using percentage tolerances provided an unbiased, generalizable diagnostic method. Bootstrapping with replacement was used to upsample the data and create smooth receiver operator characteristic (ROC) curves. A total of 12 breast segmentation configurations were used to demonstrate the robustness of the method.

RESULTS

Fitting the VDM to median-filtered data gave consistent results for one VDM coefficient (" a ") across all breasts. The second VDM coefficient (" b ") showed diagnostic potential with breast segments having consistent coefficients in healthy breasts. In cancerous breasts " b " coefficients were found to be statistically different in segments containing and adjacent to the tumor compared with the segment furthest from the tumor with p < 0.02 using the Student t-Test. Large discrepancies in " b " coefficients were found to be indicative of a tumor with a 14.5% tolerance resulting in sensitivity and specificity of 76.9%. The optimal breast configuration resulted in an area under the ROC curve (AUC) of 0.81 with sensitivity and specificity at 77% and 72%, respectively.

CONCLUSION

This VDM method enables a computationally simple diagnostic technique using DIET for comfortable breast screening for women of all ages. Regular screening potential allows for tolerance alteration based on age, prior subject-specific results, and other risk factors to manage false positives, reducing psychological harm while optimizing early detection for successful treatment and decreased mortality.

Breast Arterial Calcification: A Potential Biomarker for Atherosclerotic Cardiovascular Disease Risk?

PURPOSE OF REVIEW

We aimed to summarize the current evidence regarding the association between breast arterial calcification (BAC) and atherosclerotic cardiovascular disease (ASCVD) in women and discuss the potential role of BAC in the risk stratification and preventive approaches for ASCVD.

RECENT FINDINGS

BAC has emerged as a potential women-specific risk marker for ASCVD. Although BAC presents as a medial calcification of the arteries, notably different from the intimal atherosclerotic process, current evidence supports a correlation between BAC and ASCVD risk factors or subclinical and clinical ASCVD, such as coronary artery disease or stroke. As millions of women undergo mammograms each year, the potential clinical application of BAC in enhanced ASCVD risk estimation, with no additional cost or radiation, has tremendous appeal. Although further research regarding optimal risk assessment and management in women with BAC is required, the presence of BAC should prompt healthy cardiovascular lifestyle modifications.

Advanced and futuristic approaches for breast cancer diagnosis

Background

Breast cancer is the most frequent cancer and one of the most common causes of death in women, impacting almost 2 million women each year. Tenacity or perseverance of breast cancer in women is very high these days with an extensive increasing rate of 3 to 5% every year. Along with hurdles faced during treatment of breast tumor, one of the crucial causes of delay in treatment is invasive and poor diagnostic techniques for breast cancer hence the early diagnosis of breast tumors will help us to improve its management and treatment in the initial stage.

Main body

Present review aims to explore diagnostic techniques for breast cancer that are currently being used, recent advancements that aids in prior detection and evaluation and are extensively focused on techniques that are going to be future of breast cancer detection with better efficiency and lesser pain to patients so that it helps to a physician to prevent delay in treatment of cancer. Here, we have discussed mammography and its advanced forms that are the need of current era, techniques involving radiation such as radionuclide methods, the potential of nanotechnology by using nanoparticle in breast cancer, and how the new inventions such as breath biopsy, and X-ray diffraction of hair can simply use as a prominent method in breast cancer early and easy detection tool.

Conclusion

It is observed significantly that advancement in detection techniques is helping in early diagnosis of breast cancer; however, we have to also focus on techniques that will improve the future of cancer diagnosis in like optical imaging and HER2 testing.

Errors in Mammography Cannot be Solved Through Technology Alone

Mammography has been the frontline screening tool for breast cancer for decades. However, high error rates in the form of false negatives (FNs) and false positives (FPs) have persisted despite technological improvements. Radiologists still miss between 10% and 30% of cancers while 80% of woman recalled for additional views have normal outcomes, with 40% of biopsied lesions being benign. Research show that the majority of cancers missed is actually visible and looked at, but either go unnoticed or are deemed to be benign. Causal agents for these errors include human related characteristics resulting in contributory search, perception and decision-making behaviours. Technical, patient and lesion factors are also important relating to positioning, compression, patient size, breast density and presence of breast implants as well as the nature and subtype of the cancer itself, where features such as architectural distortion and triple-negative cancers remain challenging to detect on screening. A better understanding of these causal agents as well as the adoption of technological and educational interventions, which audits reader performance and provide immediate perceptual feedback, should help. This paper reviews the current status of our knowledge around error rates in mammography and explores the factors impacting it. It also presents potential solutions for maximizing diagnostic efficacy thus benefiting the millions of women who undergo this procedure each year.

Radioactive Seed Localization Program for Patients With Nonpalpable Breast Lesions

Without early diagnosis and treatment, many lives are lost to breast cancer. Increased breast cancer awareness has facilitated research to guide health care providers toward improving patient outcomes. Research in diagnostic and treatment modalities has expanded to focus on improving the quality of life for patients with breast cancer who are living longer than expected. Providers can offer patients with nonpalpable breast lesions new screening techniques and improved treatment options, including radioactive seed localization lumpectomy. This treatment offers patients the potential for decreased tumor re-excision for positive margins near the surgical site, a lower volume of excised breast tissue, decreased operative time, convenient surgical scheduling, and less pain. Additionally, radioactive seed localization lumpectomy can improve patient and staff member satisfaction.

A comparison of two digital mammography systems: are there any differences?

AIM

To compare the performance of two newly introduced digital mammography technologies (Sectra and Hologic) to the Welsh breast-screening service; specifically, whether there are differences in the number, type, size, and grade of tumour identified.

MATERIALS AND METHODS

This was a retrospective study of a prospectively collected database of 50,000 consecutive screening episodes from 2012; clients were aged 49-88 years (mean 61.9 years). All studies were double-blind read by two readers. All tumours identified in the two arms of the study were detailed and compared specifically with regards to type (ductal or lobular) size, grade, and whether invasive or non-invasive. Performance was analysed for any statistically significant differences.

RESULTS

Twenty-five thousand consecutive women were screened with Hologic (recall rate 5.9% of which 18% were cancer) and 25,000 were screened with Sectra digital mammography (recall rate 4.3% and 22% were cancer). Five hundred tumours were found with no significant difference in invasive cancer detection or between ductal or lobular subtypes. The Hologic system detected 267 tumours; of which 81 (30.33%) were non-invasive (3.24 per 1000), compared to the Sectra system with 233 cancers overall including 36 non-invasive (15.45%, 1.44 per 1000). The difference in non-invasive lesions (mainly ductal carcinoma in situ [DCIS]) detection was significant (p<0.001); 38% of which were high nuclear grade (HNG) using Hologic and 50% HNG lesions using Sectra. There was no significant difference in non-invasive size between the two technologies. The mean glandular dose received using the Sectra system was significantly less (0.7 mGy) compared to the Hologic system (1.6 mGy) for a 50-60 mm breast thickness.

CONCLUSIONS

Population breast screening is frequently criticised for identifying lesions irrelevant to long-term outcomes or life expectancy and although the two systems seem comparable in terms of invasive cancer detection, a statistically significant difference in the detection of non-invasive lesions was seen, not reported in previous studies. This is a contentious issue, as identifying more DCIS has the potential to over-diagnose screened women leading to increased morbidity, higher "cancer detection rates", longer cancer waiting times, and reduced patient psychological wellbeing. The Sectra system is able to deliver a similar invasive detection cancer delivering a much lower dose mammogram, which is important in limiting overall population radiation dose. Further study as to whether the differences in tumour detection rates are clinically significant long term are now required.