Mammography Procedures Research Articles

Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images

Breast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect early-stage cancer cells. This traditional method of mammography while valuable has limitations in its potential for false positives and negatives, patient discomfort, and radiation exposure. Therefore, there is a probe for more accurate techniques required in detecting breast cancer, leading to exploring the potential of machine learning in the classification of diagnostic images due to its efficiency and accuracy. This study conducted a comparative analysis of pre-trained CNNs (ResNet50 and VGG16) and vision transformers (ViT-base and SWIN transformer) with the inclusion of ViT-base trained from scratch model architectures to effectively classify mammographic breast cancer images into benign and malignant cases. The SWIN transformer exhibits superior performance with 99.9% accuracy and a precision of 99.8%. These findings demonstrate the efficiency of deep learning to accurately classify mammographic breast cancer images for the diagnosis of breast cancer, leading to improvements in patient outcomes.

Resilience in Healthcare: A Hospital-based Investigation of Breast Cancer Diagnostics Amid the Pandemic in Indonesia

Background: Widespread disruptions in healthcare services have occurred due to ongoing challenges during the pandemic. The tremendous impacts have struck countries with limited resources, greater distances of geographical access to healthcare services, and a shortage of healthcare personnel. Long delay of diagnosis and disruption in patient care affects the long-term prognosis of breast cancer. This study was conducted to investigate the effects of the COVID-19 pandemic and government-mandated social restrictions on the provision of diagnostic services for breast cancer patients in a tertiary referral hospital. The study aimed to explore how travel restrictions and patients' apprehension about COVID-19 exposure have contributed to notable declines in diagnostic and treatment procedures for breast cancer within this healthcare setting. Methods: This study was retrospective design and used a hospital registry to collect information on demographics, imaging, and pathology from January 2018 to September 2021. Breast ultrasound (US) and mammography data were collected from the Picture Archiving and Communication System (PACS), while pathology data were collected from e-medical records. The descriptive statistics of the annual total volume of imaging and pathological examinations were interpreted and statistics were only calculated for diagnostics mammography. Results: Between 2018 and 2021, the volume of monthly breast sonograms drastically decreased by 65% in 2020 and 2021 during the pandemic, while mammography significantly reduced by more than 40% from the 2019 levels. Breast US and mammography procedures were significantly lower during the first and second waves of the pandemic in March until May 2020 and June until September 2021, respectively. Although the proportion of breast ultrasound-guided fine-needle aspiration biopsy (FNAB) increased year by year, the number of FNAB for primary breast lesions significantly decreased by 84% in 2020 and 2021. Conclusions: We observed significant decreases in diagnostic procedures for breast cancer. Reconfiguration of breast cancer care scheduling is required to accommodate the potential for increased hospital visits after the travel restrictions.

Estimating Local Diagnostic Reference Levels for Mammography in Dubai.

As the total volume of mammograms in Dubai is increasing consistently, it is crucial to focus on the process of dose optimization by determining dose reference levels for such sensitive radiographic examinations as mammography. This work aimed to determine local diagnostic reference levels (DRLs) for mammography procedures in Dubai at different ranges of breast thickness. A total of 2599 anonymized mammograms were randomly retrieved from a central dose survey database. Mammographic cases for screening women aged from 40 to 69 years were included, while cases of breast implants and breast thickness outside the range of 20-100 mm were excluded. Mean, median, and 75 percentiles were obtained for the mean glandular dose (MGD) distribution of each mammography projection for all compressed breast thickness (CBT) ranges. The local DRLs for mammography in Dubai were found to be between 0.80 mGy and 0.82 mGy for the craniocaudal (CC) projection and between 0.89 mGy and 0.971.8 mGy for the mediolateral oblique (MLO) projection. Local DRLs were proposed according to different breast thicknesses, starting from 20 to 100 mm. All groups of CBT showed a slight difference in MGD values, with higher values in MLO views rather than CC views. The local DRLs in this study were lower than some other Middle Eastern countries and lower than the standard reference levels reported by the International Atomic Energy Agency (IAEA) at 3 mGy/view.

An investigation on protection properties of Tantalum (V) oxide reinforced glass screens on unexposed breast tissue for mammography examinations

IntroductionThe utilization of radiation shielding material positioned between the both breasts are crucial for the reduction of glandular dose and the safeguarding of the contralateral breast during mammographic procedures. This study proposes an alternative substance for shielding the contralateral breast from radiation exposure during mammography screening. MethodsIn this study, we present an analysis of the shielding effectiveness of transparent glass that has been doped with Tantalum (V) oxide encoded as BTZT6. The evaluation of this shielding material was conducted using the MCNPX code, specifically for the ipsilateral and contralateral breasts. The design of the left and right breast phantoms involved the creation of three-layer heterogeneous breast phantoms, consisting of varying proportions of glandular tissue (25%, 50%, and 75%). The design of BTZT6 and lead-acrylic shielding screens is implemented using the MCNPX code. The comparative analysis of dose outcomes is conducted to assess the protective efficacy of BTZT6 and lead-acrylic shielding screens. ResultsThe utilization of BTZT6 shielding material resulted in a reduction in both breast dose and skin dose exposure when compared to the lead-acrylic shield. ConclusionBased on the findings acquired, the utilization of BTZT6 shielding material screens during mammography procedures involving X-rays with energy levels ranging from 26 to 30 keV is associated with a decrease in radiation dose. Implications for practiceIt can be inferred that the utilization of BTZT6 demonstrates potential efficacy in mitigating excessive radiation exposure to the breasts and facilitating the quantification of glandular doses in mammography procedures.

Longitudinal Study of COVID-19 Impact on Breast Cancer Screening in Northwest Indiana

Background: During the COVID -19 pandemic, elective procedures such as mammography were suspended from late March to late April. Previous analyses done by Green and Han revealed that mammography screenings continued to be down in 2020 and 2021 from their baseline in 2019 prior to the pandemic. Continued efforts in monitoring how mammography screenings have been affected following the pandemic is crucial especially in understudied cities with predominantly black populations such as Gary, IN.
 Methods: Data was provided from “Hospital A” on 22,693 mammography encounters and this data was analyzed to determine how mammography screenings have changed after the suspension period. 
 Results: Following the lift on the suspension of elective procedures on April 27, 2020, there was a sharp increase of mammograms the following 8 weeks to near pre-pandemic levels. However, after this 8-week post suspension period of elective procedures on April 27, 2020, the weekly average began to decrease starting at the beginning of 2021. The weekly average went from 171 (SD 21.9) mammograms in 2019 to 108 (SD 40.0) mammograms in 2021. Furthermore, the weekly average has continued to decrease in 2022 with 101 (SD 46.8) mammograms.
 Conclusion: “Hospital A” successfully returned mammography procedures to pre-pandemic levels initially during the 8 weeks following the suspension on elective procedures. However, strategies should be implemented to mitigate the continuing decrease in mammography procedures following the COVID-19 pandemic.

Clinical prototype implementation enabling an improved day-to-day mammography compression

PurposeIn mammography, breast compression is achieved by lowering a compression paddle on the breast. Despite the directive that compression is needed, there is no concrete guideline on its execution. To estimate the degree of compression, current mammography units only provide compression force and breast thickness as parameters. Therefore, radiographers could be induced to mainly determine the level of compression based on compression force and apply the same value to all breast sizes. In this case, smaller breast sizes are exposed to higher pressure. This results in a highly varying perception of discomfort or even pain during the procedure, depending on the breast size. MethodsTo overcome this imbalance, current research results suggest that pressure might be a more qualified parameter for a more uniform compression among all breast sizes. To utilize pressure, the contact area between breast and compression paddle must be determined. In this paper, we present an easy-to-implement prototype enabling a real-time pressure-based measure without the need of direct patient contact. Using an optical camera, the contact area between the breast and the compression paddle is automatically segmented by a deep learning model. ResultsThe model provides a mean pixel accuracy of 96.7% (SD: 2.3%), mean frequency-weighted intersection over union of 88.5% (SD: 6.3%), and a Dice score of 93.6% (SD: 2.2%). The subsequent pressure display is updated more than five times per second which enables the use in clinical routines to set the compression level. ConclusionThis prototype could help guiding to an improved breast compression routine in mammography procedures.

Assessment of male patients’ average glandular dose during mammography procedure

Breast cancer is a common malignancy for females (25% of female cancers) and also has low incidence in males. It was estimated that 1% of all breast malignancies occur in males with mortality rate about 20%, with annual increase in incidence. Risk factors include age, family history, exposure to ionizing radiation and high estrogen and low of androgens hormones level. Diagnosis and screening are challenging due to limiting effectiveness of breast cancer screening. Therefore, patients may expose to ionizing radiation that may contribute in breast cancer incidence in males. In literature, limited studies were published regarding radiation exposure for males during mammography. The objective of this research is to quantify patient doses during male mammogram and to estimate the projected radiogenic risk during the procedure. In total, 42 male patients were undergone mammogram for breast cancer diagnosis during two consecutive years. The mean and range of patient age (years) is 45 (23–80). The mean and standard deviation (SD) of the peak tube potential and tube current time product are 28.64 ± 2. and 149 ± 35.1, respectively. The mean, and range of patients' entrance surface air kerma (ESAK, mGy) per single breast procedure was 5.3 (0.47–27.5). Male patient's received comparable radiation dose per mammogram compared to female procedures. With increasing incidence of male breast cancer, proper guidelines are necessary for the mammographic procedure are necessary to reduce unnecessary radiation doses and radiogenic risk.

Comparison of GLCM and First Order Feature Extraction Methods for Classification of Mammogram Images

Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values ​​in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.

Typical effective dose values from diagnostic and interventional radiology

Effective dose (E) in medical procedures is of practical value for comparing doses from different types of procedures which is not possible with the different measurable dose quantities. In this survey we estimated and compared the values of E in 12 medical imaging procedures. The mean E for conventional X-ray in mSv were ranged between 0.01 for skull lateral to 0.5 for abdominal while the mean E for cardiac interventional radiology in mSv was up to 16 for percutaneous transluminal coronary angioplasty (PTCA). For dental radiology the mean E in μSv was 1.2 for intraoral and 10 for panoramic. In mammography the mean E was 0.5 mSv. Compared with the literature, chest postero–anterior (PA), lumbar spine AP, PTCA and mammography procedures had shown larger E values. The obtained results can help in justification of techniques.

Automated Assessment of Breast Positioning Quality in Screening Mammography.

Simple SummaryInadequate breast positioning quality is the main cause behind misdiagnosis of breast cancer in screening mammography. For this reason, the first step before any cancer diagnosis is to ensure that the acquired mammograms have adequate breast positioning quality according to predefined criteria. If this is not the case, the patient must return for a new mammography. In this study, we proposed an approach for an automatic assessment of breast positioning quality in screening mammography using Convolutional Neural Networks. Eventually, this approach is not intended to replace radiology technicians, but rather to assist them in identifying inadequately positioned mammograms in real time, reduce the number of returned patient and improve the efficiency of cancer detection. For each predefined criterion, a specific convolutional neural network was separately trained and then combined into an overall system that predicts whether the breast is well positioned or not, achieving an efficient accuracy of 96.5% for craniocaudal and 93.3% for mediolateral oblique images. Our approach differs from already available studies and commercial tools by taking into account more useful breast positioning criteria that have to be considered by the expert, and thus providing a more holistic assistance.Screening mammography is a widely used approach for early breast cancer detection, effectively increasing the survival rate of affected patients. According to the Food and Drug Administration’s Mammography Quality Standards Act and Program statistics, approximately 39 million mammography procedures are performed in the United States each year. Therefore, breast cancer screening is among the most common radiological tasks. Interpretation of screening mammograms by a specialist radiologist includes primarily the review of breast positioning quality, which is a key factor affecting the sensitivity of mammography and thus the diagnostic performance. Each mammogram with inadequate positioning may lead to a missed cancer or, in case of false positive signal interpretation, to follow-up activities, increased emotional burden and potential over-therapy and must be repeated, requiring the return of the patient. In this study, we have developed deep convolutional neuronal networks to differentiate mammograms with inadequate breast positioning from the adequate ones. The aim of the proposed automated positioning quality evaluation is to assist radiology technologists in detecting poorly positioned mammograms during patient visits, improve mammography performance, and decrease the recall rate. The implemented models have achieved 96.5% accuracy in cranio-caudal view classification and 93.3% accuracy in mediolateral oblique view regarding breast positioning quality. In addition to these results, we developed a software module that allows the study to be applied in practice by presenting the implemented model predictions and informing the technologist about the missing quality criteria.

The Impact of the COVID-19 Pandemic on Medical Imaging Case Volumes in Aseer Region: A Retrospective Study.

COVID-19 has had a significant impact on global health systems. The aim of this study was to evaluate how imaging volumes and imaging types in radiology departments have been affected by the COVID-19 pandemic across different locations. Methods: Imaging volumes in the Aseer region (in the south of Saudi Arabia) across main hospitals were reviewed retrospectively including all cases referred from different locations (outpatient, inpatient and emergency departments). Data for years 2019 and 2020 were compared. The mean monthly cases were compared using a t-test. Results: The total imaging volumes in 2019 were 205,805 compared to 159,107 in 2020 with a 22.7% overall reduction. A substantial decline was observed in both the April to June and the July to September periods of approximately 42.9% and 44.4%, respectively. With respect to location, between April and June, the greatest decline was observed in outpatient departments (76% decline), followed by emergency departments (25% decline), and the least impact was observed in inpatient departments, with only 6.8% decline over the same period. According to modality type, the greatest decreases were reported in nuclear medicine, ultrasound, MRI, and mammography, by 100%, 76%, 74%, and 66%, respectively. Our results show a statistically significant (p-value 0.05) decrease of cases in 2020 compared to 2019, except for mammography procedures. Conclusion: There has been a significant decline in radiology volumes due to COVID-19. The overall reduction in radiology volumes was dependent on the stage/period of lockdown, location, and imaging modality.

Cost-effectiveness of screening mammography in a low income country: a Markov simulation analysis

BackgroundBreast cancer is the most common cancer diagnosed in women. Screening mammography is the only imaging screening study for breast cancer with a proven. mortality benefit. This study aims to analyze the cost-effectiveness of screening mammography in Ethiopia.MethodsMultistate Markov model was used for computer simulation to estimate cost and health benefits of screening mammography interventions for age-group of 40–49 years and 50–59 years. The cost-effectiveness analysis was made for 4 policies based on where the screening mammography procedures were conducted: government institution only, the private institution only, 50% ratio for each, and 10% private institution policy. Outputs were expressed in total cost, life-years gained (LYG) incremental cost-effectiveness ratio (ICER), and incremental net monetary benefit (INMB).ResultsAll 4 policies of annual screening mammography failed to achieve acceptable ICER and lead to a net loss in INMB. The lowest ICER value was for government institution-only policy with 3510.3 USD/LYG and 3224.9 USD/LYG both above the cost-effectiveness threshold of 2808.5 USD. The cost per single death averted for each group was 110,206.7 USD and 77,088.2 USD for age-group 40–49 years and 50–59 years respectively.ConclusionScreening mammography could not be shown to be cost-effective in Ethiopia with the current low cost-effectiveness threshold. Alternative screening approach like annual clinical breast examination may need to be investigated.

Radiation doses and potential cancer risks during mammography procedures at southern Saudi Arabia

Radiation doses and potential cancer risks during mammography procedures at southern Saudi Arabia

Radiation doses and potential cancer risks during mammography procedures at southern Saudi Arabia

Department of Radiological Sciences, Applied Medical Sciences College, Najran University, Najran, Saudi Arabia , mohamedrick@gmail.com

Evaluation of patients radiation dose during mammography imaging procedure

This study investigates patients’ dose levels during digital mammography procedures and proposes a local diagnostic reference level (DRL). The patient sample is 1055 patients who have been examined at the Riyadh Care Hospital, Riyadh, Saudi Arabia. All procedures were carried out for medically justified clinical conditions. All procedures were carried out using a direct digital mammography (DDR) radiology system. The mean and range of ESAK (mGy) were 5.19 ± 3.18 (0.33–29.9), while the mean AGD (mGy) is 1.3±(1.0–7.2) per procedure. The third quartile value for ESAK (mGy) and AGD (mGy) is 6 and 1.5, respectively. Measured ESAK (mGy) per procedure and estimated AGD are comparable with previous studies. The interpatient and interdepartmental variation is attributed mainly to the number of projections per procedure.

The lateral arm device for mammographic breast procedures: overview of its uses, safety, and efficacy

ABSTRACT Introduction: Percutaneous image-guided biopsy is the procedure of choice for diagnosing suspicious abnormalities on breast imaging. Stereotactic, ultrasound, and magnetic resonance imaging are used for image-guided breast biopsies. Stereotactic guidance uses mammography to localize lesions and facilitate placement of a core biopsy needle. The first systems used a vertical-approach needle insertion. The lateral arm device, which is the most recent advancement in stereotactic biopsies and pre-surgical localization allows procedures to be performed using a needle insertion parallel to the compression plate. Areas covered: The lateral arm device was introduced to the market in 2007 and is the first device of its kind. In this article we review the mechanism of this device, the risks and benefits of the device and other the different other modalities utilized to biopsy and localize the breast. We summarize the current literature on this device along with our own experiences utilizing this device. Expert opinion: The lateral arm device has changed the face of stereotactic-guided breast biopsies and localizations by allowing a new approach to perform these procedures. It has improved care to patients by allowing us to get to areas previously not within the biopsy window, decreased biopsy time and increased patient throughput.

Does the use of self-compression in mammography affect compression force, breast thickness, and mean glandular dose?

PurposeThe purpose of the study was to investigate whether the use of self-compression in craniocaudal (CC) projection has an effect on compression force, breast thickness, radiation dose and image quality compared to the standard mammographic procedure. MethodsThe study was conducted on 200 female patients that were referred for mammographic imaging. Patients were randomly divided into two equal groups. In the first group, self-compression was performed on the right breast and in the second group on the left breast. The data about compression force (N), breast thickness (mm), and mean glandular dose (MGD; mGy) were collected. In addition, the differences in the mentioned variables according to the side of self-compression were compared. All mammographic images were evaluated by two experienced radiologists according to the criteria established by the European Commission. ResultsThe use of self-compression resulted in a significant increase in compression force by 21.7 % (19.8 N) and a significant reduction of breast thickness by 5% (2.43 mm) and MGD by 6.3 % (0.09 mGy), respectively. There were no statistically significant differences based on the self-compression side, and no differences were observed in image quality assessment. ConclusionThis study demonstrates that the imaging protocol in mammography of the CC projection can be adopted by the use of self-compression in order to achieve better results.

Reduction of scattered radiation dose by X-ray shielding during mammography

Scattered X-rays during mammography can cause undesired increased exposure to radiation during the generation of medical images, which could cause cancer because the breast is highly sensitive to radiation. Hence, to prevent indirect radiation to the contralateral breast tissue from scattered X-rays, a lead acrylic plate has been developed that can be placed between the two breasts during mammography procedures. However, there is a lack of studies assessing the reduction in the exposure dose to the breast using shielding tools, which would consequently reduce radiation to the surrounding organs during mammography. Thus, this study aimed to evaluate the usefulness of the breast shield for mammography, and the average glandular dose (AGD) was measured during craniocaudal (CC) projection mammography. The spatial dose, calculated as the distance from the imaging center in the direction of the contralateral breast; the surface dose, assessed using a thermoluminescence dosimeter (TLD) at the 5 points; and the exposure dose in the contralateral breast in the breast phantom were measured with and without the use of the shield. The measured AGD was 1.6 mGy, and the spatial dose from the imaging center and the surface dose to the contralateral breast were reduced by ~97% and ~93%, respectively, with X-ray shield use. Thus, the study outcomes suggest that using an inter-breast X-ray shield during mammography can effectively reduce indirect radiation from scattered X-rays to the contralateral breast tissue.

Evaluation of average glandular dose and investigation of the relationship with compressed breast thickness in dual energy contrast enhanced digital mammography and digital breast tomosynthesis

PurposeTo quantitatively assess the dose of Dual energy contrast enhanced digital mammography (CEDM) and digital breast tomosynthesis (DBT) and to investigate the relationship between average absorbed glandular dose (AGD), compressed breast thickness (CBT) and compression force (CF). Materials and methodsAll CEDM and DBT examinations were performed in cranio-caudal (CC) and medio-lateral oblique (MLO) view. Exposure parameters of 135 mammographic procedures that using AEC (automatic exposure control) mode were recorded. AGDs were calculated. Kruskal Wallis test was performed. ResultsCBT population ranged from 23 to 94 mm with a thickness median value of 52 mm in CC view and of 57 mm in MLO views. CEDM AGD median value was significatively lower than DBT AGD in each views (p << 0.01). AGD showed a positive correlation and linear regression with CBT for both CEDM and DBT while CF did not show a correlation and linear regression with AGD. The highest values were found for MLO view: R2 of 0.74 for CEDM and R2 of 0.61 for DBT. Kruskal Wallis test shows that there was a difference statistically significant between AGD values of CEDM and DBT in CC view respect to MLO views (p < 0.01). ConclusionsDose values of both techniques meet the recommendations for maximum dose in mammography. The results of the present study indicated that there was significant difference between AGD for CEDM and DBT exposure in different views (AGD in CC views had the lowest value) and that CBT could influence the AGD while CF was not correlated to AGD.

Estimated Average Glandular Dose for 1,828 Mammography Procedures in China: A Multicenter Study

ObjectiveTo understand the distribution of the average glandular dose (AGD) in mammography by investigating 1,828 exposure parameters of 8 mammography machines in three cities, by using random sampling. MethodsA survey of 8 mammography machines in three different cities, sampled using stratified random sampling methods, was performed, and 1,828 mammography exposure parameters were recorded. Incident air kerma (k) was measured by Quality-Assurance (QA) dosimeters, and AGD was calculated by series conversion coefficients based on a 3D detailed Monte Carlo breast model, published by Wang et al. ResultsThe distribution of compressed breast thickness (CBT) fitted a normal distribution, while that of AGD fitted a skewed distribution. The mean value of CBT in a medio-lateral oblique (MLO) view was about 5.6% higher than that in the craniocaudal (CC) view, with significant statistical difference; mean value of AGD and CBT in the sample was 1.3 mGy and 4.6 cm, respectively. The AGD trended upward with increasing CBT, similar to the results of other researches. ConclusionThe mean AGD and CBT levels in our study for mammography practice in China were 1.3 mGy and 4.6 cm, respectively. AGD is influenced by manufacturer-specific variation as machine response to CBT changes and target/filter combination. The present study can provide evidence for establishing a diagnostic reference level in China.