数字化乳腺断层合成摄影及其联合人工智能技术在乳腺癌筛查中的研究进展

乳腺癌是我国女性发病率第一的恶性肿瘤。由于我国女性乳腺多属于致密型乳腺, 而乳腺X线摄影筛查对致密型乳腺中非钙化病变检出灵敏度较低, 数字化乳腺断层合成摄影(DBT)虽然能够减少致密乳腺组织中对病变的掩盖, 提高乳腺癌的检出率并降低召回率, 但DBT具有图像数量多导致医师阅片时间延长的局限性。基于此, 人工智能技术联合DBT应用于乳腺癌筛查应用前景广泛。该文就DBT以及DBT联合人工智能技术在乳腺癌筛查中的应用价值和研究进展进行综述。     

数字乳腺断层X线成像技术在乳腺癌筛查中的应用

【摘要】乳腺影像检查是降低乳腺癌死亡率的有效方法,数字乳腺断层融合X 线成像（DBT）作为近年来新出现的影像成像技术,大大提高了乳腺癌筛查的敏感度和特异度。本文就DBT与传统乳腺X线摄影检查的对比研究、在致密型与非致密型乳腺中的应用、诊断早期与浸润性乳腺癌的效能以及其目前存在的局限性等方面进行综述,旨在提高对乳腺癌的诊断,为DBT技术的发展实践提供策略。     

致密型乳腺影像学筛查技术及进展

乳腺癌是女性最常见的恶性肿瘤之一,其死亡率居女性恶性肿瘤的第6位,严重影响女性健康[1]。早期发现和治疗是降低乳腺癌死亡率、改善乳腺癌患者治疗效果及生活质量的关键。乳腺癌筛查是早期发现乳腺癌的重要措施。乳腺 X 线摄影(mammography, MAM)是乳腺癌筛查的主要手段,但对致密型乳腺其敏感性降低。我国女性多为致密型乳腺,且乳腺癌发病年龄较欧美年轻化,而腺体密度与年龄呈负相关,故MAM用于我国女性乳腺癌筛查的检测灵敏度较欧美国家降低。这对我国乳腺癌筛查工作提出了更艰巨的挑战,以下就目前国际上用于致密型乳腺的影像学筛查技术及其进展进行综述。     

MRI对X线上致密型乳腺中乳腺癌的诊断价值

目的:探讨致密型乳腺中乳腺癌MRI表现,以组织病理学为标准,与非致密型乳腺中乳腺癌作对照分析。方法:2009年3月至2010年3月来我院完成乳腺MRI及X线摄影检、病理组织学诊断为乳腺癌的连续180例病人纳入研究,年龄28～85岁,平均54.4岁;按X线摄影上纤维腺体组织密度分型标准将入组病例分为致密型和非致密型,并对两组的乳腺癌MRI表现进行对比分析,进一步归纳出致密型中乳腺癌的MRI特点。结果:致密型乳腺77例,其中浸润性导管癌66例、导管内癌(DCIS)8例及其他病理类型3例;非致密型乳腺103例,其中浸润性导管癌85例、导管内癌(DCIS)7例及其他病理类型11例。致密型乳腺中乳腺癌平均直径2.3cm,明显大于非致密型乳腺中乳腺癌的平均直径(1.9cm)(P=0.011);致密型乳腺中肿块样强化的乳腺癌边缘毛刺或模糊者约71.7%(43/60),较非致密型乳腺(54.0%,47/87)更易表现为边缘不光滑(P=0.031);致密型乳腺组浸润性导管癌病理分级高于非致密型乳腺组(P=0.009);致密型乳腺组患者平均年龄(47.2岁)较非致密型乳腺组(60.1岁)年轻(P<0.01)。结论:致密型乳腺中乳腺癌较非致密型乳腺中的病变范围更大,乳腺癌更易表现为边缘毛糙,且在病理学上乳腺癌的病理分级更高。     

乳腺X线致密度与激素受体和人表皮生长因子受体2的相关性探讨

目的探讨乳腺X线致密度与乳腺癌中雌激素受体、孕激素受体及人表皮生长因子受体2之间是否具有相关性。方法回顾性收集了615例经手术证实的原发性乳腺癌患者。就诊时均行乳腺X线摄影,并根据美国放射学会制定的乳腺影像报告及数据系统(BI-RADS)对乳腺X线致密度进行分型。所有病例术后或穿刺后标本均行免疫组织化学染色检测雌激素受体、孕激素受体及人表皮生长因子受体2表达水平,并分析乳腺X线致密度与激素受体、HER2表达及年龄因素之间的相关性。结果乳腺X线致密度随年龄增长逐渐由高向低过渡(r=-0.529,P<0.001)。乳腺X线致密度与孕激素受体表达呈正相关(r=0.099,P=0.014<0.05),与雌激素受体(r=0.016,P=0.699>0.05)及人表皮生长因子受体2表达(r=0.077,P=0.057>0.05)未见明显相关性。结论乳腺X线致密度与乳腺癌孕激素受体表达呈正相关,与患者发病年龄呈负相关。     

数字化乳腺摄影在乳腺癌筛查中的作用：一项超过800万韩国女性的对比研究

正在乳腺癌筛查中,全数字化乳腺X线摄影(FFDM)优于传统的屏-片乳腺摄影(SFM)已得到公认,尤其对于年龄50岁或致密型乳腺的妇女。目的评价FFDM筛查乳腺     

基于深度学习的乳腺X线摄影的临床应用价值

乳腺X线摄影是乳腺癌筛查的有效手段,但具有一定局限性。人工智能（AI）具有提取图像特征并分析的强大能力,是推动未来智能医学影像进步的核心技术。近年来深度学习（DL）在乳腺X线摄影上的应用迅速发展,能够提高医生的工作效率、诊断准确率并降低漏诊率。对基于DL的乳腺X线摄影在乳腺癌筛查、临床诊断及风险评估中的应用价值和发展前景予以综述与展望。     

数字乳腺断层摄影及其合成二维影像技术在乳腺癌筛查中的研究进展

目前乳腺X线检查仍是乳腺癌早期诊断的有效检查方法之一,主要包括全视野数字化乳腺摄影（FFDM）、数字乳腺断层摄影（DBT）、合成乳腺X线摄影（SM）以及3种技术的联合应用（FFDM联合DBT、SM联合DBT）。对DBT、SM和SM联合DBT在乳腺筛查中诊断效能、影像质量及辐射剂量等进行比较。SM联合DBT可有效平衡辐射剂量和诊断效能,但仍然在判读时间、信息的存储与传输和检查成本方面存在局限性。就以上3种检查技术在乳腺癌筛查中的研究进展予以综述。     

致密型乳腺对乳腺癌的影响及其补充筛查

【摘要】目前数字乳腺断层摄影（DBT）已逐渐替代传统乳腺钼靶。超声联合乳腺钼靶用以探查其他早期的、侵袭性乳腺癌，然而缺少熟练操作者、对操作者的依赖限制了其广泛应用。自动乳腺全容积成像（ABVS）是一种有应用前景的技术，但其仍有处理时间长和假阳性率高的问题。对高风险女性进行对比增强磁共振成像（CE-MRI）补充筛查可减少晚期癌的发生率，减少MRI扫描序列可以降低检查成本，增加其可操作性。对比增强数字乳房X线照相术（CESM）和分子乳腺成像（MBI）可提高癌症检出率，但是需要进一步筛查和直接活检证实其准确性。本文回顾了致密型乳腺对乳腺癌的影响及致密型乳腺筛查的临床应用新进展，旨在提高致密型乳腺癌症的检出率。     

数字乳腺断层摄影诊断乳腺癌现状

乳腺癌严重威胁女性健康,乳腺摄影是早期检出肿瘤的方法之一。数字乳腺断层摄影（DBT）能够克服全数字化乳腺摄影（FFDM）因组织重叠而影响病变观察的问题,降低复检率,减少不必要的活检,提高癌灶的检出率。对于致密型乳腺,DBT可以减少＂假阳性＂的检出,降低乳腺癌筛查的成本,提高诊断的准确性。     

The incremental contribution of clinical breast examination to invasive cancer detection in a mammography screening program

OBJECTIVE: The objective of this study was to determine the potential added contribution of clinical breast examination (CBE) to invasive breast cancer detection in a mammography screening program, by categories of age and breast density. SUBJECTS AND METHODS: We prospectively followed 61,688 women aged 40 years or older who had undergone at least one screening examination with mammography and CBE between January 1, 1996, and December 31, 2000, for 1 year after their mammogram for invasive cancer. We computed the incremental sensitivity, specificity, and positive predictive value of CBE over mammography alone for combinations of age and breast density (predominantly fatty or dense). RESULTS: Mammography sensitivity was 78% and combined mammography-CBE sensitivity was 82%, thus CBE detected an additional 4% of invasive cancers. CBE detected a minority of invasive cancers compared with mammography for all age groups and all breast densities. Sensitivity increased from adding CBE to screening mammography for all ages, from 6.8% in women ages 50-59 with dense breasts to 1.8% in women ages 60-69 years with fatty breasts. CBE generally added incrementally more to sensitivity among women with dense breasts. Specificity and positive predictive value declined when CBE was used in conjunction with mammography, and this decrement was more pronounced in women with dense breasts. CONCLUSION: CBE had modest incremental benefit to invasive cancer detection over mammography alone in a screening program, but also led to greater risk of false-positive results. These risks and benefits were greater in women with dense breasts. The balance of risks and benefits must be weighed carefully when evaluating the inclusion of CBE in a screening examination.     

Effect of age and breast density on screening mammograms with false-positive findings

OBJECTIVE: The objective of this study was to examine the effect of breast density and age on screening mammograms with false-positive findings. MATERIALS AND METHODS: The study sample was taken from the Washington State Mammography Tumor Registry, which links data from participating radiologists with the Puget Sound Cancer Surveillance System and the Washington State Cancer Registry. Participants (n = 73,247) were women 35 years old and older who underwent screening mammography for which an assessment and a four-category density rating were coded. A total of 46,340 mammograms were sampled to avoid interpreter bias. In this study of false-positive mammograms, only women with no diagnosis of breast cancer within 12 months of the index mammogram were included. Logistic regression was used to estimate the odds ratios of a false-positive mammogram being associated with each category of breast density or age, adjusting for the other factor as a covariate. RESULTS: After controlling for breast density, we found that the risk of a false-positive mammogram was not affected by age (p = 27). However, the trend of increasing risk of a false-positive mammogram with increasing breast density was highly significant (p < .001). Women with extremely dense breast tissue were almost two times more likely to have a false-positive mammogram than were women with fatty breast tissue. This effect persisted after controlling for age. CONCLUSION: Breast density, not age, is an important factor when predicting risk of a false-positive mammogram. Breast density should be considered when educating individual women on the risks and benefits of screening mammography.     

Clinical utility of bilateral whole-breast US in the evaluation of women with dense breast tissue.

PURPOSE: To evaluate the clinical utility of bilateral whole-breast ultrasonography (US) as an adjunct examination to mammography in asymptomatic women with dense (Breast Imaging Reporting and Data System [BI-RADS] density category 3 or 4) breast tissue. MATERIALS AND METHODS: Between July 1998 and April 2000, 1,862 patients with negative findings at clinical examinations, negative mammographic results, and breast tissue with BI-RADS category 3 or 4 density were evaluated with bilateral whole-breast US for occult cystic and solid masses, areas of architectural distortion, and acoustic shadowing. Suggestive findings were compared with tissue diagnoses from US-guided core biopsy specimens. US was initially performed by a US or a mammography technologist. The average time to perform the examination was approximately 10 minutes. Abnormal findings were corroborated by a fellowship-trained breast-imaging radiologist. RESULTS: In the 1,862 women examined with bilateral whole-breast US, 57 biopsies were recommended in 56 patients; follow-up data were available in 51 of the 56 patients. Six breast cancers were detected (cancer detection rate, 0.3%). CONCLUSION: Bilateral whole-breast US, when performed in patients with dense (BI-RADS category 3 or 4 density) breast tissue, is useful in detecting breast cancer not discovered with mammography or clinical breast examination. The 0.3% cancer detection rate compares favorably with that of screening mammography and with that in previously published studies involving bilateral whole-breast US.     

Impact of the New Jersey Breast Density Law on Imaging and Intervention Volumes and Breast Cancer Diagnosis

PurposeIncreased breast density is acknowledged as an independent risk factor for breast cancer and may obscure malignancy on mammography. Approximately half of all mammograms depict dense breasts. Legislation related to mandatory breast density notification was first enacted in Connecticut in 2009. On May 1, 2014, New Jersey joined other states with similar legislation. The New Jersey breast density law (NJBDL) mandates that mammography reports acknowledge the relevance and masking effect of mammographic breast density. The aim of this study was to assess the impact of the NJBDL at one of the state’s largest ACR-accredited breast centers.MethodsA retrospective chart review was performed to determine changes in imaging and intervention utilization and modality of cancer diagnosis after enactment of the legislation. Data for the present study were extracted from a review of all patients with core biopsy–proven malignancy at a large outpatient breast center between November 1, 2012, and October 31, 2015. Data were divided into the 18-month period before the implementation of the NJBDL (November 1, 2012 to April 30, 2014) and the 18-month period after passage of the law (May 1, 2014 to October 31, 2015).ResultsScreening ultrasound increased significantly after the implementation of the NJBDL, by 651% (1,530 vs 11,486). MRI utilization increased by 59.3% (2,595 vs 4,134). A total of 1,213 cancers were included in the final analysis, 592 in the first time period and 621 after law implementation. Breast cancer was most commonly detected on screening mammography, followed by diagnostic mammography with ultrasound for palpable concern, in both time periods. Of the 621 cancers analyzed, 26.1% (n = 162) were found in patients 50 years of age or younger. Results demonstrated that with respect to how malignancies were detected, age and average mammographic density were both statistically significant (P = .002).ConclusionsThe NJBDL succeeded in publicizing the masking effect of dense breasts. The number of supplemental screening ultrasound and MRI examinations increased after the implementation of this legislation. An efficacy analysis affirmed the high sensitivity of screening MRI compared with other modalities. The use of MRI increased core biopsy efficiency and reduced the number of biopsies needed per cancer diagnosed.     

Invasive cancers detected after breast cancer screening yielded a negative result: relationship of mammographic density to tumor prognostic factors

PURPOSE: To evaluate common breast tumor prognostic characteristics, including estrogen receptor (ER) status, grade, size, and method of detection, in relationship to mammographic density. MATERIALS AND METHODS: The study involved 121 women who had negative results at both screening mammography and breast physical examination within 17 months before a diagnosis of breast cancer. Mammographic density was classified according to Breast Imaging Reporting and Data System patterns 1 through 4 (where 1 indicates a fatty breast and 4 indicates a dense breast). Axillary nodal status and tumor histologic ER status, histologic grade, size, stage, and method of detection (mammography alone, palpation alone, or both palpation and mammography) were analyzed by density category and tested for statistically significant differences across categories by using analysis of variance. RESULTS: Statistically significant differences (P <.05) by density category were found for the following variables: ER positivity (15 of 15 tumors in category 1 breasts, 32 of 41 tumors in category 2 breasts, 37 of 49 tumors in category 3 breasts, and eight of 16 tumors in category 4 breasts were ER positive), occurrence of grade 1 tumors (eight, 11, 19, and four tumors in category 1, category 2, category 3, and category 4 breasts, respectively, were grade 1), mean tumor size (11.3, 13.0, 14.7, and 19.7 mm for category 1, category 2, category 3, and category 4 breasts, respectively), detection with mammography alone (13, 31, 36, and four tumors in category 1, category 2, category 3, and category 4 breasts, respectively, were detected with mammography alone), and occurrence of stage I tumors (10, 25, 28, and five tumors in category 1, category 2, category 3, and category 4 breasts, respectively, were stage I). CONCLUSION: In women with negative results at clinical and mammographic screening within 17 months before breast tumor detection, subsequently diagnosed cancers tend to be ER negative, of higher grade, and larger in size in those with dense tissue patterns than in those with fat patterns.     

Improved breast cancer detection in asymptomatic women using 3D-automated breast ultrasound in mammographically dense breasts

Automated breast ultrasound (ABUS)was performed in 3418 asymptomatic women with mammographically dense breasts. The addition of ABUS to mammography in women with greater than 50% breast density resulted in the detection of 12.3 per 1,000 breast cancers, compared to 4.6 per 1,000 by mammography alone. The mean tumor size was 14.3 mm and overall attributable risk of breast cancer was 19.92 (95% confidence level, 16.75 - 23.61) in our screened population. These preliminary results may justify the cost-benefit of implementing the judicious us of ABUS in conjunction with mammography in the dense breast screening population.     

Staying abreast of imaging – Current status of breast cancer detection in high density breast

ObjectivesThe aim of this paper is to illustrate the current status of imaging in high breast density as we enter a new decade of advancing medicine and technology to diagnose breast lesions.Key findingsEarly detection of breast cancer has become the chief focus of research from governments to individuals. However, with varying breast densities across the globe, the explosion of breast density information related to imaging, phenotypes, diet, computer aided diagnosis and artificial intelligence has witnessed a dramatic shift in new screening recommendations in mammography, physical examination, screening younger women and women with comorbid conditions, screening women at high risk, and new screening technologies. Breast density is well known to be a risk factor in patients with suspected/known breast neoplasia. Extensive research in the field of qualitative and quantitative analysis on different tissue characteristics of the breast has rapidly become the chief focus of breast imaging. A summary of the available guidelines and modalities of breast imaging, as well as new emerging techniques under study that can potentially provide an augmentation or even a replacement of those currently available.ConclusionDespite all the advances in technology and all the research directed towards breast cancer, detection of breast cancer in dense breasts remains a dilemma.Implications for practiceIt is of utmost importance to develop highly sensitive screening modalities for early detection of breast cancer.     

Breast cancer detection using automated whole breast ultrasound and mammography in radiographically dense breasts

Purpose

Mammography, the standard method of breast cancer screening, misses many cancers, especially in dense-breasted women. We compared the performance and diagnostic yield of mammography alone versus an automated whole breast ultrasound (AWBU) plus mammography in women with dense breasts and/or at elevated risk of breast cancer.

Methods

AWBU screening was tested in 4,419 women having routine mammography (Trial Registration: ClinicalTrials.gov Identifier: NCT00649337). Cancers occurring during the study and subsequent 1-year follow-up were evaluated. Sensitivity, specificity and positive predictive value (PPV) of biopsy recommendation for mammography alone, AWBU and mammography with AWBU were calculated.

Results

Breast cancer detection doubled from 23 to 46 in 6,425 studies using AWBU with mammography, resulting in an increase in diagnostic yield from 3.6 per 1,000 with mammography alone to 7.2 per 1,000 by adding AWBU. PPV for biopsy based on mammography findings was 39.0% and for AWBU 38.4%. The number of detected invasive cancers 10 mm or less in size tripled from 7 to 21 when AWBU findings were added to mammography.

Conclusion

AWBU resulted in significant cancer detection improvement compared with mammography alone. Additional detection and the smaller size of invasive cancers may justify this technology’s expense for women with dense breasts and/or at high risk for breast cancer.     

Hormone replacement therapy and mammographic screening

The benefits of hormone replacement therapy (HRT) with oestrogen are well known and have led to widespread usage of HRT in post-menopausal women. There is an increased relative risk of breast cancer with prolonged HRT use of 1.7 at worst and this does not warrant more frequent screening. HRT itself makes mammographic screening less effective by adversely affecting both the sensitivity and specificity of screening mammography.A number of large studies have shown a reduction in the sensitivity of screening mammography of between 7% and 21% in current HRT users. This reduction in sensitivity is seen only in women over the age of 50 and is more marked when using single view mammography. The reduction in sensitivity is largely confined to those women who have a dense mammographic background pattern while on HRT. HRT use is also associated with a reduction in specificity of between 12% and almost 50%. This reduction in specificity is mainly found at incident screens. What can be done to minimize the adverse effects of HRT on mammographic screening? The imminent introduction of two views at all screens within the National Health Breast Screening Programme will be helpful. Short-term cessation of HRT use may deter attendance for screening by HRT users and is unproven. Combined oestrogen and progesterone preparations taken continuously appear to be particularly associated with adverse breast screening performance, while tibolone may have little effect on mammographic density. Manipulation of the type of HRT preparations used may allow the adverse effects of HRT on breast screening to be reduced.     

Impact of breast density on computer-aided detection for breast cancer

OBJECTIVE: Our aim was to determine whether breast density affects the performance of a computer-aided detection (CAD) system for the detection of breast cancer. MATERIALS AND METHODS: Nine hundred six sequential mammographically detected breast cancers and 147 normal screening mammograms from 18 facilities were classified by mammographic density. BI-RADS 1 and 2 density cases were classified as nondense breasts; BI-RADS 3 and 4 density cases were classified as dense breasts. Cancers were classified as either masses or microcalcifications. All mammograms from the cancer and normal cases were evaluated by the CAD system. The sensitivity and false-positive rates from CAD in dense and nondense breasts were evaluated and compared. RESULTS: Overall, 809 (89%) of 906 cancer cases were detected by CAD; 455/505 (90%) cancers in nondense breasts and 354/401 (88%) cancers in dense breasts were detected. CAD sensitivity was not affected by breast density (p=0.38). Across both breast density categories, 280/296 (95%) microcalcification cases and 529/610 (87%) mass cases were detected. One hundred fourteen (93%) of the 122 microcalcifications in nondense breasts and 166 (95%) of 174 microcalcifications in dense breasts were detected, showing that CAD sensitivity to microcalcifications is not dependent on breast density (p=0.46). Three hundred forty-one (89%) of 383 masses in nondense breasts, and 188 (83%) of 227 masses in dense breasts were detected-that is, CAD sensitivity to masses is affected by breast density (p=0.03). There were more false-positive marks on dense versus nondense mammograms (p=0.04). CONCLUSION: Breast density does not impact overall CAD detection of breast cancer. There is no statistically significant difference in breast cancer detection in dense and nondense breasts. However, the detection of breast cancer manifesting as masses is impacted by breast density. The false-positive rate is lower in nondense versus dense breasts. CAD may be particularly advantageous in patients with dense breasts, in which mammography is most challenging.