A Semiautonomous Deep Learning System to Reduce False Positives in Screening Mammography.

Purpose To evaluate the ability of a semiautonomous artificial intelligence (AI) model to identify screening mammograms not suspicious for breast cancer and reduce the number of false-positive examinations. Materials and Methods The deep learning algorithm was trained using 123 248 two-dimensional digital mammograms (6161 cancers) and a retrospective study was performed on three nonoverlapping datasets of 14 831 screening mammography examinations (1026 cancers) from two U.S. institutions and one U.K. institution (2008-2017). The stand-alone performance of humans and AI was compared. Human plus AI performance was simulated to examine reductions in the cancer detection rate, number of examinations, false-positive callbacks, and benign biopsies. Metrics were adjusted to mimic the natural distribution of a screening population, and bootstrapped CIs and P values were calculated. Results Retrospective evaluation on all datasets showed minimal changes to the cancer detection rate with use of the AI device (noninferiority margin of 0.25 cancers per 1000 examinations: U.S. dataset 1, P = .02; U.S. dataset 2, P < .001; U.K. dataset, P < .001). On U.S. dataset 1 (11 592 mammograms; 101 cancers; 3810 female patients; mean age, 57.3 years ± 10.0 [SD]), the device reduced screening examinations requiring radiologist interpretation by 41.6% (95% CI: 40.6%, 42.4%; P < .001), diagnostic examinations callbacks by 31.1% (95% CI: 28.7%, 33.4%; P < .001), and benign needle biopsies by 7.4% (95% CI: 4.1%, 12.4%; P < .001). U.S. dataset 2 (1362 mammograms; 330 cancers; 1293 female patients; mean age, 55.4 years ± 10.5) was reduced by 19.5% (95% CI: 16.9%, 22.1%; P < .001), 11.9% (95% CI: 8.6%, 15.7%; P < .001), and 6.5% (95% CI: 0.0%, 19.0%; P = .08), respectively. The U.K. dataset (1877 mammograms; 595 cancers; 1491 female patients; mean age, 63.5 years ± 7.1) was reduced by 36.8% (95% CI: 34.4%, 39.7%; P < .001), 17.1% (95% CI: 5.9%, 30.1%: P < .001), and 5.9% (95% CI: 2.9%, 11.5%; P < .001), respectively. Conclusion This work demonstrates the potential of a semiautonomous breast cancer screening system to reduce false positives, unnecessary procedures, patient anxiety, and medical expenses. Keywords: Artificial Intelligence, Semiautonomous Deep Learning, Breast Cancer, Screening Mammography Supplemental material is available for this article. Published under a CC BY 4.0 license.

Focal breast pain: imaging evaluation and outcomes.

OBJECTIVES: To determine the number and characteristics of cancers detected and the optimal imaging evaluation in women presenting with focal breast pain (FBP). MATERIALS AND METHODS: We performed a retrospective review of 4720 women who underwent imaging for FBP from 2001 to 2013. Women 18 and over with one or two foci of breast pain and no concurrent breast symptoms were included. 944 patients met criteria. We recorded the imaging work-up, presence and type of finding at the site of pain, BI-RADS® assessment, and pathological outcomes. Subsequent imaging and clinical follow up was recorded. RESULTS: Imaging evaluation consisted of sonogram alone in 286 women, mammogram alone in 231 women, and both in 427 women. 113 women had an imaging finding at the site of pain; 103 were designated benign or probably benign. 12 biopsies of corresponding findings were performed: 9 benign, 1 invasive lobular carcinoma, 1 invasive ductal carcinoma, 1 ductal carcinoma in situ. All three malignancies were seen mammographically; 2 had an ultrasound correlate. At initial evaluation, 4 incidental breast cancers were diagnosed remote from the site of FBP. All were seen on mammogram and 2 of 4 had an ultrasound correlate. On follow up evaluation, 9 cancers were diagnosed at the site of pain and 13 incidental cancers were diagnosed. CONCLUSION: FBP is rarely associated with malignancy. Targeted ultrasound may be deferred in women 40 and older with FBP, no other clinical findings, and a negative mammogram.

Palpable breast abnormalities in women under age 40.

Although the prevalence of malignancy in average risk women under age 40 presenting with a palpable breast abnormality is low, the management of benign-appearing palpable abnormalities remains controversial. This study assesses the imaging evaluation, subsequent management, and outcomes of women under age 40 presenting with a palpable area of concern. This study also evaluates the costs, utility, and outcomes of BI-RADS 3 assessment in this patient population. A single institution retrospective case review from July 2010 through June 2013 identified women under age 40 presenting with a new palpable breast abnormality. Diagnostic imaging evaluation was performed. BI-RADS assessments and recommendations were recorded prospectively. Outcome was determined by tissue diagnosis, 2 years of surveillance, or search of the hospital tumor registry. Performance measures were calculated. Among 1440 cases, 1052 were initially assessed as BI-RADS 1 or 2 (73.1%), 184 as BI-RADS 3 (12.8%), 182 as BI-RADS 4 (12.6%), and 22 as BI-RADS 5 (1.5%). In all, 30 breast malignancies were diagnosed (cancer yield 2.1%). All 30 cancers were initially categorized as BI-RADS 4 or 5. No BI-RADS 1, 2, or 3 findings proved malignant. The imaging evaluation sensitivity was 100%, specificity was 87.7%, and accuracy was 87.9%. The negative predictive value was 100% and the positive predictive value was 14.7%. Average risk women under age 40 presenting with a palpable abnormality have a low prevalence of breast cancer. Imaging evaluation has a high sensitivity and negative predictive value, thereby allowing for confident characterization and appropriate management recommendations. For palpable solid masses with benign imaging features in women under age 40, short-term interval follow-up with subsequent periodic imaging or clinical examination for a total of 2 years is a cost-effective and safe alternative to biopsy.

Evidence-Based Performance Measures: Quality Metrics for the Care of Patients Undergoing Breast Reconstruction.

The American Society of Plastic Surgeons commissioned the Breast Reconstruction Performance Measure Development Work Group to identify and draft quality measures for the care of patients undergoing breast reconstruction surgery. Two outcome measures were identified. The first desired outcome was to reduce the number of returns to the operating room following reconstruction within 60 days of the initial reconstructive procedure. The second desired outcome was to reduce flap loss within 30 days of the initial reconstructive procedure. All measures in this report were approved by the American Society of Plastic Surgeons Breast Reconstruction Performance Measures Work Group and the American Society of Plastic Surgeons Executive Committee. The Work Group recommends the use of these measures for quality initiatives, Continuing Medical Education, Maintenance of Certification, American Society of Plastic Surgeons' Qualified Clinical Data Registry reporting, and national quality reporting programs.

Is There an Association Between Bone Mineral Density and Mammographic Density? A Systematic Review.

INTRODUCTION: Both bone mineral density (BMD) and breast density are related to reproductive hormone levels. This suggests that BMD and breast density could be meaningfully associated, and serve as surrogate markers for breast cancer risk. However, few studies have investigated the association of BMD with percent mammographic density, making it difficult to draw meaningful conclusions. MATERIALS AND METHODS: We conducted a systematic review of studies published in electronic databases till April 2016 using the following search terms: "bone density," "bone mineral density," "mammographic breast density," "breast density," and "mammographic density." We identified 203 articles, of which 8 met the inclusion criteria for this review. RESULTS: BMD does not appear to be associated with percent mammographic density. BMD at the spine was weakly positively associated with percent mammographic density among postmenopausal women who were not hormone users, while BMD at the hip and legs was positively associated with percent mammographic density among premenopausal women. On the other hand, one study reported an inverse association of BMD at the spine and hip with percent mammographic density among perimenopausal women. CONCLUSION: In this review, we found no evidence of an association between BMD and percent mammographic density.

ACR Appropriateness Criteria Evaluation of the Symptomatic Male Breast.

Most male breast problems are benign, and men with typical symptoms of gynecomastia or pseudogynecomastia do not usually need imaging. When a differentiation between benign disease and breast cancer cannot be made on the basis of clinical findings or when the clinical findings are suspicious for breast cancer, imaging is indicated. Mammography is useful in both identifying cancer and obviating the need for biopsy in patients for whom a benign mammographic impression confirms the clinical impression. However, because of the relationship of breast cancer to increasing age, age-based protocols that do not include mammography have been developed. For men with an indeterminate palpable mass, begin with ultrasound if the patient is <25 years of age, because breast cancer is highly unlikely. Mammography should be performed if ultrasound is suspicious. For men ≥25 years of age or having a highly concerning physical examination, usually begin with mammography; ultrasound is useful if mammography is inconclusive or suspicious. The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every 3 years by a multidisciplinary expert panel. The guideline development and review include an extensive analysis of current medical literature from peer-reviewed journals, and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In instances in which evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment.

Pathologic outcomes of nonmalignant papillary breast lesions diagnosed at imaging-guided core needle biopsy.

PURPOSE: To determine the upstage rate from nonmalignant papillary breast lesions obtained at imaging-guided core needle biopsy (CNB) and if there are any clinical, imaging, or pathologic features that can be used to predict eventual upstaging to malignancy. MATERIALS AND METHODS: This retrospective case review was institutional review board approved and HIPAA compliant, with a waiver of informed consent. A database search (from January 2001 to March 2010) was performed to find patients with a nonmalignant papillary breast lesion diagnosed at CNB. Of the resulting 128 patients, 86 (67%) underwent surgical excision; 42 (33%) patients were observed with imaging, for a median observation time of 4.1 years (range, 1.0-8.6 years). Chart review was performed to determine pertinent features of each case. RESULTS: Fourteen of 128 patients were subsequently found to have malignancy at excision, for an upstage rate of 11%. Nine (7%) of the 128 patients were subsequently found to have atypia at excision. Comparisons between patients with upstaged lesions and patients whose lesions were not upstaged demonstrated patients with upstaged lesions to be slightly older (65 vs 56 years, P=.01), more likely to have a mass than calcifications at imaging (P=.03), and to have had less tissue obtained at biopsy (three vs five cores obtained, P=.02; 14- vs 9-gauge needle used, P<.01; no vacuum assistance used, P<.01). Most strongly predictive of eventual malignancy, however, was whether the interpreting pathologist qualified the benign diagnosis at CNB with additional commentary (P<.01). CONCLUSION: Given the substantial upstage rate (11%) of papillary lesions diagnosed at imaging-guided CNB, surgical excision is an appropriate management decision; however, careful evaluation in concert with an expert breast pathologist may allow for observation in appropriately selected patients.

Teratomas: a multimodality review.

Germ cell tumors (GCTs) may occur in both children and adults and include a broad array of histologic subtypes, such as teratoma, seminoma (known as dysgerminoma in the ovary and germinoma in the pineal gland), choriocarcinoma, yolk sac tumor, embryonal cell carcinoma, and mixed GCT. In adults, GCTs occur most commonly in the gonads. In children, sacrococcygeal tumors predominate. Teratomas are a common form of GCT. They are defined histologically as containing tissues derived from all 3 germ cell layers: ectoderm, mesoderm (most teratomas contain fat, an imaging hallmark, which is a mesodermal derivative), and endoderm. Teratomas are also classified as mature or immature, depending on the degree of differentiation of its components, and in adults, immature tumors are more likely to exhibit malignant behavior.

Changes in extracellular pH are neither required nor sufficient for activation of mitogen-activated protein kinases (MAPKs) in response to systemin and fusicoccin in tomato.

Leaf wounding and the wound signaling peptide systemin induce expression of wound response genes while the fungal toxin fusicoccin (FC) induces expression of pathogenesis-related genes. Consistent with their functional differences, FC and systemin regulate the extracellular pH in opposite ways, with systemin inducing an alkalinization and FC an acidification response. Here we show that systemin, wounding and FC activate the same mitogen-activated protein kinases (MAPKs; MPKs) MPK1 and 2 in tomato (Lycopersicon esculentum) leaves and L. peruvianum suspension-cultured cells. Wounding and FC activated an additional MAPK, MPK3. Pronounced differences were observed with regard to MAPK activation kinetics. FC induced prolonged, and systemin transient activity of the MAPKs. This shows that functionally different elicitors engage the same signaling components, yet induce signal-specific activation dynamics. A comparative analysis of pH effects and MAPK activity in response to specific treatments revealed that the kinetics of pH changes and MAPK activation did not correlate. Simultaneous application of FC and systemin did not lead to immediate pH changes but resulted in rapid increases in MAPK activity. Furthermore, changes in extracellular pH could be induced without concomitant MAPK activation by exchanging conditioned medium with fresh medium. This shows that changes in the extracellular pH are neither required nor sufficient for MAPK activation, suggesting that signaling pathways involving MAPKs and extracellular pH changes operate in parallel and are not part of the same linear pathway.

Infants' use of category knowledge and object attributes when segregating objects at 8.5 months of age.

The current research investigates infants' perception of a novel object from a category that is familiar to young infants: key rings. We ask whether experiences obtained outside the lab would allow young infants to parse the visible portions of a partly occluded key ring display into one single unit, presumably as a result of having categorized it as a key ring. This categorization was marked by infants' perception of the keys and ring as a single unit that should move together, despite their attribute differences. We showed infants a novel key ring display in which the keys and ring moved together as one rigid unit (Move-together event) or the ring moved but the keys remained stationary throughout the event (Move-apart event). Our results showed that 8.5-month-old infants perceived the keys and ring as connected despite their attribute differences, and that their perception of object unity was eliminated as the distinctive attributes of the key ring were removed. When all of the distinctive attributes of the key ring were removed, the 8.5-month-old infants perceived the display as two separate units, which is how younger infants (7-month-old) perceived the key ring display with all its distinctive attributes unaltered. These results suggest that on the basis of extensive experience with an object category, infants come to identify novel members of that category and expect them to possess the attributes typical of that category.

The structure of the carboxyltransferase component of acetyl-coA carboxylase reveals a zinc-binding motif unique to the bacterial enzyme.

Acetyl-coA carboxylase (ACC) is a central metabolic enzyme that catalyzes the committed step in fatty acid biosynthesis: biotin-dependent conversion of acetyl-coA to malonyl-coA. The bacterial carboxyltransferase (CT) subunit of ACC is a target for the design of novel therapeutics that combat severe, hospital-acquired infections resistant to the established classes of frontline antimicrobials. Here, we present the structures of the bacterial CT subunits from two prevalent nosocomial pathogens, Staphylococcus aureus and Escherichia coli, at a resolution of 2.0 and 3.0 A, respectively. Both structures reveal a small, independent zinc-binding domain that lacks a complement in the primary sequence or structure of the eukaryotic homologue.

Convergence of signaling pathways induced by systemin, oligosaccharide elicitors, and ultraviolet-B radiation at the level of mitogen-activated protein kinases in Lycopersicon peruvianum suspension-cultured cells.

We tested whether signaling pathways induced by systemin, oligosaccharide elicitors (OEs), and ultraviolet (UV)-B radiation share common components in Lycopersicon peruvianum suspension-cultured cells. These stress signals all induce mitogen-activated protein kinase (MAPK) activity. In desensitization assays, we found that pretreatment with systemin and OEs transiently reduced the MAPK response to a subsequent treatment with the same or a different elicitor. In contrast, MAPK activity in response to UV-B increased after pretreatment with systemin and OEs. These experiments demonstrate the presence of signaling components that are shared by systemin, OEs, and UV-B. Based on desensitization assays, it is not clear if the same or different MAPKs are activated by different stress signals. To identify specific stress-responsive MAPKs, we cloned three MAPKs from a tomato (Lycopersicon esculentum) leaf cDNA library, generated member-specific antibodies, and performed immunocomplex kinase assays with extracts from elicited L. peruvianum cells. Two highly homologous MAPKs, LeMPK1 and LeMPK2, were activated in response to systemin, four different OEs, and UV-B radiation. An additional MAPK, LeMPK3, was only activated by UV-B radiation. The common activation of LeMPK1 and LeMPK2 by many stress signals is consistent with the desensitization assays and may account for substantial overlaps among stress responses. On the other hand, MAPK activation kinetics in response to elicitors and UV-B differed substantially, and UV-B activated a different set of LeMPKs than the elicitors. These differences may account for UV-B-specific responses.