RESUMO
OBJECTIVE: To assess the influence of the COVID-19 pandemic on breast cancer screening. METHODS: This was a cross-sectional and retrospective study, which used data extracted from "TABNET" between 2014 to 2020. Statistical analysis was carried out using the ANOVA model. RESULT: In 2019, a total of 3,068,776 mammograms were conducted, which significantly decreased to 1,808,765 in 2020. Since the onset of the pandemic in Brazil in March 2020, there has been a reduction in the number of mammograms performed. Mammography coverage increased from 0.11 to 0.18 between 2014 and 2019 but sharply declined from 0.18 to 0.10 between 2019 and 2020. CONCLUSION: The COVID-19 pandemic has had a detrimental impact on breast cancer screening efforts, especially in detecting the disease in early stages. Health services shifted their focus towards caring for COVID-19 patients, therefore neglecting routine screening programs and interventions. Additionally, the population's fear of contagion contributed to a decrease in demand for screening tests.
Assuntos
Neoplasias da Mama , COVID-19 , Detecção Precoce de Câncer , Mamografia , SARS-CoV-2 , Humanos , COVID-19/epidemiologia , Feminino , Neoplasias da Mama/diagnóstico , Neoplasias da Mama/epidemiologia , Mamografia/estatística & dados numéricos , Detecção Precoce de Câncer/estatística & dados numéricos , Detecção Precoce de Câncer/métodos , Estudos Transversais , Estudos Retrospectivos , Brasil/epidemiologia , Pessoa de Meia-Idade , Adulto , Programas de Rastreamento/métodos , IdosoRESUMO
Objective: Triple-negative breast cancer (TNBC) has an aggressive clinical behaviour, with advanced stages at initial diagnostic evaluation, early recurrences and poor survival, so the purpose was to determine the clinical and radiological manifestations associated with TNBC. Materials and methods: A case-control study in women diagnosed with breast cancer from January 2015 to August 2022 at the 'Instituto Regional de Enfermedades Neoplásicas del Norte'. We classified cases (Triple Negative subtype) and controls (Luminal A, Luminal B and HER2) according to immunohistochemistry ical analysis. Bivariate and multivariate logistic regression models were used to calculate the odds ratio (OR) with their respective 95% confidence intervals (CIs). Results: The medical reports of 88 cases and 236 controls were reviewed. Cases were more likely to report pain (p = 0.001), nodules on ultrasound (p = 0.01) and mammography (p = 0.003), superior median size (p < 0.05), posterior enhancement (p = 0.001) and moderate density (p = 0.003). Multivariate analysis identified that TNBC was more likely to have a nodular type lesion by ultrasound (OR: 9.73, 95% CI: 1.10-86.16; p = 0.04), ultrasound lesion larger than 36 mm (OR: 4.99, 95% CI: 1.75-14.17; p = 0.003) and moderate density (OR: 3.83, 95% CI: 1.44-10.14; p = 0.007). Conclusion: There are particular clinical and imaging manifestations of TNBC, showing that radiological lesions that presented characteristics in ultrasound as nodular type lesions larger than 36 mm and in mammography moderate grade density, were associated with this subtype of breast tumours in a Peruvian population.
RESUMO
BACKGROUND: Breast and cervical cancer are major public health issues globally. The reduction in incidence and mortality rates of these cancers is linked to effective prevention, early detection, and appropriate treatment measures. This study aims to analyze the temporal trends in the prevalence of mammography and Papanicolaou test coverage among women living in Brazilian state capitals between 2007 and 2023, and to compare the coverage of these tests before and during the Covid-19 pandemic. METHODS: A time series study was conducted using data from the Surveillance System for Risk and Protective Factors for Chronic Diseases by Telephone Survey from 2007 to 2023. The variables analyzed included mammography and Papanicolaou test coverage according to education level, age group, race/skin color, regions, and Brazilian capitals. The Prais-Winsten regression model was used to analyze the time series, and Student's t-test was employed to compare the prevalence rates between 2019 and 2023. RESULTS: Between 2007 and 2023, mammography coverage showed a stationary trend (71.1% in 2007 and 73.1% in 2023; p-value = 0.75) with a declining trend observed among women with 12 years or more of education (APC= -0.52% 95%CI -1.01%; -0.02%). Papanicolaou test coverage for all women aged between 25 and 64 exhibited a downward trend from 82% in 2007 to 76.8% in 2023 (APC= -0.45% 95%CI -0.76%; -0.13%). This decline was also noticed among those with 9 years or more of education; in the 25 to 44 age group; among women with white and mixed race; and in the Northeast, Central-West, Southeast, and South regions. When comparing coverage before and during Covid-19 pandemic, a reduction was noted for both tests. CONCLUSIONS: Over the years, there has been stability in mammography coverage and a decline in Papanicolaou test. The COVID-19 pandemic negatively impacted the number of these tests carried out among women, highlighting the importance of actions aimed at increasing coverage, especially among the most vulnerable groups.
Assuntos
Neoplasias da Mama , COVID-19 , Mamografia , Teste de Papanicolaou , Neoplasias do Colo do Útero , Humanos , Feminino , Teste de Papanicolaou/estatística & dados numéricos , COVID-19/epidemiologia , Brasil/epidemiologia , Mamografia/estatística & dados numéricos , Mamografia/tendências , Adulto , Pessoa de Meia-Idade , Neoplasias da Mama/diagnóstico , Neoplasias da Mama/epidemiologia , Neoplasias da Mama/diagnóstico por imagem , Neoplasias do Colo do Útero/diagnóstico , Neoplasias do Colo do Útero/epidemiologia , Detecção Precoce de Câncer/estatística & dados numéricos , Detecção Precoce de Câncer/tendências , Detecção Precoce de Câncer/métodos , Idoso , Adulto Jovem , Esfregaço Vaginal/estatística & dados numéricosRESUMO
Objective: To evaluate the indications for and results of magnetic resonance imaging (MRI) examinations for breast cancer screening at a cancer center in Brazil. Materials and Methods: This was a retrospective observational study, based on electronic medical records, of patients undergoing MRI for breast cancer screening at a cancer center in Brazil. Results: We included 597 patients between 19 and 82 years of age. The main indications for MRI screening were a personal history of breast cancer, in 354 patients (59.3%), a family history of breast cancer, in 102 (17.1%), and a confirmed genetic mutation, in 67 (11.2%). The MRI result was classified, in accordance with the categories defined in the Breast Imaging Reporting and Data System, as benign (category 1 or 2), in 425 patients (71.2%), probably benign (category 3), in 143 (24.0%), or suspicious (category 4 or 5), in 29 (4.9%). On MRI, 11 malignant tumors were identified, all of which were invasive carcinomas. Among those 11 carcinomas, six (54.5%) were categorized as minimal cancers (< 1 cm), and the axillary lymph nodes were negative in 10 (90.9%). The cancer detection rate was 18.4/1,000 examinations, and the positive predictive value for suspicious lesions submitted to biopsy was 37.9%. Conclusion: In our sample, the main indication for breast MRI screening was a personal history of breast cancer. The results indicate that MRI is a highly accurate method for the early detection of breast neoplasms in this population.
Objetivo: Avaliar as indicações e resultados de exames de ressonância magnética (RM) para rastreamento de câncer de mama em um centro oncológico no Brasil. Materiais e Métodos: Estudo observacional, realizado mediante análise retrospectiva de pacientes submetidos a RM das mamas para rastreamento de câncer de mama, por meio de revisão do prontuário eletrônico em um centro oncológico. Resultados: Foram incluídas 597 pacientes com idade variando de 19 a 82 anos. As principais indicações para rastreamento foram história pessoal de câncer de mama em 354 (59,3%) pacientes, história familiar em 102 (17,1%) e mutação genética confirmada em 67 (11,2%). O resultado da RM foi benigno (BI-RADS 1 ou 2) em 425 (71,2%) pacientes, provavelmente benigno (BI-RADS 3) em 143 (24,0%) e suspeito (BI-RADS 4 ou 5) em 29 (4,9%). Foram identificados 11 tumores malignos na RM, todos carcinomas invasivos, porcentagem de cânceres "mínimos" (< 1 cm) de 54,5% e porcentagem de axila negativa de 90,9%. A taxa de detecção de câncer na RM foi 18,4/1000 exames e o valor preditivo positivo para as lesões suspeitas submetidas a biópsia foi 37,9%. Conclusão: A principal indicação para RM de rastreamento na nossa população foi história pessoal de câncer de mama. Os resultados mostraram que a RM constitui um método com alta acurácia para detecção precoce de neoplasias da mama nessa população.
RESUMO
Extramammary metastases are uncommon and usually related to a poor prognosis, but the radiologist can suspect the diagnosis based on the patient's clinical history and specific imaging findings. Several imaging procedures may be used to evaluate breast metastases from different extramammary malignancies, including mammography, ultrasound, magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography-CT (PET-CT). The clinical and imaging presentation of these metastases is contingent upon how the illness spreads, however, they have the potential to resemble either benign or malignant breast tumors. Metastases that disseminate hematologically tend to appear as a single round or oval mass with circumscribed margins. Sonographically, they are usually hypoechoic, and with CT or MRI, they usually enhance. Lymphatic dissemination, for example, frequently reveals significant asymmetry with skin thickening and diffuse breast edema, which is compatible with an inflammatory breast carcinoma. Knowing the many types of cancers that have the potential to spread to the breast as well as being able to accurately diagnose them is crucial to prevent a needless mastectomy and provide guidance for subsequent treatment. The purpose of this article is to provide a better understanding of the imaging features and immunohistochemistry (IHC) of secondary tumors of the breast by presenting eight distinctive cases, which will enable radiologists to recognize this entity.
Assuntos
Neoplasias da Mama , Imagem Multimodal , Feminino , Humanos , Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/secundário , Imagem Multimodal/métodos , Metástase Neoplásica/diagnóstico por imagemRESUMO
Artifacts and foreign bodies can mimic microcalcifications. We report a series of 17 postsurgical women in whom mammograms showed fine linear radiodensities at the surgical bed. Vacuum-assisted biopsy histopathology of one of the lesions showed foreign bodies of different sizes with macrophage reaction. After discussion with the surgeons, we ascertained that a particular type of gauze was used that had fragmented, and we reproduced the mammographic appearance in a chicken breast. Furthermore, we showed the same pathology was reproduced in mice implanted with the gauze threads. It is important to be aware of this entity to avoid unnecessary examinations and even biopsy. The presence of foreign body linear gauze fragments at the surgical site can pose challenges in the mammographic follow-up of these patients.
Assuntos
Artefatos , Corpos Estranhos , Mamografia , Feminino , Animais , Humanos , Corpos Estranhos/diagnóstico por imagem , Corpos Estranhos/patologia , Mamografia/métodos , Pessoa de Meia-Idade , Calcinose/patologia , Calcinose/diagnóstico por imagem , Calcinose/cirurgia , Camundongos , Galinhas , Idoso , Adulto , Doenças Mamárias/patologia , Doenças Mamárias/diagnóstico por imagem , Doenças Mamárias/cirurgia , Neoplasias da Mama/patologia , Neoplasias da Mama/cirurgia , Neoplasias da Mama/diagnóstico por imagem , Mama/diagnóstico por imagem , Mama/patologia , Mama/cirurgiaRESUMO
Mobile health apps are widely used for breast cancer detection using artificial intelligence algorithms, providing radiologists with second opinions and reducing false diagnoses. This study aims to develop an open-source mobile app named "BraNet" for 2D breast imaging segmentation and classification using deep learning algorithms. During the phase off-line, an SNGAN model was previously trained for synthetic image generation, and subsequently, these images were used to pre-trained SAM and ResNet18 segmentation and classification models. During phase online, the BraNet app was developed using the react native framework, offering a modular deep-learning pipeline for mammography (DM) and ultrasound (US) breast imaging classification. This application operates on a client-server architecture and was implemented in Python for iOS and Android devices. Then, two diagnostic radiologists were given a reading test of 290 total original RoI images to assign the perceived breast tissue type. The reader's agreement was assessed using the kappa coefficient. The BraNet App Mobil exhibited the highest accuracy in benign and malignant US images (94.7%/93.6%) classification compared to DM during training I (80.9%/76.9%) and training II (73.7/72.3%). The information contrasts with radiological experts' accuracy, with DM classification being 29%, concerning US 70% for both readers, because they achieved a higher accuracy in US ROI classification than DM images. The kappa value indicates a fair agreement (0.3) for DM images and moderate agreement (0.4) for US images in both readers. It means that not only the amount of data is essential in training deep learning algorithms. Also, it is vital to consider the variety of abnormalities, especially in the mammography data, where several BI-RADS categories are present (microcalcifications, nodules, mass, asymmetry, and dense breasts) and can affect the API accuracy model.
Assuntos
Algoritmos , Neoplasias da Mama , Mama , Aprendizado Profundo , Mamografia , Humanos , Feminino , Neoplasias da Mama/diagnóstico por imagem , Mamografia/métodos , Mama/diagnóstico por imagem , Aplicativos Móveis , Ultrassonografia Mamária/métodos , Processamento de Imagem Assistida por Computador/métodosRESUMO
BACKGROUND: Fibroadenoma (FA) is the most common tumor found in young women, although it can occur in any age group. Ductal carcinoma in situ (DCIS) that is confined in a FA is rare; it is most frequently reported as an incidental finding. CASE SUMMARY: We report a case of DCIS within a FA in a 46-year-old female without cancer-related personal and family histories. The patient was diagnosed with a breast conglomerate of nodules and was followed for 1 year. In the current control image study, we found suspicious microcalcification, as a new finding, within one of the nodules. Consequently, a core biopsy of the tumor, which appeared hypoechoic, oval, and circumscribed, was performed. The pathological diagnosis was ductal carcinoma in situ within a fibroepithelial lesion. The patient underwent breast-conserving surgery and received radiotherapy as well as endocrine therapy (tamoxifen). CONCLUSION: We recommend a multidisciplinary approach for adequate treatment and follow-up.
RESUMO
PURPOSE: Breast density is a significant risk factor for breast cancer and can impact the sensitivity of screening mammography. Area-based breast density measurements may not provide an accurate representation of the tissue distribution, therefore volumetric breast density (VBD) measurements are preferred. Dual-energy mammography enables volumetric measurements without additional assumptions about breast shape. In this work we evaluated the performance of a dual-energy decomposition technique for determining VBD by applying it to virtual anthropomorphic phantoms. METHODS: The dual-energy decomposition formalism was used to quantify VBD on simulated dual-energy images of anthropomorphic virtual phantoms with known tissue distributions. We simulated 150 phantoms with volumes ranging from 50 to 709 mL and VBD ranging from 15% to 60%. Using these results, we validated a correction for the presence of skin and assessed the method's intrinsic bias and variability. As a proof of concept, the method was applied to 14 sets of clinical dual-energy images, and the resulting breast densities were compared to magnetic resonance imaging (MRI) measurements. RESULTS: Virtual phantom VBD measurements exhibited a strong correlation (Pearson's r > 0.95 $r > 0.95$ ) with nominal values. The proposed skin correction eliminated the variability due to breast size and reduced the bias in VBD to a constant value of -2%. Disagreement between clinical VBD measurements using MRI and dual-energy mammography was under 10%, and the difference in the distributions was statistically non-significant. VBD measurements in both modalities had a moderate correlation (Spearman's ρ $\rho \ $ = 0.68). CONCLUSIONS: Our results in virtual phantoms indicate that the material decomposition method can produce accurate VBD measurements if the presence of a third material (skin) is considered. The results from our proof of concept showed agreement between MRI and dual-energy mammography VBD. Assessment of VBD using dual-energy images could provide complementary information in dual-energy mammography and tomosynthesis examinations.
Assuntos
Densidade da Mama , Neoplasias da Mama , Mamografia , Imagens de Fantasmas , Imagem Radiográfica a Partir de Emissão de Duplo Fóton , Humanos , Mamografia/métodos , Feminino , Neoplasias da Mama/diagnóstico por imagem , Imagem Radiográfica a Partir de Emissão de Duplo Fóton/métodos , Mama/diagnóstico por imagem , Processamento de Imagem Assistida por Computador/métodos , Algoritmos , Imageamento por Ressonância Magnética/métodosRESUMO
Background: Breast cancer is the leading cause of cancer-related fatalities among women worldwide. Conventional screening and risk prediction models primarily rely on demographic and patient clinical history to devise policies and estimate likelihood. However, recent advancements in artificial intelligence (AI) techniques, particularly deep learning (DL), have shown promise in the development of personalized risk models. These models leverage individual patient information obtained from medical imaging and associated reports. In this systematic review, we thoroughly investigated the existing literature on the application of DL to digital mammography, radiomics, genomics, and clinical information for breast cancer risk assessment. We critically analyzed these studies and discussed their findings, highlighting the promising prospects of DL techniques for breast cancer risk prediction. Additionally, we explored ongoing research initiatives and potential future applications of AI-driven approaches to further improve breast cancer risk prediction, thereby facilitating more effective screening and personalized risk management strategies. Objective and methods: This study presents a comprehensive overview of imaging and non-imaging features used in breast cancer risk prediction using traditional and AI models. The features reviewed in this study included imaging, radiomics, genomics, and clinical features. Furthermore, this survey systematically presented DL methods developed for breast cancer risk prediction, aiming to be useful for both beginners and advanced-level researchers. Results: A total of 600 articles were identified, 20 of which met the set criteria and were selected. Parallel benchmarking of DL models, along with natural language processing (NLP) applied to imaging and non-imaging features, could allow clinicians and researchers to gain greater awareness as they consider the clinical deployment or development of new models. This review provides a comprehensive guide for understanding the current status of breast cancer risk assessment using AI. Conclusion: This study offers investigators a different perspective on the use of AI for breast cancer risk prediction, incorporating numerous imaging and non-imaging features.
RESUMO
Resumen La mamografía contrastada (CEDM, contrast-enhanced digital mammography) es una herramienta nueva que ha ido implementándose de forma creciente. Aparece como alternativa a la resonancia magnética (RM), y al igual que esta, tiene como principio el uso de contraste endovenoso para explorar la angiogénesis tumoral. Combina la imagen de mamografía convencional (Mx) con la técnica de sustracción con energía dual poscontraste, lo que resulta en un incremento en la detección de cáncer de mama, en un tiempo corto de estudio y a un bajo costo. Es un método prometedor en casos seleccionados y de fácil lectura, siendo útil principalmente en pacientes con diagnóstico de cáncer de mama para detectar lesiones adicionales y determinar el tamaño tumoral, ayudando en la planificación quirúrgica, así como también en la evaluación de la respuesta a la neoadyuvancia. También en el seguimiento de pacientes operadas, para caracterizar lesiones dudosas en Mx y ecografía, o como alternativa ante contraindicación de la RM. El objetivo de este trabajo es valorar la utilidad de la mamografía contrastada en la práctica diaria y determinar sus principales indicaciones. Repasamos con casos propios las utilidades y características del método.
Abstract Contrast-enhanced digital mammography (CEDM) is an emerging tool that has been increasingly implemented. It appears as an alternative to magnetic resonance imaging (MRI), using intravenous contrast to explore tumor angiogenesis. It combines conventional mammography (Mx) with post-contrast dual energy subtraction technique, resulting in increased detection of breast cancer, in a short study time and at a low cost. It is a promising method in selected cases and easy to read, being useful mainly in patients with breast cancer to detect additional lesions and determine the tumor size, that helps surgical planning, as well as in the evaluation of post-neoadjuvant chemotherapy response in the follow-up of patients treated with surgery, to address inconclusive findings in screening mammogram, or as an alternative when MRI is contraindicated. The purpose of this article is to assess the usefulness of contrasted mammography in daily practice and to determine its main indications. We review with our own cases the applications and characteristics of this method.
RESUMO
PURPOSE: Recruit and sequence breast cancer subjects in Guatemalan and US Hispanic populations. Identify optimum strategies to recruit Latin American and Hispanic women into genetic studies of breast cancer. METHODS: We used targeted gene sequencing to identify pathogenic variants in 19 familial breast cancer susceptibility genes in DNA from unselected Hispanic breast cancer cases in the US and Guatemala. Recruitment across the US was achieved through community-based strategies. In addition, we obtained patients receiving cancer treatment at major hospitals in Texas and Guatemala. RESULTS: We recruited 287 Hispanic US women, 38 (13%) from community-based and 249 (87%) from hospital-based strategies. In addition, we ascertained 801 Guatemalan women using hospital-based recruitment. In our experience, a hospital-based approach was more efficient than community-based recruitment. In this study, we sequenced 103 US and 137 Guatemalan women and found 11 and 10 pathogenic variants, respectively. The most frequently mutated genes were BRCA1, BRCA2, CHEK2, and ATM. In addition, an analysis of 287 US Hispanic patients with pathology reports showed a significantly higher percentage of triple-negative disease in patients with pathogenic variants (41% vs. 15%). Finally, an analysis of mammography usage in 801 Guatemalan patients found reduced screening in women with a lower socioeconomic status (p < 0.001). CONCLUSION: Guatemalan and US Hispanic women have rates of hereditary breast cancer pathogenic variants similar to other populations and are more likely to have early age at diagnosis, a family history, and a more aggressive disease. Patient recruitment was higher using hospital-based versus community enrollment. This data supports genetic testing in breast cancer patients to reduce breast cancer mortality in Hispanic women.
Assuntos
Predisposição Genética para Doença , Mutação em Linhagem Germinativa , Hispânico ou Latino , Neoplasias de Mama Triplo Negativas , Adulto , Idoso , Feminino , Humanos , Pessoa de Meia-Idade , Guatemala/epidemiologia , Hispânico ou Latino/genética , Hispânico ou Latino/estatística & dados numéricos , Seleção de Pacientes , Neoplasias de Mama Triplo Negativas/genética , Neoplasias de Mama Triplo Negativas/patologia , Neoplasias de Mama Triplo Negativas/etnologia , Neoplasias de Mama Triplo Negativas/epidemiologia , Estados Unidos/epidemiologia , Texas/epidemiologiaRESUMO
This project addresses the global challenge of breast cancer, particularly in low-resource settings, by creating a pioneering mammography database. Breast cancer, identified by the World Health Organization as a leading cause of cancer death among women, often faces diagnostic and treatment resource constraints in low- and middle-income countries. To enhance early diagnosis and address educational setbacks, the project focuses on leveraging artificial intelligence (AI) technologies through a comprehensive database. Developed in collaboration with Ambra Health, a cloud-based medical image management software, the database comprises 941 mammography images from 100 anonymized cases, with 62 % including 3D images. Accessible through http://mamografia.unifesp.br, the platform facilitates a simple registration process and an advanced search system based on 169 clinical and imaging variables. The website, customizable to the user's native language, ensures data security through an automatic anonymization system. By providing high-resolution, 3D digital images and supplementary clinical information, the platform aims to promote education and research in breast cancer diagnosis, representing a significant advancement in resource-constrained healthcare environments.
Assuntos
Inteligência Artificial , Neoplasias da Mama , Feminino , Humanos , Medicina de Precisão , Mamografia/métodos , Mama/diagnóstico por imagem , Neoplasias da Mama/diagnóstico por imagemRESUMO
Las manifestaciones cutáneas de los tumores malignos comprenden un grupo de dermatosis que pueden ser marcadores de la presencia de neoplasias ocultas y permiten su diagnóstico oportuno. El objetivo de este informe es presentar las características clínicas de una acantosis nigricans asociada a carcinoma de mamario. Para ello, se describe el caso clínico de una paciente de 50 años, color de piel negro, asistida en la consulta de Dermatología del Policlínico Universitario Raúl Sánchez, por tener una placa única eritematosa localizada en la mama izquierda, acompañada de dolor, aumento de la temperatura local y máculas hipercrómicas en las axilas; así como adenopatías axilares múltiples. Los exámenes complementarios mostraron la presencia de acantosis nigricans maligna asociada a un carcinoma inflamatorio de la mama izquierda. Fue intervenida quirúrgicamente, con la consiguiente desaparición de las lesiones cutáneas, pero con un pronóstico reservado. La mayoría de los síndromes paraneoplásicos son inespecíficos; existe una necesidad urgente de sospechar una correlación entre los cambios cutáneos y la posibilidad de una neoplasia interna, por lo que es de suma importancia derivar a estos pacientes para su identificación y el diagnóstico precoz de la enfermedad de base. Esto mejoraría el pronóstico y atenuaría en gran medida las consecuencias.
The skin manifestations of malignant tumors include a group of dermatoses that can be the sign of the occult neoplasms presence and allow their timely diagnosis. The objective of this report is to present the acanthosis nigricans' clinical characteristics associated with breast carcinoma. The clinical case of a 50-years-old black-skinned patient is described, assisted in the Dermatology consultation of the Raúl Sánchez University Polyclinic, for having a single erythematous plaque located in the left breast, accompanied by pain, increased local temperature and hyperchromic macules in the armpits; as well as multiple axillary lymphadenopathy. Complementary examinations showed the presence of malignant acanthosis nigricans associated with an inflammatory carcinoma of the left breast. She underwent surgery, with the consequent disappearance of the skin lesions, but with a reserved prognosis. Most paraneoplastic syndromes are nonspecific; there is an urgent need to suspect a correlation between skin changes and the possibility of an internal neoplasia, so it is of utmost importance to refer these patients for identification and early diagnosis of the underlying disease. This would improve the prognosis and greatly mitigate the consequences.
RESUMO
This prospective exploratory study conducted from January 2023 through May 2023 evaluated the ability of ChatGPT to answer questions from Brazilian radiology board examinations, exploring how different prompt strategies can influence performance using GPT-3.5 and GPT-4. Three multiple-choice board examinations that did not include image-based questions were evaluated: (a) radiology and diagnostic imaging, (b) mammography, and (c) neuroradiology. Five different styles of zero-shot prompting were tested: (a) raw question, (b) brief instruction, (c) long instruction, (d) chain-of-thought, and (e) question-specific automatic prompt generation (QAPG). The QAPG and brief instruction prompt strategies performed best for all examinations (P < .05), obtaining passing scores (≥60%) on the radiology and diagnostic imaging examination when testing both versions of ChatGPT. The QAPG style achieved a score of 60% for the mammography examination using GPT-3.5 and 76% using GPT-4. GPT-4 achieved a score up to 65% in the neuroradiology examination. The long instruction style consistently underperformed, implying that excessive detail might harm performance. GPT-4's scores were less sensitive to prompt style changes. The QAPG prompt style showed a high volume of the "A" option but no statistical difference, suggesting bias was found. GPT-4 passed all three radiology board examinations, and GPT-3.5 passed two of three examinations when using an optimal prompt style. Keywords: ChatGPT, Artificial Intelligence, Board Examinations, Radiology and Diagnostic Imaging, Mammography, Neuroradiology © RSNA, 2023 See also the commentary by Trivedi and Gichoya in this issue.
Assuntos
Inteligência Artificial , Radiologia , Brasil , Estudos Prospectivos , Radiografia , MamografiaRESUMO
Breast cancer is the second most common cancer type and the first in mortality among Brazilian women. Mammograms are one of the main early diagnosis strategies. National breast cancer screening coverage is still low. Brazil's low screening coverage is due to high mammography access inequality. Skin color defines healthcare access differences. Our article explores the natural event of the COVID-19 pandemic to analyze differences in screening rates between two racial groups of women through the application of the differences in differences (DiD) estimator. The results indicate that BBI women (Black, Brown, and Indigenous Brazilian) have lower screening rates than WY women (White and Yellow) and that the pandemic reduced the difference between these two groups due to the lower number of mammograms performed by WY women. It is believed that the information channel can explain much of this result. The BA population, wealthier and more educated, may have had additional information about COVID-19 and its consequences, as well as an increased likelihood of working remotely and practicing social distance. Structural racism causes many social indicators to be correlated with inequality of access to mammography and negatively impacts health conditions for BBI women. Public policies are necessary for equal access to breast cancer screening for the most vulnerable women.
RESUMO
Lymphoma is the most frequent hematologic malignancy that involves the breast. It represents less than 1% of all breast cancer. The most common subtype is the secondary B-cell lymphoma. Clinically, lymphomas are divided into primary and secondary breast lymphoma. We presented a case of 49-year-old female, who has diagnosed of Non-Hodgkin's Lymphoma, finalizing the treatment 2 months ago. Currently, she came for a check-up due to a palpable lump in the right breast. Mammography shows a dense, oval, and circumscribed mass. Ultrasound revealed a 3.6 cm oval, hypoechoic, lobulated mass with internal vascularity at color Doppler. Axillary nodes show cortical thickening of 7 mm, cortical blood flood, and absence of fatty hilum. The histopathology report corresponds to infiltration of the right breast and bilateral axillary nodes by Non-Hodgkin Lymphoma. This case corresponds with lymphoma recurrence manifested in breast. The diagnosis of lymphoma is an imaging challenge that simulates benign and malignant pathologies.
RESUMO
Abstract Objective To conduct a systematic review of external validation studies on the use of different Artificial Intelligence algorithms in breast cancer screening with mammography. Data source Our systematic review was conducted and reported following the PRISMA statement, using the PubMed, EMBASE, and Cochrane databases with the search terms "Artificial Intelligence," "Mammography," and their respective MeSH terms. We filtered publications from the past ten years (2014 - 2024) and in English. Study selection A total of 1,878 articles were found in the databases used in the research. After removing duplicates (373) and excluding those that did not address our PICO question (1,475), 30 studies were included in this work. Data collection The data from the studies were collected independently by five authors, and it was subsequently synthesized based on sample data, location, year, and their main results in terms of AUC, sensitivity, and specificity. Data synthesis It was demonstrated that the Area Under the ROC Curve (AUC) and sensitivity were similar to those of radiologists when using independent Artificial Intelligence. When used in conjunction with radiologists, statistically higher accuracy in mammogram evaluation was reported compared to the assessment by radiologists alone. Conclusion AI algorithms have emerged as a means to complement and enhance the performance and accuracy of radiologists. They also assist less experienced professionals in detecting possible lesions. Furthermore, this tool can be used to complement and improve the analyses conducted by medical professionals.
RESUMO
BACKGROUND: X-ray breast imaging modalities are commonly employed for breast cancer detection, from screening programs to diagnosis. Thus, dosimetry studies are important for quality control and risk estimation since ionizing radiation is used. PURPOSE: To perform multiscale dosimetry assessments for different breast imaging modalities and for a variety of breast sizes and compositions. The first part of our study is focused on macroscopic scales (down to millimeters). METHODS: Nine anthropomorphic breast phantoms with a voxel resolution of 0.5 mm were computationally generated using the BreastPhantom software, representing three breast sizes with three distinct values of volume glandular fraction (VGF) for each size. Four breast imaging modalities were studied: digital mammography (DM), contrast-enhanced digital mammography (CEDM), digital breast tomosynthesis (DBT) and dedicated breast computed tomography (BCT). Additionally, the impact of tissue elemental compositions from two databases were compared. Monte Carlo (MC) simulations were performed with the MC-GPU code to obtain the 3D glandular dose distribution (GDD) for each case considered with the mean glandular dose (MGD) fixed at 4 mGy (to facilitate comparisons). RESULTS: The GDD within the breast is more uniform for CEDM and BCT compared to DM and DBT. For large breasts and high VGF, the ratio between the minimum/maximum glandular dose to MGD is 0.12/4.02 for DM and 0.46/1.77 for BCT; the corresponding results for a small breast and low VGF are 0.35/1.98 (DM) and 0.63/1.42 (BCT). The elemental compositions of skin, adipose and glandular tissue have a considerable impact on the MGD, with variations up to 30% compared to the baseline. The inclusion of tissues other than glandular and adipose within the breast has a minor impact on MGD, with differences below 2%. Variations in the final compressed breast thickness alter the shape of the GDD, with a higher compression resulting in a more uniform GDD. CONCLUSIONS: For a constant MGD, the GDD varies with imaging modality and breast compression. Elemental tissue compositions are an important factor for obtaining MGD values, being a source of systematic uncertainties in MC simulations and, consequently, in breast dosimetry.
Assuntos
Mamografia , Radiometria , Raios X , Método de Monte Carlo , Radiometria/métodos , Mamografia/métodos , Imagens de Fantasmas , Doses de RadiaçãoRESUMO
Resumo: A detecção precoce de câncer de mama permite formas de tratamentos mais eficazes. Entretanto, o acesso generalizado à principal ferramenta de rastreamento, a mamografia, ainda é um desafio para o sistema público de saúde brasileiro. Este estudo tem o objetivo de analisar o efeito da alocação de mamógrafos sobre indicadores de saúde da mulher. Em 2013, dentre os 4.557 municípios que não tinham o equipamento, 260 receberam até 2019. A principal hipótese é que o efeito de receber o mamógrafo seja heterogêneo entre as localidades e que receber o equipamento dependa de variáveis observáveis (pareamento por escore de propensão) e não observáveis (modelo de efeitos fixos). Os resultados indicam que os municípios brasileiros que tiveram mamógrafo em uso a partir de 2014 obtiveram aumentos na realização de exames, porém sem efeitos de curto prazo para diagnósticos e óbitos por neoplasia maligna da mama. Além de equipamentos, uma estrutura mais complexa que envolve outros fatores como acesso a consultas, profissionais qualificados, tempo de espera etc. são importantes para melhorar os indicadores de saúde femininos no recorte de municípios analisados.
Abstract: The early detection of breast cancer enables more effective forms of treatment. However, widespread access to its main screening tool, mammography, remains a challenge for the Brazilian public health system. This study aimed to analyze the effect of allocating mammography equipment on women's health indicators. In 2013, of the 4,557 municipalities that lacked the equipment, 260 received it up to 2019. The main hypothesis of this study suggests that receiving the mammography device would show a heterogeneous effect between locations and that such receival would depend on observable (propensity score matching) and non-observable variables (fixed effects model). Results indicate that the Brazilian municipalities that had mammography equipment in use from 2014 onward increased their number of exams without short-term effects to diagnoses and deaths due to malignant breast neoplasia. In addition to equipment, a more complex structure involving other factors (such as access to consultations, qualified professionals, waiting time, etc.) is important to improve women's health indicators in the analyzed municipalities.
Resumen: La detección temprana del cáncer de mama permite formas de tratamientos más eficaces. Sin embargo, el acceso generalizado a la principal herramienta de seguimiento, la mamografía, sigue siendo un desafío para el sistema público de salud brasileño. Este estudio tiene como objetivo analizar el efecto de la asignación de mamógrafos en los indicadores de salud de la mujer. En 2013, de los 4.557 municipios que no tenían el equipo, 260 lo recibieron hasta 2019. La hipótesis principal es que el efecto de recibir un mamógrafo es heterogéneo entre las localidades y que recibir el equipo depende de variables observables (emparejamiento por puntaje de propensión) y no observables (modelo de efectos fijos). Los resultados indican que en los municipios brasileños que han tenido mamógrafo en uso a partir de 2014 obtuvieron aumentos en la realización de exámenes, pero sin efectos a corto plazo sobre los diagnósticos y las muertes por neoplasia maligna de la mama. Además de los equipos, una estructura más compleja que involucra otros factores como el acceso a consultas, profesionales calificados, tiempo de espera, etc. son importantes para mejorar los indicadores de salud de las mujeres en el recorte de municipios analizados.