RESUMO
The aim was to determine whether an artificial intelligence (AI)-based, computer-aided detection (CAD) software can be used to reduce false positive per image (FPPI) on mammograms as compared to an FDA-approved conventional CAD. A retrospective study was performed on a set of 250 full-field digital mammograms between January 1, 2013, and March 31, 2013, and the number of marked regions of interest of two different systems was compared for sensitivity and specificity in cancer detection. The count of false-positive marks per image (FPPI) of the two systems was also evaluated as well as the number of cases that were completely mark-free. All results showed statistically significant reductions in false marks with the use of AI-CAD vs CAD (confidence interval = 95%) with no reduction in sensitivity. There is an overall 69% reduction in FPPI using the AI-based CAD as compared to CAD, consisting of 83% reduction in FPPI for calcifications and 56% reduction for masses. Almost half (48%) of cases showed no AI-CAD markings while only 17% show no conventional CAD marks. There was a significant reduction in FPPI with AI-CAD as compared to CAD for both masses and calcifications at all tissue densities. A 69% decrease in FPPI could result in a 17% decrease in radiologist reading time per case based on prior literature of CAD reading times. Additionally, decreasing false-positive recalls in screening mammography has many direct social and economic benefits.
Assuntos
Inteligência Artificial , Neoplasias da Mama/diagnóstico por imagem , Mamografia/métodos , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Mama/diagnóstico por imagem , Reações Falso-Positivas , Feminino , Humanos , Estudos Retrospectivos , Sensibilidade e EspecificidadeRESUMO
Rapidly increasing U.S. healthcare spending has been a hot topic over the past few decades. Imaging studies, including screening mammography, are possible targets for cost savings. Radiologists need to be more proactive and take charge by actively participating in the cost reduction conversation, improving the quality of care, providing patients with accurate cost estimates and educating patients along with clinicians on the value we have provided and can provide in the future.
Assuntos
Mamografia/economia , Neoplasias da Mama/diagnóstico , Detecção Precoce de Câncer , Feminino , Humanos , Mamografia/métodos , Programas de Rastreamento , RadiologistasRESUMO
Tracing the use of computers in the radiology department from administrative functions through image acquisition, storage, and reporting, to early attempts at improved diagnosis, we begin to imagine possible new frontiers for their use in exam interpretation. Given their initially slow but ultimately substantial progress in the noninterpretive areas, we are left desiring and even expecting more in the interpretation realm. New technological advances may provide the next wave of progress and radiologists should be early adopters. Several potential applications are discussed and hopefully will serve to inspire future progress.
Assuntos
Inteligência Artificial , Interpretação de Imagem Radiográfica Assistida por Computador , Radiologia , Humanos , Aprendizado de MáquinaRESUMO
As the health care environment continually changes, radiologists look to the ACR's Imaging 3.0® initiative to guide the search for value. By leveraging new technology, a cloud-based image exchange network could provide secure universal access to prior images, which were previously siloed, to facilitate accurate interpretation, improved outcomes, and reduced costs. The breast imaging department represents a viable starting point given the robust data supporting the benefit of access to prior imaging studies, existing infrastructure for image sharing, and the current workflow reliance on prior images. This concept is scalable not only to the remainder of the radiology department but also to the broader medical record.
Assuntos
Computação em Nuvem/economia , Diagnóstico por Imagem/estatística & dados numéricos , Custos de Cuidados de Saúde/estatística & dados numéricos , Registro Médico Coordenado , Sistemas de Informação em Radiologia/economia , Valores Sociais , Estados UnidosRESUMO
In preparation for impending changes to the health care delivery and reimbursement models, the ACR has provided a roadmap for success via the Imaging 3.0 (®)platform. The authors illustrate how the field of breast imaging demonstrates the following Imaging 3.0 concepts: value, patient-centered care, clinical integration, structured reporting, outcome metrics, and radiology's role in the accountable care organization environment. Much of breast imaging's success may be adapted and adopted by other fields in radiology to ensure that all radiologists become more visible and provide the value sought by patients and payers.