Preliminary study of the technical limitations of automated breast ultrasound: from procedure to diagnosis

Abstract

Objective: To evaluate the main technical limitations of automated breast ultrasound and to determine the proportion of examinations excluded. Materials and Methods: We evaluated 440 automated breast ultrasound examinations performed, over a 12-month period, by technicians using an established protocol. Results: In five cases (1.1%), the examination was deemed unacceptable for diagnostic purposes, those examinations therefore being excluded. Conclusion: Automated breast ultrasound is expected to overcome some of the major limitations of conventional ultrasound in breast cancer screening. In Brazil, this new method can be accepted for inclusion in routine clinical practice only after its advantages have been validated in the national context.

Perfil do rastreio do câncer de mama no Município de Campina Grande, Paraíba, Brasil

“…Com relação a ultrassonografia das mamas (USG), sua indicação traduz um método complementar e auxiliar ao exame de mamografia. A USG apresenta capacidade de visualizar pequenos tumores, e permite a correta diferenciação entre nódulos sólidos e cistos, que na mamografia não foram visualizados (Calas et al, 2020). No entanto, em casos individualizados, como por exemplo, pacientes que apresentem mamas densas, verifica-se que a USG efetuada isoladamente não demonstra benefício como método de rastreio (Mendonça et al, 2018).…”

A Review of the Challenges in Deep Learning for Skeletal and Smooth Muscle Ultrasound Images

“…Additionally, ultrasound characteristics pose specific challenges in 1D [6], 2D [7], 3D [8], and 4D [9] images, such as image quality due to noise, scarce data, low image quality, and hand-held or operator skill, which may have a substantial influence on the efficacy of deep learning performance when compared with X-ray, computed tomography (CT), or magnetic resonance imaging (MRI) images [10] due to the special attention and resources required in the deep learning process. Furthermore, the challenges in the muscle ultrasound imaging process include the identification of landmarks, reliability testing, muscle site tracking, image acquisition and analysis, equipment use, normative data, and the interpretation of results [11,12]. The limitations of muscle ultrasound imaging can be overcome with good training for clinical personnel and clinical experience [4], and such practice is common in clinics and is painless and noninvasive [13]; however, it is costly and time consuming.…”