SBIR Phase II: Enhanced Medical Ultrasound for Breast Cancer Imaging

这个小企业创新研究（SBIR）二期项目的更广泛的影响/商业潜力是通过显著增强临床乳房超声图像，解决乳房x光检查致密性乳房组织的女性对替代成像技术的需求。乳房x光检查是乳腺癌筛查的黄金标准；然而，致密的乳腺组织和癌变灶在乳房x光片上都呈现白色，这使得很难可靠地检测出癌症。有致密组织的妇女——仅在美国就有2600万——需要替代的早期癌症检测成像技术。研究表明，与单独的乳房x光检查相比，增加单一的超声波筛查可使癌症检出率提高28%，同时显著提高了综合诊断的准确性。尽管有这些发现，假阳性率的四倍增加削弱了医生在乳房成像中使用超声波。一项提高致密乳腺组织超声图像清晰度的技术将彻底改变乳腺癌成像，使医生能够无创地检测出以前因其大小和/或对比度低而被掩盖的恶性肿瘤，并将其与良性病变区分开来。通过大幅提高总体癌症检出率，同时减少假阳性的数量，有很大可能挽救生命。该项目旨在开发一种自适应波束形成技术，该技术将显著提高超声成像的临床应用。与传统的波束形成不同，自适应波束形成估计超声探头元件之间的时间延迟，并且不需要事先知道沿波束路径的声速来产生组织图像。更精确的时间延迟导致改进的光束聚焦，并允许更大的传感器阵列，这反过来又允许更深的信号穿透-增强信号强度，空间分辨率和图像对比度。之前的第一阶段项目使用模拟超声数据开发了一种新颖的自适应波束形成技术，该技术采用最小均方滤波器，可将信噪比提高32 dB，图像对比度提高38%。第二阶段项目的目标是从代表性乳房幻影和体内研究中获取原始的射频超声数据；优化并确定自适应波束形成算法；对研究数据进行处理，评价改善后的图像对比度和临床效益；制作一个体现自适应波束形成技术的软件应用程序；并设计将该软件作为许可证或软件即服务（SaaS）产品交付给医疗机构所需的网络架构和数据管理方法。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project is to address the need for alternative imaging technologies for women with mammographically dense breast tissue by significantly enhancing clinical breast ultrasound images. Mammography is the gold standard for breast cancer screening; however, both dense breast tissue and cancerous lesions appear white on a mammogram, making it difficult to reliably detect cancers. Women who have dense tissue - 26 million in the United States alone - need alternative imaging technologies for early stage cancer detection. Studies show that the addition of a single screening ultrasound increases cancer detection by 28% over mammography alone, with significantly higher combined diagnostic accuracy. Despite these findings, a fourfold increase in the false positive rate undermines ultrasound use by physicians in breast imaging. A technology that improves ultrasound image clarity in dense breast tissue would revolutionize breast cancer imaging by allowing physicians to noninvasively detect malignancies previously obscured by their size and/or poor contrast and distinguish them from benign lesions. There is the strong potential to save lives by substantially increasing the overall cancer detection rate while simultaneously reducing the number of false positives.The proposed project seeks to develop an adaptive beamforming technology that will significantly improve the clinical utility of ultrasound imaging. Unlike traditional beamforming, adaptive beamforming estimates the time delays between ultrasound probe elements and does not require prior knowledge of the speed of sound along the beam path to produce an image of the tissue. The more accurate time delays result in improved beam focusing and allow for larger transducer arrays, which in turn allows for deeper signal penetration - enhancing signal strength, spatial resolution, and image contrast. The preceding Phase I project used simulated ultrasound data to develop a novel adaptive beamforming technique with least-mean square filters that improves signal-to-noise ratio by up to 32 dB and image contrast by up to 38%. The Phase II project objectives are to acquire raw, radio-frequency ultrasound data from both representative breast phantoms and an in vivo study; to optimize and finalize the adaptive beamforming algorithm; to process the study data and evaluate improved image contrast and clinical benefit; to produce a software application embodying the adaptive beamforming technique; and to design the network architecture and data management approach required to deliver that software as a license or as a Software as a Service (SaaS) product to medical facilities.