The SMART (Smart Medicine and AI-Based Radiology Technology) Lab, Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China; School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China.
Department of Ultrasound, Tongren Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200050, China.
Comput Methods Programs Biomed. 2022 Apr;217:106698. doi: 10.1016/j.cmpb.2022.106698. Epub 2022 Feb 9.
Neoadjuvant chemotherapy (NAC) is a valuable treatment approach for locally advanced breast cancer. Contrast-enhanced ultrasound (CEUS) potentially enables the assessment of therapeutic response to NAC. In order to evaluate the response accurately, quantitatively and objectively, a method that can effectively compensate motions of breast cancer in CEUS videos is urgently needed.
We proposed the four-quadrant fast compressive tracking (FQFCT) approach to automatically perform CEUS video tracking and compensation for mice undergoing NAC. The FQFCT divided a tracking window into four smaller windows at four quadrants of a breast lesion and formulated the tracking at each quadrant as a binary classification task. After the FQFCT of breast cancer videos, the quantitative features of CEUS including the mean transit time (MTT) were computed. All mice showed a pathological response to NAC. The features between pre- (day 1) and post-treatment (day 3 and day 5) in these responders were statistically compared.
When we tracked the CEUS videos of mice with the FQFCT, the average tracking error of FQFCT was 0.65 mm, reduced by 46.72% compared with the classic fast compressive tracking method (1.22 mm). After compensation with the FQFCT, the MTT on day 5 of the NAC was significantly different from the MTT before NAC (day 1) (p = 0.013).
The FQFCT improves the accuracy of CEUS video tracking and contributes to the computer-aided response evaluation of NAC for breast cancer in mice.
新辅助化疗（NAC）是局部晚期乳腺癌的一种有价值的治疗方法。对比增强超声（CEUS）可能能够评估 NAC 的治疗反应。为了准确、定量和客观地评估反应，迫切需要一种能够有效补偿乳腺癌在 CEUS 视频中运动的方法。
我们提出了四象限快速压缩跟踪（FQFCT）方法，用于自动对接受 NAC 的小鼠进行 CEUS 视频跟踪和补偿。FQFCT 将跟踪窗口分为四个较小的窗口，位于乳房病变的四个象限，并将每个象限的跟踪表示为二进制分类任务。在对乳腺癌视频进行 FQFCT 后，计算 CEUS 的定量特征，包括平均渡越时间（MTT）。所有小鼠均对 NAC 有病理反应。在这些响应者中，比较了治疗前（第 1 天）和治疗后（第 3 天和第 5 天）的特征。
当我们使用 FQFCT 跟踪小鼠的 CEUS 视频时，FQFCT 的平均跟踪误差为 0.65mm，比经典快速压缩跟踪方法（1.22mm）减少了 46.72%。用 FQFCT 补偿后，NAC 第 5 天的 MTT 与 NAC 前（第 1 天）的 MTT 有显著差异（p=0.013）。
FQFCT 提高了 CEUS 视频跟踪的准确性，有助于计算机辅助评价乳腺癌 NAC 的反应。
