Wei Ting-Ruen, Hell Michele, Vierra Aren, Pang Ran, Kang Young, Patel Mahesh, Yan Yuling
Santa Clara University Santa Clara CA 95053 USA.
Santa Clara Valley Medical Center San Jose CA 95128 USA.
IEEE Open J Eng Med Biol. 2024 Sep 5;6:100-106. doi: 10.1109/OJEMB.2024.3454958. eCollection 2025.
This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.
本研究旨在通过采用以数据为中心的方法，利用双视角超声检查来增强人工智能辅助的乳腺癌诊断。我们在独家的双视角乳腺超声数据集上定制了一个基于密集连接网络（DenseNet）的模型，以提高该模型区分恶性和良性肿块的能力。设计了各种组合策略，将双视角整合到模型输入中，与仅使用单视角形成对比，目标是使性能最大化。随后，我们将该模型与放射科医生进行比较，并量化关键性能指标的提升情况。我们还进一步评估了在该模型的辅助下，放射科医生的诊断准确性是如何提高的。我们的实验一致发现，通过使用一种将两个视角进行通道维度堆叠的方法（其中一个视角复制作为第三个通道）可实现最佳结果。这种配置使模型表现出色，其受试者工作特征曲线下面积（AUC）为0.9754，特异性为0.96，灵敏度为0.9263，特异性方面比放射科医生高出50%。在该模型的指导下，放射科医生在关键指标上的表现有所提升：准确率提高了17%，精确率提高了26%，特异性提高了29%。我们针对双视角图像输入进行了优化配置的定制模型，在文献中超过了放射科医生和现有模型的结果。将该模型作为独立工具或放射科医生的辅助工具集成使用，可以大大提高特异性，减少假阳性，从而最大限度地减少不必要的活检，并减轻放射科医生的工作量。
