背景:乳腺纤维腺瘤引起了重大的健康问题,尤其是年轻女性。计算机辅助诊断已成为早期和准确检测各种实体瘤的有效和高效方法。乳腺纤维腺瘤的自动分割是重要的,并可能减少不必要的活检,但由于图像质量低且超声检查中存在各种伪影,因此具有挑战性。
方法:人类学习涉及模块化完整的信息,然后以直观有效的方式通过密集的上下文连接将其集成。这里,引入了人类学习范式,通过两个连续的阶段来指导神经网络:特征碎片阶段和信息聚合阶段。为了优化这个范例,根据超声检查的特点,调整了三种碎片注意力机制和信息聚集机制。评估是使用本地数据集进行的,该数据集包括来自中国遂宁市中心医院30名患者的600张乳腺超声图像。此外,使用由来自Dataset_BUSI和DatasetB的246张乳腺超声图像组成的公共数据集来进一步验证所提出的网络的鲁棒性.通过Dice相似系数(DSC)评估分割性能和推理速度,Hausdorff距离(HD),和训练时间,然后与基线模型(TransUNet)和其他最先进的方法进行比较。
结果:大多数由人类学习范式指导的模型在本地数据集上显示出改进的分割效果,其中最好的一个(包含C3ECA和LogSparseAttention模块)在DSC中优于基线模型0.76%,在HD中优于3.14mm,并将训练时间减少了31.25%。它在公共数据集上的鲁棒性和效率也得到了证实,在DSC方面超过TransUNet0.42%,在HD方面超过5.13mm。
结论:我们提出的人类学习范式已经证明了在公共和本地数据集中超声乳腺纤维腺瘤分割的优越性和效率。这种直观有效的学习范式作为神经网络的核心,在医学图像处理中具有巨大的潜力。
BACKGROUND: Breast fibroadenoma poses a significant health concern, particularly for young women. Computer-aided diagnosis has emerged as an effective and efficient method for the early and accurate detection of various solid tumors. Automatic segmentation of the breast fibroadenoma is important and potentially reduces unnecessary biopsies, but challenging due to the low image quality and presence of various artifacts in sonography.
METHODS: Human learning involves modularizing complete information and then integrating it through dense contextual connections in an intuitive and efficient way. Here, a human learning paradigm was introduced to guide the neural network by using two consecutive phases: the feature fragmentation stage and the information aggregation stage. To optimize this paradigm, three fragmentation attention mechanisms and information aggregation mechanisms were adapted according to the characteristics of sonography. The evaluation was conducted using a local dataset comprising 600 breast ultrasound images from 30 patients at Suining Central Hospital in China. Additionally, a public dataset consisting of 246 breast ultrasound images from Dataset_BUSI and DatasetB was used to further validate the robustness of the proposed network. Segmentation performance and inference speed were assessed by Dice similarity coefficient (DSC), Hausdorff distance (HD), and training time and then compared with those of the baseline model (TransUNet) and other state-of-the-art methods.
RESULTS: Most models guided by the human learning paradigm demonstrated improved segmentation on the local dataset with the best one (incorporating C3ECA and LogSparse Attention modules) outperforming the baseline model by 0.76% in DSC and 3.14 mm in HD and reducing the training time by 31.25%. Its robustness and efficiency on the public dataset are also confirmed, surpassing TransUNet by 0.42% in DSC and 5.13 mm in HD.
CONCLUSIONS: Our proposed human learning paradigm has demonstrated the superiority and efficiency of ultrasound breast fibroadenoma segmentation across both public and local datasets. This intuitive and efficient learning paradigm as the core of neural networks holds immense potential in medical image processing.