Li Fengze, Ma Jieming, Wen Tianxi, Tian Zhongbei, Liang Hai-Ning
University of Liverpool, Liverpool, UK.
Xi'an Jiaotong-Liverpool University, Suzhou, China.
Heliyon. 2024 Sep 27;10(19):e38410. doi: 10.1016/j.heliyon.2024.e38410. eCollection 2024 Oct 15.
Since 2020, breast cancer has remained the most prevalent cancer worldwide and the World Health Organisation projects significant increases by 2040, with new cases expected to exceed 3 million annually (a 40% increase) and deaths to surpass 1 million (a 50% increase), highlighting the urgent need for advancements in detection and treatment. Current detection of metastasis is highly dependent on labour-intensive and error-prone pathological examination of large-scale biotissue. Given the high-resolution (100,000 × 100,000 gigapixels) but limited quantity of open-source pathological slide datasets, existing deep learning models face preprocessing challenges. This paper introduces HI-Net, a high-speed panoramic feature-extraction pyramid network for rapid and accurate detection of metastatic breast cancer, balancing panoramic segmentation and local attention. Additionally, a lightweight pathological slide dataset optimised for 512 x 512-pixel resolution, derived from downsampled and reassembled competitive datasets, accelerates training and reduces computational costs. HI-Net demonstrates superior performance on existing medical imaging competition datasets and our lightweight dataset, evidencing its effectiveness across datasets and potential for contributing to the generalisation of intelligent diagnostics.
自2020年以来，乳腺癌一直是全球最常见的癌症，世界卫生组织预计到2040年其发病率将大幅上升，预计每年新增病例将超过300万（增长40%），死亡人数将超过100万（增长50%），这凸显了在检测和治疗方面取得进展的迫切需求。目前对转移的检测高度依赖于对大规模生物组织进行劳动密集型且容易出错的病理检查。鉴于开源病理切片数据集具有高分辨率（100,000×100,000千兆像素）但数量有限，现有的深度学习模型面临预处理挑战。本文介绍了HI-Net，一种用于快速准确检测转移性乳腺癌的高速全景特征提取金字塔网络，它平衡了全景分割和局部注意力。此外，一个针对512×512像素分辨率优化的轻量级病理切片数据集，由下采样和重新组装的竞争数据集派生而来，加速了训练并降低了计算成本。HI-Net在现有的医学成像竞赛数据集和我们的轻量级数据集上表现出卓越的性能，证明了其在跨数据集方面的有效性以及对智能诊断泛化做出贡献的潜力。
