Hua Haojun, Zhou Yunlan, Li Wei, Zhang Jing, Deng Yanlin, Khoo Bee Luan
Department of Clinical Laboratory, Xinhua Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200092, China.
Department of Biomedical Engineering, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong 999077, China.
Biomicrofluidics. 2024 Jan 12;18(1):014101. doi: 10.1063/5.0172146. eCollection 2024 Jan.
Cancer spatial and temporal heterogeneity fuels resistance to therapies. To realize the routine assessment of cancer prognosis and treatment, we demonstrate the development of an Intelligent Disease Detection Tool (IDDT), a microfluidic-based tumor model integrated with deep learning-assisted algorithmic analysis. IDDT was clinically validated with liquid blood biopsy samples (n = 71) from patients with various types of cancers (e.g., breast, gastric, and lung cancer) and healthy donors, requiring low sample volume (∼200 l) and a high-throughput 3D tumor culturing system (∼300 tumor clusters). To support automated algorithmic analysis, intelligent decision-making, and precise segmentation, we designed and developed an integrative deep neural network, which includes Mask Region-Based Convolutional Neural Network (Mask R-CNN), vision transformer, and Segment Anything Model (SAM). Our approach significantly reduces the manual labeling time by up to 90% with a high mean Intersection Over Union (mIoU) of 0.902 and immediate results (<2 s per image) for clinical cohort classification. The IDDT can accurately stratify healthy donors (n = 12) and cancer patients (n = 55) within their respective treatment cycle and cancer stage, resulting in high precision (∼99.3%) and high sensitivity (∼98%). We envision that our patient-centric IDDT provides an intelligent, label-free, and cost-effective approach to help clinicians make precise medical decisions and tailor treatment strategies for each patient.
癌症的时空异质性导致对治疗产生抗性。为了实现癌症预后和治疗的常规评估，我们展示了一种智能疾病检测工具（IDDT）的开发，这是一种基于微流控的肿瘤模型，集成了深度学习辅助算法分析。IDDT通过来自各种癌症（如乳腺癌、胃癌和肺癌）患者及健康供体的液体活检样本（n = 71）进行了临床验证，所需样本量低（约200 μl），并采用了高通量3D肿瘤培养系统（约300个肿瘤簇）。为了支持自动化算法分析、智能决策和精确分割，我们设计并开发了一种集成深度神经网络，其中包括基于掩码区域的卷积神经网络（Mask R-CNN）、视觉Transformer和分割一切模型（SAM）。我们的方法显著减少了人工标注时间，最多可减少90%，平均交并比（mIoU）高达0.902，并且对于临床队列分类能立即给出结果（每张图像<2秒）。IDDT能够在各自的治疗周期和癌症阶段准确地对健康供体（n = 12）和癌症患者（n = 55）进行分层，从而实现高精度（约99.3%）和高灵敏度（约98%）。我们设想，我们以患者为中心的IDDT提供了一种智能、无标记且具有成本效益的方法，以帮助临床医生做出精确的医疗决策，并为每位患者量身定制治疗策略。
