Department of Computer Science and Engineering, Indian Institute of Technology Indore, Khandwa Road, Simrol, Indore, 453552, Madhya Pradesh, India.
Department of Computer Science, The University of Texas at Dallas, 800 W Campbell Rd, Richardson, 75080, TX, USA.
Comput Biol Med. 2024 Sep;179:108821. doi: 10.1016/j.compbiomed.2024.108821. Epub 2024 Jul 6.
Swift and accurate blood smear analyses are crucial for diagnosing leukemia and other hematological malignancies. However, manual leukocyte count and morphological evaluation remain time-consuming and prone to errors. Additionally, conventional image processing methods struggle to differentiate cells due to visual similarities between malignant and benign cell morphology.
In response to above challenges, we propose Coupled Transformer Convolutional Network (CoTCoNet) framework for leukemia classification. CoTCoNet integrates dual-feature extraction to capture long-range global features and fine-grained spatial patterns, facilitating the identification of complex hematological characteristics. Additionally, the framework employs a graph-based module to uncover hidden, biologically relevant features of leukocyte cells, along with a Population-based Meta-Heuristic Algorithm for feature selection and optimization. Furthermore, we introduce a novel combination of leukocyte segmentation and synthesis, which isolates relevant regions while augmenting the training dataset with realistic leukocyte samples. This strategy isolates relevant regions while augmenting the training data with realistic leukocyte samples, enhancing feature extraction, and addressing data scarcity without compromising data integrity.
We evaluated CoTCoNet on a dataset of 16,982 annotated cells, achieving an accuracy of 0.9894 and an F1-Score of 0.9893. We tested CoTCoNet on four diverse, publicly available datasets (including those above) to assess generalizability. Results demonstrate a significant performance improvement over existing state-of-the-art approaches.
CoTCoNet represents a significant advancement in leukemia classification, offering enhanced accuracy and efficiency compared to traditional methods. By incorporating explainable visualizations that closely align with cell annotations, the framework provides deeper insights into its decision-making process, further solidifying its potential in clinical settings.
快速准确的血涂片分析对于诊断白血病和其他血液系统恶性肿瘤至关重要。然而，手动白细胞计数和形态评估仍然费时且容易出错。此外，由于恶性和良性细胞形态之间存在视觉相似性，传统的图像处理方法难以区分细胞。
针对上述挑战，我们提出了用于白血病分类的耦合变换卷积网络（CoTCoNet）框架。CoTCoNet 集成了双特征提取，以捕获长程全局特征和细粒度空间模式，有助于识别复杂的血液学特征。此外，该框架采用基于图的模块来揭示白细胞细胞的隐藏的、与生物学相关的特征，以及基于群体的元启发式算法进行特征选择和优化。此外，我们引入了白细胞分割和合成的新组合，该组合在增强具有现实白细胞样本的训练数据集的同时分离相关区域。这种策略在增强具有现实白细胞样本的训练数据集的同时分离相关区域，增强特征提取，并解决数据稀缺性问题，而不会影响数据完整性。
我们在一个包含 16982 个注释细胞的数据集上评估了 CoTCoNet，准确率为 0.9894，F1 分数为 0.9893。我们在四个不同的、公开可用的数据集（包括上述数据集）上测试了 CoTCoNet，以评估其泛化能力。结果表明，与现有最先进的方法相比，CoTCoNet 取得了显著的性能提升。
CoTCoNet 代表了白血病分类的重大进展，与传统方法相比，它提供了更高的准确性和效率。通过引入与细胞注释紧密对齐的可解释可视化，该框架提供了对其决策过程的更深入了解，进一步巩固了其在临床环境中的潜力。
