Yan Geng, Mingyang Gao, Wei Shi, Hongping Liang, Liyuan Qin, Ailan Liu, Xiaomei Kong, Huilan Zhao, Juanjuan Zhao, Yan Qiang
Department of Physiology, Shanxi Medical University, Taiyuan, China.
Key Laboratory of Cellular Physiology, Ministry of Education (Shanxi Medical University), Taiyuan, China.
Cancer Sci. 2025 Feb;116(2):533-543. doi: 10.1111/cas.16374. Epub 2024 Nov 18.
Leukemia is highly heterogeneous, meaning that different types of leukemia require different treatments and have different prognoses. Current clinical diagnostic and typing tests are complex and time-consuming. In particular, all of these tests rely on bone marrow aspiration, which is invasive and leads to poor patient compliance, exacerbating treatment delays. Morphological analysis of peripheral blood cells (PBC) is still primarily used to distinguish between benign and malignant hematologic disorders, but it remains a challenge to diagnose and type these diseases solely by direct observation of peripheral blood(PB) smears by human experts. In this study, we apply a segmentation-based enhanced residual network that uses progressive multigranularity training with jigsaw patches. It is trained on a self-built annotated dataset of 21,208 images from 237 patients, including five types of benign white blood cells(WBCs) and eight types of leukemic cells. The network is not only able to discriminate between benign and malignant cells, but also to typify leukemia using a single peripheral blood cell. The network effectively differentiated acute promyelocytic leukemia (APL) from other types of acute myeloid leukemia (non-APL), achieving a precision rate of 89.34%, a recall rate of 97.37%, and an F1 score of 93.18% for APL. In contrast, for non-APL cases, the model achieved a precision rate of 92.86%, but a recall rate of 74.63% and an F1 score of 82.75%. In addition, the model discriminates acute lymphoblastic leukemia(ALL) with the Ph chromosome from those without. This approach could improve patient compliance and enable faster and more accurate typing of leukemias for early diagnosis and treatment to improve survival.
白血病具有高度异质性，这意味着不同类型的白血病需要不同的治疗方法，且预后也不同。当前的临床诊断和分型检测复杂且耗时。特别是，所有这些检测都依赖骨髓穿刺，这是一种侵入性操作，会导致患者依从性差，进而加剧治疗延误。外周血细胞（PBC）的形态学分析仍然主要用于区分良性和恶性血液系统疾病，但仅通过人类专家直接观察外周血（PB）涂片来诊断和分型这些疾病仍然是一项挑战。在本研究中，我们应用了一种基于分割的增强残差网络，该网络使用拼图块进行渐进式多粒度训练。它在一个自建的注释数据集上进行训练，该数据集包含来自237名患者的21208张图像，包括五种类型的良性白细胞（WBC）和八种类型的白血病细胞。该网络不仅能够区分良性和恶性细胞，还能够使用单个外周血细胞对白血病进行分型。该网络有效地将急性早幼粒细胞白血病（APL）与其他类型的急性髓系白血病（非APL）区分开来，APL的精确率达到89.34%，召回率达到97.37%，F1分数达到93.18%。相比之下，对于非APL病例，该模型的精确率为92.86%，但召回率为74.63%，F1分数为82.75%。此外，该模型还能区分有Ph染色体的急性淋巴细胞白血病（ALL）和无Ph染色体的急性淋巴细胞白血病。这种方法可以提高患者的依从性，并能够更快、更准确地对白血病进行分型，以便早期诊断和治疗，从而提高生存率。
