Acute leukemia is usually diagnosed when a test of peripheral blood shows at least 20% of abnormal immature cells (blasts), a figure even lower in case of recurrent cytogenetic abnormalities. Blast identification is crucial for white blood cell (WBC) counting, which depends on both identifying the cell type and characterizing the cellular morphology, processes susceptible of inter- and intraobserver variability. The present work introduces an image combined-descriptor to detect blasts and determine their probable lineage. This strategy uses an intra-nucleus mosaic pattern (InMop) descriptor that captures subtle nuclei differences within WBCs, and Haralick's statistics which quantify the local structure of both nucleus and cytoplasm. The InMop captures WBC inner-nucleus structure by applying a multiscale Shearlet decomposition over a repetitive pattern (mosaic) of automatically-segmented nuclei. As a complement, Haralick's statistics characterize the local structure of the whole cell from an intensity co-occurrence matrix representation. Both InMoP and Haralick-based descriptors are calculated using the b-channel from Lab color-space. The combined-descriptor is assessed by differentiating blasts from nonleukemic cells with support vector machine (SVM) classifiers and different transformation kernels, in two public and independent databases. The first database-D1 (n = 260) is composed of healthy and acute lymphoid leukemia (ALL) single cell images, and second database-D2 contains acute myeloid leukemia (AML) blasts (n = 3294) and nonblast (n = 15,071) cell images. In a first experiment, blasts versus nonblast differentiation is performed by training with a subset of D2 (n = 6588) and testing in D1 (n = 260), obtaining a training AUC of 0.991 ± 0.002 and AUC = 0.782 for the independent validation. A second experiment automatically differentiates AML blasts (260 images from D2) from ALL blasts (260 images from D1), with an AUC of 0.93. In a third experiment, state-of-the-art strategies, VGG16 and RESNEXT convolutional neural networks (CNN), separate blast from nonblast cells in both databases. The VGG16 showed an AUC of 0.673 and the RESNEXT of 0.75. Reported metrics for all the experiments are area under the ROC curve (AUC), accuracy and F1-score.

中文翻译：

---

核内镶嵌图案 (InMop) 和全细胞 Haralick 组合描述符用于识别和表征单细胞外周血图像上的急性白血病母细胞

当外周血检查显示至少 20% 的异常未成熟细胞（原始细胞）时，通常即可诊断出急性白血病，在复发性细胞遗传学异常的情况下，该数字甚至更低。原始细胞鉴定对于白细胞 (WBC) 计数至关重要，这取决于细胞类型的识别和细胞形态的表征，以及容易受到观察者间和观察者内变异影响的过程。目前的工作引入了一种图像组合描述符来检测爆炸并确定其可能的谱系。该策略使用核内镶嵌模式 (InMop) 描述符来捕获 WBC 内细微的细胞核差异，并使用 Haralick 的统计数据来量化细胞核和细胞质的局部结构。InMop 通过对自动分割的细胞核的重复模式（马赛克）应用多尺度剪切波分解来捕获 WBC 内部细胞核结构。作为补充，Haralick 的统计数据通过强度共生矩阵表示来表征整个细胞的局部结构。InMoP 和基于 Haralick 的描述符都是使用 Lab 色彩空间的 b 通道计算的。通过在两个公共和独立数据库中使用支持向量机 (SVM) 分类器和不同的转化内核区分原始细胞与非白血病细胞来评估组合描述符。第一个数据库 -D1 ( n = 260) 由健康和急性淋巴细胞白血病 (ALL) 单细胞图像组成，第二个数据库 -D2 包含急性髓系白血病 (AML) 母细胞 ( n = 3294) 和非母细胞 ( n = 15,071)细胞图像。在第一个实验中，通过使用 D2 子集 ( n = 6588) 进行训练并在 D1 ( n = 260) 中进行测试来进行母细胞与非母细胞的分化，获得的训练 AUC 为 0.991 ± 0.002，独立验证的 AUC = 0.782。第二个实验自动区分 AML 原始细胞（来自 D2 的 260 个图像）和所有原始细胞（来自 D1 的 260 个图像），AUC 为 0.93。在第三个实验中，采用最先进的策略 VGG16 和 RESNEXT 卷积神经网络 (CNN)，将两个数据库中的母细胞与非母细胞分开。VGG16 显示 AUC 为 0.673，RESNEXT 为 0.75。所有实验的报告指标包括 ROC 曲线下面积 (AUC)、准确性和 F1 分数。