Diaz Resendiz Jose Luis, Ponomaryov Volodymyr, Reyes Reyes Rogelio, Sadovnychiy Sergiy
Instituto Politecnico Nacional, Escuela Superior de Ingenieria Mecanica y Electrica-Culhuacan, Av. Sta. Ana 1000, Mexico City 04440, Mexico.
Instituto Mexicano del Petroleo, Eje Central Lazaro Cardenas Norte 152, Mexico City 07730, Mexico.
Cancers (Basel). 2023 Jun 27;15(13):3376. doi: 10.3390/cancers15133376.
Leukemia is a significant health challenge, with high incidence and mortality rates. Computer-aided diagnosis (CAD) has emerged as a promising approach. However, deep-learning methods suffer from the "black box problem", leading to unreliable diagnoses. This research proposes an Explainable AI (XAI) Leukemia classification method that addresses this issue by incorporating a robust White Blood Cell (WBC) nuclei segmentation as a hard attention mechanism. The segmentation of WBC is achieved by combining image processing and U-Net techniques, resulting in improved overall performance. The segmented images are fed into modified ResNet-50 models, where the MLP classifier, activation functions, and training scheme have been tested for leukemia subtype classification. Additionally, we add visual explainability and feature space analysis techniques to offer an interpretable classification. Our segmentation algorithm achieves an Intersection over Union (IoU) of 0.91, in six databases. Furthermore, the deep-learning classifier achieves an accuracy of 99.9% on testing. The Grad CAM methods and clustering space analysis confirm improved network focus when classifying segmented images compared to non-segmented images. Overall, the proposed visual explainable CAD system has the potential to assist physicians in diagnosing leukemia and improving patient outcomes.
白血病是一项重大的健康挑战，发病率和死亡率都很高。计算机辅助诊断（CAD）已成为一种很有前景的方法。然而，深度学习方法存在“黑箱问题”，导致诊断不可靠。本研究提出了一种可解释人工智能（XAI）白血病分类方法，通过纳入强大的白细胞（WBC）细胞核分割作为一种硬注意力机制来解决这一问题。白细胞的分割是通过结合图像处理和U-Net技术实现的，从而提高了整体性能。分割后的图像被输入到经过修改的ResNet-50模型中，其中的MLP分类器、激活函数和训练方案已针对白血病亚型分类进行了测试。此外，我们添加了视觉可解释性和特征空间分析技术，以提供可解释的分类。我们的分割算法在六个数据库中实现了0.91的交并比（IoU）。此外，深度学习分类器在测试中达到了99.9%的准确率。Grad CAM方法和聚类空间分析证实，与未分割图像相比，在对分割图像进行分类时网络的注意力得到了改善。总体而言，所提出的视觉可解释CAD系统有潜力协助医生诊断白血病并改善患者预后。
