Blood Cell Revolution: Unveiling 11 Distinct Types with ‘Naturalize’ Augmentation

• Published in: Algorithms 2023-12, Vol.16 (12), p.562
• Main Authors: Abou Ali, Mohamad, Dornaika, Fadi, Arganda-Carreras, Ignacio
• Format: Article
• Language: English
• Subjects: Accuracy; Analyzers; Artificial intelligence; Automation; Blood; Blood cells; Bone marrow; Classification; convolutional neural net (CNN); Datasets; Deep learning; deep learning (DP); Equipment and supplies; Granulocytes; Health aspects; Health care facilities; Hematology; Homeostasis; Image analysis; Image processing; ImageNet models; Leukocytes; Machine learning; machine learning (ML); Medical centers; Medical imaging; Medical imaging equipment; Medical research; Medicine, Experimental; Neutrophils; Recall; Stem cells; transfer learning (TL); vision transformer (ViT); Workloads
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a16120562

Artificial intelligence (AI) has emerged as a cutting-edge tool, simultaneously accelerating, securing, and enhancing the diagnosis and treatment of patients. An exemplification of this capability is evident in the analysis of peripheral blood smears (PBS). In university medical centers, hematologists routinely examine hundreds of PBS slides daily to validate or correct outcomes produced by advanced hematology analyzers assessing samples from potentially problematic patients. This process may logically lead to erroneous PBC readings, posing risks to patient health. AI functions as a transformative tool, significantly improving the accuracy and precision of readings and diagnoses. This study reshapes the parameters of blood cell classification, harnessing the capabilities of AI and broadening the scope from 5 to 11 specific blood cell categories with the challenging 11-class PBC dataset. This transformation facilitates a more profound exploration of blood cell diversity, surpassing prior constraints in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking “Naturalize” augmentation technique produces remarkable results. The 2K-PBC dataset generated with “Naturalize” boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The “Naturalize” technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.