Dynamic kernel generation through hybrid involution and convolution neural networks for leukemia and white blood cell classification

Abstract

Blood cancer diagnosis through microscopic image analysis is challenging due to subtle morphological differences between cell stages and subtypes. This study aims to develop a Hybrid Involutional-Convolutional Neural Network (HICNN) for automated leukemia detection and white blood cell morphology analysis, enabling precise classification of leukemia stages and leukocyte subtypes to improve diagnostic accuracy. The HICNN integrates involution layers, which dynamically generate spatially adaptive kernels for context-specific feature extraction, with convolutional layers that capture translation-invariant hierarchical patterns. This hybrid architecture leverages parallel processing within hybrid blocks to enhance discrimination of subtle cellular variations. The HICNN achieved exceptional performance with 99.5% accuracy on a leukemia staging dataset and 98.00% accuracy on a leukocyte subtyping dataset, surpassing state-of-the-art models. Model reliability was demonstrated through Brier scores of 0.0019 and 0.0069, with inter-class misclassifications below 2% and minimal overlap between class confidence scores. Training performance showed stable convergence within 50 epochs, with validation accuracy exceeding 99% by epoch 30. The HICNN advances automated hematological diagnostics by successfully addressing feature discrimination and model calibration challenges. The framework demonstrates robust performance in both cancer staging and cell subtype classification tasks, showing promise for reducing diagnostic ambiguity and improving early detection in leukemia and related hematological disorders.

Keywords: Blood cancer classification; Clinical diagnostic reliability; Hybrid CNN-involution networks; Leukemia staging (Hema-DA); Leukocyte subtyping (Hema-DB); Microscopic image analysis; Model calibration (Brier Score); Spatial-hierarchical feature learning.

Fig. 1

Representative samples from the Hema-DA dataset, illustrating morphological variations across the four cancer stages.

Fig. 2

Visual examples from the Hema-DB dataset, highlighting distinct morphological features of leukocyte subtypes.

Fig. 3

Architecture of the proposed HICNN, showing the parallel processing structure within hybrid blocks. Detailed views contrast the dynamic kernel generation in involution operations against traditional convolution’s fixed kernel approach. The network employs three sequential hybrid blocks with increasing channel dimensions for feature extraction.

Fig. 4

Training and validation learning curves for Hema-DA dataset. The proposed HICNN exhibits sharp convergence with validation accuracy reaching 99.85% within 50 epochs.

Fig. 5

Training and validation learning curves for Hema-DB dataset. The proposed HICNN exhibits sharp convergence with validation accuracy reaching 99.65% within 50 epochs.

Fig. 6

Normalized confusion matrice for Hema-DA dataset.

Fig. 7

Normalized confusion matrice for Hema-DB dataset.

Fig. 8

Class-wise probability density distributions for Hema-DA dataset. Sharp peaks near 1.0 for Benign class reflect high prediction confidence, while minimal overlap between Early and Pre stages (0.5–0.8 range) underscores the model’s discriminative capability.

Fig. 9

Class-wise probability density distributions for (a) Hema-DA and (b) Hema-DB datasets. Sharp peaks near 1.0 for EOSINOPHIL class reflect high prediction confidence, while minimal overlap between LYMPHOCYTE and MONOCYTE stages underscores the model’s discriminative capability.

Fig. 10

Grad-CAM visualizations for Hema-DB classes: (a) Motorcycle, (b) Neutrophil, (c) Lymphocyte, (d) Eosinophil, highlighting structural and cellular features influencing predictions.

Fig. 11

Grad-CAM visualizations for Hema-DA classes: (a) Early, (b) Pre, (c) Pro, (d) Benign, emphasizing progressive cellular features and diagnostic markers.

Fig. 12

Confusion matrix for cross-dataset evaluation on Blood Cells Image Dataset. The matrix shows strong diagonal dominance, indicating excellent class discrimination with minimal misclassification.