CoTCoNet: An Optimized Coupled Transformer-Convolutional Network with an Adaptive Graph Reconstruction for Leukemia Detection

TL;DR

CoTCoNet is a novel deep learning framework combining transformers, convolutional networks, and graph-based feature reconstruction for highly accurate leukemia cell classification, addressing data imbalance and interpretability.

Contribution

This paper introduces CoTCoNet, an integrated transformer-convolutional model with adaptive graph reconstruction and meta-heuristic optimization for improved leukemia detection.

Findings

Achieves 98.94% accuracy and 98.93% F1-score on a large leukemia dataset.

Outperforms existing state-of-the-art methods across multiple datasets.

Provides explainability through feature visualization aligned with cell annotations.

Abstract

Swift and accurate blood smear analysis is an effective diagnostic method for leukemia and other hematological malignancies. However, manual leukocyte count and morphological evaluation using a microscope is time-consuming and prone to errors. Conventional image processing methods also exhibit limitations in differentiating cells due to the visual similarity between malignant and benign cell morphology. This limitation is further compounded by the skewed training data that hinders the extraction of reliable and pertinent features. In response to these challenges, we propose an optimized Coupled Transformer Convolutional Network (CoTCoNet) framework for the classification of leukemia, which employs a well-designed transformer integrated with a deep convolutional network to effectively capture comprehensive global features and scalable spatial patterns, enabling the identification of complex and large-scale hematological features. Further, the framework incorporates a graph-based feature reconstruction module to reveal the hidden or unobserved hard-to-see biological features of leukocyte cells and employs a Population-based Meta-Heuristic Algorithm for feature selection and optimization. To mitigate data imbalance issues, we employ a synthetic leukocyte generator. In the evaluation phase, we initially assess CoTCoNet on a dataset containing 16,982 annotated cells, and it achieves remarkable accuracy and F1-Score rates of 0.9894 and 0.9893, respectively. To broaden the generalizability of our model, we evaluate it across four publicly available diverse datasets, which include the aforementioned dataset. This evaluation demonstrates that our method outperforms current state-of-the-art approaches. We also incorporate an explainability approach in the form of feature visualization closely aligned with cell annotations to provide a deeper understanding of the framework.