Clinical Report: NeurALLNet: An Attention-Driven Spiking Neural Network for Efficient Multi-Class Classification of Acute Lymphoblastic Leukemia

Overview

NeurALLNet is a convolutional spiking neural network designed for the multi-class classification of Acute Lymphoblastic Leukemia (ALL) subtypes, achieving real-time inference with a minimal parameter footprint.

Background

Acute Lymphoblastic Leukemia (ALL) is the most prevalent cancer in children, necessitating prompt and accurate diagnosis. Current diagnostic practices are labor-intensive and subject to variability.

Data Highlights

NeurALLNet achieves real-time inference with approximately 0.3M trainable parameters and a model size of 1.35 MB.

Key Findings

• NeurALLNet integrates a Squeeze-and-Excitation attention mechanism.
• The model demonstrated over 30% accuracy drop when the attention mechanism was removed.
• Robustness analysis showed model resilience under various noise conditions and image distortions.
• NeurALLNet is designed for deployment on low-power edge devices.
• The architecture addresses the performance gap between Spiking Neural Networks and Convolutional Neural Networks.

Clinical Implications

NeurALLNet provides a potential solution for improving diagnostic accuracy in ALL classification.

Conclusion

NeurALLNet represents an advancement in the automated classification of Acute Lymphoblastic Leukemia.

Related Resources & Content

1. Frontiers in Medicine, 2026 -- Optimized deep learning ensemble using Fast Osprey algorithm for accurate lymphoblastic leukemia detection
2. Frontiers in Oncology, 2026 -- Hybrid handcrafted and deep feature fusion for automated acute myeloid leukemia classification using TCMA-Net on a class-balanced dataset
3. Utilizing Deep Learning for Predicting Overall Survival in Patients with Rare Cancers: Insights from Primary Central Nervous System Lymphoma
4. Frontiers in Medicine, 2026 -- Automated bone marrow cell classification using ensemble learning: performance, generalization, and clinical interpretability
5. Childhood Acute Lymphoblastic Leukemia Treatment (PDQ®) - NCI
6. American Society of Hematology (ASH), 2026 -- Clinical practice guidelines focused on adolescents and young adults
7. Childhood Acute Lymphoblastic Leukemia Treatment (PDQ®) - NCI
8. https://www.hematology.org/-/media/hematology/files/clinicians/guidelines/all-in-ayas-2026/ash-all-aya-frontline-snapshot.pdf
9. Blinatumomab in Standard-Risk B-Cell Acute Lymphoblastic Leukemia in Children | New England Journal of Medicine