NeurALLNet: An attention-based spiking neural network for energy-efficient multi-class classification of acute lymphoblastic leukemia - Takeaways - MDSpire

NeurALLNet: An attention-based spiking neural network for energy-efficient multi-class classification of acute lymphoblastic leukemia

  • By

  • Md Rafsan Hassan

  • Rejaul Islam Shanto

  • Umar Hasan

  • Sifat Momen

  • July 1, 2026

  • 0 min

Share

  • 1

    Acute Lymphoblastic Leukemia (ALL) is the most common childhood cancer, accounting for 75-80% of childhood leukemias globally.

  • 2

    Timely diagnosis of pediatric ALL can lead to five-year survival rates exceeding 90% in high-income countries.

  • 3

    Current diagnostic methods rely on manual examination of blood smears, which is labor-intensive and subject to variability.

  • 4

    NeurALLNet is a memory-efficient spiking neural network designed for accurate multi-class classification of ALL subtypes.

  • 5

    NeurALLNet integrates a Squeeze-and-Excitation attention mechanism, improving classification accuracy and enabling deployment on low-power devices.

Original Source(s)

NeurALLNet: An attention-based spiking neural network for energy-efficient multi-class classification of acute lymphoblastic leukemia

  • by Md Rafsan Hassan, Rejaul Islam Shanto, Umar Hasan, Sifat Momen

  • July 1, 2026

Related Content

Scientific approach to derive occupational exposure limits for formaldehyde releasers

A prediction model for urological tumor metastasis using liquid biopsy-derived biomarkers

A review on in-silico analysis of immune cell trafficking and interactions with the tumour microenvironment