A hybrid deep learning and cellular automata framework with fractional derivatives for skin type and skin disease classification - Takeaways - MDSpire

A hybrid deep learning and cellular automata framework with fractional derivatives for skin type and skin disease classification

  • By

  • M. V. N. S. S. Kiranmai

  • C. Thanmayee Reddy

  • Gaddam Nikitha

  • Pattabiraman Venkattasubbu

  • Parvathi Ramasubramanian

  • July 15, 2026

Share

  • 1

    The study proposes a hybrid approach combining deep learning, cellular automata, and fractional derivatives for skin type and disease classification.

  • 2

    The method integrates convolutional neural networks with cellular automata to enhance texture analysis and skin type classification accuracy.

  • 3

    Fractional-order derivatives improve sensitivity to edge continuity and texture variations, aiding in the detection of delicate skin patterns.

  • 4

    Experimental results show the integrated model achieves 92.8% accuracy for skin disease classification and 92.4% for skin type classification.

  • 5

    The proposed framework offers a scalable solution for intelligent dermatological assessment and skin image analysis.

Original Source(s)

A hybrid deep learning and cellular automata framework with fractional derivatives for skin type and skin disease classification

  • by M. V. N. S. S. Kiranmai, C. Thanmayee Reddy, Gaddam Nikitha, Pattabiraman Venkattasubbu, Parvathi Ramasubramanian

  • July 15, 2026

Related Content

Reorganization and functional divergence of the CD4+ memory T cell compartment in hidradenitis suppurativa

Effectiveness and safety of switching biologics after secukinumab treatment failure in moderate-to-severe plaque psoriasis: a retrospective cohort study

Real-life experience of tildrakizumab 200 mg in complex psoriatic patients: a case series