Dermatological Image Diagnosis Using Deep Learning Framework Integrating CNN and BiLSTM

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 1, pp. 203-209, January 2026.

https://doi.org/10.58482/ijersem.v2i1.28

This work is licensed under a Creative Commons Attribution 4.0 International License.

Dermatological Image Diagnosis Using Deep Learning Framework Integrating CNN and BiLSTM

Full Text PDF

M. Manivannan

B.N. Pavan

Dasu Munemma

Mannuru Tejdeep

Karanam Shivaji

M.D. Nazish

Department of CSE, Siddartha Institute of Science and Technology, Puttur, India.

Abstract: Skin diseases are among the most prevalent health conditions globally, affecting individuals of all ages and location. To ensure timely diagnosis, prevent disease progression, and reduce healthcare expenses, it is essential to identify dermatological disorders early. Conversely, dermatological diagnosis in the traditional sense is based on visual examination by trained specialists; this method is time-consuming and subjective, often times limited by the availability of trained professionals, especially in rural and underprivileged regions. Also, as skin lesions become more diverse and visually comparable, diagnosis becomes more challenging even for experts. Advances in deep learning have greatly improved automated medical image analysis, making computer-aided dermatological diagnosis more feasible. This is a promising development. Convolutional neural networks (CNNs) have been successful in extracting spatial features from skin images, while sequence-based models such as Long Short-Term Memory (LSTM) networks model contextual and sequential dependencies. Despite the use of CNN-based methods, they often miss out on higher level feature dependencies that can enhance discrimination among similarly visualized skin types. The paper suggests a hybrid deep learning model that employs Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks to develop automated dermatological image diagnosis.

Keywords: Telemedicine, Conventional, Dermatological, Precision, Dermoscopic.

References: 

  1. A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, Jan. 2017, doi: 10.1038/nature21056.
  2. N. C. F. Codella et al., “Deep learning ensembles for melanoma recognition in dermoscopy images,” in IBM Journal of Research and Development, vol. 61, no. 4/5, pp. 5:1-5:15, 1 July-Sept. 2017, doi: 10.1147/JRD.2017.2708299.
  3. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
  4. K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.
  5. S. Hochreiter and J. Schmidhuber, “Long Short-Term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
  6. A. Graves and J. Schmidhuber, “Framewise phoneme classification with bidirectional LSTM networks,” Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., Montreal, QC, Canada, 2005, pp. 2047-2052 vol. 4, doi: 10.1109/IJCNN.2005.1556215.
  7. N. Gessert, M. Nielsen, M. Shaikh, R. Werner, and A. Schlaefer, “Skin lesion classification using ensembles of multi-resolution EfficientNets with meta data,” MethodsX, vol. 7, p. 100864, Jan. 2020, doi: 10.1016/j.mex.2020.100864.
  8. P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Scientific Data, vol. 5, no. 1, p. 180161, Aug. 2018, doi: 10.1038/sdata.2018.161.
  9. T. K. N. Thanh, Q. B. Truong, Q. D. Truong, and H. H. Xuan, “Depth Learning with Convolutional Neural Network for Leaves Classifier Based on Shape of Leaf Vein,” in Lecture notes in computer science, 2018, pp. 565–575. doi: 10.1007/978-3-319-75417-8_53.
  10. L. Yu, H. Chen, Q. Dou, J. Qin and P. -A. Heng, “Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks,” in IEEE Transactions on Medical Imaging, vol. 36, no. 4, pp. 994-1004, April 2017, doi: 10.1109/TMI.2016.2642839.
  11. G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, Jul. 2017, doi: 10.1016/j.media.2017.07.005.
  12. T. J. Brinker et al., “Deep neural networks are superior to dermatologists in melanoma image classification,” European Journal of Cancer, vol. 119, pp. 11–17, Aug. 2019, doi: 10.1016/j.ejca.2019.05.023.
  •  
Download PDF

This article is part of Volume 2, Issue 1 (January 2026)