Citation :

P Muthamil Selvan, S Pazhanirajan, K Abhirami, "Progression-Aware Synthetic Image Generation with Explainable Deep Learning Framework for Rare Skin Disease Detection and Classification," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 8, pp. 483-495, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I8P132

Abstract

Rare diseases affect approximately 300 to 400 million individuals around the world, posing major difficulties in medical diagnosis. Among these, rare skin disorders represent a significant subset, frequently characterized by intricate visual patterns and higher inter-class similarity, which creates substantial obstacles in precise diagnosis. Artificial Intelligence (AI)-driven research for rare skin diseases has accelerated rapidly, unlocking new potential for timely, precise diagnosis and better long-term management strategies. DL techniques have considerably enhanced the classification and detection of skin diseases, including rare skin diseases, across clinical image analysis. However, the availability of adequate labeled datasets for rare skin diseases is limited, which restricts the generality of deep learning systems. To address these challenges, this study presents a Progression-Aware Synthetic Learning Framework for Rare Skin Disease Diagnosis (PASLF-RSDD). The primary objective of this study is to enhance rare skin disease diagnosis through multi-modal synthetic data augmentation, thereby improving the performance of the Deep Learning Model. Initially, the proposed PASLF-RSDD model employs Multi-Modal CycleGAN for synthetic image generation. Following that, high-level discriminative features are extracted using DenseNet121 integrated with Squeeze-and-Excitation blocks for improved feature representation. The extracted features are then passed into a bidirectional convolutional long-short term memory network for accurate rare skin condition classification, such as Elastosis Perforans Serpiginosa, Lentigo Maligna, Nevus Sebaceus, and Blue Naevus. The hyperparameters of the proposed BiConvLSTM classifier are automatically optimized by the Ant Lion Optimizer (ALO), which can effectively search the hyperparameter space to find optimal parameter combinations. This optimization approach stabilizes convergence, reduces the manual selection of parameters in the optimization, and improves the classification performance. Eigen-CAM is embedded to produce explanations in the form of images that make the model more interpretable and boost confidence in the diagnosis predictions by clinicians. The proposed PASLF-RSDD framework was evaluated experimentally with a benchmark dataset called DermaEvolve. Comparative analysis shows that they have better classification results in several evaluation metrics.

Keywords

Rare Skin Disease, Deep Learning, Multi-Modal CycleGAN, Feature extraction, Hyperparameter optimization, Explainable artificial intelligence.

References

[1] Mengqiao He et al., “FPGDKG 1.0: An Integrated Facial Phenotype-Gene-Disease Knowledge Graph for Rare Disease Diagnosis and Explanation,” IEEE Journal of Biomedical and Health Informatics, pp. 1-10, 2026. 
[CrossRef] [Google Scholar] [Publisher Link]

[2] Shahnazeer Chembalakkat Kunjumohamad, and Sureshkumar Govindaraj, “NLP-Driven Federated Learning Framework for Multi-Organ Rare Disease Prediction,” Iran Journal of Computer Science, vol. 9, no. 1, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Kimberly F.Greco et al., “A Weakly Supervised Transformer for Rare Disease Diagnosis and Sub Phenotyping from EHRs with Pulmonary Case Studies,” npj Digital Medicine, vol. 9, no. 1, pp. 1-13, 2026. 
[CrossRef] [Google Scholar] [Publisher Link]

[4] Richard Noll et al., “Enhancing Diagnostic Precision for Rare Diseases using Case-based Reasoning,” Journal of the American Medical Informatics Association, vol. 33, no. 1, pp. 98-111, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Ana M.B. Amorim et al., “Artificial Intelligence in Rare Diseases: Toward Clinical Impact,” Trends in Pharmacological Sciences, vol. 46, no. 12, pp. 1241-1268, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Serena Lembo et al., “AI4RDD: Artificial Intelligence and Rare Disease Diagnosis: A Proposal to Improve the Anamnesis Process,” Image and Vision Computing, vol. 162, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] M. Mendez et al., “Leveraging Domain Knowledge for Synthetic Ultrasound Image Generation: A Novel Approach to Rare Disease AI Detection,” International Journal of Computer Assisted Radiology and Surgery, vol. 20, no. 2, pp. 415-431, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Lucas Cortial et al., “Artificial Intelligence in Drug Repurposing for Rare Diseases: A Mini-Review,” Frontiers in Medicine, vol. 11, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Shanavaz Mohammed et al., “A Review of AI-Powered Diagnosis of Rare Diseases,” International Journal of Current Science Research and Review, vol. 7, no. 9, pp. 6837-6843, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Felix Haller et al., “Utilizing Artificial Intelligence and Next-Generation Sequencing to Facilitate the Diagnosis of Rare Diseases,” Clinical Kidney Journal, vol. 17, no. 1, pp. 1-2, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Xi Chen et al., “RareAlert: Aligning Heterogeneous Large Language Model Reasoning for Early Rare Disease Risk Screening,” arXiv preprint, pp. 1-28, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Jingyu Tang, “Multi-Modal Fusion and Transferable Deep Learning for Rare Disease Detection: A CNN-Transformer Framework with Cross-Domain Adaptation on Limited CT and MRI Data,” Advances in Engineering Innovation, vol. 16, no. 6, pp. 144-148, 2025.
[CrossRef] [Publisher Link]

[13] Xin Wang, Da He, and Chunlin Jin, “AI-Driven Enhancements in Rare Disease Diagnosis and Support System Optimization,” Intractable and Rare Diseases Research, vol. 14, no. 4, pp. 306-308, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Giulio Napolitano et al., “Potential of Artificial Intelligence to Accelerate Drug Development for Rare Diseases,” Pharmaceutical Medicine, vol. 38, no. 2, pp. 79-86, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Magda Wojtara et al., “Artificial Intelligence in Rare Disease Diagnosis and Treatment,” Clinical and Translational Science, vol. 16 no. 11, pp. 2106-2111, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Jiayu Li et al., “Estimating Rare Disease Incidences with Large-Scale Internet Search data: Development and Evaluation of a Two-Step Machine Learning Method,” JMIR Infodemiology, vol. 3, no. 1, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Chaitran Chakilam, and Aaluri Seenu, “Transformative Applications of AI and ML in Personalized Treatment Pathways: Enhancing Rare Disease Support Through Advanced Neural Networks,” Frontiers in Health Informatics, vol. 13, no. 8, 2024.
[Google Scholar]

[18] Kaggle, DermaEvolve - Augmented unprocessed 64, Kaggle, 2025. [Online]. Available: https://www.kaggle.com/datasets/lokeshbhaskarnr/dermaevolve-augmented-unprocessed-64/data

[19] Ye Eun Kim et al., “Optical Coherence Tomography Image Enhancement and Layer Detection using Cycle-GAN,” Diagnostics, vol. 15, no. 3, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Gunjan Shandilya et al., “Proposed Dense Variational Autoencoder Model Integrated with Contrastive Learning for Foot Ulcer Classification,” Scientific Reports, vol. 16, no. 1, pp. 1-42, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Yunpeng Chang, and Bin Luo, “Bidirectional Convolutional LSTM Neural Network for Remote Sensing Image Super-Resolution,” Remote Sensing, vol. 11, no. 20, pp. 1-18, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Amirhosein Hojati et al., “Chaotic Hybrid Meta-Heuristic Optimization Algorithm for Construction Site Layout Planning Problem,” Letters in High Energy Physics, vol. 2024, pp. 4788-4791, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Mara Giavina-Bianchi et al., “Explainability Agreement Between Dermatologists and Five Visual Explanations Techniques in Deep Neural Networks for Melanoma AI Classification,” Frontiers in Medicine, vol. 10, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Anna Visibelli et al., “The Impact of Artificial Intelligence in the Odyssey of Rare Diseases,” Biomedicines, vol. 11 no. 3, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Irfan Al-Hussaini et al., “An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia,” Journal of Clinical Medicine, vol. 13, no. 6, pp. 1-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]