Harmonized Dual Deep Learning Architectures for Image-Based Diagnostics of Skin Neglected Tropical Diseases: Benchmark Study via Novel Funnel Framework
JMIR Dermatology · 2026
DOI: 10.2196/91544 ↗At a glance
Journal article in JMIR Dermatology, 2026. Written by Yohannes Minyilu and 2 co-authors. Institution: Faculty of Computing and Software Engineering, Institute of Technology, Arba Minch University, SE, Arba Minch, Ethiopia, 251 0911434681. Major MEDLINE topics: Deep Learning, Neglected Diseases, Skin Diseases. Cited 1 times so far (Crossref); 49 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
While deep learning–based methods are the potential technological solutions for the diagnosis of skin Neglected Tropical Diseases (skin NTDs), limited efforts were seen toward the use of such tools in Ethiopia. Data scarcity, methods, and models selection issues created further challenges in an attempt to close the previous gap.
Objective
This study attempts to design a benchmark image-based diagnostic model for skin NTDs through a synergistic combination of feature extraction pretrained models, a custom-designed convolutional neural network (CNN) model trained on the extracted features, and an integrated data augmentation method applied dynamically.
Methods
For this study, a new skin images dataset is created using skin photographs collected by a team of researchers from the NTDs research center of Arba Minch University Medical College. The new dataset contains 1495 images in 3 classes having severe class imbalance. Extensive experiments were conducted to find the optimal deep learning approach by designing a new CNN model, applying transfer learning, and designing the 2-stage approach that uses pretrained models for feature extraction and trains the new CNN model using the extracted features from the pretrained models and applying data augmentation based on the integrated 2-stage approach. For model selection, the study proposed a novel approach, the funnel framework with cascaded selection of methods and models.
Results
After hyperparameter tuning, the model trained using DenseNet121 feature extractor scored the highest accuracy of 96.6%, F 1 -score of 95%, and sensitivity of 95%, while the MNv2-based model scored comparable results of 95.6% accuracy, 90% F 1 -score, and 90% sensitivity. This study finally selected the DenseNet121 and MNv2 models for feature extraction to build the final model for skin NTDs classification.
Conclusions
The 2-stage approach significantly boosted the models’ performance compared with other methods, while the data augmentation method further enhanced the performance of the selected models. Finally, this study suggests further studies using advanced class-balancing methods with more data and a possible integration of other clinical data types.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Faculty of Computing and Software Engineering, Institute of Technology, Arba Minch University, SE, Arba Minch, Ethiopia, 251 0911434681.
- School of Information Science, College of Natural and Computational Sciences, Addis Ababa University, Addis Ababa, Ethiopia.
ORCID profiles: Yohannes Minyilu, Mohammed Abebe Yimer, Million Meshesha
Cite
APA
Minyilu, Y., Yimer, M. A., & Meshesha, M. (2026). Harmonized Dual Deep Learning Architectures for Image-Based Diagnostics of Skin Neglected Tropical Diseases: Benchmark Study via Novel Funnel Framework. JMIR Dermatology. https://doi.org/10.2196/91544
Vancouver
Minyilu Y, Yimer MA, Meshesha M. Harmonized Dual Deep Learning Architectures for Image-Based Diagnostics of Skin Neglected Tropical Diseases: Benchmark Study via Novel Funnel Framework. JMIR Dermatology. 2026. doi:10.2196/91544
BibTeX
@article{Minyilu2026,
author = {Minyilu, Yohannes and Yimer, Mohammed Abebe and Meshesha, Million},
title = {Harmonized Dual Deep Learning Architectures for Image-Based Diagnostics of Skin Neglected Tropical Diseases: Benchmark Study via Novel Funnel Framework},
journal = {JMIR Dermatology},
year = {2026},
doi = {10.2196/91544}
}
EUVIMED