Million Meshesha

Dr. Million Meshesha

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

4 December 2025 in JMIR AI
Verified
Journal Article
Open access
YMYohannes Minyilu
Yohannes Minyilu
MYMohammed Abebe Yimer
Mohammed Abebe Yimer
MMMillion Meshesha
Million Meshesha
Background: Neglected tropical diseases (NTDs) are the most prevalent diseases and comprise 21 different conditions. One-half of these conditions have skin manifestations, known as skin NTDs. The diagnosis of skin NTDs incorporates visual examination of patients, and deep learning (DL)–based diagnostic tools can be used to assist the diagnostic procedures. The use of advanced DL-based methods, including multimodal data fusion (MMDF) functionality, could be a potential approach to enhance the diagnostic procedures of these diseases. However, little has been done toward the application of such tools, as confirmed by the very few studies currently available that implemented MMDF for skin NTDs. Objective: This article presents a systematic review regarding the use of DL-based MMDF methods for the diagnosis of skin NTDs and related diseases (non-NTD skin diseases), including the ethical risks and potential risk of bias. Methods: The review was conducted based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) method using 6 parameters (research approach followed, disease[s] diagnosed, dataset[s] used, algorithm[s] applied, performance achieved, and future direction[s]). Results: Initially, 437 articles were collected from 5 major groups of identified sources; 14 articles were selected for the final analysis. Results revealed that, compared with traditional methods, the MMDF methods improved model performances for the diagnoses of skin NTDs and non-NTD skin diseases. Algorithmically, convolutional neural network (CNN)–based models were the predominantly used DL architectures (9/14 studies, 64% ), providing feature extraction, feature fusion, and disease classification, which were also conducted with transformer-based methods (1/14, 7%). Furthermore, recurrent neural networks were used in combination with CNN-based feature extractors to fuse multimodal data (1/14, 7%) and with generative models (1/14, 7%). The remaining studies used study-specific algorithms using transformers (1/14, 7%) and generative models (1/14, 7%). Conclusions: Finally, this article suggests that further studies should be conducted about using DL-based MMDF methods for skin NTDs, considering model efficiency, data scarcity, algorithm selection and use, fusion strategies of multiple modalities, and the possible adoption of such tools for resource-constrained areas.


17 February 2026 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
TSTariku Fetene Sewunet
Tariku Fetene Sewunet
MMMillion Meshesha
Million Meshesha
HSHussien Seid
Hussien Seid
Researchers and urban planners needs an enhanced strategies to handle their smart city development and this article is to provide a path for them about improving satellite driven urban intelligence, this Systematic Literature Review (SLR) presents technical advancements for smart city development needs, highlighting gaps in real-time processing and urban context generalization to offer a roadmap for researchers and planners to enhance satellite-driven urban intelligence. Image segmentation which is one of the image analysis technique that segments parts of the image as per the need of the application and semantic segmentation of satellite imagery specifically in this case is a pivotal task in remote sensing (RS) and Artificial Intelligence, leverages deep learning (DL) to classify each pixel, enabling applications from urban planning to disaster management. This SLR employs the SALSA framework (Search, Appraisal, Synthesis, Analysis) to systematically review 50 studies from January 2019 to September 2024, by exploring Deep Learning (DL) methodologies followed, datasets used, evaluation techniques, and contributions to smart city development. Searching papers from Scopus, IEEE Xplore, and Web of Science, we retrieved 1245 articles, finally refined to 50 via explicit criteria such as DL focus, satellite-specific, smart city relevance and peer-reviewed articles. Findings reveal that, U-Net and DeepLab V3 + dominate (IoU 0.8–0.90), driven by datasets like Sentinel-2 and DeepGlobe, supporting smart city goals such as intelligent mobility, environmental monitoring, and governance. However, challenges continue and future directions such as lightweight models, domain adaptation, and interdisciplinary impact studies are forwarded.

23 June 2026 in JMIR Dermatology
Verified
Journal Article
Open access
YMYohannes Minyilu
Yohannes Minyilu
MYMohammed Abebe Yimer
Mohammed Abebe Yimer
MMMillion Meshesha
Million Meshesha
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.