VMVincent Majanga

Vincent Majanga

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vincent Majanga has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • InjectGuard-RAG: Lightweight Defence Against Indirect Prompt Injection in Retrieval-Augmented Small-LLM Agents

    by Daniel Ayo Oladele, Vincent Majanga, Prince Yaw Owusu Amoako, Ernest Mnkandla, Malusi Sibiya

  • Open Access

    QEEF: A Quantitative Explainability Evaluation Framework for CNN and Vision Transformer-Based Segmentation Models in Dental Images

    by Vincent Majanga, Ernest Mnkandla, Yifan Luo, Daniel Oladele

    Deep learning methods have exemplified performance in various dental image segmentation tasks. However, their interpretability inadequacy remains a hindrance to clinical adoption. This study introduces a quantitative explainability-driven evaluation framework to systematically assess and compare convolutional and transformer-based segmentation models in dental imaging. Specifically, we evaluate a convolutional Watershed Encoder–Decoder Neural Network (WEDN) and the hybrid Vision Transformer U-Net (ViTUNet) model using both qualitative and quantitative explainability metrics. The qualitative analysis employs Grad-CAM, occlusion sensitivity, and attribution-based visualization techniques to assess model decision patterns. Quantitatively, we define and apply explainability metrics, including Dice coefficient, boundary Dice, sparsity, and faithfulness metric scores, to independently evaluate segmentation performance and explanation quality. The experimental results show that ViTUNet achieves superior spatial localization, with higher Dice (0.765) and boundary Dice (0.421), compared to the WEDN model (0.664 and 0.221), indicating improved lesion delineation in dental images. Moreover, the ViTUNet model exhibits higher sparsity scores in attribution maps, indicating more concentrated and structured interpretability regions, while the WEDN model demonstrates higher faithfulness scores under perturbation-based evaluations, thus reflecting stronger dependence on localized feature representations. These findings highlight a key distinction between convolutional and transformer-based architectures with predictive behavior and explanation characteristics. Notably, the results further indicate that gradient-based explanation methods are more stable for transformer-based models, while perturbation-based methods better capture the decision logic of convolutional networks. In general, this study establishes an integrated framework for collectively evaluating segmentation performance and explainability, allowing more transparent and clinically reliable deployment of deep learning models in dental imaging.


  • Physics-Informed Neural Network for Energy Demand Forecasting in South Africa

    by David Attipoe, Donatien Koulla Moulla, Sree Ganesh Thottempudi, Emmanuel Freeman, Jelil Olatunbosun Agbo-Ajala, Lateef Adesola Akinyemi, Olufisayo Sunday Ekundayo, Vincent Majanga, Ernest Mnkandla, Alain Abran

  • Open Access

    ViTUNet: Vision Transformer U-Net Hybrid Model for Carious Lesions Segmentation on Bitewing Dental Images

    by Vincent Majanga, Ernest Mnkandla, Ekundayo Olufisayo Sunday, Bosun Ajala, Thottempundi Sree

    Meticulous segmentation of medical images requires obtaining both local and global spatial detailed information. The conventional U-Net model excels at local spatial feature extraction through residual convolutional blocks but struggles to capture global features. To resolve this issue, we propose the vision transformer U-NeT (ViTUNet) model framework, which combines the self-attention mechanism of the vision transformer (ViT) to capture global information while maintaining the extraction of local features via U-NeT. This proposed architecture introduces vision transformers to the existing residual convolution blocks in the U-Net encoder path, thereby capturing both local and global features. The decoder path then rebuilds this information into high-quality segmentation maps with accurately highlighted boundaries/edges. This model is utilized to segment carious lesions in bitewing dental radiographs. These images are pre-processed using augmentation, morphological operations, and segmentation to identify the boundaries/edges of the regions of interest (caries/cavity). The proposed method is evaluated on an augmented dataset containing 3000 image–watershed mask pairs. It was trained on 2400 training images and tested on 600 testing images. The experimental results exemplified significant improvements in segmentation performance, achieving 98.45% validation accuracy, 97.88% validation Dice coefficient, and 95.87% validation intersection over union (IoU) metric scores. These results are superior compared to other conventional and state-of-the-art U-NeT models, thus highlighting the impact of transformer-based hybrid architectures in improving medical image segmentation tasks.


  • Open Access

    Watershed Encoder–Decoder Neural Network for Nuclei Segmentation of Breast Cancer Histology Images

    by Vincent Majanga, Ernest Mnkandla, Donatien Koulla Moulla, Sree Thotempudi, Attipoe David Sena

    Recently, deep learning methods have seen major advancements and are preferred for medical image analysis. Clinically, deep learning techniques for cancer image analysis are among the main applications for early diagnosis, detection, and treatment. Consequently, segmentation of breast histology images is a key step towards diagnosing breast cancer. However, the use of deep learning methods for image analysis is constrained by challenging features in the histology images. These challenges include poor image quality, complex microscopic tissue structures, topological intricacies, and boundary/edge inhomogeneity. Furthermore, this leads to a limited number of images required for analysis. The U-Net model was introduced and gained significant traction for its ability to produce high-accuracy results with very few input images. Many modifications of the U-Net architecture exist. Therefore, this study proposes the watershed encoder–decoder neural network (WEDN) to segment cancerous lesions in supervised breast histology images. Pre-processing of supervised breast histology images via augmentation is introduced to increase the dataset size. The augmented dataset is further enhanced and segmented into the region of interest. Data enhancement methods such as thresholding, opening, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted parts from the image. Consequently, further segmentation via the connected component analysis method is used to combine image pixel components with similar intensity values and assign them their respective labeled binary masks. The watershed filling method is then applied to these labeled binary mask components to separate and identify the edges/boundaries of the regions of interest (cancerous lesions). This resultant image information is sent to the WEDN model network for feature extraction and learning via training and testing. Residual convolutional block layers of the WEDN model are the learnable layers that extract the region of interest (ROI), which is the cancerous lesion. The method was evaluated on 3000 images–watershed masks, an augmented dataset. The model was trained on 2400 training set images and tested on 600 testing set images. This proposed method produced significant results of 98.53% validation accuracy, 96.98% validation dice coefficient, and 97.84% validation intersection over unit (IoU) metric scores.


  • Open Access

    Active Contours Connected Component Analysis Segmentation Method of Cancerous Lesions in Unsupervised Breast Histology Images

    by Vincent Majanga, Ernest Mnkandla, Zenghui Wang, Donatien Koulla Moulla

    Automatic segmentation of nuclei on breast cancer histology images is a basic and important step for diagnosis in a computer-aided diagnostic approach and helps pathologists discover cancer early. Nuclei segmentation remains a challenging problem due to cancer biology and the variability of tissue characteristics; thus, their detection in an image is a very tedious and time-consuming task. In this context, overlapping nuclei objects present difficulties in separating them by conventional segmentation methods; thus, active contours can be employed in image segmentation. A major limitation of the active contours method is its inability to resolve image boundaries/edges of intersecting objects and segment multiple overlapping objects as a single object. Therefore, we present a hybrid active contour (connected component + active contours) method to segment cancerous lesions in unsupervised human breast histology images. Initially, this approach prepares and pre-processes data through various augmentation methods to increase the dataset size. Then, a stain normalization technique is applied to these augmented images to isolate nuclei features from tissue structures. Secondly, morphology operation techniques, namely erosion, dilation, opening, and distance transform, are used to highlight foreground and background pixels while removing overlapping regions from the highlighted nuclei objects on the image. Consequently, the connected components method groups these highlighted pixel components with similar intensity values and assigns them to their relevant labeled component to form a binary mask. Once all binary-masked groups have been determined, a deep-learning recurrent neural network (RNN) model from the Keras architecture uses this information to automatically segment nuclei objects having cancerous lesions on the image via the active contours method. This approach, therefore, uses the capabilities of connected components analysis to solve the limitations of the active contour method. This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 15,179 images. This proposed method produced a significant evaluation result of 98.71% accuracy score.


  • Open Access

    Automatic Blob Detection Method for Cancerous Lesions in Unsupervised Breast Histology Images

    by Vincent Majanga, Ernest Mnkandla, Zenghui Wang, Donatien Koulla Moulla

    The early detection of cancerous lesions is a challenging task given the cancer biology and the variability in tissue characteristics, thus rendering medical image analysis tedious and time-inefficient. In the past, conventional computer-aided diagnosis (CAD) and detection methods have heavily relied on the visual inspection of medical images, which is ineffective, particularly for large and visible cancerous lesions in such images. Additionally, conventional methods face challenges in analyzing objects in large images due to overlapping/intersecting objects and the inability to resolve their image boundaries/edges. Nevertheless, the early detection of breast cancer lesions is a key determinant for diagnosis and treatment. In this study, we present a deep learning-based technique for breast cancer lesion detection, namely blob detection, which automatically detects hidden and inaccessible cancerous lesions in unsupervised human breast histology images. Initially, this approach prepares and pre-processes data through various augmentation methods to increase the dataset size. Secondly, a stain normalization technique is applied to the augmented images to separate nucleus features from tissue structures. Thirdly, morphology operation techniques, namely erosion, dilation, opening, and a distance transform, are used to enhance the images by highlighting foreground and background pixels while removing overlapping regions from the highlighted nucleus objects in the image. Subsequently, image segmentation is handled via the connected components method, which groups highlighted pixel components with similar intensity values and assigns them to their relevant labeled components (binary masks). These binary masks are then used in the active contours method for further segmentation by highlighting the boundaries/edges of ROIs. Finally, a deep learning recurrent neural network (RNN) model automatically detects and extracts cancerous lesions and their edges from the histology images via the blob detection method. This proposed approach utilizes the capabilities of both the connected components method and the active contours method to resolve the limitations of blob detection. This detection method is evaluated on 27,249 unsupervised, augmented human breast cancer histology dataset images, and it shows a significant evaluation result in the form of a 98.82% F1 accuracy score.


  • Open Access

    Automatic Watershed Segmentation of Cancerous Lesions in Unsupervised Breast Histology Images

    by Vincent Majanga, Ernest Mnkandla

    Segmentation of nuclei in histology images is key in analyzing and quantifying morphology changes of nuclei features and tissue structures. Conventional diagnosis, segmenting, and detection methods have relied heavily on the manual-visual inspection of histology images. These methods are only effective on clearly visible cancerous lesions on histology images thus limited in their performance due to the complexity of tissue structures in histology images. Hence, early detection of breast cancer is key for treatment and profits from Computer-Aided-Diagnostic (CAD) systems introduced to efficiently and automatically segment and detect nuclei cells in pathology. This paper proposes, an automatic watershed segmentation method of cancerous lesions in unsupervised human breast histology images. Firstly, this approach pre-processes data through various augmentation methods to increase the size of dataset images, then a stain normalization technique is applied to these augmented images to isolate nuclei features from tissue structures. Secondly, data enhancement techniques namely; erosion, dilation, and distance transform are used to highlight foreground and background pixels while removing unwanted regions from the highlighted nuclei objects on the image. Consequently, the connected components method groups these highlighted pixel components with similar intensity values and, assigns them to their relevant labeled component binary mask. Once all binary masked groups have been determined, a deep-learning recurrent neural network from the Keras architecture uses this information to automatically segment nuclei objects with cancerous lesions and their edges on the image via watershed filling. This segmentation method is evaluated on an unsupervised, augmented human breast cancer histology dataset of 11,151 images. This proposed method produced a significant evaluation result of 98% F1-accuracy score.


  • Open Access

    A Survey of Dental Caries Segmentation and Detection Techniques

    by Vincent Majanga, Serestina Viriri

    Dental caries detection, in the past, has been a challenging task given the amount of information got from various radiographic images. Several methods have been introduced to improve the quality of images for faster caries detection. Deep learning has become the methodology of choice when it comes to analysis of medical images. This survey gives an in-depth look into the use of deep learning for object detection, segmentation, and classification. It further looks into literature on segmentation and detection methods of dental images through deep learning. From the literature studied, we found out that methods were grouped according to the type of dental caries (proximal, enamel), type of X-ray images used (extraoral, intraoral), and segmentation method (threshold-based, cluster-based, boundary-based, and region-based). From the works reviewed, the main focus has been found to be on threshold-based segmentation methods. Most of the reviewed papers have preferred the use of intraoral X-ray images over extraoral X-ray images to perform segmentation on dental images of already isolated parts of the teeth. This paper presents an in-depth analysis of recent research in deep learning for dental caries segmentation and detection. It involves discussing the methods and algorithms used in segmenting and detecting dental caries. It also discusses various existing models used and how they compare with each other in terms of system performance and evaluation. We also discuss the limitations of these methods, as well as future perspectives on how to improve their performance.


  • Open Access

    Dental Images’ Segmentation Using Threshold Connected Component Analysis

    by Vincent Majanga, Serestina Viriri

    Recent advances in medical imaging analysis, especially the use of deep learning, are helping to identify, detect, classify, and quantify patterns in radiographs. At the center of these advances is the ability to explore hierarchical feature representations learned from data. Deep learning is invaluably becoming the most sought out technique, leading to enhanced performance in analysis of medical applications and systems. Deep learning techniques have achieved great performance results in dental image segmentation. Segmentation of dental radiographs is a crucial step that helps the dentist to diagnose dental caries. The performance of these deep networks is however restrained by various challenging features of dental carious lesions. Segmentation of dental images becomes difficult due to a vast variety in topologies, intricacies of medical structures, and poor image qualities caused by conditions such as low contrast, noise, irregular, and fuzzy edges borders, which result in unsuccessful segmentation. The dental segmentation method used is based on thresholding and connected component analysis. Images are preprocessed using the Gaussian blur filter to remove noise and corrupted pixels. Images are then enhanced using erosion and dilation morphology operations. Finally, segmentation is done through thresholding, and connected components are identified to extract the Region of Interest (ROI) of the teeth. The method was evaluated on an augmented dataset of 11,114 dental images. It was trained with 10 090 training set images and tested on 1024 testing set images. The proposed method gave results of for both precision and recall values, respectively.