Lama Abdulrahman AlDakhil

Ms. Lama Abdulrahman AlDakhil

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 July 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
LALama Abdulrahman AlDakhil
Lama Abdulrahman AlDakhil
HAHaifa Fahad Alhasson
Haifa Fahad Alhasson
SAShuaa S Alharbi
Shuaa S Alharbi
Breast cancer diagnosis from histopathology images is often time consuming and prone to human error, impacting treatment and prognosis. Deep learning diagnostic methods offer the potential for improved accuracy and efficiency in breast cancer detection and classification. However, they struggle with limited data and subtle variations within and between cancer types. Attention mechanisms provide feature refinement capabilities that have shown promise in overcoming such challenges. To this end, this paper proposes the Efficient Channel Spatial Attention Network (ECSAnet), an architecture built on EfficientNetV2 and augmented with a convolutional block attention module (CBAM) and additional fully connected layers. ECSAnet was fine-tuned using the BreakHis dataset, employing Reinhard stain normalization and image augmentation techniques to minimize overfitting and enhance generalizability. In testing, ECSAnet outperformed AlexNet, DenseNet121, EfficientNetV2-S, InceptionNetV3, ResNet50, and VGG16 in most settings, achieving accuracies of 94.2% at 40×, 92.96% at 100×, 88.41% at 200×, and 89.42% at 400× magnifications. The results highlight the effectiveness of CBAM in improving classification accuracy and the importance of stain normalization for generalizability.

19 March 2024 in IEEE Access
Verified
Journal Article
Open access
LALama Abdulrahman AlDakhil
Lama Abdulrahman AlDakhil
AAAeshah Almutairi
Aeshah Almutairi
The simultaneous classification and grading of fruits are essential yet underexplored facets of computer vision in agricultural automation. This study proposes the application of same-domain transfer learning using the EfficientNetV2 architecture to facilitate multi-fruit classification and grading. Our dual-model framework initially employs EfficientNetV2 to distinguish between six fruit types—bananas, apples, oranges, pomegranates, limes, and guavas—within the FruitNet dataset. Subsequently, the learned parameters are transferred to a second model, which focuses on grading the quality of the fruits. To address the class imbalance in the dataset, we incorporate a combination of AugMix, CutMix, and MixUp, significantly improving model generalization. Our experiments demonstrate robust performance, with both classification and grading achieving an average test accuracy of 99%. These findings affirm the utility of same-domain transfer learning in enhancing grading accuracy using knowledge gained from classification tasks. The study shows promising potential for integrating this approach into machine vision systems to advance agricultural automation. Moving forward, this approach could be scaled to address broader cultivation challenges through the continued development of fine-grained visual analysis capabilities.

13 March 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
LALama Abdulrahman AlDakhil
Lama Abdulrahman AlDakhil
SAShuaa S Alharbi
Shuaa S Alharbi
AAAbdulrahman Aloraini
Abdulrahman Aloraini
HAHaifa Fahad Alhasson
Haifa Fahad Alhasson
Background: Breast cancer diagnosis is a global health challenge, requiring innovative methods to improve early detection accuracy and efficiency. This study investigates the integration of attention-based deep learning models with traditional machine learning (ML) methods to classify histopathological breast cancer images. Specifically, the Efficient Channel-Spatial Attention Network (ECSAnet) is utilized, optimized for binary classification by leveraging advanced attention mechanisms to enhance feature extraction across spatial and channel dimensions. Methods: Experiments were conducted using the BreakHis dataset, which includes histopathological images of breast tumors categorized as benign or malignant across four magnification levels: 40×, 100×, 200×, and 400×. ECSAnet was evaluated independently and in combination with traditional ML models, such as Decision Trees and Logistic Regression. The study also analyzed the impact of magnification levels on classification accuracy, robustness, and generalization. Results: Lower magnification levels consistently outperformed higher magnifications in terms of accuracy, robustness, and generalization, particularly for binary classification tasks. Additionally, combining ECSAnet with traditional ML models improved classification performance, especially at lower magnifications. These findings highlight the diagnostic strengths of attention-based models and the importance of aligning magnification levels with diagnostic objectives. Conclusions: This study demonstrates the potential of attention-based deep learning models, such as ECSAnet, to improve breast cancer diagnostics when integrated with traditional ML methods. The findings emphasize the diagnostic utility of lower magnifications and provide a foundation for future research into hybrid architectures and multimodal approaches to further enhance breast cancer diagnosis.

1 January 2025 in Applied Computational Intelligence and Soft Computing
Verified
Journal Article
Open access
LALama Abdulrahman AlDakhil
Lama Abdulrahman AlDakhil
HAHaifa Fahad Alhasson
Haifa Fahad Alhasson
SAShuaa S Alharbi
Shuaa S Alharbi
RKRehan Ullah Khan
Rehan Ullah Khan
Ali QamarAli Qamar
Ali Qamar
Breast cancer is characterized by abnormal cell growth, which leads to tumor formation. Autonomous breast cancer detection has seen good progress. However, there are still several challenges to robust detection. This survey article explores the complexities inherent in multiclass classification for breast cancer diagnosis, aiming to improve patient care, efficiency, and timeliness. In our study, we focus on using histopathology slide images and assess the current state of breast cancer classification, particularly with artificial intelligence, specifically deep learning and convolutional neural networks. The histopathology images are key tools in the diagnosis process, allowing pathologists to visually assess tissue samples for signs of cancer. Our analysis reveals several challenges that hinder the effectiveness of current diagnostic methods. One significant issue is the need for more diversity in the existing datasets, which often fail to represent a wide range of patient populations. This limitation reduces the accuracy of diagnostic results, mainly when applied to different clinical environments. Furthermore, class imbalances within these datasets, where certain cancer types or stages are underrepresented, lead to biased diagnoses, with more common cases being easily identified while rarer cases are frequently missed. Another challenge is the limited generalizability of current diagnostic techniques, which perform well in controlled environments but often need to improve when applied to new, unseen data from different institutions or imaging systems. Additionally, the complexity of histopathological analysis means that it can be difficult for clinicians to interpret certain findings, leading to uncertainty in the diagnostic process. Our study reveals that addressing these issues requires collaborative efforts to improve the quality of datasets, reduce class imbalances, and develop optimal standardized diagnostic methods. By overcoming these challenges, we can enhance the accuracy, efficiency, and accessibility of breast cancer diagnosis, ultimately leading to better patient outcomes and global healthcare. We believe that by examining several factors and variables and conducting an in‐depth analysis of the state of the art, this study will contribute to the state of the art and benefit researchers in both computing and medical domains.