3D CNN-BN: A Breakthrough in Colorectal Cancer Detection with Deep Learning Technique DOI
Khadija Hicham, Abdeljalil El-Ibrahimi, Sara Laghmati

и другие.

Опубликована: Май 16, 2024

The Convolutional neural network (CNN) has made significant strides in the medical domain. CNN excels at extraction of highly representative features acute pathology. Amidst layers, allows classification Through process filtering, selecting, and implementing these characteristics final layer level that is fully connected. Colon cancer rises from cells cover inner lining colon. Frequently originating a noncancerous growth known as polyp, it progresses gradually eventually becomes cancerous. Our study aims to develop computer-aided detection (CAD) system using CT colonography dataset for colorectal (CRC) prevention by classifying scans polyp or polyp-free. After preprocessing phase, we developed deep-learning model with two variations: 3D CNN-BN & Dropout. images abdomen according presence polyps its absence primordial enhance chance early detection. Thus, move toward appropriate treatment. primary emphasis on enhancing training deep learning models improving their performance during testing phase. findings suggest 3DCNN-BN demonstrated superior performance, achieving an accuracy 92%.

Язык: Английский

An Integrated Multimodal Deep Learning Framework for Accurate Skin Disease Classification DOI Open Access
Soufiane Hamida, Driss Lamrani, Mohammed Amine Bouqentar

и другие.

International Journal of Online and Biomedical Engineering (iJOE), Год журнала: 2024, Номер 20(02), С. 78 - 94

Опубликована: Фев. 14, 2024

In order to effectively treat skin diseases, an accurate and prompt diagnosis is required. this article, a novel method for classifying disorders using multimodal classifier presented. The proposed utilizes multiple information sources enhance the accuracy of disease classification. It incorporates images lesions patient-specific data. simultaneously classifies diseases by combining image structured data inputs. effectiveness was evaluated ISIC 2018 dataset, which includes clinical seven categories diseases. results indicate that model outperforms conventional single-modal single-task classifiers, achieving 98.66% classification 94.40% addition, we compare performance with other methodologies, demonstrating its superiority. Despite yielding promising results, has limitations in terms requirements generalizability. Future research directions include incorporating additional sources, investigating genetic integration, applying various medical conditions. This study illustrates potential integrating techniques transfer learning deep neural networks cutaneous

Язык: Английский

Процитировано

5
Multimodal Skin Cancer Prediction: Integrating Dermoscopic Images and Clinical Metadata with Transfer Learning DOI Open Access
Ramya Panneerselvam, Sathiyabhama Balasubramaniam, Vidhushavarshini Sureshkumar

и другие.

The Open Bioinformatics Journal, Год журнала: 2025, Номер 18(1)

Опубликована: Янв. 28, 2025

Background Skin cancers exist as the most pervasive in world; to increase survival rates, early prediction has become more predominant. Many conventional techniques frequently depend on visual review of clinical information and dermoscopic illustrations. In recent technological developments, enthralling algorithms combining modalities are used for increasing diagnosis accuracy deep learning. Methods Our research proposes a multi-faceted approach skin cancer that incorporates metadata with visuals. The pre-trained convolutional neural networks, like EfficientNetB3, were images along transfer learning excavate some attributes this study. Moreover, TabNet was processing metadata, including age, gender, medical history. features obtained from both fusion integrated enhance accuracy. benchmark datasets, ISIC 2018, 2019, HAM10000, assess model. Results proposed system achieved 98.69% classification cancer, surpassing model snapshots data. convergence substantially enhanced resilience, demonstrating importance multimodal lesion diagnosis. Conclusion This focused mainly efficiency integrating visuals using prediction. offers promising tool improving diagnostic accuracy, further could explore its application other fields requiring data integration.

Язык: Английский

Процитировано

0
Predictive Modeling of Flood Susceptibility in Tetouan, Morocco Using Machine Learning Algorithms DOI

Moutaouakil Wassima,

Soufiane Hamida,

Nouhaila Akouz

и другие.

Опубликована: Май 16, 2024

Floods represent a significant natural hazard causing extensive damages. The research aims to demonstrate the robustness of employing Machine Learning (ML) models, namely Random Forest (RF), Support Vector (SVM), Logistic Regression (LR), K-nearest neighbor (KNN), and Decision Tree (DT) generate flood susceptibility maps for Tetouan city in Morocco. methodology relies on spatial dataset comprising 1000 samples, including eight conditioning factors: elevation, slope, distance river (DR), drainage density (DD), Land Use (LU), Stream Power Index (SPI), Topographic Witness (TWI), Normalized Difference Vegetation (NDVI). These factors were extracted using remote sensing techniques. Performance comparisons ML algorithms reveal that RF exhibited highest accuracy area under curve (AUC) values, reaching 95%, thereby outperforming other models. key findings this study can serve as guidelines authorities hydrologists proactively predict flood-prone areas implement necessary measures mitigate risks.

Язык: Английский

Процитировано

2
Fuzzy Logic based Expert System for Early Predicting of Chronic Kidney Disease DOI
Abdeljalil El-Ibrahimi, Sara Laghmati, Khadija Hicham

и другие.

Опубликована: Май 16, 2024

Chronic kidney disease (CKD) is a dangerous illness defined as the presence of damage in which cannot filter blood way they should. to human kidneys occurs gradually over long period. There are five stages development CKD, late stage patient needs transplant or dialysis treatment remain alive. Early diagnosis (stages 1 3) can slow its progression and minimize complications patients. Numerous methods models have been developed diagnose CKD early stages. In this paper, we employ fuzzy logic theory develop an expert system predict CKD. The most difficult task designing logic-based find set rules construct membership functions. Therefore, study use Fuzzy C-means clustering (FCM) method automatically cluster training data generate along with was implemented on MATLAB software. experimental result showed that designed attains higher outcome than existing methods, achieving remarkable accuracy 100%.

Язык: Английский

Процитировано

1
3D CNN-BN: A Breakthrough in Colorectal Cancer Detection with Deep Learning Technique DOI
Khadija Hicham, Abdeljalil El-Ibrahimi, Sara Laghmati

и другие.

Опубликована: Май 16, 2024

The Convolutional neural network (CNN) has made significant strides in the medical domain. CNN excels at extraction of highly representative features acute pathology. Amidst layers, allows classification Through process filtering, selecting, and implementing these characteristics final layer level that is fully connected. Colon cancer rises from cells cover inner lining colon. Frequently originating a noncancerous growth known as polyp, it progresses gradually eventually becomes cancerous. Our study aims to develop computer-aided detection (CAD) system using CT colonography dataset for colorectal (CRC) prevention by classifying scans polyp or polyp-free. After preprocessing phase, we developed deep-learning model with two variations: 3D CNN-BN & Dropout. images abdomen according presence polyps its absence primordial enhance chance early detection. Thus, move toward appropriate treatment. primary emphasis on enhancing training deep learning models improving their performance during testing phase. findings suggest 3DCNN-BN demonstrated superior performance, achieving an accuracy 92%.

Язык: Английский

Процитировано

1