Portal Penelitian CNN Breast Cancer

No	Type BC	Dataset	Model	Overview of CNN Blocks	Result	Author
31	Breast Pathology	VinDr-Mammo in Vietnam, MiniDDSM, Chinese Mammography Database (CMMD)	Convolutional Neural Networks (CNN), yaitu EfficientNet dan ConvNeXt. Ensemble model YOLOX untuk ekstraksi ROI dan EfficientNet/ConvNeXt	Not reported	Prec=0.860, F1-score=0.810	Region-of-Interest Optimization for Deep-Learning-Based Breast Cancer Detection in Mammograms
32	Mass Lesions BC	Total of 875 patient studies with complete DBT (digital breast tomosynthesis) and ultrasound images	Metode machine learning dan upstream data fusion (UDF)	Not reported	In 55 test cases, 40% (22/55) showed ML detection across all three modalities (DBT CC, DBT MLO, and US), of which 90.9% (20/22) yielded correct fused detections and accurate lesion classification using UDF. FROC analysis demonstrated 90% sensitivity at only 0.3 false positives per case, whereas ML alone produced an average of 8.0 false alarms per case.	Breast cancer detection with upstream data fusion, machine learning, and automated registration initial results
33	Malign Breast Cancer	Data klinis di Rumah Sakit Universitas Tampere, Finlandia pada 392 mammogram	AI, sistem mammografi MicroDose SI dari Philips Healthcare dan Senographe Essential dari General Electric Medical Systems (GE)	Not reported	END2END: AUC=0.950, GLAM: AUC=0.888 ,GMIC: AUC=0.93 , DMV CNN: AUC=0.886	Saliency of breast lesions in breast cancer detection using artificial intelligence
34	Tubule segmentation	51 Whole Slide Images (WSIs), 8.225 patch citra	encoder: EfficientNetB3, ResNet34, dan DenseNet161 -decoder: EfficientNetB3-U-Net, ResNet34-U-Net, dan DenseNet161-U-Net	Reported	Rec=0.937, Spec=0.900, Dice=0.953,	Tubule-U-Net a novel dataset and deep learning-based tubule segmentation framework in whole slide images of breast cancer
35	Breast Pathology	DDSM (Digital Database for Screening Mammography), Inbreast, MIAS, WBC	FDCT-WRP (Fast Discrete Curvelet Transform with Wrapping) untuk ekstraksi fitur, diikuti oleh PCA dan LDA untuk reduksi fitur, lalu menggunakan Modified Particle Swarm Optimization (MODPSO) yang dikombinasikan dengan Extreme Learning Machine (ELM) sebagai	Not reported	DDSM, MIAS, dan INbreast dengan akurasi mencapai sekitar 98.94% (DDSM), 100% (MIAS), serta sensitivitas, presisi, spesifisitas, dan AUC yang tinggi (mendekati 1.0 pada MIAS).	Recent advancements in machine learning and deep learning-based breast cancer detection using mammograms
36	Breast Pathology	596 Breast Cancer Dataset from Kaggle	Machine Learning klasik dan ensemble soft voting	Reported	Acc=0.990, Prec=0.980, Rec=1, F1-score=0.990, AUC=1	An Efficient Breast Cancer Detection Using Machine Learning Classification Models
37	HER2 (Human Epidermal Growth Factor Receptor 2)	Clinical data, 847 images	Convolutional Neural Network (CNN) dengan arsitektur Resnet34	Reported	IoU=0.989	Single Vesicle Surface Protein Profiling and Machine Learning-Based Dual Image Analysis for Breast Cancer Detection
38	Malign Breast Cancer	MSI (Mammography Image Analysis Society), DDSM (Digital Database for Screening Mammography), INbreast, dan BreakHis (Breast Cancer Histopathological Database)	Hybrid CNN and Pruned Ensembled Extreme Learning Machine	Reported	Acc=0.872, AUC=0.96,	Breast Cancer Detection and Analytics Using Hybrid CNN and Extreme Learning Machine
39	Malign Breast Cancer	Dual-polarized UWB bra-tenna on ERI breast phantom dataset	Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Methods (GBM), Categorical Boost (CatBoost), Adaptive Boosting (AdaBoost), Decision Trees (DT), XGBoost	Not reported	SVM Acc=0.94, Prec=0.93, Rec=0.96, F1-score=0.94, AUC=0.96	Machine Learning for Breast Cancer Detection with Dual-Port Textile UWB MIMO Bra-Tenna System
40	Pectoral muscle segmentation	MIAS, INBREAST, dan DDSM	AI incorporating convolutional neural networks (CNNs)	Reported	Acc=0.989, Dice=0.982, Jacc=0.966	An Artificial Intelligence-Based Tool for Enhancing Pectoral Muscle Segmentation in Mammograms Addressing Class Imbalance and Validation Challenges in Automated Breast Cancer Diagnosis

Portal Penelitian CNN Breast Cancer

📈 Tren Penelitian Berdasarkan Jenis (Type BC)