Portal Penelitian CNN Breast Cancer

No	Type BC	Dataset	Model	Overview of CNN Blocks	Result	Author
21	Breast Pathology	The dataset consisted of 120 female patients with breast lumps admitted to a hospital in Changsha, Hunan Province, China	In AI, integrating residual and inception blocks within the SSD (Single Shot MultiBox Detector) architecture enhances feature representation and improves multi-scale object detection efficiency.	Reported	Acc=0.9476, for differentiating benign and malignant breast lesions Acc=0.9822, Sens=0.9713, Spec=0.9432	Multimodal Imaging of Target Detection Algorithm under Artificial Intelligence in the Diagnosis of Early Breast Cancer
22	Breast carcinoma	Breast Cancer Database of Coimbra, UCI (University of California Irvine) repository	Comparative study Machine Learning Decision Tree, Random Forest, KNN, ANN, SVM, dan Logistic Regression	Not reported	RF Acc=0.8330, Sens=1, Spec=0.6400 AUC=0.8810	Application of Machine Learning Models to the Detection of Breast Cancer
23	Breast Pathology	Wisconsin breast cancer (WBC)	An ensemble of four machine learning models?SVM, Logistic Regression, Na?ve Bayes, and Decision Tree?was combined, and the final diagnosis and prognosis of breast cancer were generated using an Artificial Neural Network (ANN).	Reported	The best diagnostic ensemble (SVM+LR+NB+DT) Acc=0.9767 without and 0.9883 with upsampling, while the best prognostic ensemble (SVM+LR+RF+NB) reached 0.8315 and 0.8833, showing improvements of 1.16% and 5.18%, respectively.	An Automatic Detection of Breast Cancer Diagnosis and Prognosis Based on Machine Learning Using Ensemble of Classifiers
24	Breast Pathology	This study employed a public mammography dataset from the University of South Florida (USF).	Reconstruction Independent Component Analysis (RICA)	Not reported	RICA+SVM RBF: Acc=0.9488, ROC=0.9914 RICA + texture using SVM Gaussian: Acc=0.9755, ROC=0.9976 RICA + morphological using SVM Polinomial: Acc=0.9622, ROC=0.9878	Automated breast cancer detection by reconstruction independent component analysis (RICA) based hybrid features using machine learning paradigms
25	Mass Lesions BC	This research employed a DCE-MRI breast dataset of 110 patients, consisting of 60 cases (847 images) for model training and 50 cases (721 images: 438 mass-type, 283 non-mass-type) for evaluation, obtained from Affiliated Jiangmen Hospital of Sun Yat-sen U	The Active Contour Model (ACM) integrates Extreme Learning Machine (ELM) and fuzzy C-means clustering (FCM).	Not reported	Dice=0.8939, Jacc=0.6416,	Active contour model of breast cancer DCE-MRI segmentation with an extreme learning machine and a fuzzy C-means cluster
26	Invasive Breast Cancer (IC)	The dataset comprised 115,457 H&E slides from 25,874 cases for algorithm development, 2,153 annotated slides, and over 2 million labeled patches for training. Internal testing included 2,252 slides from 1,090 cases, while external validation used 841 slid	Deep multi-magnification networks apply a deep learning approach.	Not reported	Invasive Cancer: Sens=0.9902, Spec=0.9827, AUC=0.9980 DCIS: Sens=1, Spec=0.9864, AUC=0.9990	Validation and real-world clinical application of an artificial intelligence algorithm for breast cancer detection in biopsies
27	Invasive Ductal Carcinoma (IDC)	Data from 238 asymptomatic breast cancer patients screened by ultrasound at Seoul National University Hospital	Algoritma deep convolutional neural network berbasis ResNet-34, yang diimplementasikan dalam perangkat lunak komersial Lunit INSIGHT MMG versi 1.1.4.0 (Lunit, Seoul, Korea)	Not reported	AI detected 66 of 253 breast cancers (26.1%), mainly in dense tissue or cases misread by radiologists, with detection influenced by larger tumor size (OR 2.2). In 160 controls, AI generated 19 false positives (11.9%).	Artificial Intelligence Improves Detection of Supplemental Screening Ultrasound-detected Breast Cancers in Mammography
28	Breast Pathology	Wisconsin breast cancer (WBC)	Ensemble Machine Learning (EML) Stacking Ensemble Model ( stack-1 NN)	Not reported	Acc=0.9989, Prec=1, F1-score=1, ROC=1, Sens=1, Spec=0.999, AUC=1	Enhancing Breast Cancer Detection and Classification Using Advanced Multi-Model Features and Ensemble Machine Learning Techniques
29	Breast Pathology	Mammographic Image Analysis Society (MIAS)	Metode klasifikasi SVM, RF, ANN, NB, dan DT + algoritma Median Filter (MF), Contrast Limited Adaptive Histogram Equalization (CLAHE), dan Unsharp Masking (USM)	Not reported	SVM+CLAHE+USM: Acc=1, F1-score=1, Sens=1, Spec=1 RF+CLAHE+USM: Acc=0.970 F1-score=0.969, Sens=0.941, Spec=1 ANN+CLAHE+USM: Acc=1, F1-score=1, Sens=1, Spec=1	A Novel Medical Image Enhancement Algorithm for Breast Cancer Detection on Mammography Images Using Machine Learning
30	Invasive Ductal Carcinoma (IDC)	This study utilized 378 digital mammograms collected from several public hospitals in Jeddah, Saudi Arabia	AI, MammoScreen, sebuah sistem berbasis CNN (Convolutional Neural Networks)	Not reported	Acc=0.923, ROC=0.923, Sens=0.928, Spec=0.919	Application of Artificial Intelligence in the Mammographic Detection of Breast Cancer in Saudi Arabian Women

Portal Penelitian CNN Breast Cancer

📈 Tren Penelitian Berdasarkan Jenis (Type BC)