Asisten Kanker Payudara

Portal Penelitian CNN Breast Cancer

No Type BC Dataset Model Overview of CNN Blocks Result Author Keterangan
41 Malign Breast Cancer A clinical study at Capio Sankt G?ran Hospital, Sweden, involved 55.581 women. AI-based CAD (Computer-Aided Detection) algorithm called ScreenTrustCAD, integrated with Philips devices Not reported Penggunaan AI membantu radiolog dalam pengambilan keputusan dengan nyaman sebagai pembaca tambahan daripada pembaca independen Radiologists perceptions of using artificial intelligence for breast cancer detection in mammography screening in a clinical setting
42 Malign Breast Cancer Detection of breast cancer using machine learning on time-series diffuse optical transillumination data AI with Support Vector Machine (SVM) dan AutoGluon Reported AUC=0.95, Sens=0.833-0.889, Spec=0.874-0.881 Detection of breast cancer using machine learning on time-series diffuse optical transillumination data
43 Malign Breast Cancer Kohort 1: Berisi 299 kasus sebagai data pelatihan model Kohort 2: Berisi 369 kasus sebagai data validasi eksternal Kohort 3: Berisi 92 kasus sebagai data validasi eksternal AI with Wide ResNet50 Not reported Acc=0.95-0.97 dalam mengidentifikasi HER2 Low dan HER2 Positif sesuai panduan ASCO/CAP 2018. Tingkat kesesuaiannya dengan penilaian ahli (ICC = 0,77) lebih tinggi dibandingkan kesesuaian antar-patolog senior (ICC = 0,4568). Development of a Deep Learning model Tailored for HER2 Detection in Breast Cancer to aid pathologists in interpreting HER2-Low cases
44 Metastasis lymph node Memorial Sloan Kettering Cancer Center WSI's dataset AI by Paige BLN Not reported Waktu baca rata-rata per slide turun dari 129 detik menjadi 58 detik, meningkatkan efisiensi 55% (P<0,001) pada WSI jinak maupun ganas. Dua dari tiga ahli patologi menunjukkan peningkatan sensitivitas signifikan, dari 74,5% ke 93,5%?(P?0,006). Artificial Intelligence Helps Pathologists Increase Diagnostic Accuracy and Efficiency in the Detection of Breast Cancer Lymph Node Metastases
45 Malign Breast Cancer Total 190 specimens, clinical dataset AI by Visiopharm Not reported AI-assisted pathology with IHC reduced risk (RR = 0.680), saved ~?3,000, cut processing time by ~2 min 23 sec, and improved sensitivity by up to 30%, supporting its safety, efficiency, and cost-effectiveness. Clinical implementation of artificial-intelligence-assisted detection of breast cancer metastases in sentinel lymph nodes the CONFIDENT-B single-center, non-randomized clinical trial
46 Breast Pathology VinDr-Mammo dataset Algoritma Ensemble edRVFL (Ensemble Deep Random Vector Functional Link Neural Network) Not reported VGG16 Benign edRVFL: Acc=0.967, Prec=0.967, Rec=0.966, F1-score=0.967, Time=0.77, AUC 0.99 VGG16 Malign edRVFL: Acc=0.964, Prec=0.964, Rec=0.963, F1-score=0.963, Time=0.26, AUC=0.996 DenseNet21 Benign edRVFL: Acc=0.983, Prec=0.984, Rec=0.983, F1-score=0.984, Time=0.30, AUC=1 DenseNet21 Malign edRVFL: Acc=0.983, Prec=0.984, Rec=0.983, F1-score=0.984, Time=0.30 AUC=1 Hybrid ensemble deep learning model for advancing breast cancer detection and classification in clinical applications Jac
47 Invasive Breast Cancer (IC) Histopathology WSIs + clinical data Arsitektur CNN (Convolutional Neural Networks), dengan fokus utama pada Inception V3 Not reported Acc=0.935, Prec=0.958, Spec=0.852, Dice=0.946 Ensemble-based deep learning improves detection of invasive Dice
48 Breast Pathology About 1100 images, clinical dataset Enhanced U-Net dan Capsule Network (UCapsNet) Reported Acc=0.990, Prec=0.92, Dice=0.951, IoU=0.942 UCapsNet: A Two-Stage Deep Learning Model Using U-Net and Capsule Network for Breast Cancer Segmentation and Classification in Ultrasound Imaging AUC
49 Breast Pathology More than 683 patients, clinical dataset Deep Neural Network with Support Value (DNNS) Not reported Acc=0.972, Prec=0.979, Rec=0.97 Breast cancer detection by leveraging Machine Learning ROC
50 Breast Pathology Numerical dataset Wisconsin breast cancer (WBC) Hybrid (algoritma Gradient Boosting Decision Tree (GBDT) dan algoritma optimisasi Mayfly (Mayfly Optimization) Not reported Acc=0.963, Prec=0.972, Rec=0.985, F-measure=0.975, ROC=0.963, Sens=0.972, Spec=0.976, Time=14.25 GBDTMO as new option for early-stage breast cancer detection and classification using machine learning F1-score

📈 Tren Penelitian Berdasarkan Jenis (Type BC)