A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 19, 2025

Artificial Intelligence (AI) research in breast cancer Magnetic Resonance Imaging (MRI) faces challenges due to limited expert-labeled segmentations. To address this, we present a multicenter dataset of 1506 pre-treatment T1-weighted dynamic contrast-enhanced MRI cases, including expert annotations primary tumors and non-mass-enhanced regions. The integrates imaging data from four collections Cancer Archive (TCIA), where only 163 cases with segmentations were initially available. facilitate the annotation process, deep learning model was trained produce preliminary for remaining cases. These subsequently corrected verified by 16 experts (averaging 9 years experience), creating fully annotated dataset. Additionally, includes 49 harmonized clinical demographic variables, as well pre-trained weights baseline nnU-Net on data. This resource addresses critical gap publicly available datasets, enabling development, validation, benchmarking advanced models, thus driving progress diagnostics, treatment response prediction, personalized care.

Language: Английский

---

Classification and Segmentation of Breast Tumor Ultrasound Images using VGG-16 and UNet

Biomedical & Pharmacology Journal, Journal Year: 2025, Volume and Issue: 18(1), P. 569 - 580

Published: March 31, 2025

Breast cancer remains a leading cause of mortality among women worldwide, necessitating accurate and efficient diagnostic methods. This study leverages ultrasound imaging for the early detection breast tumors, employing advanced deep learning models: VGG-16 convolutional neural network (CNN) to classify images UNet architecture tumor segmentation. The model, known extracting high-level features, achieved classification accuracy 90%, while reached an impressive 98% in segmenting regions. integration these models provides robust framework diagnosis, potentially enhancing clinical workflows facilitating treatment planning.

Language: Английский

---

Domesticating SAM for Breast Ultrasound Image Segmentation via Spatial-Frequency Fusion and Uncertainty Correction

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 20 - 37

Published: Oct. 30, 2024

Language: Английский

---

分割一切模型（SAM）在医学图像分割中的应用

Chinese Journal of Lasers, Journal Year: 2024, Volume and Issue: 51(21), P. 2107102 - 2107102

Published: Jan. 1, 2024

---