We propose a new method for breast cancer screening from DCE-MRI based on a post-hoc approach that is trained using weakly annotated data (i.e., labels are available only at the image level without any lesion delineation). Our proposed post-hoc method automatically diagnosis the whole volume and, for positive cases, it localizes the malignant lesions that led to such diagnosis. Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy -- this approach is trained using strongly annotated data (i.e., it needs a delineation and classification of all lesions in an image). Another goal of this paper is to establish the advantages and disadvantages of both approaches when applied to breast screening from DCE-MRI. Relying on experiments on a breast DCE-MRI dataset that contains scans of 117 patients, our results show that the post-hoc method is more accurate for diagnosing the whole volume per patient, achieving an AUC of 0.91, while the pre-hoc method achieves an AUC of 0.81. However, the performance for localising the malignant lesions remains challenging for the post-hoc method due to the weakly labelled dataset employed during training.
The University of Adelaide（阿德莱德大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）；Delft University of Technology（代尔夫特理工大学）；Queensland University of Technology（昆士兰科技大学）
There is a heated debate on how to interpret the decisions provided by deep learning models (DLM), where the main approaches rely on the visualization of salient regions to interpret the DLM classification process. However, these approaches generally fail to satisfy three conditions for the problem of lesion detection from medical images: 1) for images with lesions, all salient regions should represent lesions, 2) for images containing no lesions, no salient region should be produced,and 3) lesions are generally small with relatively smooth borders. We propose a new model-agnostic paradigm to …
PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-class breast DCE-MRI classification
Nankai University（南开大学）；Zhongguancun Academy（中关村学院）；The First Medical Center of Chinese PLA General Hospital（中国人民解放军总医院第一医学中心）；Beijing University of Posts and Telecommunications（北京邮电大学）；The Six Medical Center of Chinese PLA General Hospital（中国人民解放军总医院第六医学中心）；Tsinghua University（清华大学）
Iran University of Science and Technology（伊朗科技大学）；Radboud University Medical Center（拉德堡德大学医学中心）；Netherlands Cancer Institute（荷兰癌症研究所）
Purpose: We propose a deep learning-based computer-aided detection (CADe) method to detect breast lesions in ultrafast DCE-MRI sequences. This method uses both the three-dimensional spatial information and temporal information obtained from the early-phase of the dynamic acquisition. Methods: The proposed CADe method, based on a modified 3D RetinaNet model, operates on ultrafast T1 weighted sequences, which are preprocessed for motion compensation, temporal normalization, and are cropped before passing into the model. The model is optimized to enable the detection of relatively small breast le…
Image Sciences Institute, University Medical Center Utrecht（乌得勒支大学医学中心影像科学研究所）；Department of Radiology, Antoni van Leeuwenhoek Hospital - The Netherlands Cancer Institute（荷兰癌症研究所安东尼·范·列文虎克医院放射科）
Response of breast cancer to neoadjuvant chemotherapy (NAC) can be monitored using the change in visible tumor on magnetic resonance imaging (MRI). In our current workflow, seed points are manually placed in areas of enhancement likely to contain cancer. A constrained volume growing method uses these manually placed seed points as input and generates a tumor segmentation. This method is rigorously validated using complete pathological embedding. In this study, we propose to exploit deep learning for fast and automatic seed point detection, replacing manual seed point placement in our existing …
Evaluating ADC-only deep learning pipelines for breast cancer detection and segmentation using standalone diffusion-weighted MRI
University of Oviedo（奥维耶多大学）；University of A Coruña（拉科鲁尼亚大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Purdue University（普渡大学）；Asturias Central University Hospital (HUCA)（阿斯图里亚斯中央大学医院）
Deep transfer learning using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has shown strong predictive power in characterization of breast lesions. However, pretrained convolutional neural networks (CNNs) require 2D inputs, limiting the ability to exploit the rich 4D (volumetric and temporal) image information inherent in DCE-MRI that is clinically valuable for lesion assessment. Training 3D CNNs from scratch, a common method to utilize high-dimensional information in medical images, is computationally expensive and is not best suited for moderately sized healthcare datasets. …
Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI
School of Health Science and Engineering, University of Shanghai for Science and Technology（上海理工大学健康科学与工程学院）；School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Ruijin Hospital, Shanghai Jiaotong University School of Medicine（上海交通大学医学院附属瑞金医院）；Shanghai General Hospital（上海交通大学附属第一人民医院）
TopoTxR: A topology-guided deep convolutional network for breast parenchyma learning on DCE-MRIs
State University of New York at Stony Brook（纽约州立大学石溪分校）；Newark Beth Israel Medical Center（纽瓦克贝斯以色列医疗中心）；Columbia University Irving Medical Center（哥伦比亚大学欧文医疗中心）；Emory University School of Medicine（埃默里大学医学院）；Georgia Institute of Technology（佐治亚理工学院）
Pre- to Post-Contrast Breast MRI Synthesis for Enhanced Tumour Segmentation
Universitat de Barcelona（巴塞罗那大学）；Helmholtz Center Munich（慕尼黑亥姆霍兹中心）；Technical University of Munich（慕尼黑工业大学）；Karolinska Institutet（卡罗林斯卡学院）；King’s College London（伦敦国王学院）
To deform or not: treatment-aware longitudinal registration for breast DCE-MRI during neoadjuvant chemotherapy via unsupervised keypoints detection
Radboud University Medical Centre（拉德堡德大学医学中心）；The Netherlands Cancer Institute（荷兰癌症研究所）；Macao Polytechnic University（澳门理工大学）；Maastricht University Medical Centre（马斯特里赫特大学医学中心）
LesiOnTime -- Joint Temporal and Clinical Modeling for Small Breast Lesion Segmentation in Longitudinal DCE-MRI
Computational Imaging Research Lab, Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria（医学影像研究实验室，生物医学影像与影像引导治疗系，维也纳医科大学）；Comprehensive Center for AI in Medicine, Medical University of Vienna, Austria（医学人工智能综合中心，维也纳医科大学）；Breast Health Center, Privatklinik Döbling, Austria（乳腺健康中心，多克林根私人诊所）；Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria（生物医学影像与影像引导治疗系，维也纳医科大学）；Department of Obstetrics and Gynecology, Medical University of Vienna, Austria（妇产科系，维也纳医科大学）；Department of Pathology, Medical University of Vienna, Austria（病理学系，维也纳医科大学）；Comprehensive Cancer Center, Medical University of Vienna, Austria（综合癌症中心，维也纳医科大学）
Case Western Reserve University（凯斯西储大学）；University of Mons（蒙斯大学）；Cleveland Clinic（克利夫兰诊所）；Yale School of Medicine（耶鲁医学院）；Institut Jules Bordet（朱尔斯·博尔代研究所）；University Hospitals Cleveland Medical Center（大学医院克利夫兰医学中心）；Louis Stokes Cleveland VA Medical Center（路易斯·斯托克斯克利夫兰退伍军人事务医疗中心）
Predicting response to neoadjuvant therapy is a vexing challenge in breast cancer. In this study, we evaluate the ability of deep learning to predict response to HER2-targeted neo-adjuvant chemotherapy (NAC) from pre-treatment dynamic contrast-enhanced (DCE) MRI acquired prior to treatment. In a retrospective study encompassing DCE-MRI data from a total of 157 HER2+ breast cancer patients from 5 institutions, we developed and validated a deep learning approach for predicting pathological complete response (pCR) to HER2-targeted NAC prior to treatment. 100 patients who received HER2-targeted ne…
This work presents a novel self-supervised pre-training method to learn efficient representations without labels on histopathology medical images utilizing magnification factors. Other state-of-theart works mainly focus on fully supervised learning approaches that rely heavily on human annotations. However, the scarcity of labeled and unlabeled data is a long-standing challenge in histopathology. Currently, representation learning without labels remains unexplored for the histopathology domain. The proposed method, Magnification Prior Contrastive Similarity (MPCS), enables self-supervised lear…
Anguinus Sculpturae: Compositional Synthesis of Peak-Enhancement Breast DCE-MRI Scans
German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）；HIDSS4Health – Helmholtz Information and Data Science School for Health（HIDSS4Health – 亥姆霍兹健康信息与数据科学学校）；Helmholtz Imaging（亥姆霍兹成像中心）
The Chinese University of Hong Kong（香港中文大学）；Imsight Medical Technology, Co., Ltd.（推想医疗科技股份有限公司）；Imperial College London（伦敦帝国理工学院）；The Fifth Medical Center of Chinese PLA General Hospital（中国人民解放军总医院第五医学中心）；Beijing Image Diagnostic Center of Rimag（北京一脉阳光影像诊断中心）
Accurate and automatic analysis of breast MRI plays an important role in early diagnosis and successful treatment planning for breast cancer. Due to the heterogeneity nature, accurate diagnosis of tumors remains a challenging task. In this paper, we propose to identify breast tumor in MRI by Cosine Margin Sigmoid Loss (CMSL) with deep learning (DL) and localize possible cancer lesion by COrrelation Attention Map (COAM) based on the learned features. The CMSL embeds tumor features onto a hypersphere and imposes a decision margin through cosine constraints. In this way, the DL model could learn …
Classification of malignancy for breast cancer and other cancer types is usually tackled as an object detection problem: Individual lesions are first localized and then classified with respect to malignancy. However, the drawback of this approach is that abstract features incorporating several lesions and areas that are not labelled as a lesion but contain global medically relevant information are thus disregarded: especially for dynamic contrast-enhanced breast MRI, criteria such as background parenchymal enhancement and location within the breast are important for diagnosis and cannot be cap…
School of Information Technology and Electrical Engineering, University of Queensland（昆士兰大学信息技术与电气工程学院）；Science and Engineering Faculty, Queensland University of Technology（昆士兰科技大学科学与工程学院）
Previous studies on computer aided detection/diagnosis (CAD) in 4D breast magnetic resonance imaging (MRI) regard lesion detection, segmentation and characterization as separate tasks, and typically require users to manually select 2D MRI slices or regions of interest as the input. In this work, we present a breast MRI CAD system that can handle 4D multimodal breast MRI data, and integrate lesion detection, segmentation and characterization with no user intervention. The proposed CAD system consists of three major stages: region candidate generation, feature extraction and region candidate cla…
Department of Medicine I, LMU University Hospital, LMU Munich, Germany（慕尼黑大学医学部第一部门，LMU大学医院，慕尼黑，德国）；Lunit Inc.（Lunit公司）
Large annotated datasets are essential for training robust Computer-Aided Diagnosis (CAD) models for breast cancer detection or risk prediction. However, acquiring such datasets with fine-detailed annotation is both costly and time-consuming. Vision-Language Models (VLMs), such as CLIP, which are pre-trained on large image-text pairs, offer a promising solution by enhancing robustness and data efficiency in medical imaging tasks. This paper introduces a novel Multi-View Mammography and Language Model for breast cancer classification and risk prediction, trained on a dataset of paired mammogram…
Multiparametric Deep Learning Tissue Signatures for a Radiological Biomarker of Breast Cancer: Preliminary Results
The Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院）；Sidney Kimmel Comprehensive Cancer Center（西德尼·基梅尔综合癌症中心）；The Johns Hopkins University（约翰霍普金斯大学）；University of Kentucky（肯塔基大学）；University of Wisconsin School of Medicine and Public Health（威斯康星大学医学与公共卫生学院）
Ecole Centrale de Nantes（南特中央理工学院）；Hera-MI, SAS（Hera-MI股份有限公司）
We study the fully convolutional neural networks in the context of malignancy detection for breast cancer screening. We work on a supervised segmentation task looking for an acceptable compromise between the precision of the network and the computational complexity.
Ultrasound-based detection and malignancy prediction of breast lesions eligible for biopsy: A multi-center clinical-scenario study using nomograms, large language models, and radiologist evaluation
Shahid Beheshti University of Medical Sciences（沙希德·贝赫什提医科大学）；Urmia University of Medical Science（乌尔米耶医科大学）；University of Health Sciences（健康科学大学）；Kartal Dr. Lütfi Kırdar City Hospital（卡尔塔尔·吕特菲·克尔达尔市医院）；University of Padova（帕多瓦大学）；Universal Scientific Education and Research Network (USERN)（全球科学教育与研究网络（USERN））；Tehran University of Medical Sciences（德黑兰医科大学）；Danube Private University（多瑙河私立大学）；Austrian Center for Medical Innovation and Technology (ACMIT)（奥地利医学创新与技术中心（ACMIT））；University of Southern Queensland（南昆士兰大学）
Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks
Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM)（巴塞罗那人工智能医学实验室）；Departament de Matemàtiques i Informàtica, Universitat de Barcelona（巴塞罗那大学数学与计算机科学系）；Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich（生物医学成像机器学习研究所，海德堡慕尼黑）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑技术大学计算、信息与技术学院）；Department of Oncology-Pathology, Karolinska Institutet（卡罗林斯卡研究所肿瘤-病理学系）；School of Biomedical Engineering & Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与成像科学学院）
I3S - Instituto de Investigação e Inovação em Saúde, Universidade Do Porto（波尔图大学健康创新与研究学院（I3S））；INEB - Instituto de Engenharia Biomédica, Universidade Do Porto（波尔图大学生物医学工程研究所（INEB））；Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto（波尔图大学分子病理学与免疫学研究所Ipatimup诊断中心）；Tongji University（同济大学）；National University of Defense Technology（国防科技大学）；University of Udine（乌迪内大学）；Sharif University of Technology（谢里夫理工大学）；Private Group Practice for Pathology, Lübeck（吕贝克私人病理联合诊所）；DeePathology（DeePathology公司）；Roche Diagnostics GmbH（罗氏诊断有限公司）；Arontier Co., Ltd（Arontier有限公司）；INESC TEC - Institute for Systems and Computer Engineering, Technology and Science（系统与计算机工程技术科学研究所（INESC TEC））；FEUP - Faculty of Engineering, University of Porto（波尔图大学工程学院（FEUP））；FMUP - Faculty of Medicine, University of Porto（波尔图大学医学院（FMUP））
Breast cancer is the most common malignancy in women, being responsible for more than half a million deaths every year. As such, early and accurate diagnosis is of paramount importance. Human expertise is required to diagnose and correctly classify breast cancer and define appropriate therapy, which depends on the evaluation of the expression of different biomarkers such as the transmembrane protein receptor HER2. This evaluation requires several steps, including special techniques such as immunohistochemistry or in situ hybridization to assess HER2 status. With the goal of reducing the number…
Robustness of breast lesion segmentation under MRI undersampling improves with k-space-aware deep learning
Institute for AI in Medicine (IKIM), University Hospital Essen（人工智能医学研究所（IKIM），埃森大学医院）；Department of Physics, Technical University Dortmund（物理系，多特蒙德技术大学）；Division of Radiology, German Cancer Research Center (DKFZ)（放射学部，德国癌症研究中心（DKFZ））；Cancer Research Center Cologne Essen (CCCE), University Medicine Essen（科隆埃森癌症研究中心（CCCE），埃森大学医学中心）；RACOON Study Group, Site Essen（RACOON研究组，埃森站点）；German Cancer Consortium (DKTK), Partner Site Essen（德国癌症联合会（DKTK），埃森合作伙伴站点）；Medical Faculty and Faculty of Computer Science, University of Duisburg-Essen（医学系和计算机科学系，杜伊斯堡-埃森大学）
Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Institute for Systems and Robotics, Instituto Superior Tecnico（高等技术学院系统与机器人研究所）
Meta-training has been empirically demonstrated to be the most effective pre-training method for few-shot learning of medical image classifiers (i.e., classifiers modeled with small training sets). However, the effectiveness of meta-training relies on the availability of a reasonable number of hand-designed classification tasks, which are costly to obtain, and consequently rarely available. In this paper, we propose a new method to unsupervisedly design a large number of classification tasks to meta-train medical image classifiers. We evaluate our method on a breast dynamically contrast enhanc…
Mammography-based screening has helped reduce the breast cancer mortality rate, but has also been associated with potential harms due to low specificity, leading to unnecessary exams or procedures, and low sensitivity. Digital breast tomosynthesis (DBT) improves on conventional mammography by increasing both sensitivity and specificity and is becoming common in clinical settings. However, deep learning (DL) models have been developed mainly on conventional 2D full-field digital mammography (FFDM) or scanned film images. Due to a lack of large annotated DBT datasets, it is difficult to train a …
Sustainable Deep Learning-Based Breast Lesion Segmentation: Impact of Breast Region Segmentation on Performance
Norwegian University of Science and Technology（挪威科技大学）；More og Romsdal Hospital Trust（默勒-鲁姆斯达尔医院信托基金）；Stavanger University Hospital（斯塔万格大学医院）；The University of Stavanger（斯塔万格大学）；Akershus University Hospital（阿克什胡斯大学医院）；University of Oslo（奥斯陆大学）
Data scarcity and class imbalance are two fundamental challenges in many machine learning applications to healthcare. Breast cancer classification in mammography exemplifies these challenges, with a malignancy rate of around 0.5% in a screening population, which is compounded by the relatively small size of lesions (~1% of the image) in malignant cases. Simultaneously, the prevalence of screening mammography creates a potential abundance of non-cancer exams to use for training. Altogether, these characteristics lead to overfitting on cancer cases, while under-utilizing non-cancer data. Here, w…
In practice, histopathological diagnosis of tumor malignancy often requires a human expert to scan through histopathological images at multiple magnification levels, after which a final diagnosis can be accurately determined. However, previous research on such classification tasks using convolutional neural networks primarily determine a diagnosis for a single magnification level. In this paper, we propose a case-based approach using deep residual neural networks for histopathological malignancy diagnosis, where a case is defined as a sequence of images from the patient at all available levels…
Automated detection and segmentation of non-mass enhancing breast tumors with dynamic contrast-enhanced magnetic resonance imaging
Universidad de Granada（格拉纳达大学）；Memorial Sloan-Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）；Medical University Vienna/AKH Wien（维也纳医科大学/维也纳总医院）；Florida State University（佛罗里达州立大学）
Large Kernel MedNeXt for Breast Tumor Segmentation and Self-Normalizing Network for pCR Classification in Magnetic Resonance Images
Department of Computer Engineering, Kwame Nkrumah University of Science and Technology（计算机工程系，库马西大学科学与技术学院）；Infectious Disease Group, Kumasi Centre for Collaborative Research in Tropical Medicine（传染病研究组，库马西热带医学协作研究中心）
A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations
Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM)（巴塞罗那医学人工智能实验室（BCN-AIM））；Facultat de Matemàtiques i Informàtica, Universitat de Barcelona（巴塞罗那大学数学与信息学院）；Institute of Machine Learning in Biomedical Imaging, Helmholtz Center Munich（慕尼黑亥姆霍兹中心生物医学影像机器学习研究所）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Department of Oncology-Pathology, Karolinska Institutet（卡罗林斯卡学院肿瘤病理学系）；nd Dept. of Radiology, Medical University of Gdansk（格但斯克医科大学第二放射科）；Área de Radiología Mamaria y Ginecológica (UDIAT CD), Parc Taulí Hospital Universitari（陶利大学医院乳腺与妇科放射学领域（UDIAT CD））；Unitat de Diagnòstic per la Imatge de la Mama (UDIM), Hospital Germans Trias i Pujol（日耳曼特里亚斯 i 普霍尔医院乳腺影像诊断单元（UDIM））；Centro Mamario Instituto Alexander Fleming（亚历山大·弗莱明研究所乳腺中心）
New York University（纽约大学）；New York University School of Medicine（纽约大学医学院）
We trained and evaluated a localization-based deep CNN for breast cancer screening exam classification on over 200,000 exams (over 1,000,000 images). Our model achieves an AUC of 0.919 in predicting malignancy in patients undergoing breast cancer screening, reducing the error rate of the baseline (Wu et al., 2019a) by 23%. In addition, the models generates bounding boxes for benign and malignant findings, providing interpretable predictions.
