| Application Number | Title |
|---|---|
| 1 | Effect of Computer-Aided Detection Prompts on Breast Screening Performance |
| 2 | A multicentre international evaluation of the assessment systems currently used for assessing mammographic image quality in breast screening |
| 3 | Product X - Computerized reading of mammograms and digital breast tomosynthesis |
| 4 | Structural and statistical regularities that expert radiologists extract allowing them to assess the normality |
| 5 | Computer Aided Monitoring |
| 6 | Mammography Classification and Segmentation with ConvNets |
| 9 | Developing a Convolution Neuronal Network for Cancer Detection in Mammograms |
| 11 | Deep Learning for Mammography Screening / PRECISION |
| 13 | Machine Learning for Detection, Characterisation and Risk Stratification of Lesions in Breast Imaging |
| 14 | Mammographic CAD device testing using computationally inserted microcalcification clusters and masses |
| 15 | Deep learning approaches to digital breast tomosynthesis screening mammography interpretation |
| 16 | Image quality measurement from clinical digital breast images |
| 17 | Prediction and early detection of breast cancer from screening mammograms using deep learning |
| 18 | Deep learning for smart mammography screening |
| 19 | Semi-automated mammography with Machine Learning. |
| 20 | Automatic Detection of Suspicious Lesions of Breast Cancer in Mammograms via Deep Learning |
| 22 | Validation of Dual DCNN malignancy risk classifier |
| 25 | Artificial Intelligence Algorithm applied to automated screening mammograms analysis |
| 27 | Competition X: Training images for participants |
| 30 | Classification of micro-calcifications |
| 33 | Investigation on image and lesion features that affect mammography interpretation |
| 35 | Automated Detection and Diagnosis of Breast Cancer based on Mammography Images |
| 43 | Calibration and Validation of Deep Learning Algorithms for Improved Detection of Breast Cancer in Population Screening |
| 44 | Company X Mammograpnhy Product Development |
| 47 | Smart Elimination of normal cases in breast cancer screening |
| 48 | Radiomics & deep learning can aid classification of masses on mammograms |
| 49 | Investigation into the practicalities of deploying Deep Learning models within a screening programme |
| 51 | An evaluation of Deep Learning approaches to classify breast arterial calcification from 2D digital mammography images |
| 53 | Development of machine learning method of identifying underlying tumour genotype of early stage breast cancer using mammography |
| 54 | A Deep Learning Approach for the Analysis of Masses in Mammograms |
| 55 | Company X Imaging Care Advisor for Breast |
| 61 | Company X Machine Learning Computer Aided Detection Software |
| 65 | The gist of the abnormal in prior and current mammographic images |
| 66 | Automatic Analysis and Diagnosis of Mammography |
| 69 | Interpretable and robust deep learning for breast cancer screening exam classification |
| 71 | An AI system for real-time risk assessment at mammography screening |
| 73 | Creating ML algorithm for malignancy detection on mammography studies |
| 74 | Image Computing for Enhancing Breast Cancer Radiomics |
| 80 | Predicting the severity and detecting the early stages of breast cancer by analysing mammograms with Deep Learning Algorithms |
| 84 | Attention based multiview detection of masses in mammograms |
| 85 | 3D reconstruction to improve deep learning prediction for 2D mammograms |
| 90 | Comparison of AI-Assisted breast cancer screening between DBT & 2D mammography |
| 93 | Geometic Deep Learning approaches for CADx in digital mammography |
| 94 | Using collective intelligence to differentiate between benign from malignant breast lesions |
| 98 | Deep Learning Based Computer Aided Breast Lesion Diagnosis System |
| 101 | A European Cancer Image Platform linked to Biological and Health Data for next generation AI & Precision medicine in Oncology |
| 102 | Combining end to end DL architectures with diverse histologically confirmed data in order to improve upon the state-of-the-art machine interpretation of digital mammography |
| 106 | To identify women with difficult to-detect or masked cancers |
| 118 | Studying volumetric breast density of women undergoing mammographic screening |
| 123 | Deep learning to detect breast cancer in women with high density mammary glands |
| 128 | Using AI algorithms to assist with cancer screening |
| 129 | To improve effectiveness of breast screening through computational solutions and human performance using gist signal |
| 130 | To develop breast cancer risk predictions models |
| 133 | Using screening mammograms and corresponding time-to-event data to train a deep neural networks |
| 134 | Deep learning models to assist clinicians with their decisions |
| 136 | To evaluate AI models in order to standardise research in deep learning for screening mammography |
| 139 | A pending patented method will be used analyse mammograms for tissue disruption levels over time |
| 141 | A study investigating cancer detection across large and small malignancies. |
| 143 | To re-validate the performance of a software that can diagnose breast legions. |
| 148 | To improve the accuracy of a AI system in supporting radiologist in reading screening mammograms and breast tomosynthesis exams as well as to develop methods to assess breast cancer risk |
| 152 | To create maps that describe the progression of breast malignancies, for modelling and risk estimation. |
| 156 | Developing breast cancer screening algorithms from 2D mammogram studies from a number of manufactures and devices |
| 160 | Developing AI based on deep neural networks for early detection of cancer from a series of digital mammography images |
| 161 | To develop a cloud-based image processing tool, validate it against the standard tool, and optimize processing for various vendor-specific instances using OPTIMAM. |
| 162 | To Predict the risk of Breast Cancer by Combining multiple imaging modalities in Convolutional Neural Networks |
| 165 | To evaluate deep learning for mammogram triage, risk prediction in developing countries, and compare commercial AI network performance. |
| 166 | To develop robust and effective model for mammogram analysis for early breast cancer detection and diagnosis. |
| 169 | To develop a new AI model that can detect malignant lesions through a prospective study in Vietnamese population |
| 170 | Training the AI model for predicting upstaging using images and breast biopsies |
| 176 | Breast tissue density can be a challenge for Radiologists to make accurate diagnoses; this project is developing deep-learning solutions to enhance the accuracy and efficiency of identifying suspicious lesions. |
| 183 | To test and internally validate an image processing software and to calculate cancer risk predictions |
| 184 | External validation of long-term breast cancer risk with OPTIMAM digital mammograms |
| 185 | To develop an innovative AI software to detect breast lesions to support clinicians with patient treatment. |
| 186 | To meet statistical accuracy for commercial viability to train the underlying commercial AI model |
| 187 | To make the Licensed Product widely available and certified for use in patient care using FDA validation protocols |
| 188 | To develop a lightweight CNN model for classification of Microcalcifications Clusters (MCCs) in mammogram patches on annotated MCC regions, and using data augmentation for training. |
| 189 | To introduce patient-radiologist clustering, develop an equitable medical image analysis system, and propose new evaluation measures for mammogram analysis |
| 194 | To identify specific types of cancer based on a large amount of data derived from breast cancer screening. |
| 199 | To classify mammographic data as lesion and healthy and segregating them by classifying them on the basis of standard descriptors and evaluating different machine learning techniques and own approaches. |
| 200 | To develop an automated system to diagnose breast cancer by using a huge data set obtained from across different populations around the world. |
| 202 | To develop a model to diagnose breast cancer and the short-term risk of breast cancer using a large set of data. |
| 205 | To use data from multiple sources for training and analysis process to detect breast lesions. |
| 207 | To improve the accuracy of AI system in the detection of breast cancer using a huge collection of data. |
| 197 | To develop a model to organise and analyse mammography data, making sure patients' personal information stays private and secure. |
| 211 | To create a strong and reliable AI tool that can combine information from different sources to predict breast cancer progression and assess risk. |
| 203 | To develop an AI system that takes mammogram images as input and automatically detects cases with no signs of breast cancer. |
| 214 | The study has 2 aims. One is to improve ways to prevent breast cancer and find fast-growing tumours early. The other one is to test how well MIRAI and breast density-based screening methods work for finding breast cancer in different groups of people. |
| 221 | Continued Validation and development of methods to assess breast cancer risks using mammograms. |
| 193 | Develop and validate machine learning models that examine mammogram images to evaluate the likelihood of breast cancer. |
| 243 | Using Artificial Intelligence to Better Detect Suspicious Changes in Mammograms by Comparing Past and Current Images |
| 234 | To show that AI for breast cancer can be safely tested under stress using realistic synthetic data, helping guide future safety regulations. |
| 238 | To use deep learning models to study mammogram images to find early signs of cancer, helping predict each patient’s risk and giving radiologists a view of important patterns. |
| 240 | To train a model that combines 2D and DBT breast imaging data to accurately detect and locate malignant lesions, while also leveraging the strengths of each modality to compensate for their individual limitations, such as detecting micro-calcifications in DBT images and identifying masses in dense breast tissue on 2D images. |