OPTIMAM Mammography Image Database: A Large-Scale Resource of Mammography Images and Clinical Data

A Semiautonomous Deep Learning System to Reduce False Positives in Screening Mammography

Purpose To evaluate the ability of a semiautonomous artificial intelligence (AI) model to identify screening mammograms not suspicious for breast cancer and reduce the number of false-positive examinations. Materials and Methods The deep learning algorithm was trained using 123 248 two-dimensional digital mammograms (6161 cancers) and a retrospective study was performed on three nonoverlapping datasets of 14 831 screening mammography examinations (1026 cancers) from two U.S. institutions and one U.K. institution (2008-2017). The stand-alone performance of humans and AI was compared. Human plus AI performance was simulated to examine reductions in the cancer detection rate, number of examinations, false-positive callbacks, and benign biopsies. Metrics were adjusted to mimic the natural distribution of a screening population, and bootstrapped CIs and P values were calculated. Results Retrospective evaluation on all datasets showed minimal changes to the cancer detection rate with use of the AI device (noninferiority margin of 0.25 cancers per 1000 examinations: U.S. dataset 1, P = .02; U.S. dataset 2, P < .001; U.K. dataset, P < .001). On U.S. dataset 1 (11 592 mammograms; 101 cancers; 3810 female patients; mean age, 57.3 years ± 10.0 [SD]), the device reduced screening examinations requiring radiologist interpretation by 41.6% (95% CI: 40.6%, 42.4%; P < .001), diagnostic examinations callbacks by 31.1% (95% CI: 28.7%, 33.4%; P < .001), and benign needle biopsies by 7.4% (95% CI: 4.1%, 12.4%; P < .001). U.S. dataset 2 (1362 mammograms; 330 cancers; 1293 female patients; mean age, 55.4 years ± 10.5) was reduced by 19.5% (95% CI: 16.9%, 22.1%; P < .001), 11.9% (95% CI: 8.6%, 15.7%; P < .001), and 6.5% (95% CI: 0.0%, 19.0%; P = .08), respectively. The U.K. dataset (1877 mammograms; 595 cancers; 1491 female patients; mean age, 63.5 years ± 7.1) was reduced by 36.8% (95% CI: 34.4%, 39.7%; P < .001), 17.1% (95% CI: 5.9%, 30.1%: P < .001), and 5.9% (95% CI: 2.9%, 11.5%; P < .001), respectively. Conclusion This work demonstrates the potential of a semiautonomous breast cancer screening system to reduce false positives, unnecessary procedures, patient anxiety, and medical expenses. Keywords: Artificial Intelligence, Semiautonomous Deep Learning, Breast Cancer, Screening Mammography Supplemental material is available for this article. Published under a CC BY 4.0 license.

Towards precision medicine in breast imaging: A novel open mammography database with tailor-made 3D image retrieval for AI and teaching

This project addresses the global challenge of breast cancer, particularly in low-resource settings, by creating a pioneering mammography database. Breast cancer, identified by the World Health Organization as a leading cause of cancer death among women, often faces diagnostic and treatment resource constraints in low- and middle-income countries. To enhance early diagnosis and address educational setbacks, the project focuses on leveraging artificial intelligence (AI) technologies through a comprehensive database. Developed in collaboration with Ambra Health, a cloud-based medical image management software, the database comprises 941 mammography images from 100 anonymized cases, with 62 % including 3D images. Accessible through http://mamografia.unifesp.br, the platform facilitates a simple registration process and an advanced search system based on 169 clinical and imaging variables. The website, customizable to the user's native language, ensures data security through an automatic anonymization system. By providing high-resolution, 3D digital images and supplementary clinical information, the platform aims to promote education and research in breast cancer diagnosis, representing a significant advancement in resource-constrained healthcare environments.

Robustness of Deep Networks for Mammography: Replication Across Public Datasets

Deep neural networks have demonstrated promising performance in screening mammography with recent studies reporting performance at or above the level of trained radiologists on internal datasets. However, it remains unclear whether the performance of these trained models is robust and replicates across external datasets. In this study, we evaluate four state-of-the-art publicly available models using four publicly available mammography datasets (CBIS-DDSM, INbreast, CMMD, OMI-DB). Where test data was available, published results were replicated. The best-performing model, which achieved an area under the ROC curve (AUC) of 0.88 on internal data from NYU, achieved here an AUC of 0.9 on the external CMMD dataset (N = 826 exams). On the larger OMI-DB dataset (N = 11,440 exams), it achieved an AUC of 0.84 but did not match the performance of individual radiologists (at a specificity of 0.92, the sensitivity was 0.97 for the radiologist and 0.53 for the network for a 1-year follow-up). The network showed higher performance for in situ cancers, as opposed to invasive cancers. Among invasive cancers, it was relatively weaker at identifying asymmetries and was relatively stronger at identifying masses. The three other trained models that we evaluated all performed poorly on external datasets. Independent validation of trained models is an essential step to ensure safe and reliable use. Future progress in AI for mammography may depend on a concerted effort to make larger datasets publicly available that span multiple clinical sites.

MAM-E: Mammographic Synthetic Image Generation with Diffusion Models

Generative models are used as an alternative data augmentation technique to alleviate the data scarcity problem faced in the medical imaging field. Diffusion models have gathered special attention due to their innovative generation approach, the high quality of the generated images, and their relatively less complex training process compared with Generative Adversarial Networks. Still, the implementation of such models in the medical domain remains at an early stage. In this work, we propose exploring the use of diffusion models for the generation of high-quality, full-field digital mammograms using state-of-the-art conditional diffusion pipelines. Additionally, we propose using stable diffusion models for the inpainting of synthetic mass-like lesions on healthy mammograms. We introduce MAM-E, a pipeline of generative models for high-quality mammography synthesis controlled by a text prompt and capable of generating synthetic mass-like lesions on specific regions of the breast. Finally, we provide quantitative and qualitative assessment of the generated images and easy-to-use graphical user interfaces for mammography synthesis.

Detailed Image Data Quality and Cleaning Practices for Artificial Intelligence Tools for Breast Cancer

Standardizing image-data preparation practices to improve accuracy/consistency of AI diagnostic tools.

Are better AI algorithms for breast cancer detection also better at predicting risk? A paired case-control study

BACKGROUND

There is increasing evidence that artificial intelligence (AI) breast cancer risk evaluation tools using digital mammograms are highly informative for 1-6 years following a negative screening examination. We hypothesized that algorithms that have previously been shown to work well for cancer detection will also work well for risk assessment and that performance of algorithms for detection and risk assessment is correlated.

METHODS

To evaluate our hypothesis, we designed a case-control study using paired mammograms at diagnosis and at the previous screening visit. The study included n = 3386 women from the OPTIMAM registry, that includes mammograms from women diagnosed with breast cancer in the English breast screening program 2010-2019. Cases were diagnosed with invasive breast cancer or ductal carcinoma in situ at screening and were selected if they had a mammogram available at the screening examination that led to detection, and a paired mammogram at their previous screening visit 3y prior to detection when no cancer was detected. Controls without cancer were matched 1:1 to cases based on age (year), screening site, and mammography machine type. Risk assessment was conducted using a deep-learning model designed for breast cancer risk assessment (Mirai), and three open-source deep-learning algorithms designed for breast cancer detection. Discrimination was assessed using a matched area under the curve (AUC) statistic.

RESULTS

Overall performance using the paired mammograms followed the same order by algorithm for risk assessment (AUC range 0.59-0.67) and detection (AUC 0.81-0.89), with Mirai performing best for both. There was also a correlation in performance for risk and detection within algorithms by cancer size, with much greater accuracy for large cancers (30 mm+, detection AUC: 0.88-0.92; risk AUC: 0.64-0.74) than smaller cancers (0 to < 10 mm, detection AUC: 0.73-0.86, risk AUC: 0.54-0.64). Mirai was relatively strong for risk assessment of smaller cancers (0 to < 10 mm, risk, Mirai AUC: 0.64 (95% CI 0.57 to 0.70); other algorithms AUC 0.54-0.56).

CONCLUSIONS

Improvements in risk assessment could stem from enhancing cancer detection capabilities of smaller cancers. Other state-of-the-art AI detection algorithms with high performance for smaller cancers might achieve relatively high performance for risk assessment.

An optimization framework to guide the choice of thresholds for risk-based cancer screening

It is uncommon for risk groups defined by statistical or artificial intelligence (AI) models to be chosen by jointly considering model performance and potential interventions available. We develop a framework to rapidly guide choice of risk groups in this manner, and apply it to guide breast cancer screening intervals using an AI model. Linear programming is used to define risk groups that minimize expected advanced cancer incidence subject to resource constraints. In the application risk stratification performance is estimated from a case-control study (2044 cases, 1:1 matching), and other parameters are taken from screening trials and the screening programme in England. Under the model, re-screening in 1 year for the highest 4% AI model risk, in 3 years for the middle 64%, and in 4 years for 32% of the population at lowest risk, was expected to reduce the number of advanced cancers diagnosed by approximately 18 advanced cancers per 1000 diagnosed with triennial screening, for the same average number of screens in the population as triennial screening for all. Sensitivity analyses found the choice of thresholds was robust to model parameters, but the estimated reduction in advanced cancers was not precise and requires further evaluation. Our framework helps define thresholds with the greatest chance of success for reducing the population health burden of cancer when used in risk-adapted screening, which should be further evaluated such as in health-economic modelling based on computer simulation models, and real-world evaluations.

Data Privacy in Healthcare: In the Era of Artificial Intelligence

Data Privacy has increasingly become a matter of concern in the era of large public digital respositories of data. This is particularly true in healthcare where data can be misused if traced back to patients, and brings with itself a myriad of possibilities. Bring custodians of data, as well as being at the helm of disigning studies and products that can potentially benefit products, healthcare professionals often find themselves unsure about ethical and legal constraints that undelie data sharing. In this review we touch upon the concerns, leal frameworks as well as some common practices in these respects.

medigan: a Python library of pretrained generative models for medical image synthesis

Purpose

Deep learning has shown great promise as the backbone of clinical decision support systems. Synthetic data generated by generative models can enhance the performance and capabilities of data-hungry deep learning models. However, there is (1) limited availability of (synthetic) datasets and (2) generative models are complex to train, which hinders their adoption in research and clinical applications. To reduce this entry barrier, we explore generative model sharing to allow more researchers to access, generate, and benefit from synthetic data.

Approach

We propose medigan, a one-stop shop for pretrained generative models implemented as an open-source framework-agnostic Python library. After gathering end-user requirements, design decisions based on usability, technical feasibility, and scalability are formulated. Subsequently, we implement medigan based on modular components for generative model (i) execution, (ii) visualization, (iii) search & ranking, and (iv) contribution. We integrate pretrained models with applications across modalities such as mammography, endoscopy, x-ray, and MRI.

Results

The scalability and design of the library are demonstrated by its growing number of integrated and readily-usable pretrained generative models, which include 21 models utilizing nine different generative adversarial network architectures trained on 11 different datasets. We further analyze three medigan applications, which include (a) enabling community-wide sharing of restricted data, (b) investigating generative model evaluation metrics, and (c) improving clinical downstream tasks. In (b), we extract Fréchet inception distances (FID) demonstrating FID variability based on image normalization and radiology-specific feature extractors.

Conclusion

medigan allows researchers and developers to create, increase, and domain-adapt their training data in just a few lines of code. Capable of enriching and accelerating the development of clinical machine learning models, we show medigan's viability as platform for generative model sharing. Our multimodel synthetic data experiments uncover standards for assessing and reporting metrics, such as FID, in image synthesis studies.

Successes and challenges in extracting information from DICOM image databases for audit and research

In radiography, much valuable associated data (metadata) is generated during image acquisition. The current setup of picture archive and communication systems (PACS) can make extraction of this metadata difficult, especially as it is typically stored with the image. The aim of this work is to examine the current challenges in extracting image metadata and to discuss the potential benefits of using this rich information. This work focuses on breast screening, though the conclusions are applicable to other modalities.The data stored in PACS contain information, currently underutilised, and is of great benefit for auditing and improving imaging and radiographic practice. From the literature, we present examples of the potential clinical benefit such as audits of dose, and radiographic practice, as well as more advanced research highlighting the effects of radiographic practice, e.g. cancer detection rates affected by imaging technology.This review considers the challenges in extracting data, namely,• The search tools for data on most PACS are inadequate being both time-consuming and limited in elements that can be searched.• Security and information governance considerations• Anonymisation of data if required• Data curationThe review describes some solutions that have been successfully implemented.• Retrospective extraction: direct query on PACS• Extracting data prospectively• Use of structured reports• Use of trusted research environmentsUltimately, the data access process will be made easier by inclusion during PACS procurement. Auditing data from PACS can be used to improve quality of imaging and workflow, all of which will be a clinical benefit to patients.

VAI-B: a multicenter platform for the external validation of artificial intelligence algorithms in breast imaging

Purpose

Multiple vendors are currently offering artificial intelligence (AI) computer-aided systems for triage detection, diagnosis, and risk prediction of breast cancer based on screening mammography. There is an imminent need to establish validation platforms that enable fair and transparent testing of these systems against external data.

Approach

We developed validation of artificial intelligence for breast imaging (VAI-B), a platform for independent validation of AI algorithms in breast imaging. The platform is a hybrid solution, with one part implemented in the cloud and another in an on-premises environment at Karolinska Institute. Cloud services provide the flexibility of scaling the computing power during inference time, while secure on-premises clinical data storage preserves their privacy. A MongoDB database and a python package were developed to store and manage the data on-premises. VAI-B requires four data components: radiological images, AI inferences, radiologist assessments, and cancer outcomes.

Results

To pilot test VAI-B, we defined a case-control population based on 8080 patients diagnosed with breast cancer and 36,339 healthy women based on the Swedish national quality registry for breast cancer. Images and radiological assessments from more than 100,000 mammography examinations were extracted from hospitals in three regions of Sweden. The images were processed by AI systems from three vendors in a virtual private cloud to produce abnormality scores related to signs of cancer in the images. A total of 105,706 examinations have been processed and stored in the database.

Conclusions

We have created a platform that will allow downstream evaluation of AI systems for breast cancer detection, which enables faster development cycles for participating vendors and safer AI adoption for participating hospitals. The platform was designed to be scalable and ready to be expanded should a new vendor want to evaluate their system or should a new hospital wish to obtain an evaluation of different AI systems on their images.

Predicting Breast Cancer Risk Using Radiomics Features of Mammography Images

Mammography images contain a lot of information about not only the mammary glands but also the skin, adipose tissue, and stroma, which may reflect the risk of developing breast cancer. We aimed to establish a method to predict breast cancer risk using radiomics features of mammography images and to enable further examinations and prophylactic treatment to reduce breast cancer mortality. We used mammography images of 4000 women with breast cancer and 1000 healthy women from the 'starting point set' of the OPTIMAM dataset, a public dataset. We trained a Light Gradient Boosting Machine using radiomics features extracted from mammography images of women with breast cancer (only the healthy side) and healthy women. This model was a binary classifier that could discriminate whether a given mammography image was of the contralateral side of women with breast cancer or not, and its performance was evaluated using five-fold cross-validation. The average area under the curve for five folds was 0.60122. Some radiomics features, such as 'wavelet-H_glcm_Correlation' and 'wavelet-H_firstorder_Maximum', showed distribution differences between the malignant and normal groups. Therefore, a single radiomics feature might reflect the breast cancer risk. The odds ratio of breast cancer incidence was 7.38 in women whose estimated malignancy probability was ≥0.95. Radiomics features from mammography images can help predict breast cancer risk.

Automatic correction of performance drift under acquisition shift in medical image classification

Image-based prediction models for disease detection are sensitive to changes in data acquisition such as the replacement of scanner hardware or updates to the image processing software. The resulting differences in image characteristics may lead to drifts in clinically relevant performance metrics which could cause harm in clinical decision making, even for models that generalise in terms of area under the receiver-operating characteristic curve. We propose Unsupervised Prediction Alignment, a generic automatic recalibration method that requires no ground truth annotations and only limited amounts of unlabelled example images from the shifted data distribution. We illustrate the effectiveness of the proposed method to detect and correct performance drift in mammography-based breast cancer screening and on publicly available histopathology data. We show that the proposed method can preserve the expected performance in terms of sensitivity/specificity under various realistic scenarios of image acquisition shift, thus offering an important safeguard for clinical deployment.

Overview of trials on artificial intelligence algorithms in breast cancer screening - A roadmap for international evaluation and implementation

Accumulating evidence from retrospective studies demonstrate at least non-inferior performance when using AI algorithms with different strategies versus double-reading in mammography screening. In addition, AI algorithms for mammography screening can reduce work load by moving to single human reading. Prospective trials are essential to avoid unintended adverse consequences before incorporation of AI algorithms into UK's National Health Service (NHS) Breast Screening Programme (BSP). A stakeholders' meeting was organized in Newnham College, Cambridge, UK to undertake a review of the current evidence to enable consensus discussion on next steps required before implementation into a screening programme. It was concluded that a multicentre multivendor testing platform study with opt-out consent is preferred. AI thresholds from different vendors should be determined while maintaining non-inferior screening performance results, particularly ensuring recall rates are not increased. Automatic recall of cases using an agreed high sensitivity AI score versus automatic rule out with a low AI score set at a high sensitivity could be used. A human reader should still be involved in decision making with AI-only recalls requiring human arbitration. Standalone AI algorithms used without prompting maintain unbiased screening reading performance, but reading with prompts should be tested prospectively and ideally provided for arbitration.

OBIA: An Open Biomedical Imaging Archive

With the development of artificial intelligence (AI) technologies, biomedical imaging data play an important role in scientific research and clinical application, but the available resources are limited. Here we present Open Biomedical Imaging Archive (OBIA), a repository for archiving biomedical imaging and related clinical data. OBIA adopts five data objects (Collection, Individual, Study, Series, and Image) for data organization, and accepts the submission of biomedical images of multiple modalities, organs, and diseases. In order to protect personal privacy, OBIA has formulated a unified de-identification and quality control process. In addition, OBIA provides friendly and intuitive web interfaces for data submission, browsing, and retrieval, as well as image retrieval. As of September 2023, OBIA has housed data for a total of 937 individuals, 4136 studies, 24,701 series, and 1,938,309 images covering 9 modalities and 30 anatomical sites. Collectively, OBIA provides a reliable platform for biomedical imaging data management and offers free open access to all publicly available data to support research activities throughout the world. OBIA can be accessed at https://ngdc.cncb.ac.cn/obia.

A review of the machine learning datasets in mammography, their adherence to the FAIR principles and the outlook for the future

The increasing rates of breast cancer, particularly in emerging economies, have led to interest in scalable deep learning-based solutions that improve the accuracy and cost-effectiveness of mammographic screening. However, such tools require large volumes of high-quality training data, which can be challenging to obtain. This paper combines the experience of an AI startup with an analysis of the FAIR principles of the eight available datasets. It demonstrates that the datasets vary considerably, particularly in their interoperability, as each dataset is skewed towards a particular clinical use-case. Additionally, the mix of digital captures and scanned film compounds the problem of variability, along with differences in licensing terms, ease of access, labelling reliability, and file formats. Improving interoperability through adherence to standards such as the BIRADS criteria for labelling and annotation, and a consistent file format, could markedly improve access and use of larger amounts of standardized data. This, in turn, could be increased further by GAN-based synthetic data generation, paving the way towards better health outcomes for breast cancer.

Learnable DoG convolutional filters for microcalcification detection

Difference of Gaussians (DoG) convolutional filters are one of the earliest image processing methods employed for detecting microcalcifications on mammogram images before machine and deep learning methods became widespread. DoG is a blob enhancement filter that consists in subtracting one Gaussian-smoothed version of an image from another less Gaussian-smoothed version of the same image. Smoothing with a Gaussian kernel suppresses high-frequency spatial information, thus DoG can be regarded as a band-pass filter. However, due to their small size and overimposed breast tissue, microcalcifications vary greatly in contrast-to-noise ratio and sharpness. This makes it difficult to find a single DoG configuration that enhances all microcalcifications. In this work, we propose a convolutional network, named DoG-MCNet, where the first layer automatically learns a bank of DoG filters parameterized by their associated standard deviations. We experimentally show that when employed for microcalcification detection, our DoG layer acts as a learnable bank of band-pass preprocessing filters and improves detection performance by 4.86% AUFROC over baseline MCNet and 1.53% AUFROC over state-of-the-art multicontext ensemble of CNNs.

"Shortcuts" Causing Bias in Radiology Artificial Intelligence: Causes, Evaluation, and Mitigation

Despite the expert-level performance of artificial intelligence (AI) models for various medical imaging tasks, real-world performance failures with disparate outputs for various subgroups limit the usefulness of AI in improving patients' lives. Many definitions of fairness have been proposed, with discussions of various tensions that arise in the choice of an appropriate metric to use to evaluate bias; for example, should one aim for individual or group fairness? One central observation is that AI models apply "shortcut learning" whereby spurious features (such as chest tubes and portable radiographic markers on intensive care unit chest radiography) on medical images are used for prediction instead of identifying true pathology. Moreover, AI has been shown to have a remarkable ability to detect protected attributes of age, sex, and race, while the same models demonstrate bias against historically underserved subgroups of age, sex, and race in disease diagnosis. Therefore, an AI model may take shortcut predictions from these correlations and subsequently generate an outcome that is biased toward certain subgroups even when protected attributes are not explicitly used as inputs into the model. As a result, these subgroups became nonprivileged subgroups. In this review, the authors discuss the various types of bias from shortcut learning that may occur at different phases of AI model development, including data bias, modeling bias, and inference bias. The authors thereafter summarize various tool kits that can be used to evaluate and mitigate bias and note that these have largely been applied to nonmedical domains and require more evaluation for medical AI. The authors then summarize current techniques for mitigating bias from preprocessing (data-centric solutions) and during model development (computational solutions) and postprocessing (recalibration of learning). Ongoing legal changes where the use of a biased model will be penalized highlight the necessity of understanding, detecting, and mitigating biases from shortcut learning and will require diverse research teams looking at the whole AI pipeline.

A large public dataset of annotated clinical MRIs and metadata of patients with acute stroke

To extract meaningful and reproducible models of brain function from stroke images, for both clinical and research proposes, is a daunting task severely hindered by the great variability of lesion frequency and patterns. Large datasets are therefore imperative, as well as fully automated image post-processing tools to analyze them. The development of such tools, particularly with artificial intelligence, is highly dependent on the availability of large datasets to model training and testing. We present a public dataset of 2,888 multimodal clinical MRIs of patients with acute and early subacute stroke, with manual lesion segmentation, and metadata. The dataset provides high quality, large scale, human-supervised knowledge to feed artificial intelligence models and enable further development of tools to automate several tasks that currently rely on human labor, such as lesion segmentation, labeling, calculation of disease-relevant scores, and lesion-based studies relating function to frequency lesion maps.

Artificial Intelligence Applications in Breast Imaging: Current Status and Future Directions

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer-aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA-approved AI applications for breast imaging, but adoption and utilization are widely variable and low overall. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer, and many of the most exciting research projects and available AI applications focus on cancer detection for mammography. There are, however, multiple additional potential applications for AI in breast imaging, including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

Evaluation of an AI Model to Assess Future Breast Cancer Risk

Background Accurate breast cancer risk assessment after a negative screening result could enable better strategies for early detection. Purpose To evaluate a deep learning algorithm for risk assessment based on digital mammograms. Materials and Methods A retrospective observational matched case-control study was designed using the OPTIMAM Mammography Image Database from the National Health Service Breast Screening Programme in the United Kingdom from February 2010 to September 2019. Patients with breast cancer (cases) were diagnosed following a mammographic screening or between two triannual screening rounds. Controls were matched based on mammography device, screening site, and age. The artificial intelligence (AI) model only used mammograms at screening before diagnosis. The primary objective was to assess model performance, with a secondary objective to assess heterogeneity and calibration slope. The area under the receiver operating characteristic curve (AUC) was estimated for 3-year risk. Heterogeneity according to cancer subtype was assessed using a likelihood ratio interaction test. Statistical significance was set at P < .05. Results Analysis included patients with screen-detected (median age, 60 years [IQR, 55-65 years]; 2044 female, including 1528 with invasive cancer and 503 with ductal carcinoma in situ [DCIS]) or interval (median age, 59 years [IQR, 53-65 years]; 696 female, including 636 with invasive cancer and 54 with DCIS) breast cancer and 1:1 matched controls, each with a complete set of mammograms at the screening preceding diagnosis. The AI model had an overall AUC of 0.68 (95% CI: 0.66, 0.70), with no evidence of a significant difference between interval and screen-detected (AUC, 0.69 vs 0.67; P = .085) cancer. The calibration slope was 1.13 (95% CI: 1.01, 1.26). There was similar performance for the detection of invasive cancer versus DCIS (AUC, 0.68 vs 0.66; P = .057). The model had higher performance for advanced cancer risk (AUC, 0.72 ≥stage II vs 0.66 Collapse

Key Words Collapse

MESH Headings

• Humans
• Female
• Middle Aged
• Breast Neoplasms/diagnostic imaging
• Carcinoma, Intraductal, Noninfiltrating
• Artificial Intelligence
• Case-Control Studies
• Retrospective Studies
• State Medicine

Collapse

Grants

• 28689 Cancer Research UK
• C49757/A28689 Cancer Research UK

Collapse

Affiliation(s)

Celeste Damiani From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Grigorios Kalliatakis From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Muthyala Sreenivas From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Miaad Al-Attar From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Janice Rose From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Clare Pudney From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Emily F Lane From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Jack Cuzick From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Giovanni Montana From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)
Adam R Brentnall From the Center for Human Technologies, Istituto Italiano di Tecnologia, Via Melen 83, Genoa 16152, Italy (C.D.); Wolfson Institute of Population Health, Queen Mary University of London, London, UK (C.D., E.F.L., J.C., A.R.B.); Institute of Computer Science (ICS), Foundation of Research and Technology Hellas, Heraklion, Crete, Greece (G.K.); Joint for Director Breast Screening, University Hospitals Coventry and Warwickshire NHS Trust Coventry, Coventry, UK (M.S.); Department of Oncoplastic Breast Surgery, University Hospitals of Leicester NHS Trust, Leicester, UK (M.A.A.); Consumer member at National Cancer Research Institute, Breast Group, London, UK (J.R., C.P.); and University of Warwick, WMG, Coventry, UK (G.M.)

Collapse

Artificial Intelligence in Breast Imaging: Challenges of Integration Into Clinical Practice

Artificial intelligence (AI) in breast imaging is a rapidly developing field with promising results. Despite the large number of recent publications in this field, unanswered questions have led to limited implementation of AI into daily clinical practice for breast radiologists. This paper provides an overview of the key limitations of AI in breast imaging including, but not limited to, limited numbers of FDA-approved algorithms and annotated data sets with histologic ground truth; concerns surrounding data privacy, security, algorithm transparency, and bias; and ethical issues. Ultimately, the successful implementation of AI into clinical care will require thoughtful action to address these challenges, transparency, and sharing of AI implementation workflows, limitations, and performance metrics within the breast imaging community and other end-users.

VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography

Mammography, or breast X-ray imaging, is the most widely used imaging modality to detect cancer and other breast diseases. Recent studies have shown that deep learning-based computer-assisted detection and diagnosis (CADe/x) tools have been developed to support physicians and improve the accuracy of interpreting mammography. A number of large-scale mammography datasets from different populations with various associated annotations and clinical data have been introduced to study the potential of learning-based methods in the field of breast radiology. With the aim to develop more robust and more interpretable support systems in breast imaging, we introduce VinDr-Mammo, a Vietnamese dataset of digital mammography with breast-level assessment and extensive lesion-level annotations, enhancing the diversity of the publicly available mammography data. The dataset consists of 5,000 mammography exams, each of which has four standard views and is double read with disagreement (if any) being resolved by arbitration. The purpose of this dataset is to assess Breast Imaging Reporting and Data System (BI-RADS) and breast density at the individual breast level. In addition, the dataset also provides the category, location, and BI-RADS assessment of non-benign findings. We make VinDr-Mammo publicly available as a new imaging resource to promote advances in developing CADe/x tools for mammography interpretation.

Mammography Datasets for Neural Networks-Survey

Deep neural networks have gained popularity in the field of mammography. Data play an integral role in training these models, as training algorithms requires a large amount of data to capture the general relationship between the model's input and output. Open-access databases are the most accessible source of mammography data for training neural networks. Our work focuses on conducting a comprehensive survey of mammography databases that contain images with defined abnormal areas of interest. The survey includes databases such as INbreast, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM), the OPTIMAM Medical Image Database (OMI-DB), and The Mammographic Image Analysis Society Digital Mammogram Database (MIAS). Additionally, we surveyed recent studies that have utilized these databases in conjunction with neural networks and the results they have achieved. From these databases, it is possible to obtain at least 3801 unique images with 4125 described findings from approximately 1842 patients. The number of patients with important findings can be increased to approximately 14,474, depending on the type of agreement with the OPTIMAM team. Furthermore, we provide a description of the annotation process for mammography images to enhance the understanding of the information gained from these datasets.

An Online Mammography Database with Biopsy Confirmed Types

Breast carcinoma is the second largest cancer in the world among women. Early detection of breast cancer has been shown to increase the survival rate, thereby significantly increasing patients' lifespan. Mammography, a noninvasive imaging tool with low cost, is widely used to diagnose breast disease at an early stage due to its high sensitivity. Although some public mammography datasets are useful, there is still a lack of open access datasets that expand beyond the white population as well as missing biopsy confirmation or with unknown molecular subtypes. To fill this gap, we build a database containing two online breast mammographies. The dataset named by Chinese Mammography Database (CMMD) contains 3712 mammographies involved 1775 patients, which is divided into two branches. The first dataset CMMD1 contains 1026 cases (2214 mammographies) with biopsy confirmed type of benign or malignant tumors. The second dataset CMMD2 includes 1498 mammographies for 749 patients with known molecular subtypes. Our database is constructed to enrich the diversity of mammography data and promote the development of relevant fields.

Lessons learned from independent external validation of an AI tool to detect breast cancer using a representative UK data set

OBJECTIVE

To pilot a process for the independent external validation of an artificial intelligence (AI) tool to detect breast cancer using data from the NHS breast screening programme (NHSBSP).

METHODS

A representative data set of mammography images from 26,000 women attending 2 NHS screening centres, and an enriched data set of 2054 positive cases were used from the OPTIMAM image database. The use case of the AI tool was the replacement of the first or second human reader. The performance of the AI tool was compared to that of human readers in the NHSBSP.

RESULTS

Recommendations for future external validations of AI tools to detect breast cancer are provided. The tool recalled different breast cancers to the human readers. This study showed the importance of testing AI tools on all types of cases (including non-standard) and the clarity of any warning messages. The acceptable difference in sensitivity and specificity between the AI tool and human readers should be determined. Any information vital for the clinical application should be a required output for the AI tool. It is recommended that the interaction of radiologists with the AI tool, and the effect of the AI tool on arbitration be investigated prior to clinical use.

CONCLUSION

This pilot demonstrated several lessons for future independent external validation of AI tools for breast cancer detection.

ADVANCES IN KNOWLEDGE

Knowledge has been gained towards best practice procedures for performing independent external validations of AI tools for the detection of breast cancer using data from the NHS Breast Screening Programme.

Computer-aided breast cancer detection and classification in mammography: A comprehensive review

Cancer is the second cause of mortality worldwide and it has been identified as a perilous disease. Breast cancer accounts for ∼20% of all new cancer cases worldwide, making it a major cause of morbidity and mortality. Mammography is an effective screening tool for the early detection and management of breast cancer. However, the identification and interpretation of breast lesions is challenging even for expert radiologists. For that reason, several Computer-Aided Diagnosis (CAD) systems are being developed to assist radiologists to accurately detect and/or classify breast cancer. This review examines the recent literature on the automatic detection and/or classification of breast cancer in mammograms, using both conventional feature-based machine learning and deep learning algorithms. The review begins with a comparison of algorithms developed specifically for the detection and/or classification of two types of breast abnormalities, micro-calcifications and masses, followed by the use of sequential mammograms for improving the performance of the algorithms. The available Food and Drug Administration (FDA) approved CAD systems related to triage and diagnosis of breast cancer in mammograms are subsequently presented. Finally, a description of the open access mammography datasets is provided and the potential opportunities for future work in this field are highlighted. The comprehensive review provided here can serve both as a thorough introduction to the field but also provide indicative directions to guide future applications.

High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection

Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. However, high-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. Therefore, the sensitivity of mammography for breast cancer detection can be reduced by more than 20% in dense breasts. Additionally, extremely dense cases reported an increased risk of cancer compared to low-density breasts. This study aims to improve the mass detection performance in high-density breasts using synthetic high-density full-field digital mammograms (FFDM) as data augmentation during breast mass detection model training. To this end, a total of five cycle-consistent GAN (CycleGAN) models using three FFDM datasets were trained for low-to-high-density image translation in high-resolution mammograms. The training images were split by breast density BI-RADS categories, being BI-RADS A almost entirely fatty and BI-RADS D extremely dense breasts. Our results showed that the proposed data augmentation technique improved the sensitivity and precision of mass detection in models trained with small datasets and improved the domain generalization of the models trained with large databases. In addition, the clinical realism of the synthetic images was evaluated in a reader study involving two expert radiologists and one surgical oncologist.

Convolutional Networks and Transformers for Mammography Classification: An Experimental Study

Convolutional Neural Networks (CNN) have received a large share of research in mammography image analysis due to their capability of extracting hierarchical features directly from raw data. Recently, Vision Transformers are emerging as viable alternative to CNNs in medical imaging, in some cases performing on par or better than their convolutional counterparts. In this work, we conduct an extensive experimental study to compare the most recent CNN and Vision Transformer architectures for whole mammograms classification. We selected, trained and tested 33 different models, 19 convolutional- and 14 transformer-based, on the largest publicly available mammography image database OMI-DB. We also performed an analysis of the performance at eight different image resolutions and considering all the individual lesion categories in isolation (masses, calcifications, focal asymmetries, architectural distortions). Our findings confirm the potential of visual transformers, which performed on par with traditional CNNs like ResNet, but at the same time show a superiority of modern convolutional networks like EfficientNet.

Developing breast lesion detection algorithms for digital breast tomosynthesis: Leveraging false positive findings

BACKGROUND

Due to the complex nature of digital breast tomosynthesis (DBT) in imaging techniques, reading times are longer than 2D mammograms. A robust computer-aided diagnosis system in DBT could help radiologists reduce their workload and reading times.

PURPOSE

The purpose of this study was to develop algorithms for detecting biopsy-proven breast lesions on DBT using multi-depth level convolutional models and leveraging non-biopsied samples. As biopsied positive samples in a lesion dataset are limited, we hypothesized that false positive (FP) findings by detection algorithms from non-biopsied benign lesions could improve detection algorithms by using them as data augmentation.

APPROACH

We first extracted 2D slices from DBT volumes with biopsy-proven breast lesions (cancer and benign), with non-biopsied benign lesions (actionable), and for controls. Then, to provide lesion continuity along the z-direction, we combined a lesion slice with its immediate adjacent slices to synthesize 2.5-dimensional (2.5D) images of the lesion by assigning them into R, G, and B color channels. We used 224 biopsy-proven lesions from 39 cancer and 62 benign patients from a DBTex challenge dataset of 1000 scans. We included the 2.5D images of immediate neighboring slices from the lesion's center to increase the number of training samples. For lesion detection, we used the YOLOv5 algorithm as our base network. We trained a baseline algorithm (medium-depth level) using biopsied samples to detect actionable FPs in non-biopsied images. Afterward, we fine-tuned the baseline model on the augmented image set (actionable FPs added). For lesion inferencing, we processed the DBT volume slice-by-slice to estimate bounding boxes in each slice, and then combined them by connecting bounding boxes along the depth via volumetric morphological closing. We trained an additional model (large) with deeper-depth levels by repeating the above process. Finally, we developed an ensemble algorithm by combining the medium and large detection models. We used the free-response operating characteristic curve to evaluate our algorithms. We reported mean sensitivity per FPs per DBT volume only for biopsied views and sensitivity at 2-false positives per image (2FPI) for all views. However, due to the limited accessibility to the truth of the challenge validation and test datasets, we used sensitivity at 2FPI for statistical evaluation.

RESULTS

For the DBTex independent validation set, the medium baseline model achieved a mean sensitivity of 0.627 FPs per DBT volume, and a sensitivity of 0.640 at 2FPI. After adding actionable FP lesions, the model had an improved 2FPI of 0.769 over the baseline (p-value = 0.013). Our ensemble algorithm with multi-depth levels (medium + large) achieved a mean sensitivity of 0.815 FPs per DBT volume and an improved sensitivity at 2FPI of 0.80 over the baseline (p-value < 0.001) on the validation set. Finally, our ensemble model achieved a mean sensitivity of 0.786 FPs per DBT volume and a sensitivity of 0.743 at 2FPI on the DBTex independent test set.

CONCLUSIONS

Our results show that actionable FP findings hold useful information for lesion detection algorithms, and our ensemble detection model with multi-depth levels improves lesion detection performance.

Recommendations for the development and use of imaging test sets to investigate the test performance of artificial intelligence in health screening

Rigorous evaluation of artificial intelligence (AI) systems for image classification is essential before deployment into health-care settings, such as screening programmes, so that adoption is effective and safe. A key step in the evaluation process is the external validation of diagnostic performance using a test set of images. We conducted a rapid literature review on methods to develop test sets, published from 2012 to 2020, in English. Using thematic analysis, we mapped themes and coded the principles using the Population, Intervention, and Comparator or Reference standard, Outcome, and Study design framework. A group of screening and AI experts assessed the evidence-based principles for completeness and provided further considerations. From the final 15 principles recommended here, five affect population, one intervention, two comparator, one reference standard, and one both reference standard and comparator. Finally, four are appliable to outcome and one to study design. Principles from the literature were useful to address biases from AI; however, they did not account for screening specific biases, which we now incorporate. The principles set out here should be used to support the development and use of test sets for studies that assess the accuracy of AI within screening programmes, to ensure they are fit for purpose and minimise bias.

Domain generalization in deep learning based mass detection in mammography: A large-scale multi-center study

Computer-aided detection systems based on deep learning have shown great potential in breast cancer detection. However, the lack of domain generalization of artificial neural networks is an important obstacle to their deployment in changing clinical environments. In this study, we explored the domain generalization of deep learning methods for mass detection in digital mammography and analyzed in-depth the sources of domain shift in a large-scale multi-center setting. To this end, we compared the performance of eight state-of-the-art detection methods, including Transformer based models, trained in a single domain and tested in five unseen domains. Moreover, a single-source mass detection training pipeline was designed to improve the domain generalization without requiring images from the new domain. The results show that our workflow generalized better than state-of-the-art transfer learning based approaches in four out of five domains while reducing the domain shift caused by the different acquisition protocols and scanner manufacturers. Subsequently, an extensive analysis was performed to identify the covariate shifts with the greatest effects on detection performance, such as those due to differences in patient age, breast density, mass size, and mass malignancy. Ultimately, this comprehensive study provides key insights and best practices for future research on domain generalization in deep learning based breast cancer detection.

Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issues

Federated Learning (FL), Artificial Intelligence (AI), and Explainable Artificial Intelligence (XAI) are the most trending and exciting technology in the intelligent healthcare field. Traditionally, the healthcare system works based on centralized agents sharing their raw data. Therefore, huge vulnerabilities and challenges are still existing in this system. However, integrating with AI, the system would be multiple agent collaborators who are capable of communicating with their desired host efficiently. Again, FL is another interesting feature, which works decentralized manner; it maintains the communication based on a model in the preferred system without transferring the raw data. The combination of FL, AI, and XAI techniques can be capable of minimizing several limitations and challenges in the healthcare system. This paper presents a complete analysis of FL using AI for smart healthcare applications. Initially, we discuss contemporary concepts of emerging technologies such as FL, AI, XAI, and the healthcare system. We integrate and classify the FL-AI with healthcare technologies in different domains. Further, we address the existing problems, including security, privacy, stability, and reliability in the healthcare field. In addition, we guide the readers to solving strategies of healthcare using FL and AI. Finally, we address extensive research areas as well as future potential prospects regarding FL-based AI research in the healthcare management system.

Public governance of medical artificial intelligence research in the UK: an integrated multi-scale model

There is a growing consensus among scholars, national governments, and intergovernmental organisations of the need to involve the public in decision-making around the use of artificial intelligence (AI) in society. Focusing on the UK, this paper asks how that can be achieved for medical AI research, that is, for research involving the training of AI on data from medical research databases. Public governance of medical AI research in the UK is generally achieved in three ways, namely, via lay representation on data access committees, through patient and public involvement groups, and by means of various deliberative democratic projects such as citizens' juries, citizen panels, citizen assemblies, etc.-what we collectively call "citizen forums". As we will show, each of these public involvement initiatives have complementary strengths and weaknesses for providing oversight of medical AI research. As they are currently utilized, however, they are unable to realize the full potential of their complementarity due to insufficient information transfer across them. In order to synergistically build on their contributions, we offer here a multi-scale model integrating all three. In doing so we provide a unified public governance model for medical AI research, one that, we argue, could improve the trustworthiness of big data and AI related medical research in the future.

Image Augmentation Techniques for Mammogram Analysis

Research in the medical imaging field using deep learning approaches has become progressively contingent. Scientific findings reveal that supervised deep learning methods’ performance heavily depends on training set size, which expert radiologists must manually annotate. The latter is quite a tiring and time-consuming task. Therefore, most of the freely accessible biomedical image datasets are small-sized. Furthermore, it is challenging to have big-sized medical image datasets due to privacy and legal issues. Consequently, not a small number of supervised deep learning models are prone to overfitting and cannot produce generalized output. One of the most popular methods to mitigate the issue above goes under the name of data augmentation. This technique helps increase training set size by utilizing various transformations and has been publicized to improve the model performance when tested on new data. This article surveyed different data augmentation techniques employed on mammogram images. The article aims to provide insights into basic and deep learning-based augmentation techniques.

Advancements in Oncology with Artificial Intelligence—A Review Article

Simple Summary

With the advancement of artificial intelligence, including machine learning, the field of oncology has seen promising results in cancer detection and classification, epigenetics, drug discovery, and prognostication. In this review, we describe what artificial intelligence is and its function, as well as comprehensively summarize its evolution and role in breast, colorectal, and central nervous system cancers. Understanding the origin and current accomplishments might be essential to improve the quality, accuracy, generalizability, cost-effectiveness, and reliability of artificial intelligence models that can be used in worldwide clinical practice. Students and researchers in the medical field will benefit from a deeper understanding of how to use integrative AI in oncology for innovation and research.

Abstract

Well-trained machine learning (ML) and artificial intelligence (AI) systems can provide clinicians with therapeutic assistance, potentially increasing efficiency and improving efficacy. ML has demonstrated high accuracy in oncology-related diagnostic imaging, including screening mammography interpretation, colon polyp detection, glioma classification, and grading. By utilizing ML techniques, the manual steps of detecting and segmenting lesions are greatly reduced. ML-based tumor imaging analysis is independent of the experience level of evaluating physicians, and the results are expected to be more standardized and accurate. One of the biggest challenges is its generalizability worldwide. The current detection and screening methods for colon polyps and breast cancer have a vast amount of data, so they are ideal areas for studying the global standardization of artificial intelligence. Central nervous system cancers are rare and have poor prognoses based on current management standards. ML offers the prospect of unraveling undiscovered features from routinely acquired neuroimaging for improving treatment planning, prognostication, monitoring, and response assessment of CNS tumors such as gliomas. By studying AI in such rare cancer types, standard management methods may be improved by augmenting personalized/precision medicine. This review aims to provide clinicians and medical researchers with a basic understanding of how ML works and its role in oncology, especially in breast cancer, colorectal cancer, and primary and metastatic brain cancer. Understanding AI basics, current achievements, and future challenges are crucial in advancing the use of AI in oncology.

PeMNet for Pectoral Muscle Segmentation

Simple Summary

Deep learning has become a popular technique in modern computer-aided (CAD) systems. In breast cancer CAD systems, breast pectoral segmentation is an important procedure to remove unwanted pectoral muscle in the images. In recent decades, there are numerous studies aiming at developing efficient and accurate methods for pectoral muscle segmentation. However, some methods heavily rely on manually crafted features that can easily lead to segmentation failure. Moreover, deep learning-based methods are still suffering from poor performance at high computational costs. Therefore, we propose a novel deep learning segmentation framework to provide fast and accurate pectoral muscle segmentation result. In the proposed framework, the novel network architecture enables more useful information to be used and therefore improve the segmentation results. The experimental results using two public datasets validated the effectiveness of the proposed network.

Abstract

As an important imaging modality, mammography is considered to be the global gold standard for early detection of breast cancer. Computer-Aided (CAD) systems have played a crucial role in facilitating quicker diagnostic procedures, which otherwise could take weeks if only radiologists were involved. In some of these CAD systems, breast pectoral segmentation is required for breast region partition from breast pectoral muscle for specific analysis tasks. Therefore, accurate and efficient breast pectoral muscle segmentation frameworks are in high demand. Here, we proposed a novel deep learning framework, which we code-named PeMNet, for breast pectoral muscle segmentation in mammography images. In the proposed PeMNet, we integrated a novel attention module called the Global Channel Attention Module (GCAM), which can effectively improve the segmentation performance of Deeplabv3+ using minimal parameter overheads. In GCAM, channel attention maps (CAMs) are first extracted by concatenating feature maps after paralleled global average pooling and global maximum pooling operation. CAMs are then refined and scaled up by multi-layer perceptron (MLP) for elementwise multiplication with CAMs in next feature level. By iteratively repeating this procedure, the global CAMs (GCAMs) are then formed and multiplied elementwise with final feature maps to lead to final segmentation. By doing so, CAMs in early stages of a deep convolution network can be effectively passed on to later stages of the network and therefore leads to better information usage. The experiments on a merged dataset derived from two datasets, INbreast and OPTIMAM, showed that PeMNet greatly outperformed state-of-the-art methods by achieving an IoU of 97.46%, global pixel accuracy of 99.48%, Dice similarity coefficient of 96.30%, and Jaccard of 93.33%, respectively.

Towards nationally curated data archives for clinical radiology image analysis at scale: Learnings from national data collection in response to a pandemic

The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to execute for several reasons, including issues with data privacy, the lack of data reporting standards, interoperable technologies, and distribution methods. The coronavirus SARS-CoV-2 disease pandemic has highlighted the importance of collaboration between government bodies, healthcare institutions, academic researchers and commercial companies in overcoming these issues during times of urgency. The National COVID-19 Chest Imaging Database, led by NHSX, British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and Faculty, is an example of such a national initiative. Here, we summarise the experiences and challenges of setting up the National COVID-19 Chest Imaging Database, and the implications for future ambitions of national data curation in medical imaging to advance the safe adoption of artificial intelligence in healthcare.

Quantitative breast density analysis to predict interval and node-positive cancers in pursuit of improved screening protocols: a case-control study

BACKGROUND

This study investigates whether quantitative breast density (BD) serves as an imaging biomarker for more intensive breast cancer screening by predicting interval, and node-positive cancers.

METHODS

This case-control study of 1204 women aged 47-73 includes 599 cancer cases (302 screen-detected, 297 interval; 239 node-positive, 360 node-negative) and 605 controls. Automated BD software calculated fibroglandular volume (FGV), volumetric breast density (VBD) and density grade (DG). A radiologist assessed BD using a visual analogue scale (VAS) from 0 to 100. Logistic regression and area under the receiver operating characteristic curves (AUC) determined whether BD could predict mode of detection (screen-detected or interval); node-negative cancers; node-positive cancers, and all cancers vs. controls.

RESULTS

FGV, VBD, VAS, and DG all discriminated interval cancers (all p < 0.01) from controls. Only FGV-quartile discriminated screen-detected cancers (p < 0.01). Based on AUC, FGV discriminated all cancer types better than VBD or VAS. FGV showed a significantly greater discrimination of interval cancers, AUC = 0.65, than of screen-detected cancers, AUC = 0.61 (p < 0.01) as did VBD (0.63 and 0.53, respectively, p < 0.001).

CONCLUSION

FGV, VBD, VAS and DG discriminate interval cancers from controls, reflecting some masking risk. Only FGV discriminates screen-detected cancers perhaps adding a unique component of breast cancer risk.

Fair shares: building and benefiting from healthcare AI with mutually beneficial structures and development partnerships

Artificial intelligence (AI) algorithms are used in an increasing range of aspects of our lives. In particular, medical applications of AI are being developed and deployed, including many in image analysis. Deep learning methods, which have recently proved successful in image classification, rely on large volumes of clinical data generated by healthcare institutions. Such data is collected from their served populations. In this opinion article, using digital mammographic screening as an example, we briefly consider the background to AI development and some issues around its deployment. We highlight the importance of high quality clinical data as fundamental to these technologies, and question how the ownership of resultant tools should be defined. Though many of the ethical issues concerning the development and use of medical AI technologies continue to be discussed, the value of the data on which they rely remains a subject that is seldom considered. This potentially controversial issue can and should be addressed in a way which is beneficial to all parties, particularly the population in general and the patients we serve.

How does image quality affect radiologists' perceived ability for image interpretation and lesion detection in digital mammography?

OBJECTIVES

To study how radiologists' perceived ability to interpret digital mammography (DM) images is affected by decreases in image quality.

METHODS

One view from 45 DM cases (including 30 cancers) was degraded to six levels each of two acquisition-related issues (lower spatial resolution and increased quantum noise) and three post-processing-related issues (lower and higher contrast and increased correlated noise) seen during clinical evaluation of DM systems. The images were shown to fifteen breast screening radiologists from five countries. Aware of lesion location, the radiologists selected the most-degraded mammogram (indexed from 1 (reference) to 7 (most degraded)) they still felt was acceptable for interpretation. The median selected index, per degradation type, was calculated separately for calcification and soft tissue (including normal) cases. Using the two-sided, non-parametric Mann-Whitney test, the median indices for each case and degradation type were compared.

RESULTS

Radiologists were not tolerant to increases (medians: 1.5 (calcifications) and 2 (soft tissue)) or decreases (median: 2, for both types) in contrast, but were more tolerant to correlated noise (median: 3, for both types). Increases in quantum noise were tolerated more for calcifications than for soft tissue cases (medians: 3 vs. 4, p = 0.02). Spatial resolution losses were considered less acceptable for calcification detection than for soft tissue cases (medians: 3.5 vs. 5, p = 0.001).

CONCLUSIONS

Perceived ability of radiologists for image interpretation in DM was affected not only by image acquisition-related issues but also by image post-processing issues, and some of those issues affected calcification cases more than soft tissue cases.

KEY POINTS

• Lower spatial resolution and increased quantum noise affected the radiologists' perceived ability to interpret calcification cases more than soft tissue lesion or normal cases. • Post-acquisition image processing-related effects, not only image acquisition-related effects, also impact the perceived ability of radiologists to interpret images and detect lesions. • In addition to current practices, post-acquisition image processing-related effects need to also be considered during the testing and evaluation of digital mammography systems.

Using imaging to combat a pandemic: rationale for developing the UK National COVID-19 Chest Imaging Database

The National COVID-19 Chest Imaging Database (NCCID) is a repository of chest radiographs, CT and MRI images and clinical data from COVID-19 patients across the UK, to support research and development of AI technology and give insight into COVID-19 disease https://bit.ly/3eQeuha