Metrics reloaded: recommendations for image analysis validation.

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Understanding metric-related pitfalls in image analysis validation.

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.

National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence.

The remarkable advances of artificial intelligence (AI) technology are revolutionizing established approaches to the acquisition, interpretation, and analysis of biomedical imaging data. Development, validation, and continuous refinement of AI tools requires easy access to large high-quality annotated datasets, which are both representative and diverse. The National Cancer Institute (NCI) Imaging Data Commons (IDC) hosts large and diverse publicly available cancer image data collections. By harmonizing all data based on industry standards and colocalizing it with analysis and exploration resources, the IDC aims to facilitate the development, validation, and clinical translation of AI tools and address the well-documented challenges of establishing reproducible and transparent AI processing pipelines. Balanced use of established commercial products with open-source solutions, interconnected by standard interfaces, provides value and performance, while preserving sufficient agility to address the evolving needs of the research community. Emphasis on the development of tools, use cases to demonstrate the utility of uniform data representation, and cloud-based analysis aim to ease adoption and help define best practices. Integration with other data in the broader NCI Cancer Research Data Commons infrastructure opens opportunities for multiomics studies incorporating imaging data to further empower the research community to accelerate breakthroughs in cancer detection, diagnosis, and treatment. Published under a CC BY 4.0 license.

Reproducibility of Deep Learning Algorithms Developed for Medical Imaging Analysis: A Systematic Review.

Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible.

Proceedings from the First Global Artificial Intelligence in Gastroenterology and Endoscopy Summit.

BACKGROUND AND AIMS: Artificial intelligence (AI), specifically deep learning, offers the potential to enhance the field of GI endoscopy in areas ranging from lesion detection and classification to quality metrics and documentation. Progress in this field will be measured by whether AI implementation can lead to improved patient outcomes and more efficient clinical workflow for GI endoscopists. The aims of this article are to report the findings of a multidisciplinary group of experts focusing on issues in AI research and applications related to gastroenterology and endoscopy, to review the current status of the field, and to produce recommendations for investigators developing and studying new AI technologies for gastroenterology. METHODS: A multidisciplinary meeting was held on September 28, 2019, bringing together academic, industry, and regulatory experts in diverse fields including gastroenterology, computer and imaging sciences, machine learning, computer vision, U.S. Food and Drug Administration, and the National Institutes of Health. Recent and ongoing studies in gastroenterology and current technology in AI were presented and discussed, key gaps in knowledge were identified, and recommendations were made for research that would have the highest impact in making advances and implementation in the field of AI to gastroenterology. RESULTS: There was a consensus that AI will transform the field of gastroenterology, particularly endoscopy and image interpretation. Powered by advanced machine learning algorithms, the use of computer vision in endoscopy has the potential to result in better prediction and treatment outcomes for patients with gastroenterology disorders and cancer. Large libraries of endoscopic images, "EndoNet," will be important to facilitate development and application of AI systems. The regulatory environment for implementation of AI systems is evolving, but common outcomes such as colon polyp detection have been highlighted as potential clinical trial endpoints. Other threshold outcomes will be important, as well as clarity on iterative improvement of clinical systems. CONCLUSIONS: Gastroenterology is a prime candidate for early adoption of AI. AI is rapidly moving from an experimental phase to a clinical implementation phase in gastroenterology. It is anticipated that the implementation of AI in gastroenterology over the next decade will have a significant and positive impact on patient care and clinical workflows. Ongoing collaboration among gastroenterologists, industry experts, and regulatory agencies will be important to ensure that progress is rapid and clinically meaningful. However, several constraints and areas will benefit from further exploration, including potential clinical applications, implementation, structure and governance, role of gastroenterologists, and potential impact of AI in gastroenterology.

Noninvasive Targeted Transcranial Neuromodulation via Focused Ultrasound Gated Drug Release from Nanoemulsions.

Targeted, noninvasive neuromodulation of the brain of an otherwise awake subject could revolutionize both basic and clinical neuroscience. Toward this goal, we have developed nanoparticles that allow noninvasive uncaging of a neuromodulatory drug, in this case the small molecule anesthetic propofol, upon the application of focused ultrasound. These nanoparticles are composed of biodegradable and biocompatible constituents and are activated using sonication parameters that are readily achievable by current clinical transcranial focused ultrasound systems. These particles are potent enough that their activation can silence seizures in an acute rat seizure model. Notably, there is no evidence of brain parenchymal damage or blood-brain barrier opening with their use. Further development of these particles promises noninvasive, focal, and image-guided clinical neuromodulation along a variety of pharmacological axes.

Summary of the National Cancer Institute 2023 Virtual Workshop on Medical Image De-identification-Part 2: Pathology Whole Slide Image De-identification, De-facing, the Role of AI in Image De-identification, and the NCI MIDI Datasets and Pipeline.

De-identification of medical images intended for research is a core requirement for data sharing initiatives, particularly as the demand for data for artificial intelligence (AI) applications grows. The Center for Biomedical Informatics and Information Technology (CBIIT) of the United States National Cancer Institute (NCI) convened a two half-day virtual workshop with the intent of summarizing the state of the art in de-identification technology and processes and exploring interesting aspects of the subject. This paper summarizes the highlights of the second day of the workshop, the recordings and presentations of which are publicly available for review. The topics covered included pathology whole slide image de-identification, de-facing, the role of AI in image de-identification, and the NCI Medical Image De-Identification Initiative (MIDI) datasets and pipeline.

Summary of the National Cancer Institute 2023 Virtual Workshop on Medical Image De-identification-Part 1: Report of the MIDI Task Group - Best Practices and Recommendations, Tools for Conventional Approaches to De-identification, International Approaches to De-identification, and Industry Panel on Image De-identification.

De-identification of medical images intended for research is a core requirement for data-sharing initiatives, particularly as the demand for data for artificial intelligence (AI) applications grows. The Center for Biomedical Informatics and Information Technology (CBIIT) of the US National Cancer Institute (NCI) convened a virtual workshop with the intent of summarizing the state of the art in de-identification technology and processes and exploring interesting aspects of the subject. This paper summarizes the highlights of the first day of the workshop, the recordings, and presentations of which are publicly available for review. The topics covered included the report of the Medical Image De-Identification Initiative (MIDI) Task Group on best practices and recommendations, tools for conventional approaches to de-identification, international approaches to de-identification, and an industry panel.

AI-Generated Annotations Dataset for Diverse Cancer Radiology Collections in NCI Image Data Commons.

The National Cancer Institute (NCI) Image Data Commons (IDC) offers publicly available cancer radiology collections for cloud computing, crucial for developing advanced imaging tools and algorithms. Despite their potential, these collections are minimally annotated; only 4% of DICOM studies in collections considered in the project had existing segmentation annotations. This project increases the quantity of segmentations in various IDC collections. We produced high-quality, AI-generated imaging annotations dataset of tissues, organs, and/or cancers for 11 distinct IDC image collections. These collections contain images from a variety of modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). The collections cover various body parts, such as the chest, breast, kidneys, prostate, and liver. A portion of the AI annotations were reviewed and corrected by a radiologist to assess the performance of the AI models. Both the AI's and the radiologist's annotations were encoded in conformance to the Digital Imaging and Communications in Medicine (DICOM) standard, allowing for seamless integration into the IDC collections as third-party analysis collections. All the models, images and annotations are publicly accessible.

A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey.

In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.

End-to-end reproducible AI pipelines in radiology using the cloud.

Artificial intelligence (AI) algorithms hold the potential to revolutionize radiology. However, a significant portion of the published literature lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Although several reporting guidelines have been proposed, identifying practical means to address these issues remains challenging. Here, we show the potential of cloud-based infrastructure for implementing and sharing transparent and reproducible AI-based radiology pipelines. We demonstrate end-to-end reproducibility from retrieving cloud-hosted data, through data pre-processing, deep learning inference, and post-processing, to the analysis and reporting of the final results. We successfully implement two distinct use cases, starting from recent literature on AI-based biomarkers for cancer imaging. Using cloud-hosted data and computing, we confirm the findings of these studies and extend the validation to previously unseen data for one of the use cases. Furthermore, we provide the community with transparent and easy-to-extend examples of pipelines impactful for the broader oncology field. Our approach demonstrates the potential of cloud resources for implementing, sharing, and using reproducible and transparent AI pipelines, which can accelerate the translation into clinical solutions.

NCI Cancer Research Data Commons: Resources to Share Key Cancer Data.

Since 2014, the NCI has launched a series of data commons as part of the Cancer Research Data Commons (CRDC) ecosystem housing genomic, proteomic, imaging, and clinical data to support cancer research and promote data sharing of NCI-funded studies. This review describes each data commons (Genomic Data Commons, Proteomic Data Commons, Integrated Canine Data Commons, Cancer Data Service, Imaging Data Commons, and Clinical and Translational Data Commons), including their unique and shared features, accomplishments, and challenges. Also discussed is how the CRDC data commons implement Findable, Accessible, Interoperable, Reusable (FAIR) principles and promote data sharing in support of the new NIH Data Management and Sharing Policy. See related articles by Brady et al., p. 1384, Pot et al., p. 1396, and Kim et al., p. 1404.

Fair evaluation of federated learning algorithms for automated breast density classification: The results of the 2022 ACR-NCI-NVIDIA federated learning challenge.

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical Schools' Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location.

Understanding metric-related pitfalls in image analysis validation.

Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately in relation to the underlying research problem. This could be attributed to a lack of accessibility of metric-related knowledge: While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Focusing on biomedical image analysis but with the potential of transfer to other fields, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. To facilitate comprehension, illustrations and specific examples accompany each pitfall. As a structured body of information accessible to researchers of all levels of expertise, this work enhances global comprehension of a key topic in image analysis validation.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs).

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.

MR - eyes for cancer: looking within an impenetrable disease.

Probe development is a critical component in cancer imaging, and novel probes are making major inroads in several aspects of cancer detection and image-guided treatments. Intrinsic MR probes such as signals from metabolites and their chemical shifts have been used for more than a decade to understand cancer physiology and metabolism. Through the integration of technology, molecular biology, and chemistry, the last few years have witnessed an explosion of extrinsic probes for molecular and functional imaging of cancer that, together with techniques such as CEST and hyperpolarization, have significantly expanded the repertoire of MR techniques in basic and translational investigations of many different aspects of cancer. Furthermore, incorporation of MR probes into multifunctional nanoparticles and multimodality imaging platforms have opened new opportunities for MR in image-guided diagnosis and therapy of cancer. Here we have provided an overview of recent innovations that have occurred in the development of MRI probes for molecular and functional imaging of cancer. Although most of these novel probes are not clinically available, they offer significant promise for future translational applications. In this review, we have highlighted the areas of future development that are likely to have a profound impact on cancer detection and treatment.

Diversity and Professional Advancement in Medical Physics.

Purpose: While disparities in the inclusion and advancement of women and minorities in science, technology, engineering, mathematics, and medical fields have been well documented, less work has focused on medical physics specifically. In this study, we evaluate historical and current diversity within the medical physics workforce, in cohorts representative of professional advancement (PA) in the field, and within National Institutes of Health (NIH)-funded medical physics research activities. Methods and Materials: The 2020 American Association of Physicists in Medicine (AAPM) membership was queried as surrogate for the medical physics workforce. Select subsets of the AAPM membership were queried as surrogate for PA and early career professional advancement (ECPA) in medical physics. Self-reported AAPM-member demographics data representative of study analysis groups were identified and analyzed. Demographic characteristics of the 2020 AAPM membership were compared with those of the PA and ECPA cohorts and United States (US) population. The AAPM-NIH Research Database was appended with principal investigator (PI) demographics data and analyzed to evaluate trends in grant allocation by PI demographic characteristics. Results: Women, Hispanic/Latinx/Spanish individuals, and individuals reporting a race other than White or Asian alone comprised 50.8%, 18.7%, and 32.4% of the US population, respectively, but only 23.9%, 9.1%, and 7.9% of the 2020 AAPM membership, respectively. In general, representation of women and minorities was further decreased in the PA cohort; however, significantly higher proportions of women (P < .001) and Hispanic/Latinx/Spanish members (P < .05) were observed in the ECPA cohort than the 2020 AAPM membership. Analysis of historical data revealed modest increases in diversity within the AAPM membership since 2002. Across NIH grants awarded to AAPM members between 1985 and 2020, only 9.4%, 5.3%, and 1.7% were awarded to women, Hispanic/Latinx/Spanish, and non-White, non-Asian PIs, respectively. Conclusions: Diversity within medical physics is limited. Proactive policy should be implemented to ensure diverse, equitable, and inclusive representation within research activities, roles representative of PA, and the profession at large.

AAPM Task Group Report 238: 3D C-arms with volumetric imaging capability.

This report reviews the image acquisition and reconstruction characteristics of C-arm Cone Beam Computed Tomography (C-arm CBCT) systems and provides guidance on quality control of C-arm systems with this volumetric imaging capability. The concepts of 3D image reconstruction, geometric calibration, image quality, and dosimetry covered in this report are also pertinent to CBCT for Image-Guided Radiation Therapy (IGRT). However, IGRT systems introduce a number of additional considerations, such as geometric alignment of the imaging at treatment isocenter, which are beyond the scope of the charge to the task group and the report. Section 1 provides an introduction to C-arm CBCT systems and reviews a variety of clinical applications. Section 2 briefly presents nomenclature specific or unique to these systems. A short review of C-arm fluoroscopy quality control (QC) in relation to 3D C-arm imaging is given in Section 3. Section 4 discusses system calibration, including geometric calibration and uniformity calibration. A review of the unique approaches and challenges to 3D reconstruction of data sets acquired by C-arm CBCT systems is give in Section 5. Sections 6 and 7 go in greater depth to address the performance assessment of C-arm CBCT units. First, Section 6 describes testing approaches and phantoms that may be used to evaluate image quality (spatial resolution and image noise and artifacts) and identifies several factors that affect image quality. Section 7 describes both free-in-air and in-phantom approaches to evaluating radiation dose indices. The methodologies described for assessing image quality and radiation dose may be used for annual constancy assessment and comparisons among different systems to help medical physicists determine when a system is not operating as expected. Baseline measurements taken either at installation or after a full preventative maintenance service call can also provide valuable data to help determine whether the performance of the system is acceptable. Collecting image quality and radiation dose data on existing phantoms used for CT image quality and radiation dose assessment, or on newly developed phantoms, will inform the development of performance criteria and standards. Phantom images are also useful for identifying and evaluating artifacts. In particular, comparing baseline data with those from current phantom images can reveal the need for system calibration before image artifacts are detected in clinical practice. Examples of artifacts are provided in Sections 4, 5, and 6.

A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis.

Importance: An accurate and robust artificial intelligence (AI) algorithm for detecting cancer in digital breast tomosynthesis (DBT) could significantly improve detection accuracy and reduce health care costs worldwide. Objectives: To make training and evaluation data for the development of AI algorithms for DBT analysis available, to develop well-defined benchmarks, and to create publicly available code for existing methods. Design, Setting, and Participants: This diagnostic study is based on a multi-institutional international grand challenge in which research teams developed algorithms to detect lesions in DBT. A data set of 22 032 reconstructed DBT volumes was made available to research teams. Phase 1, in which teams were provided 700 scans from the training set, 120 from the validation set, and 180 from the test set, took place from December 2020 to January 2021, and phase 2, in which teams were given the full data set, took place from May to July 2021. Main Outcomes and Measures: The overall performance was evaluated by mean sensitivity for biopsied lesions using only DBT volumes with biopsied lesions; ties were broken by including all DBT volumes. Results: A total of 8 teams participated in the challenge. The team with the highest mean sensitivity for biopsied lesions was the NYU B-Team, with 0.957 (95% CI, 0.924-0.984), and the second-place team, ZeDuS, had a mean sensitivity of 0.926 (95% CI, 0.881-0.964). When the results were aggregated, the mean sensitivity for all submitted algorithms was 0.879; for only those who participated in phase 2, it was 0.926. Conclusions and Relevance: In this diagnostic study, an international competition produced algorithms with high sensitivity for using AI to detect lesions on DBT images. A standardized performance benchmark for the detection task using publicly available clinical imaging data was released, with detailed descriptions and analyses of submitted algorithms accompanied by a public release of their predictions and code for selected methods. These resources will serve as a foundation for future research on computer-assisted diagnosis methods for DBT, significantly lowering the barrier of entry for new researchers.