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.

Suicidal thoughts and attempts in a transdiagnostic eating disorder sample: Do diagnostic severity criteria predict risk?

OBJECTIVE: Eating disorders (EDs) are associated with elevated suicide. Low body mass index (BMI) and frequency of purging and binge eating represent severity criteria for EDs and distinguish full-threshold EDs from other specified feeding and eating disorders (OSFED). However, no work has taken a transdiagnostic approach to studying whether severity of these or other features is associated with suicidal ideation (SI) and attempts. METHOD: We examined diagnostic status, ED features, and SI and attempts in a large, transdiagnostic, community sample of 257 women with EDs and 45 controls without a current or past ED in the United States using the EDs Examination interview and the Structured Clinical Interview for the DSM-5 (Diagnostic and Statistical Manual of Mental Disorders). RESULTS: SI and suicide attempts (SA) were elevated in OSFED compared to controls but did not differ between OSFED and full-threshold EDs. Higher BMI predicted increased SI. Number of purging methods, but not frequency, was related to history of SA. Binge episode frequency and size were not significant predictors. CONCLUSIONS: OSFED presents with elevated SI and SA, and ED severity criteria that distinguish OSFED from full-threshold EDs do not predict SI or SA. Suicide risk assessments should be implemented universally across EDs in clinical practice.

Influence of nonsuicidal self-injury functions on suicide risk in individuals with eating disorders.

OBJECTIVE: Individuals with eating disorders (EDs) display elevated rates of suicidality (i.e., suicidal ideation and behaviors) as well as nonsuicidal self-injury (NSSI) (e.g., self-harm behaviors without intent to die). NSSI-and particularly the functions of NSSI-predict suicidal ideation in general samples; however, to our knowledge, the relation between NSSI functions and suicidal ideation in ED populations has been unexplored. METHOD: This study examined whether specific functions of NSSI are relevant to suicidal ideation in a treatment-seeking sample of women with EDs (n = 100). Participants completed self-report measures of suicidal ideation, NSSI, and related psychopathology upon intake to an ED treatment program. RESULTS: Using the four-function model of NSSI, we found that intrapersonal and interpersonal-negative reinforcement, but not interpersonal-positive reinforcement functions, were related to suicidal ideation in women with EDs. Contrary to expectations, we did not find that endorsement of multiple NSSI functions was related to increased suicide risk. DISCUSSION: Findings imply that some, but not all, functions of NSSI may be relevant to suicide risk in individuals with EDs. Implications for further research are discussed.

ACR's Connect and AI-LAB technical framework.

Objective: To develop a free, vendor-neutral software suite, the American College of Radiology (ACR) Connect, which serves as a platform for democratizing artificial intelligence (AI) for all individuals and institutions. Materials and Methods: Among its core capabilities, ACR Connect provides educational resources; tools for dataset annotation; model building and evaluation; and an interface for collaboration and federated learning across institutions without the need to move data off hospital premises. Results: The AI-LAB application within ACR Connect allows users to investigate AI models using their own local data while maintaining data security. The software enables non-technical users to participate in the evaluation and training of AI models as part of a larger, collaborative network. Discussion: Advancements in AI have transformed automated quantitative analysis for medical imaging. Despite the significant progress in research, AI is currently underutilized in current clinical workflows. The success of AI model development depends critically on the synergy between physicians who can drive clinical direction, data scientists who can design effective algorithms, and the availability of high-quality datasets. ACR Connect and AI-LAB provide a way to perform external validation as well as collaborative, distributed training. Conclusion: In order to create a collaborative AI ecosystem across clinical and technical domains, the ACR developed a platform that enables non-technical users to participate in education and model development.

Comparison of Thyroid Risk Categorization Systems and Fine-Needle Aspiration Recommendations in a Multi-Institutional Thyroid Ultrasound Registry.

OBJECTIVES: The aim of this study was to compare how often fine-needle aspiration (FNA) would be recommended for nodules in unselected, low-risk adult patients referred for sonographic evaluation of thyroid nodules by ACR Thyroid Imaging Reporting and Data System (TI-RADS), the American Thyroid Association guidelines (ATA), Korean Thyroid Imaging Reporting and Data System (K-TIRADS), European Thyroid Imaging Reporting and Data System (EU-TIRADS), and Artificial Intelligence Thyroid Imaging Reporting and Data System (AI-TIRADS). METHODS: Seven practices prospectively submitted thyroid ultrasound reports on adult patients to the ACR Thyroid Imaging Research Registry between October 2018 and March 2020. Data were collected about the sonographic features of each nodule using a structured reporting template with fields for the five ACR TI-RADS ultrasound categories plus maximum nodule size. The nodules were also retrospectively categorized according to criteria from ACR TI-RADS, the ATA, K-TIRADS, EU-TIRADS, and AI-TIRADS to compare FNA recommendation rates. RESULTS: For 27,933 nodules in 12,208 patients, ACR TI-RADS recommended FNA for 8,128 nodules (29.1%, 95% confidence interval [CI] 0.286-0.296). The ATA guidelines, EU-TIRADS, K-TIRADS, and AI-TIRADS would have recommended FNA for 16,385 (58.7%, 95% CI 0.581-0.592), 10,854 (38.9%, 95% CI 0.383-0.394), 15,917 (57.0%, 95% CI 0.564-0.576), and 7,342 (26.3%, 95% CI 0.258-0.268) nodules, respectively. Recommendation for FNA on TR3 and TR4 nodules was lowest for ACR TI-RADS at 18% and 30%, respectively. ACR TI-RADS categorized more nodules as TR2, which does not require FNA. At the high suspicion level, the FNA rate was similar for all guidelines at 68.7% to 75.5%. CONCLUSION: ACR TI-RADS recommends 25% to 50% fewer biopsies compared with ATA, EU-TIRADS, and K-TIRADS because of differences in size thresholds and criteria for risk levels.

The impact of a single session of aerobic exercise on positive emotional reactivity in depression: Insight into individual differences from the late positive potential.

Depression has been characterized by a broad disengagement from the environment, as reflected by dampened positive and negative emotional reactivity. Research has shown that acute exercise may enhance positive emotional reactivity in healthy adults. It is unknown whether it can alter positive emotional reactivity in depression. In the present study, positive emotional reactivity was assessed using the late positive potential (LPP) event-related potential before and after 30 min of moderate-intensity aerobic exercise in 43 adults with current or a lifetime history of depression (Mage = 32.74 years; Min/Max = 18/59) and 18 never-depressed healthy adults (Mage = 37.94 years; Min/Max = 21/61). Acute exercise increased the LPP for healthy adults; the LPP did not change among those with current or a lifetime history of depression. A secondary aim was to identify moderators of change in positive emotional reactivity among subgroups of adults with current depression. Compared to adults with impaired mood reactivity, those with intact mood reactivity had a pre-to-post increase in the LPP. The current study provides preliminary support for the LPP as a neural indicator of exercise efficacy and highlights individual differences in response to acute exercise in depression.

Highly Flexible Precisely Braided Multielectrode Probes and Combinatorics for Future Neuroprostheses.

The braided multielectrode probe (BMEP) is an ultrafine microwire bundle interwoven into a precise tubular braided structure, which is designed to be used as an invasive neural probe consisting of multiple microelectrodes for electrophysiological neural recording and stimulation. Significant advantages of BMEPs include highly flexible mechanical properties leading to decreased immune responses after chronic implantation in neural tissue and dense recording/stimulation sites (24 channels) within the 100-200 µm diameter. In addition, because BMEPs can be manufactured using various materials in any size and shape without length limitations, they could be expanded to applications in deep central nervous system (CNS) regions as well as peripheral nervous system (PNS) in larger animals and humans. Finally, the 3D topology of wires supports combinatoric rearrangements of wires within braids, and potential neural yield increases. With the newly developed next generation micro braiding machine, we can manufacture more precise and complex microbraid structures. In this article, we describe the new machine and methods, and tests of simulated combinatoric separation methods. We propose various promising BMEP designs and the potential modifications to these designs to create probes suitable for various applications for future neuroprostheses.

Risk factors associated with psychiatric readmission.

The present study focused on identifying risk factors for early readmission of patients discharged from an urban community hospital. Retrospective chart reviews were conducted on 207 consecutive inpatient psychiatric admissions that included patients who were readmitted within 15 days, within 3 to 6 months, and not admitted for at least 12 months post-discharge. Findings indicated that a diagnosis of schizophrenia/schizoaffective disorder (OR = 18; 95% CI 2.70-117.7; p < 0.05), history of alcohol abuse (OR = 9; 95% CI 1.80-40.60; p < 0.05), number of previous psychiatric hospitalizations (OR = 2; 95% CI 1.28-3.73; p < 0.05), and type of residence at initial admission (e.g., homeless, OR = 29; 95% CI 3.99-217; p < 0.05) were significant risk factors for early readmission, where OR compares readmission group 1 versus group 3 in the multinomial logistic regression. Initial positive urine drug screen, history of drug abuse or incarceration, and legal status at initial admission did not predict early readmission. Reducing the risk factors associated with psychiatric readmissions has the potential to lead to the identification and development of preventative intervention strategies that can significantly improve patient safety, quality of care, well-being, and contain health care expenditures.