Citations

ABSTRACT Purpose Optical coherence tomography (OCT) is a widely used imaging modality in ophthalmology. Accurate semantic segmentation of these images is critical for both clinical and research applications, yet existing convolutional neural network (CNN)-based methods face challenges in generalizability and robustness. This study introduces MAYOCTransformer, the first transformer-based deep learning model for comprehensive semantic segmentation of OCT images, and evaluates its performance against CNN-based models. Methods A large dataset of 3,500 OCT images was manually segmented using an iterative deep learning-assisted workflow. The MAYOCTransformer model, based on the Mask2Former architecture, was trained and compared against CNN-based segmentation models, including U-Net, U-Net++, FPN, and DeepLabV3+. Comprehensive segmentation tasks included 10 retinal layer segmentation, choroid stroma and vessel segmentation, and the identification of 9 types of discrete pathological findings including intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), subretinal hyper-reflective material (SHRM), intraretinal hyper-reflective foci, and reticular pseudodrusen. Model performance was evaluated using the Dice similarity coefficient (DSC) on a hold-out test set with five-fold cross-validation. Additional validation was performed using external datasets, open-source segmentation models, and a randomized blinded expert evaluation. Results MAYOCTransformer outperformed CNN-based models in most segmentation tasks. Choroid segmentation performance was comparable between MAYOCTransformer and CNN models. External validation demonstrated the model’s generalizability, achieving higher DSC scores than publicly available segmentation models. A blinded expert evaluation showed that MAYOCTransformer’s segmentation was non-inferior to manual annotations. Conclusion MAYOCTransformer provides improved segmentation performance over CNN-based models. Its ability to generalize to external datasets suggests potential applicability in clinical and research settings.

Deep brain stimulation (DBS) is an established therapeutic intervention for a range of neurological disorders, including Parkinson’s disease, essential tremor, and epilepsy. The efficacy of DBS is predicated on the modulation of dysfunctional neural circuits through the application of electrical pulses. Recent advancements in MRI technology have facilitated the visualization of brain nuclei and their associated networks, which is critical for proper patient-specific targeting of electrodes in surgical procedures. This advancement aims to personalize surgical planning and postoperative programming by integrating patient-specific anatomical and connectivity models. The advent of clinical ultrahigh-field MRI, particularly 7T MRI, significantly enhances the targeting of DBS by improving spatial resolution, signal-to-noise ratio, and tissue contrast. Compared with lower field strengths, 7T MRI provides superior visualization of deeply situated brain nuclei and their extensive cortical projections, including the subthalamic nucleus, globus pallidus internus, and thalamus. This review synthesizes a multi-institutional consensus regarding the technical and clinical applications of 7T MRI, drawing on experience from more than 1000 procedures using 7T DBS. It encompasses both imaging acquisition and postprocessing techniques aimed at optimizing image quality. Our extensive clinical experience informs best practices for correcting distortions, mitigating image artifacts, and employing specific imaging sequences that enhance the visualization of common DBS targets. The insights and recommendations presented are intended to promote the safe and effective utilization of 7T MRI in DBS.

Selective inhibition of the more than 100 S1 family serine proteases is a long-standing challenge due to their active site similarity. Mesotrypsin, implicated in cancer progression, exemplifies these difficulties; no current inhibitors achieve selectivity over other human trypsins. We found an unexpected autoinhibited conformation of mesotrypsin via x-ray crystallography, revealing a cryptic pocket adjacent to the active site. Using high-throughput virtual screening targeting this cryptic pocket, we identified a conformationally selective small-molecule inhibitor that stabilizes the inactive state of mesotrypsin. This inhibitor demonstrates selectivity for mesotrypsin over other trypsins. Our findings challenge the accepted view of digestive trypsins as constitutively active enzymes lacking potential for allosteric regulation. Furthermore, analyses of other structures suggest that dynamic sampling of closed states with analogous allosteric cryptic pockets appears widespread among S1 serine proteases. These observations point to a potentially generalizable strategy to achieve selective inhibition, offering broad implications for drug development targeting serine proteases in cancer and other diseases.

Importance Tumor-infiltrating lymphocytes (TILs) are a provocative biomarker in melanoma, influencing diagnosis, prognosis, and immunotherapy outcomes; however, traditional pathologist-read TIL assessment on hematoxylin and eosin–stained slides is prone to interobserver variability, leading to inconsistent clinical decisions. Therefore, development of newer TIL scoring approaches that produce more reliable and consistent readouts is important. Objective To evaluate the analytical and clinical validity of a machine learning algorithm for TIL quantification in melanoma compared with traditional pathologist-read methods. Design, Setting, and Participants This multioperator, global, multi-institutional prognostic study compared TIL scoring reproducibility between traditional pathologist-read methods and an artificial intelligence (AI)-driven approach. The study was conducted using retrospective cohorts of patients with melanoma between January 2022 and June 2023 across 45 institutions, with tissue evaluated by participants from academic, clinical, and research institutions. Participants were selected to ensure diverse expertise and professional backgrounds. Main Outcomes and Measures Intraclass correlation coefficient (ICC) values were calculated for the manual and AI-assisted arms using log-transformed data. Kendall W values were calculated for Clark scores (brisk = 3, nonbrisk = 2, and sparse = 1). Reliabilities of ICC and W values were classified as moderate (0.40-0.60), good (0.61-0.80), or excellent (>0.80). AI TIL measurements were dichotomized using the 16.6 and median cutoffs. Univariable and multivariable Cox regression analyses assessed the prognostic value of TIL scores adjusted for clinicopathologic variables. Results There were 111 patients with melanoma in the independent testing cohort (median [range] age at diagnosis, 61.0 [25.0-87.0] years; 56 [50.5%] male) who contributed melanoma whole tissue sections. A total of 98 participants evaluated TILs on 60 hematoxylin and eosin–stained melanoma tissue sections. All 40 participants in the manual arm were pathologists, while the AI-assisted arm included 11 pathologists and 47 nonpathologists (scientists). The AI algorithm demonstrated superior reproducibility, with ICCs higher than 0.90 for all machine learning TIL variables, significantly outperforming manual assessments (ICC, 0.61 for AI-derived stromal TILs vs Kendall W , 0.44 for manual Clark TIL scoring). AI-based TIL scores showed prognostic associations with patient outcomes (n = 111) using the median cutoff approach with a hazard ratio (HR) of 0.45 (95% CI, 0.26-0.80; P = .005), and using the cutoff of 16.6, with an HR of 0.56 (95% CI, 0.32-0.98; P = .04). Conclusions and Relevance In this prognostic study of TIL quantification in melanoma, the AI algorithm demonstrated superior reproducibility and prognostic associations compared with traditional methods. Although the retrospective nature of the cohorts limits demonstration of clinical utility, the publicly available dataset and open-source AI tool offer a foundation for future validation and integration into melanoma management.

Objectives Periodic quality control (QC) testing of ultrasound (US) imaging systems is essential to ensure and maintain image quality and safety. The study aims to analyze QC findings from medical physics annual surveys of modern clinical US systems in a multi‐institutional survey. Methods QC results from annual surveys between 2018 and 2021 were retrospectively collected from 12 medical physicists from 11 institutions or consulting companies (hereafter referred to as sites). QC tests were classified as scanner‐ and transducer‐related tests, where scanner‐related tests also included evaluation of diagnostic workstation display monitors and routine QC programs if applicable. Test methodology and pass/fail criteria were established by each site. QC findings were defined as results requiring follow‐up action by service engineers, vendors, or other personnel. The percentage of annual findings was calculated for each site and averaged across the years of data contributed. Furthermore, findings across all sites were aggregated for an overall analysis. Results QC data from a total of 1069 scanner tests and 4542 transducer tests were collected. The average annual percentage of scanner‐related findings varied from 0 to 40.8% among all sites (first quartile 8.7%, median 18.2%, and third quartile 34.1%), while that of transducer‐related findings ranged between 0.5% and 19.9% (first quartile 3.9%, median 7.2%, and third quartile 14.5%). For scanner‐related tests, the top 3 categories of findings were associated with physical and mechanical integrity (171 findings, 74.7%), quantitative testing of the scanner display monitor (40 findings, 17.5%), and scanner port creating artifacts (10 findings, 4.4%). The top 3 findings for transducers related to uniformity and artifact (227 findings, 79.9%), physical and mechanical integrity (44 findings, 15.5%), and sensitivity in fundamental mode (9 findings, 3.2%). Conclusions Medical physics annual surveys revealed considerable actionable findings of modern US systems, which inform the status of current US QC practices in the United States and may guide future standardization and recommendation of QC tests.

Pneumocystis pneumonia (PCP) is a serious fungal infection affecting immunocompromised hosts. Decompensated cirrhosis leads to cirrhosis-associated immune dysfunction (CAID), a form of impaired cellular immunity that may predispose patients to opportunistic infections such as PCP. We conducted a retrospective review of 727 patients with proven or probable PCP from 2017 to 2025. Of these, 33 had decompensated cirrhosis. These patients were stratified into two groups: Cirrhosis Only (n = 16) and Cirrhosis with Additional Immunocompromising Conditions (n = 17). Among the patients with cirrhosis, the overall mortality was 48%, with the 90-day mortality reaching 57.6% (95% CI: 39.2–74.5%). Compared with those without cirrhosis, the patients with cirrhosis had a higher risk of mortality (OR: 4.08, 95% CI: 2.01–8.30, p < 0.001), increased intensive care unit (ICU) admission (87% vs. 42%, p < 0.001), and greater need for renal replacement therapy (54.6% vs. 7.5%, p < 0.001). These findings suggest that decompensated cirrhosis alone may represent a sufficient and underrecognized risk factor for PCP, with a high associated mortality. Given the preventable nature of this infection, future studies are needed to assess the incidence, define the risk, and investigate the role of prophylaxis in this vulnerable population.

Abstract Background Pneumocystis jirovecii pneumonia (PCP) is increasingly seen in patients who are non-HIV immunocompromised hosts, yet modern risk factors and outcomes are poorly recognized and defined. Methods A retrospective review was conducted of adult patients who met criteria for proven or probable PCP from 2017 to 2024 across a large academic multicenter health system. The primary outcome was mortality among cohorts, defined by etiology of immunosuppression through univariate and age-adjusted logistic regression. Secondary analyses included trends in annual diagnoses and testing patterns. Results A total of 701 patients met criteria for inclusion, representing one of the largest clinically characterized cohorts of PCP to date. The median age was 65 years (IQR, 54–73) and 62% were male. The most common risk groups were hematologic malignancy (32.2%), solid tumor cancers receiving chemotherapy (22.4%), and autoimmune disease with immunosuppression (17.7%). Annual PCP diagnoses increased at a rate of 15.8% (95% CI, 8.9%–23.2%) in parallel with increased testing. Only 5.4% of patients were receiving prophylaxis at the time of diagnosis. Overall mortality was 20% (95% CI, 17%–23%) and highest in cirrhosis (adjusted odds ratio, 6.24; 95% CI, 2.84–13.69; P &lt; .001). Conclusions PCP in the current era affects a broad range of patients who are immunocompromised, with high associated mortality and low rates of prophylaxis. Patients with solid tumors and those with cirrhosis are at particularly high risk of mortality. These findings highlight the need to reassess and redefine PCP prophylaxis guidelines in specific populations and our understanding of who is at risk.

Key Points Circulating proteins independently associated with kidney stone diagnosis are related to kidney stone matrix. Lower circulating uromodulin and higher scavenger receptor cysteine-rich domain-containing group B protein levels were associated with higher kidney stone risk, whereas kidney stone presence elevates plasma matrix metalloproteinase 7 level. The protective effect of uromodulin against kidney stones was independent of kidney function. Background Kidney stones are increasingly recognized as a systemic disorder with a high global prevalence. However, large proteomics studies are lacking. Methods An individual-level proteomics study with rigorous adjustments was performed on 35,331 UK Biobank participants to uncover the independent associations between 2922 circulating proteins and prevalent kidney stone disease. Mendelian randomization analysis was used to assess causal relationships. Findings were validated using genomic data from the Mayo Clinic Biobank ( N =43,744), concentration-response analysis, transcriptomics analyses, and additional genome-wide association studies. Results Nine plasma proteins were independently associated with a kidney stone diagnosis, including reduced uromodulin (UMOD; β , −0.10; 95% confidence interval [CI], −0.15 to −0.05) and elevated scavenger receptor cysteine-rich domain-containing group B protein (SSC4D; β , 0.28; 95% CI, 0.17 to 0.38) and were enriched in extracellular matrix pathways. Mendelian randomization analysis revealed that the presence of kidney stone contributed to elevated levels of matrix metalloproteinase 7. Conversely, lower plasma UMOD (odds ratio [OR], 0.93; 95% CI, 0.90 to 0.97) and higher plasma SSC4D (OR, 1.10; 95% CI, 1.02 to 1.18) were associated with kidney stone risk. These associations were consistently replicated in the Mayo Clinic Biobank dataset (UMOD; OR, 0.92; 95% CI, 0.86 to 0.98; SSC4D; OR, 1.13; 95% CI, 1.01 to 1.27) and further validated by a concentration-response analysis. Single-nucleus RNA sequencing and quantitative trait loci analyses confirmed consistent associations between thick ascending limb UMOD expression and stone former status and with blood and urine UMOD concentrations. Genome-wide association study analysis, adjusted for eGFR, suggested that the protective role of UMOD against kidney stones was independent of kidney function. Conclusions This study highlights significant associations between concentrations of specific blood proteins and a history of kidney stones. Several implicated proteins are related to kidney stone matrix, with UMOD independently associated with lower risk and SSC4D with higher risk of kidney stones.

We investigated the prognostic impact of blast counts, TP53 allelic state determinants (number of hits, del(17p), variant allele frequency, complex karyotype),and a novel karyotypic clonal cell fraction (≤50% clonal cells vs >50% clonal cells (termed ‘CK50’)) in 495 individuals with TP53- mutated ( TP53 MUT ) myeloid neoplasms. Outcome examined was 24-month survival (OS24). The cohort (median age 71) included 29% (144/495) myelodysplastic syndromes (MDS)/MDS-acute myeloid leukaemia (AML) (1%–19% blasts) and 71% (351/495) AML (≥20% blasts), with 18% (81/460) having low CK50. Overall, 83% received front-line hypomethylating agents. Higher blast counts (<20% vs ≥20%) were marginally associated with CK50 (p=0.08). In the OS24 analysis, blast count showed a marginal association with OS24 (HR 1.3 (95% CI 1.0 to 1.6); p=0.07), while CK50 predicted significantly inferior outcomes (HR=1.7 (95% CI 1.2 to 2.3); p=0.002). In a multivariable model including all TP53 allelic state determinants, only CK50 and complex karyotype remained relevant for predicting adverse outcomes.