Callstrom, Matthew R.

Abstract The advent of high-throughput sequencing has led to an exponential increase in genomic data, highlighting the need for efficient and accurate models to analyze and interpret this information. In this study, we introduce a novel, exomic foundational model that leverages a combination of the human reference genome and multispecies data to improve variant detection and interpretation. Our model utilizes a short-range transformer architecture and is trained on a large dataset of human exomic sequences derived from the Tapestry study. Through a series of ablation studies and scaling experiments, we demonstrate the effectiveness of our model in predicting next token accuracy and identifying clinically pathogenic variants. We also show that our model outperforms existing models in a range of downstream tasks, including variant effect prediction and disease state identification. In fact, our largest sequence transformer for range adaptive nucleotide decoding variant (1B parameters) surpassed previous benchmarks, demonstrating a mean accuracy of 0.880 [an 8.2% improvement over the original nucleotide transformer (NT) and a 7% improvement over NT-v2]. Furthermore, we construct a unique exomic ClinVar dataset to evaluate the model’s performance on pathogenicity and disease states. Our results highlight the potential of this model to improve our understanding of the human exome and its role in disease. The model and its applications have significant implications for genomics-based diagnosis and personalized medicine, including tailored therapeutic development.

Abstract The advent of high-throughput sequencing has led to an exponential increase in genomic data, highlighting the need for efficient and accurate models to analyze and interpret this information. Here, we introduce a novel, exomic foundational model that leverages a combination of human reference genome and multispecies data to improve variant detection and interpretation. Our model utilizes a short- range transformer architecture and is trained on a large dataset of human exomic sequences derived from the Tapestry study. Through a series of ablation studies and scaling experiments, we demonstrate the effectiveness of our model in pre- dicting next token accuracy and identifying clinically pathogenic variants. We also show that our model outperforms existing models in a range of downstream tasks, including variant effect prediction and disease state identification. In fact, our largest STRAND variant (1B parameters) surpassed previous benchmarks, demonstrating a mean accuarcy of 0.880 (8.2% improvement over the original NT and 7% improvement over NT-v2). Furthermore, we construct a unique exomic ClinVar dataset to evaluate the model’s performance on pathogenicity and disease states. Our results highlight the potential of this model to improve our understanding of the human exome and its role in disease. The model and its applications have significant implications for genomic based diagnosis and personalized medicine including tailored therapeutic development.

Abstract Background Autonomously functioning thyroid nodules (AFTNs) constitute 5% to 7% of thyroid nodules and represent the second most common cause of hyperthyroidism following Graves’ disease. Currently, radioactive iodine (RAI) and surgery are the standard treatment options, and both incur a risk of postprocedural hypothyroidism and other surgery and radiation-related complications. Methods This work aimed at assessing the efficacy of radiofrequency ablation (RFA) as an alternative treatment option for resolving hyperthyroidism and the nodule volume rate reduction (VRR) and its associated adverse events. Results A total of 22 patients underwent RFA for a solitary AFTN. Seventy-two percent (n = 16) had subclinical hyperthyroidism, 9% (n = 2) had overt hyperthyroidism, and 18% (n = 4) were biochemically euthyroid on antithyroid medication. Average pretreatment TSH was 0.41 mIU/L (SD = 0.98) and free T4 1.29 ng/dL (SD = 0.33). Following a single RFA session, hyperthyroidism resolved in 90.9% (n = 20) and average VRR (61.13%) was achieved within 3 to 6 months following the ablation. Except for 1 nodule, none of the nodules grew during the follow-up period (16.5 months). Two patients (9%) developed transient tachycardia requiring short-term beta-blocker therapy, and 2 developed mild hypothyroidism requiring levothyroxine therapy. Two patients developed recurrent hyperthyroidism and elected to undergo lobectomy and repeat RFA respectively. No serious adverse effects were noted in this cohort. Conclusion RAI and/or surgery represent the standard of care for toxic adenomas, but RFA shows excellent efficacy and safety profile. Therefore, at centers with RFA expertise, it should be considered an alternative treatment strategy, avoiding radiation and surgery-related complications.

ObjectivesMetabolic dysfunction‐associated steatotic liver disease (MASLD) is the most prevalent liver disorder in Western countries, with approximately 20%–30% of the MASLD patients progressing to severe stages. There is an urgent need for noninvasive, cost‐effective, widely accessible, and precise biomarkers to evaluate liver steatosis. This study aims to assess and compare the diagnostic performance of a novel reference frequency method‐based ultrasound attenuation coefficient estimation (ACE) in both fundamental (RFM‐ACE‐FI) and harmonic (RFM‐ACE‐HI) imaging for detecting and grading liver steatosis.MethodsAn Institutional Review Board‐approved prospective study was carried out between December 2018 and October 2022. A total number of 130 subjects were enrolled in the study. The correlation between RFM‐ACE‐HI values and magnetic resonance imaging proton density fat fraction (MRI‐PDFF), as well as between RFM‐ACE‐FI values and MRI‐PDFF were calculated. The diagnostic performance of RFM‐ACE‐FI and RFM‐ACE‐HI was evaluated using receiver operating characteristic (ROC) curve analysis, as compared to MRI‐PDFF. The reproducibility of RFM‐ACE‐HI was assessed by interobserver agreement between two sonographers.ResultsA strong correlation was observed between RFM‐ACE‐HI and MRI‐PDFF, with R = 0.88 (95% confidence interval [CI]: 0.83–0.92; P < .001), while the correlation between RFM‐ACE‐FI and MRI‐PDFF was R = 0.65 (95% CI: 0.50–0.76; P < .001). The area under the ROC (AUROC) curve for RFM‐ACE‐HI in staging liver steatosis grades of S ≥ 1 and S ≥ 2 was 0.97 (95% CI: 0.91–0.99; P < .001) and 0.98 (95% CI: 0.93–1.00; P < .001), respectively, and 0.76 (95% CI: 0.65–0.85) and 0.80 (95% CI: 0.70–0.88) for RFM‐ACE‐FI, respectively. Great reproducibility was achieved for RFM‐ACE‐HI, with an interobserver agreement of R = 0.97 (95% CI: 0.94–0.99; P < .001).ConclusionsThe novel RFM‐ACE‐HI method offered high liver steatosis diagnostic accuracy and reproducibility, which has important clinical implications for early disease intervention and treatment evaluation.

AbstractBackgroundComputed tomography (CT) is routinely used to guide cryoablation procedures. Notably, CT‐guidance provides 3D localization of cryoprobes and can be used to delineate frozen tissue during ablation. However, metal‐induced artifacts from ablation probes can make accurate probe placement challenging and degrade the ice ball conspicuity, which in combination could lead to undertreatment of potentially curable lesions.PurposeIn this work, we propose an image‐based neural network (CNN) model for metal artifact reduction for CT‐guided interventional procedures.MethodsAn image domain metal artifact simulation framework was developed and validated for deep‐learning‐based metal artifact reduction for interventional oncology (MARIO). CT scans were acquired for 19 different cryoablation probe configurations. The probe configurations varied in the number of probes and the relative orientations. A combination of intensity thresholding and masking based on maximum intensity projections (MIPs) was used to segment both the probes only and probes + artifact in each phantom image. Each of the probe and probe + artifact images were then inserted into 19 unique patient exams, in the image domain, to simulate metal artifact appearance for CT‐guided interventional oncology procedures. The resulting 361 pairs of simulated image volumes were partitioned into disjoint training and test datasets of 304 and 57 volumes, respectively. From the training partition, 116 600 image patches with a shape of 128 × 128 × 5 pixels were randomly extracted to be used for training data. The input images consisted of a superposition of the patient and probe + artifact images. The target images consisted of a superposition of the patient and probe only images. This dataset was used to optimize a U‐Net type model. The trained model was then applied to 50 independent, previously unseen CT images obtained during renal cryoablations. Three board‐certified radiologists with experience in CT‐guided ablations performed a blinded review of the MARIO images. A total of 100 images (50 original, 50 MARIO processed) were assessed across different aspects of image quality on a 4‐point likert‐type item. Statistical analyses were performed using Wilcoxon signed‐rank test for paired samples.ResultsReader scores were significantly higher for MARIO processed images compared to the original images across all metrics (all p < 0.001). The average scores of the overall image quality, iceball conspicuity, overall metal artifact, needle tip visualization, target region confidence, and worst metal artifact, needle tip visualization, iceball conspicuity, and target region confidence improved by 34.91%, 36.29%, 39.94%, 34.17%, 35.13%, and 45.70%, respectively.ConclusionsThe proposed method of image‐based metal artifact simulation can be used to train a MARIO algorithm to effectively reduce probe‐related metal artifacts in CT‐guided cryoablation procedures.

Abstract Disclosure: M. Dhanasekaran: None. A.A. Rajwani: None. M.R. Castro: None. J.C. Morris: None. J. Schmitz: None. R.A. Lee: None. M. Callstrom: None. M. Stan: None. Context: Autonomously functioning thyroid nodules (AFTNs) constitutes 5% of thyroid nodules and is the second most common cause of hyperthyroidism following Graves’ Disease. Untreated hyperthyroidism is associated with adverse cardiovascular and skeletal complications. Currently, radioactive iodine (RAI) and surgery are the standard treatment options for AFTNs, and both incur a risk of post-procedural hypothyroidism. To overcome this and other surgery/radiation-related complications, radiofrequency ablation (RFA) has been utilized in multiple countries (for both toxic and non-toxic thyroid nodules). It has been shown to induce significant nodule volume reduction along with restoration of normal thyroid function in many AFTNs. Methods: We present a single-center experience using RFA as an alternative treatment modality for AFTNs. The study's primary aim was to assess the efficacy of RFA in normalizing thyroid hormone concentration and restoring the euthyroid state. In addition, we analyzed the efficacy of RFA in nodule volume rate reduction (VRR) and its associated adverse events. Results: A total of 22 consecutive patients (17 F and 5 M) underwent RFA for a solitary AFTN (hot nodule in thyroid uptake and scan) under variable degrees of general anesthesia. 72% (n=16) had subclinical hyperthyroidism, 9% (n=2) had overt hyperthyroidism, and 18% (n=4) were biochemically euthyroid on anti-thyroid drugs (ATD). The mean age at the time of ablation was 52.09 years (SD= 14.6), with a mean BMI of 27.36 kg/m2 (SD= 4.67). Average pre-treatment TSH was 0.41 mIU/L (SD= 0.980) and free T4 1.29 ng/dl (SD= 0.33). The thyroid function was assessed after a single RFA session. TSH normalized in all patients within 3-6 months following the ablation. All four patients on ATD pre-treatment discontinued therapy within three months following the procedure. The average VRR (62.54%) was achieved within 3-6 months following the RFA, and importantly, none of the nodules grew back during the follow-up period (up to 24 months). Two patients (9%) developed transient tachycardia requiring short-term beta-blocker therapy, and two (9%) developed mild hypothyroidism requiring levothyroxine therapy. One patient, euthyroid post RFA, developed recurrent hyperthyroidism 45 months later and elected to undergo lobectomy. No serious adverse effects were noted in this cohort. Conclusions - RAI and/or surgery represent the standard of care for toxic adenomas but RFA shows excellent efficacy along with an excellent safety profile. Therefore at centers with RFA expertise it should be considered an alternative treatment strategy, avoiding radiation and surgery-related complications. Presentation Date: Saturday, June 17, 2023