Toshimasa James Clark

Context: Thyroid nodule ultrasound-based risk stratification schemas rely on the presence of high-risk sonographic features. However, some malignant thyroid nodules have benign appearance on thyroid ultrasound. New methods for thyroid nodule risk assessment are needed. Objective: We investigated polygenic risk score (PRS) accounting for inherited thyroid cancer risk combined with ultrasound-based analysis for improved thyroid nodule risk assessment. Methods: The convolutional neural network classifier was trained on thyroid ultrasound still images and cine clips from 621 thyroid nodules. Phenome-wide association study (PheWAS) and PRS PheWAS were used to optimize PRS for distinguishing benign and malignant nodules. PRS was evaluated in 73 346 participants in the Colorado Center for Personalized Medicine Biobank. Results: When the deep learning model output was combined with thyroid cancer PRS and genetic ancestry estimates, the area under the receiver operating characteristic curve (AUROC) of the benign vs malignant thyroid nodule classifier increased from 0.83 to 0.89 (DeLong, P value = .007). The combined deep learning and genetic classifier achieved a clinically relevant sensitivity of 0.95, 95% CI [0.88-0.99], specificity of 0.63 [0.55-0.70], and positive and negative predictive values of 0.47 [0.41-0.58] and 0.97 [0.92-0.99], respectively. AUROC improvement was consistent in European ancestry-stratified analysis (0.83 and 0.87 for deep learning and deep learning combined with PRS classifiers, respectively). Elevated PRS was associated with a greater risk of thyroid cancer structural disease recurrence (ordinal logistic regression, P value = .002). Conclusion: Augmenting ultrasound-based risk assessment with PRS improves diagnostic accuracy.

Background: Contrast bolus variation during contrast‐enhanced magnetic resonance angiography (CE‐MRA) acquisition may lead to vessel blurring.Purpose: To combine knowledge of how contrast signal intensity (SI) evolves for different injection strategies with anatomically familiar parametric computer models to measure and visually assess the effects of a wide range of variables on modeled CE‐MRA, and in doing so develop contrast rate injection guidelines.Study Type: Computer modeling.Phantom: Digital three‐dimensional phantom consisting of orthogonal “aorta,” 7 mm diameter “renal arteries” (with 57% and 86% diameter stenoses), and 7 mm diameter “superior mesenteric artery” (with 57% diameter stenosis).Field Strength/Sequence: One millimeter in‐plane resolution arterial CE‐MRA imaging at 3 T.Assessment: “Background” (time invariant) and “vascular” (time varying) components of the phantom were each Fourier transformed into the spatial frequency domain, the latter modulated by the SI evolution of a contrast bolus of varying “plateau” lengths and “tail” heights. Data are presented as surface plots of stenosis measurement error and blurring vs. a reference‐standard injection.Statistical Tests: Descriptive.Results: Shorter plateau lengths and lower tail heights resulted in increased measured stenosis error and blurring vs. the reference standard. Under a 44‐second acquisition, full width half maximum stenosis error of the 86% stenosis with 25% plateau length and 25% tail height is 24% as compared to that from the reference standard. As plateau length and tail height approach 100%, stenosis error and blurring approach a floor defined by the MR acquisition's limitations.Data Conclusion: We propose that to achieve minimal degradation with CE‐MRA, one can create a contrast bolus with either 60% plateau and 50% tail height or 80% plateau with any tail. These considerations may well prove to be of practical importance, possibly via manipulating the tail by means of multiphasic contrast injections.Level of Evidence: 3Technical Efficacy: Stage 1

Adrenocortical carcinoma (ACC) is a rare orphan disease with a dismal prognosis. Surgery remains the first-line treatment, but most patients eventually develop metastatic disease. Mitotane is often used with chemotherapy with modest success. Little information is available concerning the efficacy of immunotherapy in combination with mitotane. We conducted a retrospective review of our initial six patients with metastatic ACC, for whom mitotane alone or with chemotherapy failed, and who were subsequently treated with a combination of pembrolizumab and mitotane, between July 2016 and March 2019. Imaging was analyzed per Response Evaluation Criteria in Solid Tumours 1.1 criteria. Two patients had a partial response and four patients had stable disease (8 to 19 months). One patient had grade 3 hepatitis and pembrolizumab was discontinued after 8 months. She died with disease progression 16 months after initiating pembrolizumab. One patient developed brain metastasis after 19 months of treatment and was transitioned to hospice. One patient had focal pneumonitis after 18 months of treatment, and pembrolizumab was discontinued. Three remaining patients continue pembrolizumab plus mitotane at the time of this writing. The current standard of care for ACC is a combination of etoposide, doxorubicin, cisplatin, and mitotane with an overall survival of 14.8 months. All six patients lived for at least 16 months after starting pembrolizumab added to mitotane therapy. The therapy appeared to be effective in both microsatellite instability-high and microsatellite stable tumors, suggesting some synergistic effect with mitotane. Combined immunotherapy and mitotane should be considered in future clinical trials in patients with ACC.

We studied diagnostic performance of an algorithm guiding thyroid nodule management using a malignancy risk model as compared with extant management guidelines. Single-institution, retrospective study was performed with sequential cases from pathology registry from 2012 to 2015. Seventy-eight patients were enrolled, with benign and malignant groups defined by aspiration results. Risk Threshold Algorithm determined management based off of a logistic regression model and a risk threshold. American College of Radiology Thyroid Imaging, Reporting and Data System (ACR TI-RADS), Society of Radiologists in Ultrasound (SRU), and American Thyroid Association (ATA) guidelines were used in comparison. Sensitivity, specificity, positive/negative predictive values, receiver operating characteristic (ROC) values were derived, with significance assessed via McNemar and permutation tests. Forty-four benign nodules and 40 papillary thyroid carcinomas were included. Risk Threshold Algorithm area under the ROC curve was 0.80 versus 0.59 (ACR TI-RADS), 0.49 (SRU), and 0.44 (ATA); all areas under the ROC curve differences were statistically significant. Risk Threshold Algorithm demonstrates sensitivity, specificity, positive predictive value, and negative predictive values of 63%, 91%, 86%, and 73% at the risk threshold maximizing diagnostic performance, compared with 85%, 39%, 56%, and 74% (ACR TI-RADS); 85%, 18%, 50%, and 57% (SRU); and 89%, 11%, 50%, and 83% (ATA). Sensitivity and specificity were significantly different between all groups except SRU versus TI-RADS. The Risk Threshold Algorithm, based on a malignancy risk model, demonstrates increased overall diagnostic accuracy as compared with ACR TI-RADS, SRU, and ATA management guidelines. Through eliminating unnecessary biopsy, patient anxiety, and morbidity can be reduced.

To investigate whether the histogram analysis method of characterizing adrenal nodules as adenomas is affected by increased noise with modern CT technique, and if an extension that allows for noise correction will improve diagnostic performance.