Samantha Platt

Samantha Platt

Auto-generated profile, based on publicly available information

Samantha Platt

From the Department of Radiology, NYU Langone Health, New York

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 April 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
XMXueyan Mei
Xueyan Mei
ZLZelong Liu
Zelong Liu
ASAyushi Singh
Ayushi Singh
MLMarcia Lange
Marcia Lange
PBPriyanka Boddu
Priyanka Boddu
YYYang Yang
Yang Yang
For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates based on longitudinal data are challenging to create due to disease complexity, variation, and irregular visit intervals. Here, we utilize RadImageNet pretrained models to diagnose five types of ILD with multimodal data and a transformer model to determine a patient’s 3-year survival rate. When clinical history and associated CT scans are available, the proposed deep learning system can help clinicians diagnose and classify ILD patients and, importantly, dynamically predict disease progression and prognosis.

17 August 2022 in Journal of the American College of Radiology
Verified
Journal Article
Closed access
SPSamantha Platt
Samantha Platt
GMGuy H. Montgomery
Guy H. Montgomery
JSJulie B. Schnur
Julie B. Schnur
LMLaurie Margolies
Laurie Margolies

1 June 2025 in RadioGraphics
Verified
Journal Article
Closed access
DTDanielle Toussie
Danielle Toussie
LALea Azour
Lea Azour
SGSherief Garrana
Sherief Garrana
SPSamantha Platt
Samantha Platt
KOKendrah Osei
Kendrah Osei
JCJulianna M. Czum
Julianna M. Czum
Pulmonary calcification and ossification are encountered at imaging and have fundamentally different pathogeneses, histologic characteristics, and radiologic appearances that provide insight into underlying disease as well as clinical context for radiologic interpretation.

14 August 2025 in Journal of Computer Assisted Tomography
Verified
Journal Article
Closed access
SPSamantha Platt
Samantha Platt
BBBhavik Bansal
Bhavik Bansal
BBBarun Bagga
Barun Bagga
BDBari Dane
Bari Dane
Objective: To determine the optimal iodine concentration (IC) to differentiate enhancing from nonenhancing renal lesions at venous phase photon-counting CT (PCCT). Materials and Methods: Sixty-seven patients [41 males, mean (SD) age: 68 (13) y] who underwent contrast-enhanced venous phase abdominal PCCT and contrast-enhanced MRI were retrospectively identified. MRI characterization of renal lesions as simple cysts, hemorrhagic/proteinaceous cysts or masses was the reference standard. Two radiologists, blinded to MRI characterization, independently drew region-of-interests (ROI) within each renal lesion and the aorta to determine IC, iodine concentration normalized to aortic enhancement (NIC), postcontrast and virtual noncontrast attenuation. These variables were compared using nonparametric tests, and intraclass correlation coefficient was assessed. ROC analysis for IC, NIC, and attenuation difference was performed using mean measurements. Results: Median (IQR) IC was 0.015 (0.00 to 0.20) mg/mL for cysts (n = 41) and 3.00 (1.59 to 4.10) mg/mL for masses (n = 26; P < 0.001). NIC was 2 (−1 to 4)% for cysts and 58 (33 to 81)% for masses ( P < 0.001). For differentiating cysts from masses, 0.6 mg/mL IC had 100% sensitivity and 95% specificity [AUC = 1.00 (0.99, 1.00)] and 14.1%. NIC had 100% sensitivity and 98% specificity [AUC = 1.00 (0.99, 1.00)]. For differentiating cysts from enhancing masses, a 20 HU attenuation change from VNC to postcontrast images demonstrated a sensitivity of 96% and specificity of 95% [AUC = 1.00 (0.99, 1.00)]. IC was 0.13 (−0.11 to 0.20) mg/mL for hemorrhagic cysts (n = 16) and 1.63 (1.31 to 1.89) mg/mL for papillary neoplasms (n = 8; P < 0.001). NIC was 2 (−1 to 5)% and 32 (22 to 40)%, respectively ( P < 0.001). For differentiating hemorrhagic cysts from papillary neoplasms, 0.53 mg/mL IC had 100% sensitivity and 88% specificity [AUC = 0.98 (0.93, 1.00)] and 14.1% NIC had 100% sensitivity and 94% specificity [AUC = 0.98 (0.95, 1.00)]. A 20 HU change had 88% sensitivity and specificity. For differentiating hemorrhagic cysts from papillary neoplasms, a 20 HU attenuation change had 88% sensitivity and 88% specificity [AUC = 0.98 (0.93, 1.00)]. Conclusions: PCCT iodine concentration showed outstanding diagnostic performance to differentiate renal cysts from neoplasms. A 20 HU change in attenuation from VNC to postcontrast imaging on PCCT remains a reliable threshold for enhancing lesion, similar to conventional CT. Iodine concentration demonstrated superior sensitivity and specificity compared with 20 HU change when identifying renal cysts versus masses.

8 July 2020 in Journal of Neuroimaging
Verified
Journal Article
Closed access
PDF file
KMKeon Mahmoudi
Keon Mahmoudi
YJYoung Joon
Young Joon
SKShingo Kihira
Shingo Kihira
JGJonathan Goldstein
Jonathan Goldstein
KGKatherine Laura Garvey
Katherine Laura Garvey
ADAmish Doshi
Amish Doshi

9 February 2026 in Journal of Computer Assisted Tomography
Verified
Journal Article
Closed access
SPSamantha Platt
Samantha Platt
TGTamas Gonda
Tamas Gonda
BABelinda Asare
Belinda Asare
KMKira Melamud
Kira Melamud
PCPrahan Chetlur
Prahan Chetlur
CHChenchan Huang
Chenchan Huang
Objective: To describe the imaging appearances and treatment response patterns of the pancreatic neuroendocrine tumors (panNETs) following radiofrequency ablation (RFA). Methods: From an internal database, 17 patients (8 male; mean age: 67±14 y) with 18 pathology-proven, localized, nonfunctioning panNETs <3 cm who underwent EUS-RFA for curative intent were included. A total of 32 preablation and 33 postablation scans were included (CT, MRI, or 68 Ga-DOTATATE PET). Lesion size and enhancement on CT/MRI were independently assessed by 2 readers, while SUVmax was extracted from the original PET reports by a separate reviewer. The Wilcoxon signed-rank and McNemar tests were performed. Treatment response is defined as a complete response (loss of enhancement and SUVmax), a partial response (decrease in size, enhancement, or SUVmax), or no response (no change). Results: Mean lesion size decreased from 1.4​​​​​​±0.5​ cm preablation to 0.3±0.5 cm postablation ( P <0.0001). Mean SUVmax declined from 17.3±11.2 to 3.1±6.0 ( P <0.001). Hyperenhancement was present in 15/18 (83.3%) lesions preablation versus 5/18 (27.8%) postablation ( P <0.01). Of these 15 hyperenhancing lesions, 11 were solid, 3 were cystic, and 1 was mixed cystic and solid. Complete response occurred in 12/18 (66.7%) lesions, with either complete disappearance 5/12 (41.4%) or bland cavity formation 7/12 (58.5%). Partial response occurred in 5/18 (27.8%) lesions; 4/5 decreased in size (mean±SD: 1.4±0.5 cm preablation vs. 0.6±0.7 cm postablation), and 3/5 demonstrated decreased SUVmax. One patient with partial response underwent 2 repeat ablations with an ultimate decrease in SUVmax from 34.1 to 5.9. One solid, hyperenhancing pancreatic body lesion demonstrated no response (1.3 cm); preablation SUVmax was 10.8, but they did not undergo postablation DOTATATE PET. One patient developed postablation pancreatitis. Mean clinical follow-up was 650 days (423). Conclusion: RFA is an emerging treatment for small, nonfunctioning panNET. Postablation imaging findings most commonly included complete resolution of the tumor, decreased enhancement, decreased SUVmax, and formation of a bland cavity. As interest in this technique continues to grow, radiologists’ familiarity with expected post-treatment imaging appearances and their associated response patterns is essential for accurate assessment.