About

David A Mankoff, MD, PhD, is the Matthew J. Wilson Professor of Research in Radiology at the University of Pennsylvania's Perelman School of Medicine. He is an active member of the medical staff serving as a radiologist at Chester County Hospital, Penn Presbyterian Medical Center, and Pennsylvania Hospital, and holds the position of Vice-Chair of Research in the Department of Radiology at the University of Pennsylvania. Dr. Mankoff is also the Associate Director of Education and Research at the Abramson Cancer Center. His educational background includes a B.S. in Physics from Yale University, and both a Ph.D. in Bioengineering and an M.D. in Medicine from the University of Pennsylvania. His clinical expertise encompasses Nuclear Medicine/PET, Radionuclide Therapy, and Thyroid Cancer. His research focuses on molecular imaging, breast cancer, quantitative cancer imaging, and image analysis, with a particular emphasis on translational clinical trials. Dr. Mankoff is recognized as a Susan G. Komen Scholar and has contributed to the development of imaging techniques for cancer diagnosis and treatment response assessment.

Research topics

• Medical physics
• Political Science
• Medicine
• Nuclear medicine
• Pharmacology
• Oncology
• Biology
• Internal medicine
• Law

Selected publications

• 78 Automated ML pipeline for analysis of paraesophageal hernias

  Journal of Clinical and Translational Science · 2026-04-01

  articleOpen access

  Objectives/Goals: In patients with paraesophageal hernia (PEH), evaluate associations between CT radiomic features and clinical data with (1) undergoing elective repair and (2) volvulus/gastric outlet obstruction and develop an ML pipeline for automated feature extraction and prognosis estimation. Methods/Study Population: Retrospective case–control of adults (>18) at Penn Medicine (2017–2025) with hiatal hernia ICD-9/10 codes and CT chest or CT abdomen/pelvis from clinical care. Radiology reports, H&P, and operative notes will be used to identify those with PEH. We will use traditional statistics and classical ML methods (linear/logistic regression, decision trees, random forest) to test associations between radiomic features (hiatal defect diameter (HDD), hernia sac volume (HSV), herniated gastric volume (HGV)) and outcomes. We will explore CNN-based models – nnU-Net (e.g., TotalSegmentator) and ResNet-based models (e.g., Merlin) – and foundation models (MedSAM2, VISTA-3D) to build the pipeline. Results/Anticipated Results: We hypothesize that CT-derived radiomic features will be associated with (1) undergoing elective repair and (2) developing acute volvulus/GOO. Greater HDD, HSV, and HGV are expected to be associated with increased odds of both outcomes. The ML pipeline is expected to provide organ segmentation and reproducible automated feature extraction using state-of-the-art architectures, and to capture synergistic effects between radiographic and clinical variables to inform patient-level prognosis. Discussion/Significance of Impact: In asymptomatic/minimally symptomatic patients, PEH care often defaults to watchful waiting; candidacy and timing for elective repair are uncertain. Our ML pipeline integrates clinical and CT data to standardize preop radiomics, estimate prognosis, and inform if/when to operate.

  PublisherOA PDFDOI

• CLEAR: An Auditable Foundation Model for Radiology Grounded in Clinical Concepts

  medRxiv · 2026-01-17

  articleOpen access

  Abstract “Black box” deep learning models for medical image interpretation limit clinical trust and analysis of performance degradation. Here, we introduce Concept-Level Embeddings for Auditable Radiology (CLEAR), an auditable foundation model based on clinical concepts. Trained on over 0.87 million image-report pairs from 239,091 patients, CLEAR learns a visual representation and projects chest X-rays into a semantically rich space defined by large language model embeddings, making every prediction traceable to specific radiological observations. External validation on four large, physician-annotated datasets from the United States, Europe, and Asia shows that CLEAR not only achieves state-of-the-art classification performance but also enables novel applications: auditable zero-shot pathology detection, systematic identification of radiological confounders, and the creation of expert-level concept bottleneck models from data-driven concepts. By integrating clinical knowledge directly into its reasoning process, CLEAR offers a framework for robust model auditing, safer deployment, and enhanced physician-AI collaboration, advancing towards trustworthy medical AI.

  PublisherDOI

• Differential Response to ¹⁷⁷ Lu-PSMA-617 in Patients with Tumor Suppressor Gene–Mutated Metastatic Castration-Resistant Prostate Cancer

  Journal of Nuclear Medicine · 2026-02-19

  article

  Genomic alterations are common in metastatic castration-resistant prostate cancer (mCRPC), but limited data exist on the response to ¹⁷⁷Lu-PSMA-617 (LuPSMA) in patients with these aberrations. We aimed to characterize oncologic outcomes of patients with mCRPC and germline or somatic aberrations after treatment with LuPSMA. <b>Methods:</b> The medical record was surveyed for all patients with mCRPC treated with LuPSMA between October 2022 and October 2024. All patients who had received at least 1 cycle of LuPSMA and underwent either germline or somatic testing were included. <b>Results:</b> Seventy-two patients were included. Patients with <i>TP53</i>/<i>PTEN/RB1</i> mutations demonstrated inferior overall survival, even after adjustment for age and race. <i>TP53/PTEN/RB1</i>, <i>BRCA1/2</i>, and <i>CHEK2/PALB2/ATM</i> were not associated with inferior progression-free survival. No individual mutation was significantly associated with changes in the percentage decline in prostate-specific antigen levels from baseline. <b>Conclusion:</b><i>TP53, PTEN</i>, and <i>RB1</i> mutations were linked to inferior overall survival in LuPSMA-treated patients and may serve as prognostic biomarkers. Prospective validation is required to establish their predictive value.

  PublisherDOI

• 1280 AUTOMATED PIPELINE FOR ANALYSIS OF PARAESOPHAGEAL HERNIAS

  Gastroenterology · 2026-05-01

  article
  PublisherDOI

• 1280 AUTOMATED PIPELINE FOR ANALYSIS OF PARAESOPHAGEAL HERNIAS

  Gastrointestinal Endoscopy · 2026-05-01

  article
  PublisherDOI

• Response to the Comment on “Negative 18F-FES PET/CT Despite Estrogen Receptor Positivity By Immunohistochemistry.”

  Clinical Nuclear Medicine · 2026-05-01

  article
  PublisherDOI

• A Call for High-Level Evidence Before Routine Implementation of Posttreatment SPECT

  Journal of Nuclear Medicine · 2026-05-21

  article

  TO THE EDITOR: We read with interest the article by Uribe et al. ([1][1]), which presents a timely and detailed procedure standard for posttreatment imaging in 177Lu-based radiopharmaceutical therapies (RPTs). The authors are to be commended for emphasizing key strengths, including the importance

  PublisherDOI

• [18F]Fluoroestradiol Uptake in Benign Nodular Sclerosing Adenosis of the Breast

  Clinical Nuclear Medicine · 2026-01-14

  article

  A 70-year-old woman with estrogen receptor-positive (ER+) invasive ductal carcinoma (IDC) of the right breast underwent 18F-fluoroestradiol (18F-FES) PET/CT demonstrating uptake in the IDC (SUVmax 2.5) and also extensive 18F-FES uptake in bilateral breasts corresponding to marked bilateral background enhancement on MRI. MRI-guided biopsy of a representative enhancing 18F-FES-avid region in the left breast (SUVmax 3.5) revealed nodular sclerosing adenosis without cellular atypia or malignancy, but with 30% ER positivity on immunohistochemistry. False-positive uptake of 18F-FES is reported in irradiated lung and interstitial lung disease. This case highlights another mechanism of false-positive 18F-FES uptake due to ER overexpression in benign breast tissue.

  PublisherDOI

• Supplemental Figure S5 from [&lt;sup&gt;18&lt;/sup&gt;F]FluorThanatrace ([&lt;sup&gt;18&lt;/sup&gt;F]FTT) PET Imaging of PARP-Inhibitor Drug-Target Engagement as a Biomarker of Response in Ovarian Cancer, a Pilot Study

  2025-11-25

  articleOpen access

  &lt;p&gt;Clinical response correlates.&lt;/p&gt;

  PublisherOA PDFDOI

• Novel 4D radiomics applied to dynamic FES PET images to improve prediction of breast cancer response to ER-targeted therapy

  European Journal of Nuclear Medicine and Molecular Imaging · 2025-11-23

  articleOpen accessSenior author

  PURPOSE: F] fluoroestradiol (FES) is an FDA-approved tracer that measures functional estrogen receptor (ER) expression and can estimate the likelihood of response to ER-targeted therapy. In this exploratory analysis, we tested a novel radiomics based analysis of dynamic volumetric FES PET images to predict outcomes in patients with metastatic ER positive breast cancer treated with endocrine therapy. METHODS: We utilized the Rad-Fit method, previously tested in an FDG PET data set, to identify and characterize intratumor subregions of heterogeneous time-activity through an unsupervised clustering approach. A scaled silhouette score was implemented to determine the optimal number of intratumor subregions on a per-tumor basis. Summary statistics of sum of squared error (SSE) and distance between sub regions as well as the total number of intratumor subregions were used to build prognostic models of overall survival (OS) and progression free survival (PFS). We employed Kaplan-Meyer analysis to determine model performance. RESULTS: The radiomic phenotype differentiated between a high and low risk group for progression free survival (C = 0.67, p = 0.025) in the single tumor scenario. Radiomic features of subregion distance classified a high and low risk group for OS in a single tumor (C = 0.67, p = 0.008) and average tumor (C = 0.65, p = 0.017) scenario. CONCLUSIONS: In this exploratory study, 4D radiomic features extracted from dynamic FES PET images can improve the prediction of outcomes in metastatic ER positive breast cancer. Metrics of tumor subregion distance and radiomic phenotype appear to perform as the best radiomic predictors for risk stratification of OS and PFS respectively by potentially reflecting characteristics of the overall tumor heterogeneity in FES PET images. CLINICAL TRIAL NUMBER: not applicable.

  PublisherOA PDFDOI

Recent grants

• NIH Grant P01CA042045

  NIH · $44.9M · 2017

• Area B: Multi-Tracer Volumetric PET (MTV-PET) to Measure Tumor Glutamine and Glucose Metabolic Rates in a Single Imaging Session

  NIH · $1.4M · 2017–2021

• NIH Grant R01CA090771

  NIH · $1.6M · 2008

• Advanced PET/CT Imaging for Improving Clinical Trials

  NIH · $6.0M · 2010–2021

• NIH Grant R01CA124573

  NIH · $1.8M · 2014

Frequent coauthors

• Hannah M. Linden

  University of Washington

  224 shared

• Erin K. Schubert

  208 shared

• Brenda F. Kurland

  University of Washington Medical Center

  183 shared

• Jennifer M. Specht

  Fred Hutch Cancer Center

  178 shared

• Georgiana K. Ellis

  161 shared

• Julie R. Gralow

  154 shared

• Lanell M. Peterson

  University of Washington Medical Center

  150 shared

• Robert K. Doot

  CHDI Foundation

  139 shared

Awards & honors

• Susan G. Komen Scholar