BDBorna E. Dabiri

Borna E. Dabiri

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Borna E. Dabiri has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Using interpretable rule-learning artificial intelligence to optimally differentiate adrenal pheochromocytomas from adenomas with CT radiomics

    by Daniel I. Glazer, Melissa Viator, Andrew Sharp, Jay B. Patel, Borna E. Dabiri, Christopher P. Bridge, Justine A. Barletta, Oleg S. Pianykh, William W. Mayo-Smith

    Purpose To identify interpretable CT-based radiomics features that can differentiate adrenal pheochromocytomas from adenomas. Methods An institutional database was used to identify patients with pathologically proven adrenal pheochromocytomas 5/1/05–5/1/23. To be included, patients needed to have a contrast-enhanced abdominal CT with an adrenal mass within 12 months of pathology (n = 95). For comparison, 57 adenomas were identified from a set of consecutive CT examinations. The final dataset included 152 adrenal masses (95 pheochromocytomas; 57 adenomas) with 121 used in the development set and 31 in the test set. Following confirmation of accurate automated segmentation, 463 radiomic features were evaluated and used to create an interpretable artificial intelligence (AI) rule-learning model. Model performance was reported using F1 score. Results The study included 146 patients (age 59 years +/- 21; 89 females). A three-feature rule, High Gray Level Zone Emphasis > 184, Roundness > 0.35, and Boundary Low Gray Level Emphasis < 0.021 produced an F1 score of 0.97 on the train set (95% confidence interval [CI]: 0.94, 0.99) and 0.96 on the test set (95% CI: 0.89, 1.00). The rule-learning model determined that the rule most predictive of pheochromocytoma was Maximum Pixel Attenuation > 125 HU resulting in an F1 score of 0.89 (95% CI: 0.83, 0.94) on the training set and 0.93 (95% CI: 0.83, 0.99) on the test set. Conclusion A rule-learning AI model identified the smallest optimal set of interpretable CT radiomics features, sufficient to achieve 96% accuracy in differentiating adrenal pheochromocytomas from adenomas on contrast enhanced CT. Graphical abstract


  • Bipolar radiofrequency track cautery during abdominal biopsies: teaching points and lessons learned

    by Jennifer Huang, Ravi V. Gottumukkala, Sharath K. Bhagavatula, Raul N. Uppot, Borna E. Dabiri, Vincent Wu, Ashraf Thabet, Paul B. Shyn

    Abdominal percutaneous needle biopsies are commonly performed minimally invasive procedures to obtain tissue samples for histopathological diagnosis. Severe post-biopsy bleeding is uncommon but can be associated with prolonged hospitalization, additional interventions, morbidity, and death. Many factors may increase bleeding risk and various peri-procedural and intra-procedural strategies may minimize bleeding risk. Bipolar radiofrequency track cautery is one method that may reduce the risk of post-biopsy bleeding or tumor seeding. This paper offers an illustrative case-based review of teaching points and lessons learned in our experience using a commercially available bipolar radiofrequency track cautery device during percutaneous image-guided abdominal biopsies.


  • Feasibility and safety of bipolar radiofrequency track cautery during percutaneous image-guided abdominal biopsy procedures

    by Paul B. Shyn, Adeel R. Seyal, Ravi V. Gottumukkala, Stuart G. Silverman, Sharath K. Bhagavatula, Raquel O. Alencar, Borna E. Dabiri, Daniel A. T. Souza, Eric R. Cosman, Tina Kapur

    Purpose The purpose of this study was to assess the feasibility and safety of using a bipolar radiofrequency track cautery device during percutaneous image-guided abdominal biopsy procedures in at-risk patients. Methods Forty-two patients (26–79 years old; female 44%) with at least one bleeding risk factor who underwent an abdominal image-guided (CT or US) biopsy and intended bipolar radiofrequency track cautery (BRTC) were retrospectively studied. An 18G radiofrequency electrode was inserted through a 17G biopsy introducer needle immediately following coaxial 18G core biopsy, to cauterize the biopsy track using temperature control. Bleeding risk factors, technical success, and adverse events were recorded. Results BRTC was technically successful in 41/42 (98%) of procedures; in one patient, the introducer needle retracted from the liver due to respiratory motion prior to BRTC. BRTC following percutaneous biopsy was applied during 41 abdominal biopsy procedures (renal mass = 12, renal parenchyma = 10, liver mass = 9, liver parenchyma = 5, splenic mass or parenchyma = 4, gastrohepatic mass = 1). All patients had one or more of the following risk factors: high-risk organ (spleen or renal parenchyma), hypervascular mass, elevated prothrombin time, renal insufficiency, thrombocytopenia, recent anticoagulation or anticoagulation not withheld for recommended interval, cirrhosis, intraprocedural hypertension, brisk back bleeding observed from the introducer needle, or subcapsular tumor location. No severe adverse events (grade 3 or higher) occurred. Two (2/41, 5%) mild (grade 1) bleeding events did not cause symptoms or require intervention. Conclusion Bipolar radiofrequency track cautery was feasible and safe during percutaneous image-guided abdominal biopsy procedures. IRB approval: MBG 2022P002277 Graphical abstract


  • Beyond business as usual: Radiology residency educational response to the COVID-2019 pandemic

    by Junzi Shi, Nityanand Miskin, Borna E. Dabiri, Ariadne K. DeSimone, Peter M. Schaefer, Shanna A. Matalon, Jennifer W. Uyeda, Jeffrey P. Guenette, Glenn C. Gaviola


  • Open Access

    Query-Focused EHR Summarization to Aid Imaging Diagnosis

    by Denis Jered McInerney, Borna Dabiri, Anne-Sophie Touret, Geoffrey Young, Jan-Willem van de Meent, Byron C. Wallace

    Electronic Health Records (EHRs) provide vital contextual information to radiologists and other physicians when making a diagnosis. Unfortunately, because a given patient's record may contain hundreds of notes and reports, identifying relevant information within these in the short time typically allotted to a case is very difficult. We propose and evaluate models that extract relevant text snippets from patient records to provide a rough case summary intended to aid physicians considering one or more diagnoses. This is hard because direct supervision (i.e., physician annotations of snippets relevant to specific diagnoses in medical records) is prohibitively expensive to collect at scale. We propose a distantly supervised strategy in which we use groups of International Classification of Diseases (ICD) codes observed in 'future' records as noisy proxies for 'downstream' diagnoses. Using this we train a transformer-based neural model to perform extractive summarization conditioned on potential diagnoses. This model defines an attention mechanism that is conditioned on potential diagnoses (queries) provided by the diagnosing physician. We train (via distant supervision) and evaluate variants of this model on EHR data from Brigham and Women's Hospital in Boston and MIMIC-III (the latter to facilitate reproducibility). Evaluations performed by radiologists demonstrate that these distantly supervised models yield better extractive summaries than do unsupervised approaches. Such models may aid diagnosis by identifying sentences in past patient reports that are clinically relevant to a potential diagnosis.