DDDaniel A. Donoho

Daniel A. Donoho

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Daniel A. Donoho has a total of 140 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Surgeon-in-the-loop: expert-guided machine learning framework for continuous surgical performance assessment using operative video

    by Recai Yilmaz, Aaron Mun, Margaux Masson-Forsyth, Eduardo Torres-Rodríguez, Hasan Syed, Rolando Del Maestro, Chima Oluigbo, Robert F. Keating, Daniel Donoho

    A surgeon’s level of technical proficiency plays a significant role in surgical outcomes. Rating scales, such as the objective structured assessment of technical skills (OSATS), have been validated for surgical quality assurance, skills assessment, and training. However, they are subjective, time-consuming, and dependent on experts with busy schedules, limiting scalability. Moreover, experts may face a long delay between procedure completion and their single, unitary rating, preventing continuous feedback on actions performed. Artificial intelligence systems trained on expert ratings may help overcome these limitations. This work demonstrates a comprehensive human-in-the-loop framework for developing a machine-learning system for automated, continuous OSATS ratings, from data collection to algorithm training and real-world applications. We provide demonstrations of AI assessment on two video recordings: (1) removal of an epileptogenic region during intracranial surgery, and (2) resection of a simulated subpial brain tumor. With sufficient training and validation, machine-learning systems may approximate expert assessments and provide real-time, expert-level feedback during procedures to inform surgeons of increasing patient risk and improve operative outcomes.

  • Action-Level Kinematic Analysis for Objective Performance Assessment in Microanastomosis

    by Yan Meng, Daniel A. Donoho, Robert D. M. Hutchinson, Marcelle Altshuler, Omar Arnaout

  • Open Access

    An AI Framework for Microanastomosis Motion Assessment

    by Yan Meng, Eduardo J. Torres-Rodríguez, Marcelle Altshuler, Nishanth Gowda, Arhum Naeem, Recai Yilmaz, Omar Arnaout, Daniel A. Donoho

    Proficiency in microanastomosis is a fundamental competency across multiple microsurgical disciplines. These procedures demand exceptional precision and refined technical skills, making effective, standardized assessment methods essential. Traditionally, the evaluation of microsurgical techniques has relied heavily on the subjective judgment of expert raters. They are inherently constrained by limitations such as inter-rater variability, lack of standardized evaluation criteria, susceptibility to cognitive bias, and the time-intensive nature of manual review. These shortcomings underscore the urgent need for an objective, reliable, and automated system capable of assessing microsurgical performance with consistency and scalability. To bridge this gap, we propose a novel AI framework for the automated assessment of microanastomosis instrument handling skills. The system integrates four core components: (1) an instrument detection module based on the You Only Look Once (YOLO) architecture; (2) an instrument tracking module developed from Deep Simple Online and Realtime Tracking (DeepSORT); (3) an instrument tip localization module employing shape descriptors; and (4) a supervised classification module trained on expert-labeled data to evaluate instrument handling proficiency. Experimental results demonstrate the effectiveness of the framework, achieving an instrument detection precision of 97%, with a mean Average Precision (mAP) of 96%, measured by Intersection over Union (IoU) thresholds ranging from 50% to 95% (mAP50-95).

  • The significance and utility of ventricular access devices in children with proximal CSF shunt malfunction

    by Kerri Thorn, Brannan E. O’nEill, Julie Wilson, Katherine Hofmann, Abdullah Feroze, Daniel A. Donoho, Chima O. Oluigbo, Hasan R. Syed, Robert F. Keating, John S. Myseros

    Objective The pediatric neurosurgical literature supports the placement of a ventricular access device (VAD) in the premature infant with posthemorrhagic ventricular dilatation as a temporizing measure prior to definitive diversionary shunting. However, there is an absence of data identifying the clinical utility and significance of VADs left in situ at the time of permanent shunt placement. The potential risks of leaving an initial VAD at the time of definitive contralateral cerebral spinal fluid (CSF) diversion and the benefits of a concomitant VAD in these patients with regard to potential life-saving or temporizing aspirations are not well documented. Methods Retrospective cohort review of premature infants (< 37 weeks gestational age) treated for PHH at a tertiary pediatric neurosurgery center from January 2005 to December 2021. Patients were grouped by whether a previously placed VAD was retained during permanent shunt insertion. Outcomes measured: number and outcome of VAD taps, shunt revisions, shunt infections. Statistical comparison between the two groups; p < 0.05 considered significant. Results Seventy-two premature patients (gestational age < 37 weeks) were identified. This cohort included 40 (55.55%) patients with both a VAD and shunt and 32 (44.44%) patients with a shunt only (12 with VAD removed at shunt insertion; 20 with no VAD insertion). Of the 40 patients with a shunt and VAD in situ, 17/40 (42.5%) had their VADs tapped at the time of shunt failure, resulting in 29 total VAD taps. There were 23 emergent VAD taps, of which 17/23 (73.91%) were successful. Leaving the VAD in situ did not result in increased rates of total shunt infections or revisions (p = 0.215; p = 0.129). Conclusions Based on this analysis, VADs placed for initial management of post-hemorrhagic IVH may serve an important role in children with subsequent proximal shunt malfunctions, potentially lifesaving. A high percentage of shunted patients with VADs benefited without increased risk of shunt revisions or infections. The decision for a VAD to remain in situ at the time of permanent shunt placement in these patients should be strongly considered.

  • Open Access

    Ventriculo-gallbladder shunt reflux: A case study and review of the literature

    by Ryan Neill, Peter Harris, Max S. Fleisher, Daniel Donoho

    Background: Ventriculo-gallbladder (VGB) shunt represents an uncommon yet well-documented surgical intervention for the treatment of hydrocephalus through cerebrospinal fluid (CSF) diversion into the gastrointestinal tract through the gallbladder. When other ventricular shunt types have failed or are contraindicated, VGB shunts are effective. In exceptionally rare circumstances, biliary reflux can occur and cause accumulation of bile in the ventricular system. The authors report a case of bile reflux through a ventricular gallbladder shunt with eventual patient recovery after surgical intervention. Prior reports of VGB shunt complications are discussed. Case Description: The authors present the case of a 3-year-old girl with a history of craniopharyngioma causing obstructive hydrocephalus. At an outside facility, she underwent ventriculo-peritoneal (VP) shunt placement, which failed due to abdominal pseudocyst after 6 months. The patient then underwent a subtotal resection of her tumor and placement of a right VGB shunt system with a subdural and ventricular catheter connected distally to a Certas valve. Her postoperative course was complicated by the left-sided tonic-clonic seizures and hyponatremia. Three months later, the patient presented to our emergency department with persistent hyponatremia, encephalopathy, and seizure activity in the setting of COVID-19. Imaging demonstrated a right hypodense subdural fluid collection. Right frontal craniotomy demonstrated accumulation of bile in the subdural space secondary to retrograde flow from the gallbladder, which was evacuated. After externalized subdural drainage evolved from biliary fluid to normal CSF, the externalized ventricular shunt and subdural drain were replaced with a ventriculo-atrial shunt. The patient gradually improved with each follow-up visit over the course of several years. Conclusion: This case demonstrates a potentially life-threatening complication of VGB shunt in the form of biliary reflux into the subdural space. Valveless VGB shunts should be avoided to prevent this rare but potentially fatal complication.

  • Open Access

    Characterizing CSF inflammatory proteomics in pediatric post-hemorrhagic hydrocephalus and Anti-NMDAR encephalitis

    by Taylor Broudy, Ankush Bansal, Akilah Pascall, William Suslovic, Nhu To Chau, Leigh Sepeta, Courtney Lowe, Shani Israel, Alexandra B. Kornbluh, Claire Marie Har, et al.

    Neuroinflammation is a key contributor to pathology in many central nervous system (CNS) diseases. While cerebrospinal fluid (CSF) proteomic studies in adu


  • Controversies in Artificial Intelligence in Neurosurgery

    by Recai Yilmaz, Samuel Browd, Daniel A. Donoho


  • Open Access

    "Are we recording this?" Surgeons deserve next-generation analytics

    by Dhiraj J. Pangal, Daniel A. Donoho

    ""Are we recording this?" Surgeons deserve next-generation analytics" published on 26 May 2023 by American Association of Neurological Surgeons.


  • Open Access

    Pediatric Brain Tissue Segmentation Using a Snapshot Hyperspectral Imaging (sHSI) Camera and Machine Learning Classifier

    by Naomi Kifle, Saige Teti, Bo Ning, Daniel A. Donoho, Itai Katz, Robert Keating, Richard Jaepyeong Cha

    Pediatric brain tumors are the second most common type of cancer, accounting for one in four childhood cancer types. Brain tumor resection surgery remains the most common treatment option for brain cancer. While assessing tumor margins intraoperatively, surgeons must send tissue samples for biopsy, which can be time-consuming and not always accurate or helpful. Snapshot hyperspectral imaging (sHSI) cameras can capture scenes beyond the human visual spectrum and provide real-time guidance where we aim to segment healthy brain tissues from lesions on pediatric patients undergoing brain tumor resection. With the institutional research board approval, Pro00011028, 139 red-green-blue (RGB), 279 visible, and 85 infrared sHSI data were collected from four subjects with the system integrated into an operating microscope. A random forest classifier was used for data analysis. The RGB, infrared sHSI, and visible sHSI models achieved average intersection of unions (IoUs) of 0.76, 0.59, and 0.57, respectively, while the tumor segmentation achieved a specificity of 0.996, followed by the infrared HSI and visible HSI models at 0.93 and 0.91, respectively. Despite the small dataset considering pediatric cases, our research leveraged sHSI technology and successfully segmented healthy brain tissues from lesions with a high specificity during pediatric brain tumor resection procedures.