A5046294027- Surgical Simulation and Training
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Screening and Detection
- AI in cancer detection
- Gaze Tracking and Assistive Technology
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- COVID-19 diagnosis using AI
- Augmented Reality Applications
- Robotics and Sensor-Based Localization
- Digital Imaging for Blood Diseases
- 3D Surveying and Cultural Heritage
- Advanced X-ray and CT Imaging
- Esophageal Cancer Research and Treatment
- Artificial Intelligence in Healthcare
- Advanced Graph Neural Networks
- Cardiac, Anesthesia and Surgical Outcomes
- Anatomy and Medical Technology
- Minimally Invasive Surgical Techniques
- Esophageal and GI Pathology
- Optical Imaging and Spectroscopy Techniques
- Cell Image Analysis Techniques
- Artificial Intelligence in Healthcare and Education
- Pituitary Gland Disorders and Treatments
Johns Hopkins University
2023-2024
Technical University of Munich
2019-2020
Autonomous University of Yucatán
2013
Abstract We present a comprehensive analysis of the submissions to first edition Endoscopy Artefact Detection challenge (EAD). Using crowd-sourcing, this initiative is step towards understanding limitations existing state-of-the-art computer vision methods applied endoscopy and promoting development new approaches suitable for clinical translation. routine imaging technique detection, diagnosis treatment diseases in hollow-organs; esophagus, stomach, colon, uterus bladder. However nature...
INTRODUCTION: The progression from resident to attending neurosurgeon requires developing technical and cognitive skills. Cognitive load (CL) can provide insight into the bandwidth required perform tasks whether residual capacity exists for increasing task burden. For neurosurgeons, CL associated with routine must be managed allow decision-making under duress. baseline change in pupil diameter (BCPD) used calculate CL, providing insights mental effort processes. METHODS: We recorded...
INTRODUCTION: Automated surgical phase recognition is essential to developing AI-driven models that improve intraoperative feedback and operating room efficiency. Most automated phase-detection methods target laparoscopic procedures. Here, we introduce a novel application for it in point-of-view craniotomy videos. METHODS: The TeCNO model, causal, dilated two-stage TCN, classified video segments into six phases: incision, myocutaneous flap reflection, burr hole placement, bone elevation,...
INTRODUCTION: Neurosurgical residency applicants are traditionally evaluated on metrics that do not reflect technical ability. While dexterity tests sometimes used, they reveal the internal processing behind a test outcome. Cognitive load (CL) can provide insight into bandwidth required to perform tasks and whether residual capacity exists for increasing task burden. The baseline change in pupil diameter (BCPD) be used calculate CL, providing insights mental effort decision-making processes....
INTRODUCTION: The ablative nature of surgery means that pre-operative imaging studies lose correspondence as a case progresses, which can be problematic when accurate intraoperative navigation is required. Accurate 3D surface reconstruction from endoscopic video potential strategy for real-time updates without additional equipment. We have previously used traditional computational models to generate skull base reconstructions. However, they are time-consuming and require technical skills...
Purpose: Metrics derived from eye-gaze-tracking and pupillometry show promise for cognitive load assessment, potentially enhancing training patient safety through user-specific feedback in tele-robotic surgery. However, current eye-tracking solutions' effectiveness surgery is uncertain compared to everyday situations due close-range interactions causing extreme pupil angles occlusions. To assess the of modern solutions surgery, we compare Tobii Pro 3 Glasses Pupil Labs Core, evaluating their...
Organ segmentation in CT volumes is an important pre-processing step many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of art this task. However, since problem presents a challenging environment due to high variability organ's shape similarity between tissues, generation false negative positive regions output common issue. Recent works shown that uncertainty analysis model can provide us with useful information...
Background: Eye gaze tracking and pupillometry are emerging topics in telerobotic surgery as it is believed that they will enable novel gaze-based interaction paradigms provide insights into the user’s cognitive load (CL). Further, successful integration of CL estimation systems thought to catalyze development new human-computer interfaces for personalized assistance training processes. However, this field its infancy, identifying reliable pupil-tracking solutions robotic still an area...
Organ segmentation in CT volumes is an important pre-processing step many computer assisted intervention and diagnosis methods. In recent years, convolutional neural networks have dominated the state of art this task. However, since problem presents a challenging environment due to high variability organ’s shape similarity between tissues, generation false negative positive regions output common issue. Recent works shown that uncertainty analysis model can provide us with useful information...
Survival rates for colorectal cancer are higher when polyps detected at an early stage and can be removed before they develop into malignant tumors. Automated polyp detection, which is dominated by deep learning based methods, seeks to improve detection of polyps. However, current efforts rely heavily on the size quality training datasets. The these datasets often suffers from various image artifacts that affect visibility hence, rate. In this work, we conducted a systematic analysis gain...
Robust and accurate eye gaze tracking can advance medical telerobotics by providing complementary data for surgical training, interactive instrument control, augmented human–robot interactions. However, current solutions systems such as the da Vinci Surgical System (dVSS) are limited to complex hardware installations. Additionally, existing methods do not account operator head movement inside surgeon console, invalidating original calibration. This work provides an initial solution these...
Purpose: Preoperative imaging plays a pivotal role in sinus surgery where CTs offer patient-specific insights of complex anatomy, enabling real-time intraoperative navigation to complement endoscopy imaging. However, elicits anatomical changes not represented the preoperative model, generating an inaccurate basis for during progression. Methods: We propose first vision-based approach update 3D model leveraging endoscopic video navigated relative camera poses are known. rely on comparisons...
The diagnosis process of colorectal cancer mainly focuses on the localization and characterization abnormal growths in colon tissue known as polyps. Despite recent advances deep object localization, polyps remains challenging due to similarities between tissues, high level artifacts. Recent studies have shown negative impact presence artifacts polyp detection task, started take them into account within training process. However, use prior knowledge related spatial interaction has not yet...
Introduction: The endoscopic endonasal approach (EEA) was first introduced as an adjunct to the microscope for pituitary tumor resection and has since become surgical of choice a myriad skull base pathologies. Relative traditional open approaches, EEA can offer better outcomes shorter hospitalizations. Despite its advantages, limitations including narrow operative corridors, need second surgeon, steep learning curve. Robotic systems may be means overcome some these they utility through...