The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning.

Introduction: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process. Methods: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning. Results: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well. Discussion: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved.

Deep Learning Methods for Anatomical Landmark Detection in Video Capsule Endoscopy Images.

Video capsule endoscope (VCE) is an emerging technology that allows examination of the entire gastrointestinal (GI) tract with minimal invasion. While traditional endoscopy with biopsy procedures are the gold standard for diagnosis of most GI diseases, they are limited by how far the scope can be advanced in the tract and are also invasive. VCE allows gastroenterologists to investigate GI tract abnormalities in detail with visualization of all parts of the GI tract. It captures continuous real time images as it is propelled in the GI tract by gut motility. Even though VCE allows for thorough examination, reviewing and analyzing up to eight hours of images (compiled as videos) is tedious and not cost effective. In order to pave way for automation of VCE-based GI disease diagnosis, detecting the location of the capsule would allow for a more focused analysis as well as abnormality detection in each region of the GI tract. In this paper, we compared four deep Convolutional Neural Network models for feature extraction and detection of the anatomical part within the GI tract captured by VCE images. Our results showed that VGG-Net has superior performance with the highest average accuracy, precision, recall and, F1-score compared to other state of the art architectures: GoogLeNet, AlexNet and, ResNet.

Endoscopic endonasal surgery outcomes for pediatric craniopharyngioma: a systematic review.

OBJECTIVE: The goal of this study was to systematically review the outcomes of endoscopic endonasal surgery (EES) for pediatric craniopharyngiomas so as to assess its safety and efficacy. METHODS: A systematic literature review was performed using the PubMed and MEDLINE databases for studies published between 1986 and 2019. All studies assessing outcomes following EES for pediatric craniopharyngiomas were included. RESULTS: Of the total 48 articles identified in the original literature search, 13 studies were ultimately selected. This includes comparative studies with other surgical approaches, retrospective cohort studies, and case series. CONCLUSIONS: EES for pediatric craniopharyngiomas is a safe and efficacious alternative to other surgical approaches. Achieving gross-total resection with minimal complications is feasible with EES and is comparable, if not superior in some cases, to traditional means of resection. Ideally, a randomized controlled trial might be implemented in the future to further elucidate the effectiveness of EES for resection of craniopharyngiomas.

Cortical Spreading Depression in the Setting of Traumatic Brain Injury.

Cortical spreading depression (CSD) is a pathophysiologic phenomenon that describes an expanding wave of depolarization within the cortical gray matter. Originally described over 70 years ago, this spreading depression disrupts neuronal and glial ionic equilibrium, leading to increased energy demands that can cause a metabolic crisis. This results in secondary insult, further perpetuating brain injury and neuronal death. Initially not thought to be of clinical significance, the view of CSD was modified with the advent of intracranial electroencephalography, or electrocorticography. With these improved monitoring techniques, CSD has been identified as a major mechanism by which traumatic brain injury (TBI) imparts its negative sequalae. TBI is a heterogenous disease process that runs the gamut of clinical presentations. This includes concussion, epidural and subdural hematoma, diffuse axonal injury, and subarachnoid hemorrhage. Nonetheless, CSD appears to be frequently occurring among the various types of TBI, thus allowing for the potential development of targeted therapies in an otherwise ill-fated patient cohort. Although a complete understanding of the interplay between CSD and TBI has not yet been achieved, the authors recount the efforts that have been employed over the last several decades in an effort to bridge this gap. In addition, our current understanding of the role neuroimmune cells play in CSD is discussed in the context of TBI. Finally, current therapeutic strategies using CSD as a pharmacologic target are explored with respect to their clinical use in patients with TBI.