Functional imaging and endoscopy

Endoscopists' Acceptance on the Implementation of Artificial Intelligence in Gastrointestinal Endoscopy: Development and Case Analysis of a Scale

Background

The purpose of this paper is to develop and validate a standardized endoscopist acceptance scale for the implementation of artificial intelligence (AI) in gastrointestinal endoscopy.

Methods

After investigating endoscopists who have previously used AI and consulting with AI experts, we developed a provisional scale to measure the acceptance of AI as used in gastrointestinal endoscopy that was then distributed to a sample of endoscopists who have used AI. After analyzing the feedback data collected on the provisional scale, we developed a new formal scale with four factors. Cronbach's alpha, confirmatory factor analysis (CFA), content validity, and related validity were conducted to test the reliability and validity of the formal scale. We also constructed a receiver operating characteristic (ROC) curve in order to determine the scale's ability to distinguish higher acceptance and satisfaction.

Results

A total of 210 valid formal scale data points were collected. The overall Cronbach's alpha was 0.904. All the factor loadings were >0.50, of which the highest factor loading was 0.86 and the lowest was 0.54 (AVE = 0.580, CR = 0.953). The correlation coefficient between the total score of the scale and the satisfaction score was 0.876, and the area under the ROC curve was 0.949 ± 0.031. Endoscopists with a score higher than 50 tend to be accepting and satisfied with AI.

Conclusion

This study yielded a viable questionnaire to measure the acceptance among endoscopists of the implementation of AI in gastroenterology.

Novel endoscopic optical diagnostic technologies in medical trial research: recent advancements and future prospects

Novel endoscopic biophotonic diagnostic technologies have the potential to non-invasively detect the interior of a hollow organ or cavity of the human body with subcellular resolution or to obtain biochemical information about tissue in real time. With the capability to visualize or analyze the diagnostic target in vivo, these techniques gradually developed as potential candidates to challenge histopathology which remains the gold standard for diagnosis. Consequently, many innovative endoscopic diagnostic techniques have succeeded in detection, characterization, and confirmation: the three critical steps for routine endoscopic diagnosis. In this review, we mainly summarize researches on emerging endoscopic optical diagnostic techniques, with emphasis on recent advances. We also introduce the fundamental principles and the development of those techniques and compare their characteristics. Especially, we shed light on the merit of novel endoscopic imaging technologies in medical research. For example, hyperspectral imaging and Raman spectroscopy provide direct molecular information, while optical coherence tomography and multi-photo endomicroscopy offer a more extensive detection range and excellent spatial-temporal resolution. Furthermore, we summarize the unexplored application fields of these endoscopic optical techniques in major hospital departments for biomedical researchers. Finally, we provide a brief overview of the future perspectives, as well as bottlenecks of those endoscopic optical diagnostic technologies. We believe all these efforts will enrich the diagnostic toolbox for endoscopists, enhance diagnostic efficiency, and reduce the rate of missed diagnosis and misdiagnosis.

Imaging of Fibroblast Activation Protein Alpha Expression in a Preclinical Mouse Model of Glioma Using Positron Emission Tomography

Glioblastoma multiforme (GBM) is the most aggressive glioma of the primary central nervous system. Due to the lack of effective treatment options, the prognosis for patients remains bleak. Fibroblast activation protein alpha (FAP), a 170 kDa type II transmembrane serine protease was observed to be expressed on glioma cells and within the glioma tumor microenvironment. To understand the utility of targeting FAP in this tumor type, the immuno-PET radiopharmaceutical [⁸⁹Zr]Zr-Df-Bz-F19 mAb was prepared and Lindmo analysis was used for its in vitro evaluation using the U87MG cell line, which expresses FAP endogenously. Lindmo analysis revealed an association constant (K_a) of 10^-8 M^-1 and an immunoreactivity of 52%. Biodistribution studies in U87MG tumor-bearing mice revealed increasing radiotracer retention in tumors over time, leading to average tumor-to-muscle ratios of 3.1, 7.3, 7.2, and 8.3 at 2, 24, 48 and 72 h, respectively. Small animal PET corroborated the biodistribution studies; tumor-to-muscle ratios at 2, 24, 48, and 72 h were 2.0, 5.0, 6.1 and 7.8, respectively. Autoradiography demonstrated accumulated activity throughout the interior of FAP⁺ tumors, while sequential tumor sections stained positively for FAP expression. Conversely, FAP^- tissues retained minimal radioactivity and were negative for FAP expression by immunohistochemistry. These results demonstrate FAP as a promising biomarker that may be exploited to diagnose and potentially treat GBM and other neuroepithelial cancers.

Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy

OBJECTIVE

Esophagogastroduodenoscopy (EGD) is the pivotal procedure in the diagnosis of upper gastrointestinal lesions. However, there are significant variations in EGD performance among endoscopists, impairing the discovery rate of gastric cancers and precursor lesions. The aim of this study was to construct a real-time quality improving system, WISENSE, to monitor blind spots, time the procedure and automatically generate photodocumentation during EGD and thus raise the quality of everyday endoscopy.

DESIGN

WISENSE system was developed using the methods of deep convolutional neural networks and deep reinforcement learning. Patients referred because of health examination, symptoms, surveillance were recruited from Renmin hospital of Wuhan University. Enrolled patients were randomly assigned to groups that underwent EGD with or without the assistance of WISENSE. The primary end point was to ascertain if there was a difference in the rate of blind spots between WISENSE-assisted group and the control group.

RESULTS

WISENSE monitored blind spots with an accuracy of 90.40% in real EGD videos. A total of 324 patients were recruited and randomised. 153 and 150 patients were analysed in the WISENSE and control group, respectively. Blind spot rate was lower in WISENSE group compared with the control (5.86% vs 22.46%, p<0.001), and the mean difference was -15.39% (95% CI -19.23 to -11.54). There was no significant adverse event.

CONCLUSIONS

WISENSE significantly reduced blind spot rate of EGD procedure and could be used to improve the quality of everyday endoscopy.

TRIAL REGISTRATION NUMBER

ChiCTR1800014809; Results.

Cerenkov-specific contrast agents for detection of pH in vivo

We report the design, testing, and in vivo application of pH-sensitive contrast agents designed specifically for Cerenkov imaging. Radioisotopes used for PET emit photons via Cerenkov radiation. The multispectral emission of Cerenkov radiation allows for selective bandwidth quenching, in which a band of photons is quenched by absorption by a functional dye. Under acidic conditions, (18)F-labeled derivatives emit the full spectrum of Cerenkov light. Under basic conditions, the dyes change color and a wavelength-dependent quenching of Cerenkov emission is observed.

METHODS

Mono- and di-(18)F-labeled derivatives of phenolsulfonphthalein (phenol red) and meta-cresolsulfonphthalein (cresol purple) were synthesized by electrophilic fluorination. Cerenkov emission was measured at different wavelengths as a function of pH in vitro. Intramolecular response was measured in fluorinated probes and intermolecular quenching by mixing phenolphthalein with (18)F-FDG. Monofluorocresol purple (MFCP) was tested in mice treated with acetazolamide to cause urinary alkalinization, and Cerenkov images were compared with PET images.

RESULTS

Fluorinated pH indicators were produced with radiochemical yields of 4%-11% at greater than 90% purity. Selective Cerenkov quenching was observed intramolecularly with difluorophenol red or monofluorocresol purple and intermolecularly in phenolphthalein (18)F-FDG mixtures. The probes were selectively quenched in the bandwidth closest to the indicator's absorption maximum (λmax) at pHs above the indicator pKa (the negative logarithm of the acid dissociation constant). Addition of acid or base to the probes resulted in reversible switching from unquenched to quenched emission. In vivo, the bladders of acetazolamide-treated mice exhibited a wavelength-dependent quenching in Cerenkov emission, with the greatest reduction occurring near the λmax. Ratiometric imaging at 2 wavelengths showed significant decreases in Cerenkov emission at basic pH and allowed the estimation of absolute pH in vivo.

CONCLUSION

We have created contrast agents that selectively quench photons emitted during Cerenkov radiation within a given bandwidth. In the presence of a functional dye, such as a pH indicator, this selective quenching allows for a functional determination of pH in vitro and in vivo. This method can be used to obtain functional information from radiolabeled probes using multimodal imaging. This approach allows for the imaging of nonfluorescent chromophores and is generalizable to any functional dye that absorbs at suitable wavelengths.

Light in and sound out: emerging translational strategies for photoacoustic imaging

Photoacoustic imaging (PAI) has the potential for real-time molecular imaging at high resolution and deep inside the tissue, using nonionizing radiation and not necessarily depending on exogenous imaging agents, making this technique very promising for a range of clinical applications. The fact that PAI systems can be made portable and compatible with existing imaging technologies favors clinical translation even more. The breadth of clinical applications in which photoacoustics could play a valuable role include: noninvasive imaging of the breast, sentinel lymph nodes, skin, thyroid, eye, prostate (transrectal), and ovaries (transvaginal); minimally invasive endoscopic imaging of gastrointestinal tract, bladder, and circulating tumor cells (in vivo flow cytometry); and intraoperative imaging for assessment of tumor margins and (lymph node) metastases. In this review, we describe the basics of PAI and its recent advances in biomedical research, followed by a discussion of strategies for clinical translation of the technique.

Epidemiology and diagnosis of Helicobacter pylori infection

Medline, PubMed and the Cochrane databases were searched on epidemiology and diagnosis of Helicobacter pylori for the period of April 2011-March 2012. Several studies have shown that the prevalence of H. pylori infection is decreasing in adults and children in many countries. Various diagnostic tests are available, and most of them have high sensitivity and specificity. The Maastricht IV/Florence consensus report states that the urea breath test using (13)C urea remains the best test to diagnose H. pylori infection. Among the stool antigen tests, the ELISA monoclonal antibody test is recommended. All these tests were used, either as a single diagnostic test or in combination, to investigate H. pylori infection among different populations throughout the world. Of particular interest, current improvements in high-resolution endoscopic technologies enable increased diagnostic accuracy for the detection of H. pylori infection, but none of these techniques, at present, are specific enough for obtaining a real-time diagnosis of H. pylori infection.