Real-time detection of laryngopharyngeal cancer using an artificial intelligence-assisted system with multimodal data.

BACKGROUND: Laryngopharyngeal cancer (LPC) includes laryngeal and hypopharyngeal cancer, whose early diagnosis can significantly improve the prognosis and quality of life of patients. Pathological biopsy of suspicious cancerous tissue under the guidance of laryngoscopy is the gold standard for diagnosing LPC. However, this subjective examination largely depends on the skills and experience of laryngologists, which increases the possibility of missed diagnoses and repeated unnecessary biopsies. We aimed to develop and validate a deep convolutional neural network-based Laryngopharyngeal Artificial Intelligence Diagnostic System (LPAIDS) for real-time automatically identifying LPC in both laryngoscopy white-light imaging (WLI) and narrow-band imaging (NBI) images to improve the diagnostic accuracy of LPC by reducing diagnostic variation among on-expert laryngologists. METHODS: All 31,543 laryngoscopic images from 2382 patients were categorised into training, verification, and test sets to develop, validate, and internal test LPAIDS. Another 25,063 images from five other hospitals were used as external tests. Overall, 551 videos were used to evaluate the real-time performance of the system, and 200 randomly selected videos were used to compare the diagnostic performance of the LPAIDS with that of laryngologists. Two deep-learning models using either WLI (model W) or NBI (model N) images were constructed to compare with LPAIDS. RESULTS: LPAIDS had a higher diagnostic performance than models W and N, with accuracies of 0·956 and 0·949 in the internal image and video tests, respectively. The robustness and stability of LPAIDS were validated in external sets with the area under the receiver operating characteristic curve values of 0·965-0·987. In the laryngologist-machine competition, LPAIDS achieved an accuracy of 0·940, which was comparable to expert laryngologists and outperformed other laryngologists with varying qualifications. CONCLUSIONS: LPAIDS provided high accuracy and stability in detecting LPC in real-time, which showed great potential for using LPAIDS to improve the diagnostic accuracy of LPC by reducing diagnostic variation among on-expert laryngologists.

Comparative study of optical coherence tomograph and histological images of eustachian tube nasopharyngeal region and adjacent structures in vivo and ex-vivo miniature pigs.

OBJECTIVES: Optical Coherence Tomograph (OCT) imaging technology can be used to examine, in vivo, the human ET. At present, it is impossible to achieve the OCT scanning vivo and ex vivo in the same individual human body, or study the consistency between OCT images and histological images of the eustachian tube nasopharyngeal region and adjacent structures. The aim of this study was to determine the consistency between OCT images and histological sections in vivo and ex vivo in miniature pigs. METHODS: OCT imaging was performed on five adult miniature pigs in vivo and ex vivo. The images of the eustachian tube OCT (ET-OCT), nasopharynx OCT (NP-OCT) and histological cross sections were further studied. RESULTS: All five miniature pigs achieved the OCT scan successfully, acquiring ET-OCT and NP-OCT images in vivo and ex vivo on both sides. The acquired ET OCT images closely matched the histological images, revealing details of the cartilage, submucosa, glands, and mucosa. The lower segment of the ET wall mucosa had an abundance of glands and submucosal tissues, with more low-signal areas appearing in the ex vivo images. The NP-OCT images of the nasopharynx matched the details of the mucosa and submucosal tissues. The ex-vivo OCT images showed thicker mucosa and more scattered slightly lower signal areas compared to the vivo OCT images. CONCLUSIONS: ET-OCT images and NP-OCT images matched the histological structure of eustachian tube nasopharyngeal region structures in miniature pigs both in vivo and ex vivo. OCT images may be sensitive to changes in edema and ischemia status. There is a great potential for morphological assessment of inflammation, edema, injure, mucus gland status.

Investigations on the potential of optical coherence tomography as an imaging tool for eustachian tube.

The purpose of this study was to explore the feasibility of eustachian tube optical coherence tomography (ET-OCT) for imaging the pharyngeal region of the eustachian tube (ET). Ten subjects with ear complaints underwent ET-OCT guided by nasal endoscopy, and ET-OCT examination was performed on both sides of each subject's ETs. The process and resulting images were analysed. Ten subjects ranging from 21 to 73 years old (45 ± 14.77) were enrolled in this study. Eighteen ET-OCT imaging examinations were completed. The mean duration of each examination was 2.80 ± 1.62 min (ranging from 2 to 7 min). There were no adverse events or complications. In some subjects, the ET-OCT images clearly presented the microstructures of the ET wall, including the lumen, mucosa, submucosa, cartilage and plica. However, in some subjects, it showed different characteristics, such as an unclear hierarchy and secretions in the lumen. ET-OCT may help to distinguish the structural composition of the ET and elucidate related pathophysiological mechanisms. It is a valuable imaging tool suited for the ET, with potential diagnostic value in determining the morphology of the lumen, intraluminal mucosa and submucosal tissue in the pharyngeal region of the ET.

Plasmonic SERS Biosensor Based on Multibranched Gold Nanoparticles Embedded in Polydimethylsiloxane for Quantification of Hematin in Human Erythrocytes.

This work reports a plasmonic surface-enhanced Raman scattering (SERS) biosensor that allows for quantitative analysis of hematin in erythrocytes without the need of separating it from hemoglobin (Hb). The biosensor exploits the tunable localized surface plasmon resonance (LSPR) characteristics of multibranched gold nanoparticles (M-AuNPs) and the strong plasmon coupling between an Au thin film and a flexible substrate consisting of M-AuNPs embedded in polydimethylsiloxane (PDMS) (i.e., M-AuNP-embedded PDMS substrate). In the assay, the hematin (or hematin-containing erythrocyte hemolysate) was deposited on Au film surface and covered with M-AuNP-embedded PDMS. Strong SERS signals were generated under excitation at 785 nm; the signals were sensitive to hematin concentration but not to several common coexisting biological substances. The intensities of the SERS signal (at 1623 cm-1) displayed a wide linear range using hematin concentrations in a range of at least ∼1.5 nM-1.1 µM; the limit of detection (LOD) was ∼0.03 ± 0.01 nM at a signal/noise (S/N) of 3. This assay is simple and sensitive without tedious separation procedures, thereby saving time and enhancing efficiency. This biosensor can be used to determine hematin concentration in human erythrocyte cytosols giving concentrations of ∼18.5 ± 4.5 (by averaging eight samples) and 51.5 ± 6.2 µM (by averaging three samples) for healthy and sickle erythrocytes, respectively, making it a potential application in clinical detection.

Asymmetric Multimetallic Mesoporous Nanospheres.

Mesoporous colloidal nanospheres with tailorable asymmetric nanostructures and multimetallic elemental compositions are building blocks in next-generation heterogeneous catalysts. Introducing structural asymmetry into metallic mesoporous frameworks has never been demonstrated, but it would be beneficial because the asymmetry enables the spatial control of catalytic interfaces, facilitates the electron/mass transfer and assists in the removal of poisonous intermediates. Herein, we describe a simple bottom-up strategy to generate uniform sub-100 nm multimetallic asymmetric bowl-shaped mesoporous nanospheres (BMSs). This method uses a surfactant-directed "dual"-template to control the kinetics of metal reduction on the surface of a vesicle, forming mesoporous metal islands on its surface whose spherical cone angle can be precisely controlled. The asymmetric BMS mesostructures with different spherical cone angles (structural asymmetries) and elemental compositions are demonstrated. The high surface area and asymmetric nature of the metal surfaces are shown to enhance catalytic performance in the alcohol oxidation reactions. The findings described here offer novel and interesting opportunities for rational design and synthesis of hierarchically asymmetric nanostructures with desired functions for a wide range of applications.