Figure - available from: Journal of Healthcare Engineering
This content is subject to copyright. Terms and conditions apply.
A normal right eardrum: (a) white image, (b) red image, (c) green image, (d) blue image, and (e–h) grayscale images of (a), (b), (c), and (d). (a) White image. (b) Red image. (c) Green image. (d) Blue image. (e) White grayscale image. (f) Red grayscale image. (g) Green grayscale image. (h) Blue grayscale image.
Source publication
Multispectral imaging has recently shown good performance in determining information about physiology, morphology, and composition of tissue. In the endoscopy field, many researches have shown the ability to apply multispectral or narrow-band images in surveying vascular structure based on the interaction of light wavelength with tissue composition...
Citations
... Multicolor or multispectral autofluorescence imaging [16][17][18][19] SWIR imaging [12] OCT [20,21] Otitis media DRS [22] SWIR [23,24] OCT [25][26][27][28][29] Multimodal [30] 2. Label-Free Optical Techniques 2.1. Autofluorescence Imaging Autofluorescence (AF) spectroscopy measures emissions from the natural fluorophores in biospecimens. ...
... Additionally, Tran Van et al. applied multispectral imaging to a cohort of 12 healthy volunteers and found that red-light images, compared with blue-, green-, and white-light images, provided the best contrast to visualize the borders of the tympanic membrane [18]. Wisotzky et al. introduced a multispectral imaging system combined with an endoscope that could switch between narrow-band spectral and broad-band white illuminations. ...
... However, more research on the optimization of the best set of illimitation wavelengths for each different pathology and larger clinical studies with larger patient populations are needed for the diagnosis of different pathologies before clinical application [16,17]. Additionally, Tran Van et al. applied multispectral imaging to a cohort of 12 healthy volunteers and found that red-light images, compared with blue-, green-, and white-light images, provided the best contrast to visualize the borders of the tympanic membrane [18]. Wisotzky et al. introduced a multispectral imaging system combined with an endoscope that could switch between narrow-band spectral and broad-band white illuminations. ...
Medical applications of optical technology have increased tremendously in recent decades. Label-free techniques have the unique advantage of investigating biological samples in vivo without introducing exogenous agents. This is especially beneficial for a rapid clinical translation as it reduces the need for toxicity studies and regulatory approval for exogenous labels. Emerging applications have utilized label-free optical technology for screening, diagnosis, and surgical guidance. Advancements in detection technology and rapid improvements in artificial intelligence have expedited the clinical implementation of some optical technologies. Among numerous biomedical application areas, middle-ear disease is a unique space where label-free technology has great potential. The middle ear has a unique anatomical location that can be accessed through a dark channel, the external auditory canal; it can be sampled through a tympanic membrane of approximately 100 microns in thickness. The tympanic membrane is the only membrane in the body that is surrounded by air on both sides, under normal conditions. Despite these favorable characteristics, current examination modalities for middle-ear space utilize century-old technology such as white-light otoscopy. This paper reviews existing label-free imaging technologies and their current progress in visualizing middle-ear diseases. We discuss potential opportunities, barriers, and practical considerations when transitioning label-free technology to clinical applications.
... is work presents a technique for hybrid nonlinear filtering, which is divided into two sections. e first portion of the method is described as follows: first, a judgement measure that takes into account discrepancies between nearby pixel values in the input picture [3] is applied to the rank-ordered sequence to determine whether a pixel is corrupted or not in the first step. e rank-ordered sequence is then applied to determine whether or not a pixel is corrupted or not in the second step. ...
... e presence of noise, in contrast to the ideal signal, may be caused by a broad range of reasons, including variations in detector sensitivity, the discrete nature of the radiation, environmental changes, and transmission or digitization issues, among others. It is predicted that the amount of noise created will be proportional to the number of corrupted pixels contained in the image [3,9,10]. ...
... In the past, it has been shown that median-based noise reduction techniques are more successful when dealing with fixedvalued noise, but less effective when dealing with randomvalued noise. [3,11,12] As a consequence of this research, it has been shown that the suggested (HE/ACWM) technique consistently outperforms the competition in pictures with varied noise ratios. An instance of the block diagram of the adaptive histogram equalisation-based centr-weighted median filter technique is presented in Figure 2. ...
The capacity to carry out one’s regular tasks is affected to varying degrees by hearing difficulties. Poorer understanding, slower learning, and an overall reduction in efficiency in academic endeavours are just a few of the negative impacts of hearing impairments on children’s performance, which may range from mild to severe. A significant factor in determining whether or not there will be a decrease in performance is the kind and source of impairment. Research has shown that the Artificial Neural Network technique is capable of modelling both linear and nonlinear solution surfaces in a trustworthy way, as demonstrated in previous studies. To improve the precision with which hearing impairment challenges are diagnosed, a neural network backpropagation approach has been developed with the purpose of fine-tuning the diagnostic process. In particular, it highlights the vital role performed by medical informatics in supporting doctors in the identification of diseases as well as the formulation of suitable choices via the use of data management and knowledge discovery. As part of the intelligent control method, it is proposed in this research to construct a Histogram Equalization (HE)-based Adaptive Center-Weighted Median (ACWM) filter, which is then used to segment/detect the OM in tympanic membrane images using different segmentation methods in order to minimise noise and improve the image quality. A tympanic membrane dataset, which is freely accessible, was used in all experiments.
... The study was conducted using a modified multi-wavelength narrowband otoscope in a limited cohort of five patients. More recently, a study [15] developed an analysis of otoscopy images acquired in visible spectra and concluded that the blue and green channels have an absorption pick for hemoglobin, highlighting vascular structures. In contrast, the red channel has a high penetrance to the tympanic membrane, allowing a better visualization of the structures inside the tympanic cavity. ...
... Multispectral imaging analysis has several advantages over standard otoscopy, including increased image contrast, clear visualization of middle ear elements, better assessment of tympanic membrane vascularity, and improved demarcation of critical morphological structures (e.g., the malleus and the promontory). Although there are no commercial otoscopes available that acquire images in different spectral bands in addition to RGB, the research results of the few works [9,14,15] in state of the art encourage the development of new technologies considering a multispectral approach. In this work, we explored the dependence of three different color wavelengths, including red, green, and blue channels, in the performance of a CNN-based model to predict the diagnosis of four ear conditions. ...
Artificial intelligence-assisted otologic diagnosis has been of growing interest in the scientific community, where middle and external ear disorders are the most frequent diseases in daily ENT practice. There are some efforts focused on reducing medical errors and enhancing physician capabilities using conventional artificial vision systems. However, approaches with multispectral analysis have not yet been addressed. Tissues of the tympanic membrane possess optical properties that define their characteristics in specific light spectra. This work explores color wavelengths dependence in a model that classifies four middle and external ear conditions: normal, chronic otitis media, otitis media with effusion, and earwax plug. The model is constructed under a computer-aided diagnosis system that uses a convolutional neural network architecture. We trained several models using different single-channel images by taking each color wavelength separately. The results showed that a single green channel model achieves the best overall performance in terms of accuracy (92%), sensitivity (85%), specificity (95%), precision (86%), and F1-score (85%). Our findings can be a suitable alternative for artificial intelligence diagnosis systems compared to the 50% of overall misdiagnosis of a non-specialist physician.
... A variety of imaging techniques extending beyond the visible light spectrum have shown promise in identifying middle ear pathology. Otoscopy using multi-color reflectance can offer improved assessment of middle ear structures and the tympanic membrane 34,48 . Fluorescent otoscopy can highlight the presence of cholesteatoma www.nature.com/scientificreports/ ...
Otitis media, a common disease marked by the presence of fluid within the middle ear space, imparts a significant global health and economic burden. Identifying an effusion through the tympanic membrane is critical to diagnostic success but remains challenging due to the inherent limitations of visible light otoscopy and user interpretation. Here we describe a powerful diagnostic approach to otitis media utilizing advancements in otoscopy and machine learning. We developed an otoscope that visualizes middle ear structures and fluid in the shortwave infrared region, holding several advantages over traditional approaches. Images were captured in vivo and then processed by a novel machine learning based algorithm. The model predicts the presence of effusions with greater accuracy than current techniques, offering specificity and sensitivity over 90%. This platform has the potential to reduce costs and resources associated with otitis media, especially as improvements are made in shortwave imaging and machine learning.
