RESUMEN
BACKGROUND: Digital technology offers individuals the opportunity to monitor their symptoms. Information gathered from apps, devices, and web platforms may be used to direct clinical care and to support research. AIM: Using this survey, we aim to explore the views of people attending the Anne Rowling Regenerative Neurology Clinic (ARRNC) and their relatives/caregivers regarding the use of digital health technologies to monitor health. METHOD: People attending the ARRNC were invited to complete a structured 18-item questionnaire evaluating their experience and attitudes to using technology for monitoring health. People with neurodegenerative disease (pwND) and their caregivers completed a mix of closed and open-ended questions. RESULTS: 249 people responded, 51 relatives/caregivers and 198 pwND. 67.1% (n= 167) of respondents do not use technology for monitoring their health, but 98.2% (n = 164) of these are interested in their future use. 29.7% (n = 74) respondents currently use a smartphone for health monitoring, 20.9% (n = 52) use a wearable device, and 13.3% (n = 33) use a tablet. 79.3% (n = 65) of users use their technology for monitoring physical activity, 37.8% (n = 31) use it for assisting with self-management, and 41.5% (n = 34) use it for tracking sleep. Factors which would encourage use of technology are ease of access to devices and ability to monitor health. Respondents reported data security concerns and difficulty using technology as potential barriers. CONCLUSION: People attending a neurology clinic, and their relatives/caregivers, support the use of digital technologies as an adjunct to routine care. There is a need for coordinated digital strategies for development and delivery of validated measures.
Asunto(s)
Cuidadores , Tecnología Digital , Humanos , Masculino , Femenino , Persona de Mediana Edad , Anciano , Adulto , Cuidadores/psicología , Encuestas y Cuestionarios , Dispositivos Electrónicos Vestibles , Enfermedades del Sistema Nervioso/psicología , Enfermedades del Sistema Nervioso/diagnóstico , Teléfono Inteligente , Monitoreo Fisiológico/métodos , Monitoreo Fisiológico/instrumentación , Anciano de 80 o más Años , Telemedicina , Aplicaciones Móviles , Computadoras de ManoRESUMEN
INTRODUCTION: Sporadic Creutzfeldt-Jakob disease (sCJD) is a rapidly progressive neurodegenerative disease with public health implications. Mean age of onset is 68 years. Age-specific incidence declines after 80 years. This may arise from under-ascertainment or other biological features of the disease. Accurate characterisation of late-onset sCJD is important for early diagnosis, avoiding unnecessary investigations and improving ascertainment for public health purposes. OBJECTIVE: To phenotype the clinical features and investigation profile of sCJD in adults >80 years. METHODS: We analysed all probable and definite sCJD cases identified by the UK National CJD Research & Surveillance Unit over a 10-year period (2011-2021). Individuals were grouped by age of onset. Clinical features and investigation profiles were compared. RESULTS: 10.3% (123/1196) had an age of onset over 80. Median survival was shorter (3.2 vs 4.3 months; P < 0.001). Pyramidal signs (48.3% vs 34.2%; P = 0.008) and akinetic mutism (55.1% vs 33.2%; P < 0.001) were more frequent. Psychiatric symptoms (26.3% vs 39.6%; P = 0.01) and cerebellar signs (65.4% vs 78.6%, P = 0.007) were less frequent. Cognitive impairment and myoclonus were highly prevalent regardless of age. Between age groups, the diagnostic sensitivity of cerebrospinal fluid real-time quaking-induced conversion (CSF RT-QuIC) (92.9% vs 91.9%, P = 0.74) was comparable, electroencephalography was superior (41.5% vs 25.4%; P = 0.006) and MRI was inferior (67.8% vs 91.4%; P < 0.001). CONCLUSIONS: Late-onset sCJD has distinct clinical features, shorter survival and a different profile of investigation sensitivity. CSF RT-QuIC, MRI brain and specialist CJD review is recommended in older adults with a rapidly progressive neurological disorder. Autopsy is valuable when the cause remains elusive.
Asunto(s)
Edad de Inicio , Síndrome de Creutzfeldt-Jakob , Humanos , Síndrome de Creutzfeldt-Jakob/epidemiología , Síndrome de Creutzfeldt-Jakob/diagnóstico , Síndrome de Creutzfeldt-Jakob/mortalidad , Reino Unido/epidemiología , Masculino , Femenino , Anciano de 80 o más Años , Incidencia , Fenotipo , Imagen por Resonancia Magnética , ElectroencefalografíaRESUMEN
INTRODUCTION: Incorporation of the real-time quaking-induced conversion (RT-QuIC) assays for diagnosis of sporadic Creutzfeldt-Jakob disease (CJD) has transformed diagnosis largely related to its extremely high specificity. However, the test has a c.10% false-negative result and we aim to characterize the clinical features, investigation profile, and molecular subtype in this cohort of patients. METHODS: 250 individuals diagnosed with definite sporadic CJD were identified from the UK National CJD Research and Surveillance Unit from 2012 to 2023. We compared the clinical features and investigation profile in those with a negative CSF RT-QuIC to those with a positive RT-QuIC. RESULTS: 27 individuals (10.8%) were CSF RT-QuIC negative. Median age of onset was younger (62 years vs 68 years, p = 0.002), median disease duration was longer (4.4 months vs 10.5 months, p < 0.001), and these individuals were less likely to present with gait difficulties (73% vs 93%, p = 0.003) or motor symptoms (62% vs 80%, p = 0.04). The sensitivity of electroencephalography and diffusion-weighted MRI were similar in both groups. In those who were RT-QuIC negative, there was an overrepresentation of the VV1 (32% vs 1%) and MM2 molecular subtypes (21% vs 3%). Co-occurring neurodegenerative disease was found in 33% (9/27) of those who were RT-QuIC negative. CONCLUSIONS: Individuals with sporadic CJD and a negative CSF RT-QuIC present with younger age of onset, different clinical features and are over-represented with the VV1 and MM2 subtypes of sporadic CJD. Further work is required to better understand the biochemical properties contributing to RT-QuIC negative results in these cases.
Asunto(s)
Síndrome de Creutzfeldt-Jakob , Humanos , Síndrome de Creutzfeldt-Jakob/líquido cefalorraquídeo , Síndrome de Creutzfeldt-Jakob/diagnóstico , Síndrome de Creutzfeldt-Jakob/epidemiología , Persona de Mediana Edad , Masculino , Femenino , Reino Unido/epidemiología , Anciano , Electroencefalografía , Edad de Inicio , Estudios de CohortesRESUMEN
BACKGROUND: In vivo imaging of the human retina using adaptive optics optical coherence tomography (AO-OCT) has transformed medical imaging by enabling visualization of 3D retinal structures at cellular-scale resolution, including the retinal pigment epithelial (RPE) cells, which are essential for maintaining visual function. However, because noise inherent to the imaging process (e.g., speckle) makes it difficult to visualize RPE cells from a single volume acquisition, a large number of 3D volumes are typically averaged to improve contrast, substantially increasing the acquisition duration and reducing the overall imaging throughput. METHODS: Here, we introduce parallel discriminator generative adversarial network (P-GAN), an artificial intelligence (AI) method designed to recover speckle-obscured cellular features from a single AO-OCT volume, circumventing the need for acquiring a large number of volumes for averaging. The combination of two parallel discriminators in P-GAN provides additional feedback to the generator to more faithfully recover both local and global cellular structures. Imaging data from 8 eyes of 7 participants were used in this study. RESULTS: We show that P-GAN not only improves RPE cell contrast by 3.5-fold, but also improves the end-to-end time required to visualize RPE cells by 99-fold, thereby enabling large-scale imaging of cells in the living human eye. RPE cell spacing measured across a large set of AI recovered images from 3 participants were in agreement with expected normative ranges. CONCLUSIONS: The results demonstrate the potential of AI assisted imaging in overcoming a key limitation of RPE imaging and making it more accessible in a routine clinical setting.
The retinal pigment epithelium (RPE) is a single layer of cells within the eye that is crucial for vision. These cells are unhealthy in many eye diseases, and this can result in vision problems, including blindness. Imaging RPE cells in living human eyes is time consuming and difficult with the current technology. Our method substantially speeds up the process of RPE imaging by incorporating artificial intelligence. This enables larger areas of the eye to be imaged more efficiently. Our method could potentially be used in the future during routine eye tests. This could lead to earlier detection and treatment of eye diseases, and the prevention of some causes of blindness.
RESUMEN
Motor Neuron Disease (MND) is a progressive and largely fatal neurodegeneritve disorder with a lifetime risk of approximately 1 in 300. At diagnosis, up to 25% of people with MND (pwMND) exhibit bulbar dysfunction. Currently, pwMND are assessed using clinical examination and diagnostic tools including the ALS Functional Rating Scale Revised (ALS-FRS(R)), a clinician-administered questionnaire with a single item on speech intelligibility. Here we report on the use of digital technologies to assess speech features as a marker of disease diagnosis and progression in pwMND. Google Scholar, PubMed, Medline and EMBASE were systematically searched. 40 studies were evaluated including 3670 participants; 1878 with a diagnosis of MND. 24 studies used microphones, 5 used smartphones, 6 used apps, 2 used tape recorders and 1 used the Multi-Dimensional Voice Programme (MDVP) to record speech samples. Data extraction and analysis methods varied but included traditional statistical analysis, CSpeech, MATLAB and machine learning (ML) algorithms. Speech features assessed also varied and included jitter, shimmer, fundamental frequency, intelligible speaking rate, pause duration and syllable repetition. Findings from this systematic review indicate that digital speech biomarkers can distinguish pwMND from healthy controls and can help identify bulbar involvement in pwMND. Preliminary evidence suggests digitally assessed acoustic features can identify more nuanced changes in those affected by voice dysfunction. No one digital speech biomarker alone is consistently able to diagnose or prognosticate MND. Further longitudinal studies involving larger samples are required to validate the use of these technologies as diagnostic tools or prognostic biomarkers.
RESUMEN
Blood cells trapped in stasis have been reported within the microcirculation, but their relevance to health and disease has not been established. In this study, we introduce an in vivo imaging approach that reveals the presence of a previously-unknown pool of erythrocytes in stasis, located within capillary segments of the CNS, and present in 100% of subjects imaged. These results provide a key insight that blood cells pause as they travel through the choroidal microvasculature, a vascular structure that boasts the highest blood flow of any tissue in the body. Demonstration of clinical utility using deep learning reveals that erythrocyte stasis is altered in glaucoma, indicating the possibility of more widespread changes in choroidal microvascular than previously realized. The ability to monitor the choroidal microvasculature at the single cell level may lead to novel strategies for tracking microvascular health in glaucoma, age-related macular degeneration, and other neurodegenerative diseases.
RESUMEN
Quantification of the rod photoreceptor mosaic using adaptive optics scanning light ophthalmoscopy (AOSLO) remains challenging. Here we demonstrate a method for deriving estimates of rod density and rod:cone ratio based on measures of rod spacing, cone numerosity, and cone inner segment area. Twenty-two AOSLO images with complete rod visualization were used to validate this spacing-derived method for estimating density. The method was then used to estimate rod metrics in an additional 105 images without complete rod visualization. The spacing-derived rod mosaic metrics were comparable to published data from histology. This method could be leveraged to develop large normative databases of rod mosaic metrics, though limitations persist with intergrader variability in assessing cone area and numerosity.
Asunto(s)
Ojo , Verde de Indocianina , Humanos , Colorantes , Angiografía , Células Epiteliales , Pigmentos Retinianos , Angiografía con Fluoresceína , Coroides , Fondo de OjoRESUMEN
INTRODUCTION: Sporadic Creutzfeldt-Jakob Disease (sCJD) is the commonest human prion disease, with a median age of onset of 68 years. We characterise the clinical, investigation, and neuropathological features in young individuals with sCJD using data from UK national CJD surveillance. METHODS: Referrals between 2011 and 2021 were examined, with definite (post-mortem confirmed) or probable sCJD cases included. Clinical features, MRI, EEG, CSF RT-QuIC, 14-3-3, PRNP sequencing and neuropathological findings were examined. We compared younger (≤ 50 years age of onset) with older individuals. Records of Non-sCJD referrals were also reviewed. RESULTS: 46 (4%) young individuals were identified (age at onset 25-50) from 1178 cases. 15 (33%) were autopsy confirmed. Psychiatric disturbance (37% vs 22%, p = 0.02) and headache (11% vs 3%, p = 0.01) at presentation, and longer disease duration (by 1.45 months, 95% CI 0.43-2.79, logrank p = 0.007) were commoner. CSF RT-QuIC showed lower sensitivity (82% vs 93%, p = 0.02). There was no difference in sensitivity of MR brain or CSF 14-3-3. There were no significant co-pathologies in autopsy-confirmed cases. For non-sCJD referrals, 41 cases were of other CJD subtypes, and 7 non-prion diagnoses. CONCLUSIONS: Young-onset sCJD is more likely to present with neuropsychiatric symptoms and headache, longer disease duration, and lower sensitivity of RT-QuIC. These findings may be driven by the underlying molecular subtypes. Our results guide the evaluation of younger individuals presenting with rapidly progressive cognitive, neuropsychiatric, and motor decline, and emphasise the need for additional vigilance for atypical features by clinicians and CJD surveillance programmes worldwide.
Asunto(s)
Síndrome de Creutzfeldt-Jakob , Humanos , Anciano , Síndrome de Creutzfeldt-Jakob/diagnóstico por imagen , Síndrome de Creutzfeldt-Jakob/epidemiología , Encéfalo/diagnóstico por imagen , Encéfalo/patología , Reino Unido/epidemiologíaRESUMEN
Choroideremia is an X-linked, blinding retinal degeneration with progressive loss of photoreceptors, retinal pigment epithelial (RPE) cells, and choriocapillaris. To study the extent to which these layers are disrupted in affected males and female carriers, we performed multimodal adaptive optics imaging to better visualize the in vivo pathogenesis of choroideremia in the living human eye. We demonstrate the presence of subclinical, widespread enlarged RPE cells present in all subjects imaged. In the fovea, the last area to be affected in choroideremia, we found greater disruption to the RPE than to either the photoreceptor or choriocapillaris layers. The unexpected finding of patches of photoreceptors that were fluorescently-labeled, but structurally and functionally normal, suggests that the RPE blood barrier function may be altered in choroideremia. Finally, we introduce a strategy for detecting enlarged cells using conventional ophthalmic imaging instrumentation. These findings establish that there is subclinical polymegathism of RPE cells in choroideremia.
Asunto(s)
Coroideremia , Degeneración Retiniana , Coroides/diagnóstico por imagen , Coroideremia/genética , Coroideremia/patología , Femenino , Humanos , Masculino , Óptica y Fotónica , Células Fotorreceptoras Retinianas Conos , Degeneración Retiniana/patologíaRESUMEN
Adaptive optics reflectance-based retinal imaging has proved a valuable tool for the noninvasive visualization of cells in the living human retina. Many subcellular features that remain at or below the resolution limit of current in vivo techniques may be more easily visualized with the same modalities in an ex vivo setting. While most microscopy techniques provide significantly higher resolution, enabling the visualization of fine cellular detail in ex vivo retinal samples, they do not replicate the reflectance-based imaging modalities of in vivo retinal imaging. Here, we introduce a strategy for imaging ex vivo samples using the same imaging modalities as those used for in vivo retinal imaging, but with increased resolution. We also demonstrate the ability of this approach to perform protein-specific fluorescence imaging and reflectance imaging simultaneously, enabling the visualization of nearly transparent layers of the retina and the classification of cone photoreceptor types.
RESUMEN
Purpose: To assess the structure of cone photoreceptors and retinal pigment epithelial (RPE) cells in vitelliform macular dystrophy (VMD) arising from various genetic etiologies. Methods: Multimodal adaptive optics (AO) imaging was performed in 11 patients with VMD using a custom-assembled instrument. Non-confocal split detection and AO-enhanced indocyanine green were used to visualize the cone photoreceptor and RPE mosaics, respectively. Cone and RPE densities were measured and compared across BEST1-, PRPH2-, IMPG1-, and IMPG2-related VMD. Results: Within macular lesions associated with VMD, both cone and RPE densities were reduced below normal, to 37% of normal cone density (eccentricity 0.2 mm) and to 8.4% of normal RPE density (eccentricity 0.5 mm). Outside of lesions, cone and RPE densities were slightly reduced (both to 92% of normal values), but with high degree of variability in the individual measurements. Comparison of juxtalesional cone and RPE measurements (<1 mm from the lesion edge) revealed significant differences in RPE density across the four genes (P < 0.05). Overall, cones were affected to a greater extent than RPE in patients with IMPG1 and IMPG2 pathogenic variants, but RPE was affected more than cones in BEST1 and PRPH2 VMD. This trend was observed even in contralateral eyes from a subset of five patients who presented with macular lesions in only one eye. Conclusions: Assessment of cones and RPE in retinal locations outside of the macular lesions reveals a pattern of cone and RPE disruption that appears to be gene dependent in VMD. These findings provide insight into the cellular pathogenesis of disease in VMD.
Asunto(s)
Distrofia Macular Viteliforme , Bestrofinas/genética , Proteínas de la Matriz Extracelular/genética , Proteínas del Ojo/química , Proteínas del Ojo/genética , Humanos , Óptica y Fotónica , Proteoglicanos/genética , Células Fotorreceptoras Retinianas Conos/patología , Epitelio Pigmentado de la Retina/patología , Tomografía de Coherencia Óptica/métodos , Distrofia Macular Viteliforme/diagnóstico , Distrofia Macular Viteliforme/genéticaRESUMEN
Adaptive optics scanning light ophthalmoscopy (AOSLO) allows non-invasive visualization of the living human eye at the microscopic scale; but even with correction of the ocular wavefront aberrations over a large pupil, the smallest cells in the photoreceptor mosaic cannot always be resolved. Here, we synergistically combine annular pupil illumination with sub-Airy disk confocal detection to demonstrate a 33% improvement in transverse resolution (from 2.36 to 1.58 µm) and a 13% axial resolution enhancement (from 37 to 32 µm), an important step towards the study of the complete photoreceptor mosaic in heath and disease. Interestingly, annular pupil illumination also enhanced the visualization of the photoreceptor mosaic in non-confocal detection schemes such as split detection AOSLO, providing a strategy for enhanced multimodal imaging of the cone and rod photoreceptor mosaic.
RESUMEN
In vivo imaging of human retinal pigment epithelial (RPE) cells has been demonstrated through multiple adaptive optics (AO)-based modalities. However, whether consistent and complete information regarding the cellular structure of the RPE mosaic is obtained across these modalities remains uncertain due to limited comparisons performed in the same eye. Here, an imaging platform combining multimodal AO-scanning light ophthalmoscopy (AO-SLO) with AO-optical coherence tomography (AO-OCT) is developed to make a side-by-side comparison of the same RPE cells imaged across four modalities: AO-darkfield, AO-enhanced indocyanine green (AO-ICG), AO-infrared autofluorescence (AO-IRAF), and AO-OCT. Co-registered images were acquired in five subjects, including one patient with choroideremia. Multimodal imaging provided multiple perspectives of the RPE mosaic that were used to explore variations in RPE cell contrast in a subject-, location-, and even cell-dependent manner. Estimated cell-to-cell spacing and density were found to be consistent both across modalities and with normative data. Multimodal images from a patient with choroideremia illustrate the benefit of using multiple modalities to infer the cellular structure of the RPE mosaic in an affected eye, in which disruptions to the RPE mosaic may locally alter the signal strength, visibility of individual RPE cells, or even source of contrast in unpredictable ways.
RESUMEN
Dark cone photoreceptors, defined as those with diminished or absent reflectivity when observed with adaptive optics (AO) ophthalmoscopy, are increasingly reported in retinal disorders. However, their structural and functional impact remain unclear. Here, we report a 3-year longitudinal study on a patient with oligocone trichromacy (OT) who presented with persistent, widespread dark cones within and near the macula. Diminished electroretinogram (ERG) cone but normal ERG rod responses together with normal color vision confirmed the OT diagnosis. In addition, the patient had normal to near normal visual acuity and retinal sensitivity. Occasional dark gaps in the photoreceptor layer were observed on optical coherence tomography, in agreement with reflectance AO scanning light ophthalmoscopy, which revealed that over 50% of the cones in the fovea were dark, increasing to 74% at 10° eccentricity. In addition, the cone density was 78% lower than normal histologic value at the fovea, and 20-40% lower at eccentricities of 5-15°. Interestingly, color vision testing was near normal at locations where cones were predominantly dark. These findings illustrate how a retina with predominant dark cones that persist over at least 3 years can support near normal central retinal function. Furthermore, this study adds to the growing evidence that cones can continue to survive under non-ideal conditions.
RESUMEN
Data annotation is a fundamental precursor for establishing large training sets to effectively apply deep learning methods to medical image analysis. For cell segmentation, obtaining high quality annotations is an expensive process that usually requires manual grading by experts. This work introduces an approach to efficiently generate annotated images, called "A-GANs", created by combining an active cell appearance model (ACAM) with conditional generative adversarial networks (C-GANs). ACAM is a statistical model that captures a realistic range of cell characteristics and is used to ensure that the image statistics of generated cells are guided by real data. C-GANs utilize cell contours generated by ACAM to produce cells that match input contours. By pairing ACAM-generated contours with A-GANs-based generated images, high quality annotated images can be efficiently generated. Experimental results on adaptive optics (AO) retinal images showed that A-GANs robustly synthesize realistic, artificial images whose cell distributions are exquisitely specified by ACAM. The cell segmentation performance using as few as 64 manually-annotated real AO images combined with 248 artificially-generated images from A-GANs was similar to the case of using 248 manually-annotated real images alone (Dice coefficients of 88% for both). Finally, application to rare diseases in which images exhibit never-seen characteristics demonstrated improvements in cell segmentation without the need for incorporating manual annotations from these new retinal images. Overall, A-GANs introduce a methodology for generating high quality annotated data that statistically captures the characteristics of any desired dataset and can be used to more efficiently train deep-learning-based medical image analysis applications.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Redes Neurales de la Computación , Algoritmos , Retina/diagnóstico por imagenRESUMEN
High quality data labeling is essential for improving the accuracy of deep learning applications in medical imaging. However, noisy images are not only under-represented in training datasets, but also, labeling of noisy data is low quality. Unfortunately, noisy images with poor quality labels are exacerbated by traditional data augmentation strategies. Real world images contain noise and can lead to unexpected drops in algorithm performance. In this paper, we present a non-traditional, purposeful data augmentation method to specifically transfer high quality automated labels into noisy image regions for incorporation into the training dataset. The overall approach is based on the use of paired images of the same cells in which variable image noise results in cell segmentation failures. Iteratively updating the cell segmentation model with accurate labels of noisy image areas resulted in an improvement in Dice coefficient from 77% to 86%. This was achieved by adding only 3.4% more cells to the training dataset, showing that local label transfer through graph matching is an effective augmentation strategy to improve segmentation.
RESUMEN
In medical imaging, CycleGAN has been used for various image generation tasks, including image synthesis, image denoising, and data augmentation. However, when pushing the technical limits of medical imaging, there can be a substantial variation in image quality. Here, we demonstrate that images generated by CycleGAN can be improved through explicit grading of image quality, which we call stratified CycleGAN. In this image generation task, CycleGAN is used to upgrade the image quality and content of near-infrared fluorescent (NIRF) retinal images. After manual assignment of grading scores to a small subset of the data, semi-supervised learning is applied to propagate grades across the remainder of the data and set up the training data. These scores are embedded into the CycleGAN by adding the grading score as a conditional input to the generator and by integrating an image quality classifier into the discriminator. We validate the efficacy of the proposed stratified CycleGAN by considering pairs of NIRF images at the same retinal regions (imaged with and without correction of optical aberrations achieved using adaptive optics), with the goal being to restore image quality in aberrated images such that cellular-level detail can be obtained. Overall, stratified CycleGAN generated higher quality synthetic images than traditional CycleGAN. Evaluation of cell detection accuracy confirmed that synthetic images were faithful to ground truth images of the same cells. Across this challenging dataset, F1-score improved from 76.9 ± 5.7% when using traditional CycleGAN to 85.0±3.4% when using stratified CycleGAN. These findings demonstrate the potential of stratified Cycle-GAN to improve the synthesis of medical images that exhibit a graded variation in image quality.
RESUMEN
Retinal pigment epithelial (RPE) cells play an important role in nourishing retinal neurosensory photoreceptor cells, and numerous blinding diseases are associated with RPE defects. Their fluorescence signature can now be visualized in the living human eye using adaptive optics (AO) imaging combined with indocyanine green (ICG), which motivates us to develop an automated RPE detection method to improve the quantitative evaluation of RPE status in patients. This paper proposes a spatially-aware, Dense-LinkNet-based regression approach to improve the detection of in vivo fluorescent cell patterns, achieving precision, recall, and F1-Score of 93.6 ± 4.3%, 81.4 ± 9.5%, and 86.7 ± 5.7%, respectively. These results demonstrate the utility of incorporating spatial inputs into a deep learning-based regression framework for cell detection.
Asunto(s)
Aprendizaje Profundo , Colorantes Fluorescentes , Procesamiento de Imagen Asistido por Computador/métodos , Imagen Óptica/métodos , Epitelio Pigmentado de la Retina , Técnicas de Diagnóstico Oftalmológico , Colorantes Fluorescentes/análisis , Colorantes Fluorescentes/química , Humanos , Verde de Indocianina/análisis , Epitelio Pigmentado de la Retina/citología , Epitelio Pigmentado de la Retina/diagnóstico por imagenRESUMEN
Data augmentation is an important strategy for enlarging training datasets in deep learning-based medical image analysis. This is because large, annotated medical datasets are not only difficult and costly to generate, but also quickly become obsolete due to rapid advances in imaging technology. Image-to-image conditional generative adversarial networks (C-GAN) provide a potential solution for data augmentation. However, annotations used as inputs to C-GAN are typically based only on shape information, which can result in undesirable intensity distributions in the resulting artificially-created images. In this paper, we introduce an active cell appearance model (ACAM) that can measure statistical distributions of shape and intensity and use this ACAM model to guide C-GAN to generate more realistic images, which we call A-GAN. A-GAN provides an effective means for conveying anisotropic intensity information to C-GAN. A-GAN incorporates a statistical model (ACAM) to determine how transformations are applied for data augmentation. Traditional approaches for data augmentation that are based on arbitrary transformations might lead to unrealistic shape variations in an augmented dataset that are not representative of real data. A-GAN is designed to ameliorate this. To validate the effectiveness of using A-GAN for data augmentation, we assessed its performance on cell analysis in adaptive optics retinal imaging, which is a rapidly-changing medical imaging modality. Compared to C-GAN, A-GAN achieved stability in fewer iterations. The cell detection and segmentation accuracy when assisted by A-GAN augmentation was higher than that achieved with C-GAN. These findings demonstrate the potential for A-GAN to substantially improve existing data augmentation methods in medical image analysis.