RESUMEN
Central Serous Chorioretinopathy (CSCR) is a significant cause of vision impairment worldwide, with Photodynamic Therapy (PDT) emerging as a promising treatment strategy. The capability to precisely segment fluid regions in Optical Coherence Tomography (OCT) scans and predict the response to PDT treatment can substantially augment patient outcomes. This paper introduces a novel deep learning (DL) methodology for automated 3D segmentation of fluid regions in OCT scans, followed by a subsequent PDT response analysis for CSCR patients. Our approach utilizes the rich 3D contextual information from OCT scans to train a model that accurately delineates fluid regions. This model not only substantially reduces the time and effort required for segmentation but also offers a standardized technique, fostering further large-scale research studies. Additionally, by incorporating pre- and post-treatment OCT scans, our model is capable of predicting PDT response, hence enabling the formulation of personalized treatment strategies and optimized patient management. To validate our approach, we employed a robust dataset comprising 2,769 OCT scans (124 3D volumes), and the results obtained were significantly satisfactory, outperforming the current state-of-the-art methods. This research signifies an important milestone in the integration of DL advancements with practical clinical applications, propelling us a step closer towards improved management of CSCR. Furthermore, the methodologies and systems developed can be adapted and extrapolated to tackle similar challenges in the diagnosis and treatment of other retinal pathologies, favoring more comprehensive and personalized patient care.
RESUMEN
Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges.
Asunto(s)
Algoritmos , Radiografía Torácica , Humanos , Radiografía Torácica/métodos , Aprendizaje Profundo , Pulmón/diagnóstico por imagen , Pulmón/patología , Tuberculosis/diagnóstico por imagen , Tuberculosis/diagnóstico , Tuberculosis Pulmonar/diagnóstico por imagen , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias Pulmonares/patología , Procesamiento de Imagen Asistido por Computador/métodos , Diagnóstico por Computador/métodosRESUMEN
Central Serous Chorioretinopathy (CSC) is a retinal disorder caused by the accumulation of fluid, resulting in vision distortion. The diagnosis of this disease is typically performed through Optical Coherence Tomography (OCT) imaging, which displays any fluid buildup between the retinal layers. Currently, these fluid regions are manually detected by visual inspection a time-consuming and subjective process that can be prone to errors. A series of six deep learning-based automatic segmentation architectural configurations of different levels of complexity were trained and compared in order to determine the best model intended for the automatic segmentation of CSC-related lesions in OCT images. The best performing models were then evaluated in an external validation study. Furthermore, an intra- and inter-expert analysis was conducted in order to compare the manual segmentation performed by expert ophthalmologists with the automatic segmentation provided by the models. Test results of the best performing configuration achieved a mean Dice of 0.868 ± 0.056 in the internal dataset. In the external validation set, these models achieved a level of agreement with human experts of up to 0.960 in terms of Kappa coefficient, contrasting with a value of 0.951 for agreement between human experts. Overall, the models reached a better agreement with either of the human experts than these experts with each other, suggesting that automatic segmentation models for the detection of CSC-related lesions in OCT imaging can be useful tools for assessing this disease, reducing the workload of manual inspection and leading to a more robust and objective diagnosis method.
RESUMEN
Background: The COVID-19 can cause long-term symptoms in the patients after they overcome the disease. Given that this disease mainly damages the respiratory system, these symptoms are often related with breathing problems that can be caused by an affected diaphragm. The diaphragmatic function can be assessed with imaging modalities like computerized tomography or chest X-ray. However, this process must be performed by expert clinicians with manual visual inspection. Moreover, during the pandemic, the clinicians were asked to prioritize the use of portable devices, preventing the risk of cross-contamination. Nevertheless, the captures of these devices are of a lower quality. Objectives: The automatic quantification of the diaphragmatic function can determine the damage of COVID-19 on each patient and assess their evolution during the recovery period, a task that could also be complemented with the lung segmentation. Methods: We propose a novel multi-task fully automatic methodology to simultaneously localize the position of the hemidiaphragms and to segment the lung boundaries with a convolutional architecture using portable chest X-ray images of COVID-19 patients. For that aim, the hemidiaphragms' landmarks are located adapting the paradigm of heatmap regression. Results: The methodology is exhaustively validated with four analyses, achieving an 82.31% ± 2.78% of accuracy when localizing the hemidiaphragms' landmarks and a Dice score of 0.9688 ± 0.0012 in lung segmentation. Conclusions: The results demonstrate that the model is able to perform both tasks simultaneously, being a helpful tool for clinicians despite the lower quality of the portable chest X-ray images.
RESUMEN
Retinal vascular tortuosity is an excessive bending and twisting of the blood vessels in the retina that is associated with numerous health conditions. We propose a novel methodology for the automated assessment of the retinal vascular tortuosity from color fundus images. Our methodology takes into consideration several anatomical factors to weigh the importance of each individual blood vessel. First, we use deep neural networks to produce a robust extraction of the different anatomical structures. Then, the weighting coefficients that are required for the integration of the different anatomical factors are adjusted using evolutionary computation. Finally, the proposed methodology also provides visual representations that explain the contribution of each individual blood vessel to the predicted tortuosity, hence allowing us to understand the decisions of the model. We validate our proposal in a dataset of color fundus images providing a consensus ground truth as well as the annotations of five clinical experts. Our proposal outperforms previous automated methods and offers a performance that is comparable to that of the clinical experts. Therefore, our methodology demonstrates to be a viable alternative for the assessment of the retinal vascular tortuosity. This could facilitate the use of this biomarker in clinical practice and medical research.
Asunto(s)
Inteligencia Artificial , Enfermedades de la Retina , Humanos , Vasos Retinianos/diagnóstico por imagen , Retina , Fondo de Ojo , AlgoritmosRESUMEN
Multi-task learning is a promising paradigm to leverage task interrelations during the training of deep neural networks. A key challenge in the training of multi-task networks is to adequately balance the complementary supervisory signals of multiple tasks. In that regard, although several task-balancing approaches have been proposed, they are usually limited by the use of per-task weighting schemes and do not completely address the uneven contribution of the different tasks to the network training. In contrast to classical approaches, we propose a novel Multi-Adaptive Optimization (MAO) strategy that dynamically adjusts the contribution of each task to the training of each individual parameter in the network. This automatically produces a balanced learning across tasks and across parameters, throughout the whole training and for any number of tasks. To validate our proposal, we perform comparative experiments on real-world datasets for computer vision, considering different experimental settings. These experiments allow us to analyze the performance obtained in several multi-task scenarios along with the learning balance across tasks, network layers and training steps. The results demonstrate that MAO outperforms previous task-balancing alternatives. Additionally, the performed analyses provide insights that allow us to comprehend the advantages of this novel approach for multi-task learning.
Asunto(s)
Aprendizaje Automático , Redes Neurales de la Computación , MonoaminooxidasaRESUMEN
Microorganisms can be genetically engineered to transform abundant waste feedstocks into value-added small molecules that would otherwise be manufactured from diminishing fossil resources. Herein, we report the first one-pot bio-upcycling of PET plastic waste into the prolific platform petrochemical and nylon precursor adipic acid in the bacterium Escherichia coli. Optimizing heterologous gene expression and enzyme activity enabled increased flux through the de novo pathway, and immobilization of whole cells in alginate hydrogels increased the stability of the rate-limiting enoate reductase BcER. The pathway enzymes were also interfaced with hydrogen gas generated by engineered E. coli DD-2 in combination with a biocompatible Pd catalyst to enable adipic acid synthesis from metabolic cis,cis-muconic acid. Together, these optimizations resulted in a one-pot conversion to adipic acid from terephthalic acid, including terephthalate samples isolated from industrial PET waste and a post-consumer plastic bottle.
RESUMEN
Retinal Optical Coherence Tomography (OCT) allows the non-invasive direct observation of the central nervous system, enabling the measurement and extraction of biomarkers from neural tissue that can be helpful in the assessment of ocular, systemic and Neurological Disorders (ND). Deep learning models can be trained to segment the retinal layers for biomarker extraction. However, the onset of ND can have an impact on the neural tissue, which can lead to the degraded performance of models not exposed to images displaying signs of disease during training. We present a fully automatic approach for the retinal layer segmentation in multiple neurodegenerative disorder scenarios, using an annotated dataset of patients of the most prevalent NDs: Alzheimer's disease, Parkinson's disease, multiple sclerosis and essential tremor, along with healthy control patients. Furthermore, we present a two-part, comprehensive study on the effects of ND on the performance of these models. The results show that images of healthy patients may not be sufficient for the robust training of automated segmentation models intended for the analysis of ND patients, and that using images representative of different NDs can increase the model performance. These results indicate that the presence or absence of patients of ND in datasets should be taken into account when training deep learning models for retinal layer segmentation, and that the proposed approach can provide a valuable tool for the robust and reliable diagnosis in multiple scenarios of ND.
Asunto(s)
Esclerosis Múltiple , Enfermedad de Parkinson , Humanos , Retina , Tomografía de Coherencia Óptica/métodosRESUMEN
A 46-year-old man with a personal history of a repaired aortic dissection was admitted because of hemolytic anemia. The transesophageal echocardiogram displayed an accelerated flow and a residual intimal flap in the proximal descending aorta. A total arch replacement was performed, the flap was removed, and his hemolytic anemia was resolved. (Level of Difficulty: Advanced.).
RESUMEN
Background: Glaucoma is the leading global cause of irreversible blindness. Glaucoma patients experience a progressive deterioration of the retinal nervous tissues that begins with a loss of peripheral vision. An early diagnosis is essential in order to prevent blindness. Ophthalmologists measure the deterioration caused by this disease by assessing the retinal layers in different regions of the eye, using different optical coherence tomography (OCT) scanning patterns to extract images, generating different views from multiple parts of the retina. These images are used to measure the thickness of the retinal layers in different regions. Methods: We present two approaches for the multi-region segmentation of the retinal layers in OCT images of glaucoma patients. These approaches can extract the relevant anatomical structures for glaucoma assessment from three different OCT scan patterns: circumpapillary circle scans, macular cube scans and optic disc (OD) radial scans. By employing transfer learning to take advantage of the visual patterns present in a related domain, these approaches use state-of-the-art segmentation modules to achieve a robust, fully automatic segmentation of the retinal layers. The first approach exploits inter-view similarities by using a single module to segment all of the scan patterns, considering them as a single domain. The second approach uses view-specific modules for the segmentation of each scan pattern, automatically detecting the suitable module to analyse each image. Results: The proposed approaches produced satisfactory results with the first approach achieving a dice coefficient of 0.85±0.06 and the second one 0.87±0.08 for all segmented layers. The first approach produced the best results for the radial scans. Concurrently, the view-specific second approach achieved the best results for the better represented circle and cube scan patterns. Conclusions: To the extent of our knowledge, this is the first proposal in the literature for the multi-view segmentation of the retinal layers of glaucoma patients, demonstrating the applicability of machine learning-based systems for aiding in the diagnosis of this relevant pathology.
RESUMEN
COVID-19 is a global threat for the healthcare systems due to the rapid spread of the pathogen that causes it. In such situation, the clinicians must take important decisions, in an environment where medical resources can be insufficient. In this task, the computer-aided diagnosis systems can be very useful not only in the task of supporting the clinical decisions but also to perform relevant analyses, allowing them to understand better the disease and the factors that can identify the high risk patients. For those purposes, in this work, we use several machine learning algorithms to estimate the outcome of COVID-19 patients given their clinical information. Particularly, we perform 2 different studies: the first one estimates whether the patient is at low or at high risk of death whereas the second estimates if the patient needs hospitalization or not. The results of the analyses of this work show the most relevant features for each studied scenario, as well as the classification performance of the considered machine learning models. In particular, the XGBoost algorithm is able to estimate the need for hospitalization of a patient with an AUC-ROC of 0 . 8415 ± 0 . 0217 while it can also estimate the risk of death with an AUC-ROC of 0 . 7992 ± 0 . 0104 . Results have demonstrated the great potential of the proposal to determine those patients that need a greater amount of medical resources for being at a higher risk. This provides the healthcare services with a tool to better manage their resources.
RESUMEN
PURPOSE: Since very preterm children often have increased retinal tortuosity that may indicate decisive architectural changes in the systemic microvascular network, we used a new semi-automatic software to measure retinal vessel tortuosity on fundus digital images of moderate-to-late preterm (MLP) children. METHODS: In this observational case-control study, the global and local tortuosity parameters of retinal vessels were evaluated on fundus photographs of 36 MLP children and 36 age- and sex-matched controls. The associations between birth parameters and parameters reflecting retinal vessel tortuosity were evaluated using correlation analysis. RESULTS: Even after incorporation of anatomical factors, the global and local tortuosity parameters were not significantly different between groups. The MLP group showed a smaller arteriolar caliber (0.53 ± 0.2) than the controls (0.56 ± 0.2; p = 0.013). Other local tortuosity parameters, such as vessel length, distance to fovea, and distance to optic disc, were not significantly different between arteries and veins. Tortuosity in both groups was higher among vessels closer to the fovea (r = -0.077, p < 0.001) and the optic disc (r = -0.0544, p = 0.009). Global tortuosity showed a weakly positive correlation with gestational age and a weakly negative correlation with birth weight in both groups. CONCLUSION: MLP patients did not display increased vessel tortuosity in comparison with the controls; however, the arteriolar caliber in the MLP group was smaller than that in children born full-term. Larger studies should confirm this finding and explore associations between cardiovascular and metabolic status and retinal vessel geometry in MLP children.
Asunto(s)
Disco Óptico , Vasos Retinianos , Recién Nacido , Humanos , Niño , Estudios de Casos y Controles , Disco Óptico/irrigación sanguínea , Retina , ComputadoresRESUMEN
In optical coherence tomography (OCT), there is a trade-off between the scanning time and image quality, leading to a scarcity of high quality data. OCT platforms provide different scanning presets, producing visually distinct images, limiting their compatibility. In this work, a fully automatic methodology for the unpaired visual conversion of the two most prevalent scanning presets is proposed. Using contrastive unpaired translation generative adversarial architectures, low quality images acquired with the faster Macular Cube preset can be converted to the visual style of high visibility Seven Lines scans and vice-versa. This modifies the visual appearance of the OCT images generated by each preset while preserving natural tissue structure. The quality of original and synthetic generated images was compared using BRISQUE. The synthetic generated images achieved very similar scores to original images of their target preset. The generative models were validated in automatic and expert separability tests. These models demonstrated they were able to replicate the genuine look of the original images. This methodology has the potential to create multi-preset datasets with which to train robust computer-aided diagnosis systems by exposing them to the visual features of different presets they may encounter in real clinical scenarios without having to obtain additional data. Graphical Abstract Unpaired mutual conversion between scanning presets. Two generative adversarial models are trained for the conversion of OCT images into images of another scanning preset, replicating the visual features that characterise said preset.
Asunto(s)
Diagnóstico por Computador , Tomografía de Coherencia Óptica , Tomografía de Coherencia Óptica/métodos , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Diabetes represents one of the main causes of blindness in developed countries, caused by fluid accumulations in the retinal layers. The clinical literature defines the different types of diabetic macular edema (DME) as cystoid macular edema (CME), diffuse retinal thickening (DRT), and serous retinal detachment (SRD), each with its own clinical relevance. These fluid accumulations do not present defined borders that facilitate segmentational approaches (specially the DRT type, usually not taken into account by the state of the art for this reason) so a diffuse paradigm is used for its detection and visualization. In this paper, we propose three novel approaches for the representation and characterization of these types of DME. A baseline proposal, using a convolutional neural network as backbone, another based on transfer learning from a general domain, and a third approach exploiting information of regions without a defined label. Overall, our baseline proposal obtained an AUC of 0.9583 ± 0.0093, the approach pretrained with a general-domain dataset an AUC of 0.9603 ± 0.0087, and the approach pretrained in the domain taking advantage of uncertainty, an AUC of 0.9619 ± 0.0073.
Asunto(s)
Retinopatía Diabética , Edema Macular , Humanos , Edema Macular/diagnóstico por imagen , Retinopatía Diabética/diagnóstico , Incertidumbre , Tomografía de Coherencia Óptica/métodos , Agudeza Visual , Estudios RetrospectivosRESUMEN
Optical coherence tomography angiography (OCTA) is a non-invasive ophthalmic imaging modality that is widely used in clinical practice. Recent technological advances in OCTA allow imaging of blood flow deeper than the retinal layers, at the level of the choriocapillaris (CC), where a granular image is obtained showing a pattern of bright areas, representing blood flow, and a pattern of small dark regions, called flow voids (FVs). Several clinical studies have reported a close correlation between abnormal FVs distribution and multiple diseases, so quantifying changes in FVs distribution in CC has become an area of interest for many clinicians. However, CC OCTA images present very complex features that make it difficult to correctly compare FVs during the monitoring of a patient. In this work, we propose fully automatic approaches for the segmentation and monitoring of FVs in CC OCTA images. First, a baseline approach, in which a fully automatic segmentation methodology based on local contrast enhancement and global thresholding is proposed to segment FVs and measure changes in their distribution in a straightforward manner. Second, a robust approach in which, prior to the use of our segmentation methodology, an unsupervised trained neural network is used to perform a deformable registration that aligns inconsistencies between images acquired at different time instants. The proposed approaches were tested with CC OCTA images collected during a clinical study on the response to photodynamic therapy in patients affected by chronic central serous chorioretinopathy (CSC), demonstrating their clinical utility. The results showed that both approaches are accurate and robust, surpassing the state of the art, therefore improving the efficacy of FVs as a biomarker to monitor the patient treatments. This gives great potential for the clinical use of our methods, with the possibility of extending their use to other pathologies or treatments associated with this type of imaging.
Asunto(s)
Fotoquimioterapia , Tomografía de Coherencia Óptica , Humanos , Angiografía con Fluoresceína/métodos , Tomografía de Coherencia Óptica/métodos , Retina/diagnóstico por imagen , Fotoquimioterapia/métodos , Coroides/diagnóstico por imagenRESUMEN
During the last years, deep learning techniques have emerged as powerful alternatives to solve biomedical image analysis problems. However, the training of deep neural networks usually needs great amounts of labeled data to be done effectively. This is even more critical in the case of biomedical imaging due to the added difficulty of obtaining data labeled by experienced clinicians. To mitigate the impact of data scarcity, one of the most commonly used strategies is transfer learning. Nevertheless, the success of this approach depends on the effectiveness of the available pre-training techniques for learning from little or no labeled data. In this work, we explore the application of the Context Encoder paradigm for transfer learning in the domain of retinal image analysis. To this aim, we propose several approaches that allow to work with full resolution images and improve the recognition of the retinal structures. In order to validate the proposals, the Context Encoder pre-trained models are fine-tuned to perform two relevant tasks in the domain: vessels segmentation and fovea localization. The experiments performed on different public datasets demonstrate that the proposed Context Encoder approaches allow mitigating the impact of data scarcity, being superior to previous alternatives in this domain.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Redes Neurales de la Computación , Procesamiento de Imagen Asistido por Computador/métodos , Diagnóstico por Imagen , Retina/diagnóstico por imagen , Aprendizaje AutomáticoRESUMEN
BACKGROUND AND OBJECTIVES: Age-related macular degeneration (AMD) is a degenerative disorder affecting the macula, a key area of the retina for visual acuity. Nowadays, AMD is the most frequent cause of blindness in developed countries. Although some promising treatments have been proposed that effectively slow down its development, their effectiveness significantly diminishes in the advanced stages. This emphasizes the importance of large-scale screening programs for early detection. Nevertheless, implementing such programs for a disease like AMD is usually unfeasible, since the population at risk is large and the diagnosis is challenging. For the characterization of the disease, clinicians have to identify and localize certain retinal lesions. All this motivates the development of automatic diagnostic methods. In this sense, several works have achieved highly positive results for AMD detection using convolutional neural networks (CNNs). However, none of them incorporates explainability mechanisms linking the diagnosis to its related lesions to help clinicians to better understand the decisions of the models. This is specially relevant, since the absence of such mechanisms limits the application of automatic methods in the clinical practice. In that regard, we propose an explainable deep learning approach for the diagnosis of AMD via the joint identification of its associated retinal lesions. METHODS: In our proposal, a CNN with a custom architectural setting is trained end-to-end for the joint identification of AMD and its associated retinal lesions. With the proposed setting, the lesion identification is directly derived from independent lesion activation maps; then, the diagnosis is obtained from the identified lesions. The training is performed end-to-end using image-level labels. Thus, lesion-specific activation maps are learned in a weakly-supervised manner. The provided lesion information is of high clinical interest, as it allows clinicians to assess the developmental stage of the disease. Additionally, the proposed approach allows to explain the diagnosis obtained by the models directly from the identified lesions and their corresponding activation maps. The training data necessary for the approach can be obtained without much extra work on the part of clinicians, since the lesion information is habitually present in medical records. This is an important advantage over other methods, including fully-supervised lesion segmentation methods, which require pixel-level labels whose acquisition is arduous. RESULTS: The experiments conducted in 4 different datasets demonstrate that the proposed approach is able to identify AMD and its associated lesions with satisfactory performance. Moreover, the evaluation of the lesion activation maps shows that the models trained using the proposed approach are able to identify the pathological areas within the image and, in most cases, to correctly determine to which lesion they correspond. CONCLUSIONS: The proposed approach provides meaningful information-lesion identification and lesion activation maps-that conveniently explains and complements the diagnosis, and is of particular interest to clinicians for the diagnostic process. Moreover, the data needed to train the networks using the proposed approach is commonly easy to obtain, what represents an important advantage in fields with particularly scarce data, such as medical imaging.
Asunto(s)
Aprendizaje Profundo , Degeneración Macular , Humanos , Fondo de Ojo , Degeneración Macular/diagnóstico por imagen , Redes Neurales de la Computación , Retina/diagnóstico por imagenRESUMEN
PURPOSE: There are many physiological parameters recorded by devices that are becoming more affordable, precise and accurate. However, the lack of development in the recording of voice parameters from the physiological or medical point of view is striking, given that it is a fundamental tool for the work of many people and given the high incidence and prevalence of voice pathologies that affect people's communication. In this paper we perform a complete literature review on the dosimeters used in voice research and to present a prototype dosimeter with a pilot study to show its capabilities. METHOD: We conducted a literature review using the keywords [MONITORING], [PHONATION], [ACCUMULATOR], [PORTABLE], [DOSIMETRY], [VOICE] searching in PubMed, Trip Database, HONcode, and SciELO search engines. From our review of dosimeter designs, we created our own prototype consisting of two main components: a Knowles Electronics BU-7135-0000 accelerometer mounted on a neck brace; and the ultra-low power MSP430FR5994 microcontroller. The selected sampling frequency was 2048 Hz. The device calculates the F0 every 250 ms and the amplitude and phonation activity every 31.25 ms. A pilot study was conducted using 2 subjects: one male during 11 days and one female during 14 days. RESULTS: This work includes devices that have been created during the last 45 years as tools for the diagnosis and monitoring of the treatment of cases of vocal pathology and for the detection of phonatory patterns or risk situations for developing voice disorders or vocal pathologies. We also present recordings with our new device on the pattern of daily talk time, the fundamental frequency and the relative intensity of two subjects on different days. CONCLUSIONS: Interesting work has been done in the development of voice dosimeters with different approaches. In our experience it is not possible to access them for research and they are not yet in clinical use. It is possible that a joint approach with voice and voice disorders professionals and engineers working closely together could take advantage of current technology to develop a fully portable, useful, and efficient system.
RESUMEN
Age-related macular degeneration is the leading cause of vision loss in developed countries, and wet-type AMD requires urgent treatment and rapid diagnosis because it causes rapid irreversible vision loss. Currently, AMD diagnosis is mainly carried out using images obtained by optical coherence tomography. This diagnostic process is performed by human clinicians, so human error may occur in some cases. Therefore, fully automatic methodologies are highly desirable adding a layer of robustness to the diagnosis. In this work, a novel computer-aided diagnosis and visualization methodology is proposed for the rapid identification and visualization of wet AMD. We adapted a convolutional neural network for segmentation of a similar domain of medical images to the problem of wet AMD segmentation, taking advantage of transfer learning, which allows us to work with and exploit a reduced number of samples. We generate a 3D intuitive visualization where the existence, position and severity of the fluid were represented in a clear and intuitive way to facilitate the analysis of the clinicians. The 3D visualization is robust and accurate, obtaining satisfactory 0.949 and 0.960 Dice coefficients in the different evaluated OCT cube configurations, allowing to quickly assess the presence and extension of the fluid associated to wet AMD.
Asunto(s)
Degeneración Macular , Humanos , Degeneración Macular/diagnóstico por imagen , Tomografía de Coherencia Óptica/métodos , Redes Neurales de la Computación , Diagnóstico por Computador/métodosRESUMEN
BACKGROUND AND OBJECTIVES: The Epiretinal Membrane (ERM) is an ocular disease that can cause visual distortions and irreversible vision loss. Patient sight preservation relies on an early diagnosis and on determining the location of the ERM in order to be treated and potentially removed. In this context, the visual inspection of the images in order to screen for ERM signs is a costly and subjective process. METHODS: In this work, we propose and study three end-to-end fully-automatic approaches for the simultaneous segmentation and screening of ERM signs in Optical Coherence Tomography images. These convolutional approaches exploit a multi-task learning context to leverage inter-task complementarity in order to guide the training process. The proposed architectures are combined with three different state of the art encoder architectures of reference in order to provide an exhaustive study of the suitability of each of the approaches for these tasks. Furthermore, these architectures work in an end-to-end manner, entailing a significant simplification of the development process since they are able to be trained directly from annotated images without the need for a series of purpose-specific steps. RESULTS: In terms of segmentation, the proposed models obtained a precision of 0.760 ± 0.050, a sensitivity of 0.768 ± 0.210 and a specificity of 0.945 ± 0.011. For the screening task, these models achieved a precision of 0.963 ± 0.068, a sensitivity of 0.816 ± 0.162 and a specificity of 0.983 ± 0.068. The obtained results show that these multi-task approaches are able to perform competitively with or even outperform single-task methods tailored for either the segmentation or the screening of the ERM. CONCLUSIONS: These results highlight the advantages of using complementary knowledge related to the segmentation and screening tasks in the diagnosis of this relevant pathology, constituting the first proposal to address the diagnosis of the ERM from a multi-task perspective.