Herramientas de corte para optimizar parámetros de clasificación de especies maderables con redes neuronales convolucionales / Cutting tools to optimize classification parameters of timber species with convolutional neural networks

Introducción: La gran diversidad de especies maderables tropicales demanda el desarrollo de nuevas tecnologías de identificación con base en sus patrones o características anatómicas. La aplicación de redes neuronales convolucionales (CNN) para el reconocimiento de especies maderables tropicales se ha incrementado en los últimos años por sus resultados prometedores. Objetivo: Evaluamos la calidad de las imágenes macroscópicas con tres herramientas de corte para mejorar la visualización y distinción de las características anatómicas en el entrenamiento del modelo CNN. Métodos: Recolectamos las muestras entre el 2020 y 2021 en áreas de explotación forestal y aserraderos de Selva Central, Perú. Luego, las dimensionamos y, previo a la identificación botánica y anatómica, las cortamos en secciones transversales. Generamos una base de datos de imágenes macroscópicas de la sección transversal de la madera, a través del corte, con tres herramientas para ver su rendimiento en el laboratorio, campo y puesto de control. Resultados: Usamos tres herramientas de corte para obtener una alta calidad de imágenes transversales de la madera; obtuvimos 3 750 imágenes macroscópicas con un microscopio portátil que corresponden a 25 especies maderables. El cuchillo ''Tramontina'' es duradero, pero pierde el filo con facilidad y se necesita una herramienta para afilar, el cúter retráctil ''Pretul'' es adecuado para madera suave y dura en muestras pequeñas de laboratorio; el cuchillo ''Ubermann'' es apropiado para el campo, laboratorio y puesto de control, porque tiene una envoltura duradera y láminas intercambiables en caso de pérdida de filo. Conclusiones: La calidad de las imágenes es decisiva en la clasificación de especies maderables, porque permite una mejor visualización y distinción de las características anatómicas en el entrenamiento con los modelos de red neuronal convolucional EfficientNet B0 y Custom Vision, lo cual se evidenció en las métricas de precisión.

Introduction: The great diversity of tropical timber species demands the development of new technologies capable of identifying them based on their patterns or anatomical characteristics. The application of convolutional neural networks (CNN) for the recognition of tropical timber species has increased in recent years due to the promising results of CNNs. Objective: To evaluate the quality of macroscopic images with three cutting tools to improve the visualization and distinction of anatomical features in the CNN model training. Methods: Samples were collected from 2020 to 2021 in areas of logging and sawmills in the Central Jungle, Peru. They were later sized and, after botanical and anatomical identification, cut in cross sections. A database of macroscopic images of the cross-section of wood was generated through cutting with three different tools and observing its performance in the laboratory, field, and checkpoint. Results: Using three cutting tools, we obtained high quality images of the cross section of wood; 3 750 macroscopic images were obtained with a portable microscope and correspond to 25 timber species. We found the ''Tramontina'' knife to be durable, however, it loses its edge easily and requires a sharpening tool, the ''Pretul'' retractable cutter is suitable for cutting soft and hard wood in small laboratory samples and finally the ''Ubermann'' knife is suitable for use in the field, laboratory, and checkpoint, because it has a durable sheath and interchangeable blades in case of dullness. Conclusion: The quality of the images is decisive in the classification of timber species, because it allows a better visualization and distinction of the anatomical characteristics in training with the EfficientNet B0 and Custom Vision convolutional neural network models, which was evidenced in the precision metrics.

Recurrent Quantification Analysis Based Study of Wide-Field Calcium Imaging Data in Relation to Brain's Wake/Sleep Condition

Wide-Field Calcium Images (WFCI) directly reflect neuronal excitation, but their poor frame rate could be a drawback for time series analysis. This work was aimed at exploring the diagnostic capability retained by a time series obtained from calcium imaging data. To that purpose, we analyzed publicly available data from 2.88 hour continuous recordings of calcium images obtained from seven mice at different wake/sleep stages. Data were obtained from the Physionet portal and were submitted to Recurrence Quantification Analysis (RQA). The association between retrosplenial and parietal areas was also assessed. Nonlinear RQA analysis allowed to identify the right retrosplenial and parietal areas as particularly sensitive to changes in sleep walking condition. Specifically, our results suggested that the RQA feature lmean decreases in non-REM sleep_1 stage as compared to waking stage. Sleep (both sleep_1 stage and REM) apparently elicits an increase in the association between retrosplenial and parietal areas. Overall, these results suggest that RQA and association analysis are appropriate to assess modifications associated to changes in brain condition, in spite of the low sampling rate of WFCI signals.

Las Imágenes de Calcio de Campo Ancho (Wide-Field Calcium Images, WFCI) reflejan directamente la excitación neuronal, pero su escasa resolución temporal pudiera resultar un impedimento para el análisis de series temporales. El presente trabajo tuvo por finalidad explorar la capacidad diagnostica que retiene una serie temporal extraída de imágenes de calcio. Para ello, se estudió una base de datos disponible en la red que contiene registros de 2.88 horas de duración de imágenes de calcio correspondientes a 7 ratones transgénicos a diferentes estadios de sueño/vigilia. Los datos fueron descargados del portal Physionet y sometidos a Análisis de Cuantificación Recurrente (Recurrent Quantification Analysis, RQA). La asociación entre las áreas retrosplenial y parietal derechas fue también evaluada. El análisis no lineal mediante RQA permitió identificar las áreas retrosplenial y parietal derechas como zonas particularmente sensibles a cambios en el estado de sueño/vigilia. Específicamente, nuestros resultados sugieren que el índice l mean se redujo en el estadio 1 de sueño no REM en comparación con el estado de vigilia. El estado de sueño, tanto REM como no-REM aparentemente induce un reforzamiento en la apreciación entre las áreas retrosplenial y parietal derechas. En su conjunto, estos resultados apuntan que el análisis de RQA y de asociación entre áreas son pertinentes para sensar las modificaciones asociadas a cambios en el estado del cerebro, a pesar de la baja resolución temporal de las señales WFCI.

Efeitos da Intervenção Relaxamento, Imagens Mentais e Espiritualidade em Pacientes com Diagnóstico de Câncer / Effects of the Relaxation, Mental Images and Spirituality Intervention in Patients Diagnosed with Cancer / Efectos de la Intervención Relajación, Imágenes Mentales y Espiritualidad en Pacientes con Diagnóstico de Cáncer

O câncer é considerado uma das principais doenças no mundo, e diversas estratégias vêm sendo utilizadas para amenizar suas consequências negativas. A intervenção Relaxamento, Imagens Mentais e Espiritualidade é um potencial meio para a melhoria do bem-estar dos pacientes. Portanto, o presente estudo objetivou identificar possíveis efeitos dessa intervenção em pacientes acometidos pelo câncer. Assim, realizou-se uma revisão integrativa da literatura. A busca de artigos ocorreu em agosto de 2020 nas bases de dados: Biblioteca Virtual em Saúde, SciELO, PubMed e Google Acadêmico. Os Descritores em Ciências da Saúde estabelecidos foram: "Relaxamento", "Imagens Mentais", "Espiritualidade" e "Câncer", em português e inglês, identificados no título, resumo ou palavras-chave. Foram considerados artigos em português e/ou inglês com texto completo disponível, dissertações e/ou teses, sem limite de ano de publicação. A busca resultou em 948 estudos. Desses, foram descartados: 424 pelos critérios de exclusão, e 500 com base na leitura dos títulos e resumos. Sete estudos foram selecionados para revisão, obtendo-se três categorias finais: transformação da dor simbólica da morte; benefícios no aspecto físico dos pacientes; benefícios no aspecto psicológico dos pacientes. A intervenção Relaxamento, Imagens Mentais e Espiritualidade oferece cuidado integral, sendo considerada benéfica para pacientes oncológicos, mesmo associada aos tratamentos convencionais.

Cancer is considered one of the major diseases in the world, and several strategies have been used to minimize the negative consequences of this disease. The Relaxation, Mental Images and Spirituality intervention is a potential way to improve the patients' well-being. Therefore, this study identifies possible effects of this intervention in oncologic patients. Thus, an integrative literature review was carried out. The search for articles took place in August 2020 in the following databases: Virtual Health Library, SciELO, PubMed and Academic Google. The Health Sciences Descriptors established were: "Relaxation", "Mental Images", "Spirituality" and "Cancer", in Portuguese and English, identified in the title, abstract or keywords. Articles in Portuguese and/or English with available full text, dissertations and/or theses were considered, with no limit on the year of publication. The search resulted in 948 studies. From these, 424 were discarded according to the exclusion criteria, and 500 based on reading of the titles and abstracts. Seven studies were selected for review, obtaining three final categories: transformation of the symbolic pain of death; benefits in the physical aspect of patients; benefits in the psychological aspect of patients. The Relaxation, Mental Images and Spirituality intervention offers comprehensive care, being beneficial for cancer patients, even in association with conventional treatments.

El cáncer es una de las principales enfermedades del mundo y se han utilizado estrategias para paliar consecuencias negativas. La intervención Relajación, Imágenes Mentales y Espiritualidad es un medio para mejorar el bienestar de los pacientes. Así, el presente estudio tuvo como objetivo identificar posibles efectos de esta intervención en pacientes oncológicos. Se realizó una revisión integradora de la literatura, con búsqueda de artículos en agosto de 2020 en las bases de datos: Virtual Health Library, SciELO, PubMed y Academic Google. Los Descriptores de Ciencias de la Salud establecidos: "Relajación", "Imágenes Mentales", "Espiritualidad" y "Cáncer", en portugués e inglés, identificados en el título, resumen o palabras clave. Se consideraron artículos en portugués/inglés con texto completo disponible, disertaciones/tesis, sin límite de año de publicación. La búsqueda resultó en 948 estudios. De estos, 424 se descartaron según los criterios de exclusión y 500 según la lectura de títulos y resúmenes. Se seleccionaron siete estudios para revisión, obteniendo tres categorías finales: transformación del dolor simbólico de la muerte; beneficios en el aspecto físico de los pacientes; beneficios en el aspecto psicológico de los pacientes. La intervención Relajación, Imágenes Mentales y Espiritualidad ofrece atención integral, considerándose beneficiosa para el paciente oncológico, incluso en asociación con tratamientos convencionales.

Correlações simbólicas entre o Bhagavad Gita e o processo de individuação / Symbolic Correlations between the Bhagavad Gita and the Individualization Process / Correlaciones Simbólicas entre el Bhagavad Gita y el Proceso de Individuación

O artigo propõe uma correlação simbólica entre o texto do Bhagavad Gita e o processo de individuação proposto por Jung. Interpreta a guerra entre os guenos dos Pândavas e dos Káuravas como um processo simbólico, em função do qual, Arjuna (personagem líder dos Pândavas) poderá incorporar, em sua psique, os conteúdos, simbolicamente representados e depositados no grupo dos Káuravas, sejam as características sombrias, defensivas, bem como as criativas ou iluminadas.

This paper proposes a symbolic correlation between the Bhagavad Gita text and the individuation process proposed by Jung. It interprets the war between the Pandavas' guenos and the Káuravas as a symbolic process, as a result of which Arjuna (leader of the Pândavas) will be able to embody, in his psyche, the contents, symbolically represented and deposited in the group of the Káuravas, whether the characters dark, defensive, as well as creative or light ones.

El artículo propone una correlación simbólica entre el texto del Bhagavad Gita y el proceso de individuación propuesto por Jung. Interpreta la guerra entre los guenos de los Pándavas y de los Káuravas como un proceso simbólico, en función del cual, Arjuna (personaje líder de los Pándavas) podrá incorporar en su psique los contenidos, simbólicamente representados y depositados en el grupo de los Káuravas, sean las características oscuras, defensivas, así como las creativas o iluminadas.

Identificação de Características e Propriedades Morfológicas em Texturas Táteis: Estudo sobre Gráficos Educativos e Cartografias para Crianças com Deficiência Visual / Identification of Properties and Morphological Characteristics in Tactile Textures: a Study on Educational Graphics and Cartographies for Visual Impaired Children

RESUMO: Este artigo explora as texturas táteis que têm sido utilizadas na confecção de mapas e imagens temáticas para crianças com deficiência visual no Chile nos últimos 20 anos. De um grupo representativo composto por mais de 300 lâminas de conteúdo educacional inclusivo, foram selecionadas 14 texturas para identificar sua natureza, propriedades psicofísicas e características morfológicas a partir de sua composição geométrica. O objetivo foi gerar as bases teóricas e tecnológicas relacionadas ao design e à produção digital de mapas, imagens e gráficos táteis. O trabalho buscou tipificar as formas de relevo e suas possíveis aplicações pelo uso de padrões de repetição que permitam melhorar a linguagem e o reconhecimento das texturas envolvidas com o intuito de expandir e diversificar seu uso em material educativo inclusivo no ensino e na disseminação do conhecimento por meio do toque.

ABSTRACT: This article explores the textures that have been used in the development of thematic maps and images for children with visual impairment in Chile over the last 20 years. From a representative group of more than 300 sheets of inclusive educational content, 14 textures were selected to identify their nature, psychophysical properties and morphological characteristics based on their geometric composition. The aim was to generate the theoretical and technological grounds related to the design and digital production of tactile maps, images, and graphics. The work sought to typify the embossed shapes and their possible applications by using repetition patterns that allow to improve the language and recognition of the textures involved, with the intention of expanding and diversifying their use in inclusive educational material in the teaching and dissemination of knowledge through tact.

Value of low-energy virtual monochromatic images of dual-energy CT in the evaluation of tumor visibility and T staging in hypopharyngeal squamous cell carcinoma / 中华放射学杂志

Objective:To investigate the value of low-energy virtual monoenergetic image (VMI) at 45 keV in visualizing the primary tumor and T staging of hypopharyngeal squamous cell carcinoma.Methods:The clinical and imaging data of 58 patients with hypopharyngeal squamous cell carcinoma from April 2018 to January 2020 at Eye & ENT Hospital, Fudan University were analyzed retrospectively. All the patients underwent a venous phase contrast-enhanced dual-source dual-energy CT scan before treatment. The VMI at 45 keV and standard linearly blended image (30% 80 kV+70% 140 kV) were acquired from dual-energy post-processing software. One senior radiologist and one junior radiologist independently assessed the visibility of the tumor on the 45 keV VMI and standard linearly blended image using a 5-point Likert rating scale. Furthermore, the senior radiologist assessed the visibility of the tumor at each subsite (piriform fossa, posterior pharyngeal wall, postcricoid region) and determined the invasion depth of the tumor (extension to esophagus, invasion to strip muscles and prevertebral muscles) and performed the T staging of the primary tumor using the two sets of images blindly. The accuracy of T staging was calculated, using pathological T staging (surgical cases) or clinical T staging (non-surgical cases) as the gold standard. The image scores of the two sets of images were compared using Wilcoxon rank sum test. McNemar-Bowker test was used to compare the accuracy of T staging using the two sets of images.Results:The overall image scores of the 45 keV VMI and standard linearly blended image from the senior radiologist were 3.5 (3, 4) and 3 (2, 3) respectively ( Z=-7.03, P<0.001), and the scores from the junior radiologist were 3 (3, 4) and 2 (2, 3) ( Z=-6.93, P<0.001). The scores of the 45 keV VMI were significantly higher than those of the standard linearly blended image in visualizing tumors in the piriform fossa, posterior pharyngeal wall, and postcricoid region, as well as in detecting invasion to the strip muscles ( P<0.05). There was no significant difference in the scores of the two sets of images in determining whether the tumor extended to esophagus or invaded prevertebral muscles ( P>0.05). Referring to pathological and clinical T stage, the accuracy of T staging determined by the 45 keV VMI and standard linearly blended image was 87.9% (51/58) and 81.0% (47/58) respectively, and the difference was not significant (χ 2=3.33, P=0.189). Conclusions:The 45 keV VMI is superior to the standard linearly blended image in visualizing tumors and detecting invasion to the strip muscles of hypopharynx squamous cell carcinoma. However, the accuracy of determining T staging using 45 keV VMI is slightly improved than that of standard linearly blended image, and the difference is not statistically significant. In determining whether the tumor extends to esophagus or invades prevertebral muscles, 45 keV VMI shows no significant advantage over standard linearly blended image.

Computer Vision in Medical Imaging and its Impact on the Rare Musculoskeletal Diseases / 罕见病研究

There are over 6000 rare diseases in the world, affecting more than 300 million people. Early and precise diagnosis of rare diseases has always been the goal in clinical medicine. Emerging computer vision technology now greatly enhance medicine and healthcare and shows the potential in assisting the diagnosis and treatment for rare diseases. The technology can be a useful tool for extracting disease-relevant patterns from medical imaging. However, the effectiveness of its application depends on the complexity of the medical cases. In this paper, we summarize the challenges and emerging solution for the application of computer vision in diagnosis, rehabilitation as well as management of rare musculoskeletal diseases.

Research progress on wide-field multimodal image of peripheral retinal degeneration / 国际眼科杂志(Guoji Yanke Zazhi)

Peripheral retinal degeneration is a typical lesion in ophthalmic clinical practice. Each type of degeneration affects distinct retinal layers and may lead to sight-threatening complications. Due to its specific location, where current ophthalmic imaging technologies have difficulties observing, the pathogenesis remains unclear despite previous works. This review outlines the characteristics of peripheral retinal degeneration by different wide-field imaging technologies, including ultra-wide field fundus imaging, wide field spectral domain optical coherence tomography, optical coherence tomography angiography and fundus fluorescein angiography, as well as new perspectives on their pathogenesis or pathological characteristics so as to provide new ideas for clinical diagnosis and management. Due to the small size of sample and the lack of prospective and long-term observation of multimodal imaging, it is still impossible to comprehensively evaluate the progression and risk of different types of degeneration. Therefore, it is expected that wide-field multimodal imaging technology will be more widely applied to study the mechanism of peripheral retinal degeneration and guide the clinical practice options.

Progress in TN staging of rectal cancer based on multimodal magnetic resonance imaging / 国际生物医学工程杂志

Rectal cancer is one of the most common gastrointestinal malignancies in China. Accurate and reasonable assessment of the preoperative staging of rectal cancer can significantly enhance treatment outcomes and improve patient prognosis. Magnetic resonance imaging is the technique of choice for local staging of rectal cancer and has significant advantages in the diagnosis of rectal primary tumors (T) and peri-intestinal lymph nodes (N). In this review paper, the research ideas and progress of traditional radiomics and deep learning methods for preoperative TN staging prediction of rectal cancer were reviewed around multimodal magnetic resonance images, with the aim of providing new ideas for realizing fully automated TN staging algorithms for rectal cancer.

Research Progress of Deep Learning in Bladder Cancer Pathology / 肿瘤防治研究

The incidence of bladder cancer is increasing annually, and the gold standard for its diagnosis relies on histopathological biopsy. Whole-slide digitization technology can produce thousands of high-resolution captured pathological images and has greatly promoted the development of digital pathology. Deep learning, as a new method of artificial intelligence, has achieved remarkable results in the analysis of pathological images for tumor diagnosis, molecular typing, and prediction of prognosis and recurrence of bladder cancer. Traditional pathology relies heavily on the professional level and experience of pathologists; as such, it is highly subjective and has poor reproducibility. Deep learning can automatically extract image features. It can also improve diagnostic efficiency and repeatability and reduce missed and misdiagnosed rates when used to assist pathologists in making decisions. This technology cannot only alleviate the pressure of the current shortage of skilled workforce and uneven medical resources but also promote the development of precision medicine. This article reviews the latest research progress and prospects of deep learning in pathological image analysis of bladder cancer.

Research on classification method of multimodal magnetic resonance images of Alzheimer's disease based on generalized convolutional neural networks / 生物医学工程学杂志

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer's disease.

A meta-learning based method for segmentation of few-shot magnetic resonance images / 生物医学工程学杂志

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.

Imagenología digital como recurso didáctico en el aprendizaje significativo de las Ciencias Médicas

RESUMEN La especialidad de Imagenología comprende áreas del conocimiento médico que utilizan diferentes tecnologías en creciente desarrollo y métodos que exteriorizan partes del cuerpo humano, por tal motivo, educar a través del diagnóstico por imágenes informatizadas constituye un desafío en la actualidad. El presente artículo plantea describir las características principales de los medios de enseñanza y el interés que brinda especialmente la imagen radiológica digital como recurso didáctico. Se recopiló y revisó bibliografía de mayor novedad y profundidad en el tratamiento del tema. La estrategia de búsqueda adoptada fue la utilización de las palabras clave o descriptores en español e inglés. En la Universidad de Ciencias Médicas las tecnologías modernas traen diversidad de herramientas didácticas en el marco de escenarios docentes que impulsan y motivan el desarrollo rápido de habilidades perceptivas, la utilización cada vez más frecuente de imágenes digitales como medio de enseñanza la convierten en un recurso muy utilizado actualmente que exige habilidades y manejo eficaz. Las imágenes digitales con fines docentes son una alternativa importante, pues reflejan la modernidad e incorporan el conocimiento, debido a que se transforman en un nuevo recurso destinado a comunicar.

ABSTRACT The specialty of Imaging includes areas of medical knowledge that use different technologies in growing development and methods that externalize parts of the human body, for this reason, educating through computerized imaging diagnosis is a challenge today. This article proposes to describe the main characteristics of the teaching aids and the interest that the digital radiological image offers especially as a didactic resource. Bibliography of greater novelty and depth in the treatment of the subject was collected and reviewed. The search strategy adopted was the use of keywords or descriptors in Spanish and English. In the University of Medical Sciences, modern technologies bring diversity of didactic tools within the framework of teaching scenarios that promote and motivate the rapid development of perceptual skills, the increasingly frequent use of digital images as a means of teaching make it a very useful resource. Currently used that requires skills and effective handling. Digital images for teaching purposes are an important alternative, as they reflect modernity and incorporate knowledge, because they become a new resource for communicating.

Compression of images of dermatological manifestations of paucisymptomatic COVID-19 patients through periodic principal components / Compresión de imágenes de manifestaciones dermatológicas de pacientes paucisintomáticos de COVID-19 mediante componentes principales periódicos

Introduction: The management of medical images has been gaining followers based on the advantages it offers for the diagnosis of diseases, which, like COVID-19, present with clinical manifestations that can be captured in the form of images. Objective: Take advantage of the quasi-periodicity of the principal components (PCs) in the decomposition into PCs of medical images, which represent dermatological manifestations in paucisymptomatic patients of COVID-19. Methods: Here, a set of photos was taken of one of the most frequent patterns in COVID-19, the maculopapular pattern, characterized by an erythmatopapular rash, and compression of one of the medical images was performed. Said compression was carried out in different ways: (1) using two PCs, (2) using both a periodic PC and a non-periodic PC, (3) using two periodic PCs, (4) using a single PC, and (5) using a single periodic PC. Result: The results of this research proved that it is possible to work with acceptable reconstructions of compressed images in the field of dermatology, without losing the quality and characteristics that allow to reach a correct diagnosis. In addition, this achievement permits to correctly classify many diseases without fear of being wrong. Conclusion: With the method presented, the use of a robust medical image compression technique that could be very useful in the field of health is proposed. The images allow the diagnosis of diseases such as COVID-19 in paucisymptomatic patients, understanding them allows minimizing their weight without losing quality, which facilitates their use and storage.

Introducción: El empleo de imágenes médicas en el diagnóstico de enfermedades ha ido ganando adeptos. Un ejemplo es la COVID-19 que cursa con manifestaciones clínicas dermatológicas. Objetivo: Aprovechar la cuasi-periodicidad de los componentes principales de la descomposición en imágenes médicas, que representan manifestaciones dermatológicas en pacientes paucisintomáticos de COVID-19. Métodos: Se tomó un conjunto de fotografías de uno de los patrones más frecuentes en la COVID-19 (el patrón maculopapular), caracterizado por un exantema eritematopapular, y se realizó la compresión de una de las imágenes médicas. Dicha compresión se realizó de diferentes formas: (1) usando dos componentes principales, (2) usando tanto un componente principal periódico como no periódico, (3) dos componentes principales periódicos, (4) un único componente principal, y (5) un solo componente principal periódico. Resultados: Es posible trabajar con reconstrucciones aceptables de imágenes comprimidas en el campo de la dermatología, sin perder la calidad y características que permitan llegar a un diagnóstico correcto. Además, este logro permite clasificar correctamente muchas enfermedades sin miedo a equivocarse. Conclusiones: Con el método presentado se propone el uso de una técnica robusta de compresión de imágenes médicas que podría ser de gran utilidad en el campo de la salud. Las imágenes permiten el diagnóstico de enfermedades como la COVID-19 en pacientes paucisintomáticos, con cuya compresión se minimiza su peso sin perder la calidad, lo que facilita su uso y almacenamiento.

Diverticulitis apendicular, reporte de un caso

Objetivo: Presentar un caso de diverticulitis apendicular y compararlo con la literatura actual. Material y M étodo: Registro clínico de un paciente que ingresa a urgencias del Hospital Padre Hurtado, incluyendo cuadro clínico, imagenología, manejo quirúrgico y anatomía patológica. Resultados: Paciente se presenta con cuadro de dolor abdominal atípico, con imagen sugerente de apendicitis diverticular. En pabellón se logra completar apendicectomía laparoscópica con buena evolución posterior. Al estudio patológico se confirman características histológicas de diverticulitis perforada apendicular. Discusión: Se presenta un cuadro clínico que se condice con lo descrito en la literatura actual, aportando imágenes características, tanto de radiología como histopatología. Conclusión: Debido a su mayor riesgo de perforación y mortalidad, la diverticulitis apendicular es una patología que debe considerarse en los diagnósticos diferenciales de dolores abdominales atípicos, en hombres mayores de 30 años, especialmente con los hallazgos imagenológicos característicos.

Objective: To present a clinical case of appendiceal diverticulitis and compare it to contemporary literature. Material and Method: Clinical record of a patient who attends the emergency service of Hospital Padre Hurtado, including clinical presentation, image studies, surgical management and histopathology studies. Results: A patient presents with atypical abdominal pain, image studies suggest appendiceal diverticulitis. Laparoscopic appendectomy was performed with optimal postoperative results. Pathological biopsy studies confirm histological characteristics of a perforated appendiceal diverticulitis. Discussion: A clinical case is presented, which correlates well with contemporary literature of the subject. We provide characteristic image and histopathological studies. Conclusion: Due to its higher perforation rate and mortality, appendiceal diverticulitis is a pathology which must be considered in the differential diagnosis of atypical abdominal pain, in males over 30 years old, especially with characteristic image studies.

Comparison of Accuracy of Color Spaces in Cell Features Classification in Images of Leukemia types ALL and MM / Comparación de Precisión de Espacios de Color en la Clasificación de Características de Células en Imágenes de Leucemia tipos ALL y MM

ABSTRACT This study presents a methodology for identifying the color space that provides the best performance in an image processing application. When measurements are performed without selecting the appropriate color model, the accuracy of the results is considerably altered. It is significant in computation, mainly when a diagnostic is based on stained cell microscopy images. This work shows how the proper selection of the color model provides better characterization in two types of cancer, acute lymphoid leukemia, and multiple myeloma. The methodology uses images from a public database. First, the nuclei are segmented, and then statistical moments are calculated for class identification. After, a principal component analysis is performed to reduce the extracted features and identify the most significant ones. At last, the predictive model is evaluated using the k-nearest neighbor algorithm and a confusion matrix. For the images used, the results showed that the CIE L*a*b color space best characterized the analyzed cancer types with an average accuracy of 95.52%. With an accuracy of 91.81%, RGB and CMY spaces followed. HSI and HSV spaces had an accuracy of 87.86% and 89.39%, respectively, and the worst performer was grayscale with an accuracy of 55.56%.

RESUMEN Este estudio presenta una metodología para identificar el espacio de color que proporciona el mejor rendimiento en una aplicación de procesamiento de imágenes. Cuando las mediciones se realizan sin seleccionar el modelo de color adecuado, la precisión de los resultados se altera considerablemente. Esto es significativo en el procesamiento, principalmente cuando el diagnóstico se basa en imágenes de microscopía de células teñidas. Este trabajo muestra cómo la selección adecuada del modelo de color proporciona una mejor caracterización en dos tipos de cáncer, la leucemia linfoide aguda y el mieloma múltiple. La metodología utiliza imágenes de una base de datos pública. Primero, se segmentan los núcleos y luego se calculan los momentos estadísticos para la identificación de clases. Posteriormente, se realiza un análisis de componentes principales para reducir las características extraídas e identificar las más significativas. Por último, el modelo predictivo se evalúa utilizando el algoritmo k-vecinos más cercanos y una matriz de confusión. Para las imágenes utilizadas, los resultados mostraron que el espacio de color CIE L*a*b caracterizó mejor los tipos de cáncer analizados con una precisión promedio del 95,52%. Con una precisión del 91,81%, siguieron los espacios RGB y CMY. Los espacios HSI y HSV tuvieron una precisión del 87,86% y el 89,39%, respectivamente, y el peor desempeño fue la escala de grises con una precisión del 55,56%.

Retinal Lesion Segmentation Using Transfer Learning with an Encoder-Decoder CNN / Segmentación de Lesiones en la Retina Usando Transferencia de Conocimiento con CNN Encoder-Decoder

ABSTRACT Deep learning (DL) techniques achieve high performance in the detection of illnesses in retina images, but the majority of models are trained with different databases for solving one specific task. Consequently, there are currently no solutions that can be used for the detection/segmentation of a variety of illnesses in the retina in a single model. This research uses Transfer Learning (TL) to take advantage of previous knowledge generated during model training of illness detection to segment lesions with encoder-decoder Convolutional Neural Networks (CNN), where the encoders are classical models like VGG-16 and ResNet50 or variants with attention modules. This shows that it is possible to use a general methodology using a single fundus image database for the detection/segmentation of a variety of retinal diseases achieving state-of-the-art results. This model could be in practice more valuable since it can be trained with a more realistic database containing a broad spectrum of diseases to detect/segment illnesses without sacrificing performance. TL can help achieve fast convergence if the samples in the main task (Classification) and sub-tasks (Segmentation) are similar. If this requirement is not fulfilled, the parameters start from scratch.

RESUMEN Las técnicas de Deep Learning (DL) han demostrado un buen desempeño en la detección de anomalías en imágenes de retina, pero la mayoría de los modelos son entrenados en diferentes bases de datos para resolver una tarea en específico. Como consecuencia, actualmente no se cuenta con modelos que se puedan usar para la detección/segmentación de varias lesiones o anomalías con un solo modelo. En este artículo, se utiliza Transfer Learning (TL) con la cual se aprovecha el conocimiento adquirido para determinar si una imagen de retina tiene o no una lesión. Con este conocimiento se segmenta la imagen utilizando una red neuronal convolucional (CNN), donde los encoders o extractores de características son modelos clásicos como VGG-16 y ResNet50 o variantes con módulos de atención. Se demuestra así, que es posible utilizar una metodología general con bases de datos de retina para la detección/ segmentación de lesiones en la retina alcanzando resultados como los que se muestran en el estado del arte. Este modelo puede ser entrenado con bases de datos más reales que contengan una gama de enfermedades para detectar/ segmentar sin sacrificar rendimiento. TL puede ayudar a conseguir una convergencia rápida del modelo si la base de datos principal (Clasificación) se parece a la base de datos de las tareas secundarias (Segmentación), si esto no se cumple los parámetros básicamente comienzan a ajustarse desde cero.

Reseña bibliográfica: glosario ilustrado de dermatología y dermatopatología, segunda edición / Bibliographic review: Illustrated Glossary of Dermatology and Dermatopathology, Second Edition

Resumen La segunda edición del Glosario ilustrado de dermatología y dermatopatología es un texto escrito por el médico especialista en Dermatopatología, Gerzaín Rodriguez Toro. El doctor Rodríguez fue docente de la Universidad Nacional de Colombia, en Bogotá, donde llegó a ser profesor titular y maestro universitario. Actualmente es profesor destacado de la Facultad de Medicina de la Universidad de La Sabana. Este texto constituye una sucesión de la labor que ha realizado el doctor Gerzaín durante décadas en el campo de la docencia médica, mediante sus múltiples publicaciones en el ámbito de la Dermatopatología.

Abstract The second edition of the Illustrated Glossary of Dermatology and Dermatopathology is a text written by the specialist in Dermatopathology, Gerzaín Rodriguez Toro. Dr. Rodríguez was a professor at the National University of Colombia, in Bogotá, where he became a full professor and university teacher. He is currently a prominent professor at the Faculty of Medicine of the University of La Sabana. This text constitutes a succession of the work that Dr. Gerzaín has carried out for decades in the field of medical teaching, through his multiple publications in the field of Dermatopathology.

Eye MG 3D Application - A comprehensive ocular anatomy and pathophysiology 3D atlas with real-time true color confocal images to enhance ophthalmology education and e-Counseling

Concepts pertaining to ophthalmology have lots of theoretical frameworks. Neophyte residents and novice surgeons may have to mentally visualize these concepts during the initial days of training. Only a powerful cognitive tool such as a three?dimensional (3D) eyeball model, with real?time TrueColor confocal images (and not animated images or models), can fill in these intellective mental gaps. Giving the users (i.e., residents and students) the power to choose and visualize various parts of the eye, with multiple magnitudes of zoom, is mandatory for optimal e?learning. To make ophthalmic concept learning better, we have developed a 3D app Eye MG 3D (patent pending) comprising ocular anatomy and pathophysiological 3D models, built on an advanced interactive 3D touch interface, by using patient抯 real?time confocal images to serve as a new?age pedagogical tool and e?counseling. According to our knowledge, there are no applications to date that incorporate real?time high?resolution multimodal confocal fundus images and photoreal visuals for interactive and immersive 3D learning.