RESUMEN
To visualise the tumours inside the body on a screen, a long and thin tube is inserted with a light source and a camera at the tip to obtain video frames inside organs in endoscopy. However, multiple artefacts exist in these video frames that cause difficulty during the diagnosis of cancers. In this research, deep learning was applied to detect eight kinds of artefacts: specularity, bubbles, saturation, contrast, blood, instrument, blur, and imaging artefacts. Based on transfer learning with pre-trained parameters and fine-tuning, two state-of-the-art methods were applied for detection: faster region-based convolutional neural networks (Faster R-CNN) and EfficientDet. Experiments were implemented on the grand challenge dataset, Endoscopy Artefact Detection and Segmentation (EAD2020). To validate our approach in this study, we used phase I of 2,200 frames and phase II of 331 frames in the original training dataset with ground-truth annotations as training and testing dataset, respectively. Among the tested methods, EfficientDet-D2 achieves a score of 0.2008 (mAPd[Formula: see text]0.6+mIoUd[Formula: see text]0.4) on the dataset that is better than three other baselines: Faster-RCNN, YOLOv3, and RetinaNet, and competitive to the best non-baseline result scored 0.25123 on the leaderboard although our testing was on phase II of 331 frames instead of the original 200 testing frames. Without extra improvement techniques beyond basic neural networks such as test-time augmentation, we showed that a simple baseline could achieve state-of-the-art performance in detecting artefacts in endoscopy. In conclusion, we proposed the combination of EfficientDet-D2 with suitable data augmentation and pre-trained parameters during fine-tuning training to detect the artefacts in endoscopy.
Asunto(s)
Artefactos , Redes Neurales de la Computación , Humanos , Endoscopía , Aprendizaje AutomáticoRESUMEN
Detecting various types of cells in and around the tumor matrix holds a special significance in characterizing the tumor micro-environment for cancer prognostication and research. Automating the tasks of detecting, segmenting, and classifying nuclei can free up the pathologists' time for higher value tasks and reduce errors due to fatigue and subjectivity. To encourage the computer vision research community to develop and test algorithms for these tasks, we prepared a large and diverse dataset of nucleus boundary annotations and class labels. The dataset has over 46,000 nuclei from 37 hospitals, 71 patients, four organs, and four nucleus types. We also organized a challenge around this dataset as a satellite event at the International Symposium on Biomedical Imaging (ISBI) in April 2020. The challenge saw a wide participation from across the world, and the top methods were able to match inter-human concordance for the challenge metric. In this paper, we summarize the dataset and the key findings of the challenge, including the commonalities and differences between the methods developed by various participants. We have released the MoNuSAC2020 dataset to the public.
Asunto(s)
Algoritmos , Núcleo Celular , Humanos , Procesamiento de Imagen Asistido por ComputadorRESUMEN
This study was to investigate whether various region-of-interest (ROI) methods for measuring dopamine transporter (DAT) availabilities by single photon emission computed tomography (SPECT) are statistically different, whether results of medical research are thereby influenced, and causes of these differences. Eighty-four healthy adults with (99m)Tc-TRODAT-1 SPECT and magnetic resonance imaging (MRI) scans were included. Six major analysis approaches were compared: (1) ROI drawn on the coregistered MRI; (2) ROIs drawn on the SPECT images; (3) standard ROI templates; (4) threshold-ROIs; (5) atlas-based mappings with coregistered MRI; and (6) atlas-based mappings with SPECT images. Using the atlas-based approaches we assessed the influence of striatum ROIs by slice-wise and voxel-wise comparisons. In (5) and (6), three partial-volume correction (PVC) methods were also explored. The results showed that DAT availabilities obtained from different methods were closely related but quite different and leaded to significant differences in determining the declines of DAT availability per decade (range: 5.95-11.99%). Use of 3D whole-striatum or more transverse slices could avoid biases in measuring the striatal DAT declines per decade. Atlas-based methods with PVC may be the preferable methods for medical research.
Asunto(s)
Proteínas de Transporte de Dopamina a través de la Membrana Plasmática/análisis , Tomografía Computarizada de Emisión de Fotón Único/métodos , Adulto , Femenino , Humanos , Imagen por Resonancia Magnética , Masculino , Persona de Mediana Edad , Tecnecio , Adulto JovenRESUMEN
Metformin, a widely used antidiabetic drug, has numerous effects on human metabolism. Based on emerging cellular, animal, and epidemiological studies, we hypothesized that metformin leads to cerebral metabolic changes in diabetic patients. To explore metabolism-influenced foci of brain, we used 2-deoxy-2-[(18)F]fluoro-D-glucose (FDG) positron emission tomography for type 2 diabetic patients taking metformin (MET, n = 18), withdrawing from metformin (wdMET, n = 13), and not taking metformin (noMET, n = 9). Compared with the noMET group, statistical parametric mapping showed that the MET group had clusters with significantly higher metabolism in right temporal, right frontal, and left occipital lobe white matter and lower metabolism in the left parahippocampal gyrus, left fusiform gyrus, and ventromedial prefrontal cortex. In volume of interest (VOI-) based group comparisons, the normalized FDG uptake values of both hypermetabolic and hypometabolic clusters were significantly different between groups. The VOI-based correlation analysis across the MET and wdMET groups showed a significant negative correlation between normalized FDG uptake values of hypermetabolic clusters and metformin withdrawal durations and a positive but nonsignificant correlation in the turn of hypometabolic clusters. Conclusively, metformin affects cerebral metabolism in some white matter and semantic memory related sites in patients with type 2 diabetes.
Asunto(s)
Encéfalo/metabolismo , Diabetes Mellitus Tipo 2/tratamiento farmacológico , Hipoglucemiantes/uso terapéutico , Metformina/uso terapéutico , Anciano , Encéfalo/patología , Diabetes Mellitus Tipo 2/metabolismo , Diabetes Mellitus Tipo 2/patología , Femenino , Humanos , Imagen por Resonancia Magnética , Masculino , Persona de Mediana EdadRESUMEN
Brown adipose tissue (BAT) is a highly specialized thermogenic tissue and has profound effects on body weight, energy balance, and glucose metabolism. Body temperature regulation depends on the integrated activities of the autonomic nervous system, which is centered predominantly in the hypothalamus. The purpose of this study was to explore the interaction of brain and the activation of BAT by analyzing differences in brain metabolism between patients with and without activated BAT. Fluorodeoxyglucose (FDG) with positron emission tomography/computer tomography (PET/CT) was used to determine the activation of BAT and brain metabolism. After reviewing FDG PET/CT scans, we retrospectively collected 42 patients, 21 with activated BAT and 21 matched controls without activated BAT. We used the method of defining regions of interest (ROI) to examine differences in metabolism between their hypothalami and voxel (volumetric pixel)-based statistical parametric mapping to analyze the whole brain. Compared with controls, patients with activated BAT had a significant hypermetabolic area in the right inferior parietal lobule (Brodmann area 40) and significant hypometabolic areas in the left insula (Brodmann area 13) and right cerebellum; however, there were no metabolic differences in the hypothalamic regions. Our findings illustrate the close relationship of cold temperature exposure-triggered hypermetabolism in the right inferior parietal lobule and activated BAT. They also support the hypotheses that the insula and cerebellum regulate autonomic functions, which are important for controlling BAT thermogenesis within the central pathways.
Asunto(s)
Tejido Adiposo Pardo/diagnóstico por imagen , Encéfalo/diagnóstico por imagen , Encéfalo/metabolismo , Adulto , Índice de Masa Corporal , Encéfalo/patología , Femenino , Fluorodesoxiglucosa F18 , Lateralidad Funcional , Humanos , Hipotálamo/diagnóstico por imagen , Hipotálamo/patología , Imagen por Resonancia Magnética/métodos , Masculino , Selección de Paciente , Tomografía de Emisión de Positrones/métodos , Valores de Referencia , Tomografía Computarizada por Rayos X/métodosRESUMEN
It is widely accepted and can be easily verified that any specific voxel in a class of brain single photon emission computed tomography (SPECT) volumes is of a univariate normal distribution. In this research, we conjecture that all the voxels in a class of SPECT volumes are also approximately of a multivariate normal (MVN) distribution from which in terms of the Bayes errors of statistics, an optimal classifier can be designed using quadratic discriminant functions (QDFs). However, the number of training volumes needed for deriving the covariance matrix of an MVN distribution increases quadratically with respect to the number of voxels such that practically the MVN distributions cannot be modeled. To overcome this, we selected a reduced number of voxels and put them into groups based on the P values of two-sided t tests or a greedy algorithm of discrimination between two classes of volumes. We also tried the same approach on the 3D Haar wavelet coefficients which were obtained from the discrete wavelet transform of the voxels. Experiments showed that the accuracies of QDFs, linear discriminant functions (LDFs), and support vector machines (SVMs) were not significantly different in discrimination between Alzheimer's and normal controls verifying that the proposed MVNs effectively model the discrimination information. Moreover, the proposed QDF classifier obtained satisfactory performance.
Asunto(s)
Enfermedad de Alzheimer/diagnóstico por imagen , Tomografía Computarizada de Emisión de Fotón Único/clasificación , Tomografía Computarizada de Emisión de Fotón Único/métodos , Anciano , Algoritmos , Estudios de Casos y Controles , Humanos , Análisis de OndículasRESUMEN
Tourette's syndrome, no longer considered as a rare and unusual disease, is the most severe tic disorder in children. Early differential diagnosis between Tourette's syndrome and chronic tic disorder is difficult but important because proper and early medical therapy can improve the child's condition. Brain single-photon emission computed tomography (SPECT) perfusion imaging with technetium-99m hexamethylpropylene amine oxime is a method to distinguish these two diseases. In this paper, a fuzzy system called characteristic-point-based fuzzy inference system (CPFIS) is proposed to help radiologists perform computer-aided diagnosis (CAD). The CPFIS consists of SPECT-volume processing, input-variables selection, characteristic-points (CPs) derivation, and parameter tuning of the fuzzy system. Experimental results showed that the major fuzzy rules from the obtained CPs match the major patterns of Tourette's syndrome and chronic tic disorder in perfusion imaging. If any case that was diagnosed as chronic tic by the radiologist but as Tourette's syndrome by the CPFIS was taken as Tourette's syndrome, then the accuracy of the radiologist was increased from 87.5% (21 of 24) without the CPFIS to 91.7% (22 of 24) with the CPFIS. All 17 cases of Tourette's syndrome, which is more severe than chronic tic disorder, were correctly classified. Although the construction and application process of the proposed method is complete, more samples should be used and tested in order to design a universally effective CAD without small sample-size concerns in this research.
Asunto(s)
Algoritmos , Interpretación de Imagen Asistida por Computador/métodos , Trastornos de Tic/diagnóstico por imagen , Tomografía Computarizada de Emisión de Fotón Único/métodos , Encéfalo/diagnóstico por imagen , Niño , Preescolar , Enfermedad Crónica , Diagnóstico Diferencial , Lógica Difusa , Humanos , Lactante , Recién Nacido , Reproducibilidad de los Resultados , Sensibilidad y Especificidad , Trastornos de Tic/clasificación , Síndrome de Tourette/clasificación , Síndrome de Tourette/diagnóstico por imagenRESUMEN
Bone scintigraphy is an effective method to diagnose bone diseases such as bone tumors. In the scintigraphic images, bone abnormalities are widely scattered on the whole body. Conventionally, radiologists visually check the whole-body images and find the distributed abnormalities based on their expertise. This manual process is time-consuming and it is not unusual to miss some abnormalities. In this paper, a computer-aided diagnosis (CAD) system is proposed to assist radiologists in the diagnosis of bone scintigraphy. The system will provide warning marks and abnormal scores on some locations of the images to direct radiologists' attention toward these locations. A fuzzy system called characteristic-point-based fuzzy inference system (CPFIS) is employed to implement the diagnosis system and three minimizations are used to systematically train the CPFIS. Asymmetry and brightness are chosen as the two inputs to the CPFIS according to radiologists' knowledge. The resulting CAD system is of a small-sized rule base such that the resulting fuzzy rules can be not only easily understood by radiologists, but also matched to and compared with their expert knowledge. The prototype CAD system was tested on 82 abnormal images and 27 normal images. We employed free-response receiver operating characteristics method with the mean number of false positives (FPs) and the sensitivity as performance indexes to evaluate the proposed system. The sensitivity is 91.5% (227 of 248) and the mean number of FPs is 37.3 per image. The high sensitivity and moderate numbers of FP marks per image shows that the proposed method can provide an effective second-reader information to radiologists in the diagnosis of bone scintigraphy.