RESUMEN

BACKGROUND: Although accurate preoperative diagnosis of lymph node metastasis is essential for optimizing treatment strategies for low rectal cancer, the accuracy of present diagnostic modalities has room for improvement. OBJECTIVE: The study aimed to establish a high-precision diagnostic method for lymph node metastasis of low rectal cancer using artificial intelligence. DESIGN: A retrospective observational study. SETTINGS: A single cancer center and a college of engineering in Japan. PATIENTS: Patients with low rectal adenocarcinoma who underwent proctectomy, bilateral lateral pelvic lymph node dissection, and contrast-enhanced multidetector row CT (slice ≤1 mm) between July 2015 and August 2021 were included in the present study. All pelvic lymph nodes from the aortic bifurcation to the upper edge of the anal canal were extracted, regardless of whether within or beyond the total mesenteric excision area, and pathological diagnoses were annotated for training and validation. MAIN OUTCOME MEASURES: Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. RESULTS: A total of 596 pathologically negative nodes and 43 positive nodes from 52 patients were extracted and annotated. Four diagnostic methods, with and without using super-resolution images and with and without using 3-dimensional shape data, were performed and compared. The super-resolution + 3-dimensional shape data method had the best diagnostic ability for the combination of sensitivity, negative predictive value, and accuracy (0.964, 0.966, and 0.968, respectively), whereas the super-resolution only method had the best diagnostic ability for the combination of specificity and positive predictive value (0.994 and 0.993, respectively). LIMITATIONS: Small number of patients at a single center and the lack of external validation. CONCLUSIONS: Our results enlightened the potential of artificial intelligence for the method to become another game changer in the diagnosis and treatment of low rectal cancer. See Video Abstract . DIAGNSTICO POR IMGENES CON INTELIGENCIA ARTIFICIAL MEDIANTE SUPERRESOLUCIN Y FORMA D PARA LA METSTASIS EN LOS GANGLIOS LINFTICOS DEL CNCER DE RECTO BAJO UN ESTUDIO PILOTO DE UN SOLO CENTRO: ANTECEDENTES:Aunque el diagnóstico preoperatorio preciso de metástasis en los ganglios linfáticos es esencial para optimizar las estrategias de tratamiento para el cáncer de recto bajo, la precisión de las modalidades de diagnóstico actuales tiene margen de mejora.OBJETIVO:Establecer un método de diagnóstico de alta precisión para las metástasis en los ganglios linfáticos del cáncer de recto bajo utilizando inteligencia artificial.DISEÑO:Un estudio observacional retrospectivo.AJUSTE:Un único centro oncológico y una facultad de ingeniería en Japón.PACIENTES:En el presente estudio se incluyeron pacientes con adenocarcinoma rectal bajo sometidos a proctectomía, disección bilateral de ganglios linfáticos pélvicos laterales y tomografía computarizada con múltiples detectores con contraste (corte ≤1 mm) entre julio de 2015 y agosto de 2021. Se resecaron todos los ganglios linfáticos pélvicos desde la bifurcación aórtica hasta el borde superior del canal anal, independientemente de si estaban dentro o más allá del área de escisión mesentérica total, y se registraron los diagnósticos patológicos para entrenamiento y validación.PRINCIPALES MEDIDAS DE RESULTADO:Sensibilidad, especificidad, valor predictivo positivo, valor predictivo negativo y precisión.RESULTADOS:Se extrajeron y registraron un total de 596 ganglios patológicamente negativos y 43 positivos de 52 pacientes. Se realizaron y compararon cuatro métodos de diagnóstico, con y sin imágenes de súper resolución y sin datos de imagen en 3D. El método de superresolución + datos de imagen en 3D tuvo la mejor capacidad de diagnóstico para la combinación de sensibilidad, valor predictivo negativo y precisión (0,964, 0,966 y 0,968, respectivamente), mientras que el método de súper resolución solo tuvo la mejor capacidad de diagnóstico para la combinación de especificidad y valor predictivo positivo (0,994 y 0,993, respectivamente).LIMITACIONES:Pequeño número de pacientes en un solo centro y falta de validación externa.CONCLUSIONES:Nuestros resultados iluminan el potencial de la inteligencia artificial para que el método se convierta en otro elemento de cambio en el diagnóstico y tratamiento del cáncer de recto bajo. (Traducción ---Dr. Fidel Ruiz Healy ).

Asunto(s)

Adenocarcinoma , Inteligencia Artificial , Ganglios Linfáticos , Metástasis Linfática , Neoplasias del Recto , Humanos , Neoplasias del Recto/patología , Neoplasias del Recto/diagnóstico por imagen , Metástasis Linfática/diagnóstico por imagen , Metástasis Linfática/patología , Masculino , Femenino , Proyectos Piloto , Estudios Retrospectivos , Persona de Mediana Edad , Anciano , Ganglios Linfáticos/patología , Ganglios Linfáticos/diagnóstico por imagen , Adenocarcinoma/patología , Adenocarcinoma/diagnóstico por imagen , Adenocarcinoma/diagnóstico , Adenocarcinoma/secundario , Proctectomía/métodos , Imagenología Tridimensional/métodos , Escisión del Ganglio Linfático/métodos , Tomografía Computarizada Multidetector/métodos , Valor Predictivo de las Pruebas , Sensibilidad y Especificidad , Pelvis/diagnóstico por imagen , Adulto

RESUMEN

How to obtain internal cavity features and perform image matching is a great challenge for laparoscopic 3D reconstruction. This paper proposes a method for detecting and associating vascular features based on dual-branch weighted fusion vascular structure enhancement. Our proposed method is divided into three stages, including analyzing various types of minimally invasive surgery (MIS) images and designing a universal preprocessing framework to make our method generalized. We propose a Gaussian weighted fusion vascular structure enhancement algorithm using the dual-branch Frangi measure and MFAT (multiscale fractional anisotropic tensor) to address the structural measurement differences and uneven responses between venous vessels and microvessels, providing effective structural information for vascular feature extraction. We extract vascular features through dual-circle detection based on branch point characteristics, and introduce NMS (non-maximum suppression) to reduce feature point redundancy. We also calculate the ZSSD (zero sum of squared differences) and perform feature matching on the neighboring blocks of feature points extracted from the front and back frames. The experimental results show that the proposed method has an average accuracy and repeatability score of 0.7149 and 0.5612 in the Vivo data set, respectively. By evaluating the quantity, repeatability, and accuracy of feature detection, our method has more advantages and robustness than the existing methods.

Asunto(s)

Algoritmos , Laparoscopía , Procedimientos Quirúrgicos Mínimamente Invasivos , Venas , Microvasos

RESUMEN

PURPOSE: Lymph node (LN) detection is a crucial step that complements the diagnosis and treatments involved during cancer investigations. However, the low-contrast structures in the CT scan images and the nodes' varied shapes, sizes, and poses, along with their sparsely distributed locations, make the detection step challenging and lead to many false positives. The manual examination of the CT scan slices could be time-consuming, and false positives could divert the clinician's focus. To overcome these issues, our work aims at providing an automated framework for LNs detection in order to obtain more accurate detection results with low false positives. METHODS: The proposed work consists of two stages: candidate generation and false positive reduction. The first stage generates volumes of interest (VOI) of probable LN candidates using a modified U-Net with ResNet architecture to obtain high sensitivity but with the cost of increased false positives. The second-stage processes the obtained candidate LNs for false positive reduction using 3D convolutional neural network (CNN) classifier. We further present an analysis of various deep learning models while decomposing 3D VOI into different representations. RESULTS: The method is evaluated on two publicly available datasets containing CT scans of mediastinal and abdominal LNs. Our proposed approach yields sensitivities of 87% at 2.75 false positives per volume (FP/vol.) and 79% at 1.74 FP/vol. with the mediastinal and abdominal datasets, respectively. Our method presented a competitive performance in terms of sensitivity compared to the state-of-the-art methods and encountered very few false positives. CONCLUSION: We developed an automated framework for LNs detection using a modified U-Net with residual learning and 3D CNNs. The results indicate that our method could achieve high sensitivity with relatively low false positives, which helps avoid ineffective treatments.

Asunto(s)

Neoplasias , Tomografía Computarizada por Rayos X , Humanos , Tomografía Computarizada por Rayos X/métodos , Redes Neurales de la Computación , Ganglios Linfáticos/diagnóstico por imagen , Mediastino

RESUMEN

Roadway area calculation is a novel problem in remote sensing and urban planning. This paper models this problem as a two-step problem, roadway extraction, and area calculation. Roadway extraction from satellite images is a problem that has been tackled many times before. This paper proposes a method using pixel resolution to calculate the area of the roads covered in satellite images. The proposed approach uses novel U-net and Resnet architectures called U-net++ and ResNeXt. The state-of-the-art model is combined with the proposed efficient post-processing approach to improve the overlap with ground truth labels. The performance of the proposed road extraction algorithm is evaluated on the Massachusetts dataset and it is shown that the proposed approach outperforms the existing solutions which use models from the U-net family.

RESUMEN

LiDAR data contain feature information such as the height and shape of the ground target and play an important role for land classification. The effect of convolutional neural network (CNN) for feature extraction on LiDAR data is very significant, however CNN cannot resolve the spatial relationship of features adequately. The capsule network (CapsNet) can identify the spatial variations of features and is widely used in supervised learning. In this article, the CapsNet is combined with the residual network (ResNet) to design a deep network-ResCapNet for improving the accuracy of LiDAR classification. The capsule network represents the features by vectors, which can account for the direction of the features and the relative position between the features. Therefore, more detailed feature information can be extracted. ResNet protects the integrity of information by passing input information to the output directly, which can solve the problem of network degradation caused by information loss in the traditional CNN propagation process to a certain extent. Two different LiDAR data sets and several classic machine learning algorithms are used for comparative experiments. The experimental results show that ResCapNet proposed in this article `improve the performance of LiDAR classification.

RESUMEN

Light detection and ranging (LiDAR) is a frequently used technique of data acquisition and it is widely used in diverse practical applications. In recent years, deep convolutional neural networks (CNNs) have shown their effectiveness for LiDAR-derived rasterized digital surface models (LiDAR-DSM) data classification. However, many excellent CNNs have too many parameters due to depth and complexity. Meanwhile, traditional CNNs have spatial redundancy because different convolution kernels scan and store information independently. SqueezeNet replaces a part of 3 × 3 convolution kernels in CNNs with 1 × 1 convolution kernels, decomposes the original one convolution layer into two layers, and encapsulates them into a Fire module. This structure can reduce the parameters of network. Octave Convolution (OctConv) pools some feature maps firstly and stores them separately from the feature maps with the original size. It can reduce spatial redundancy by sharing information between the two groups. In this article, in order to improve the accuracy and efficiency of the network simultaneously, Fire modules of SqueezeNet are used to replace the traditional convolution layers in OctConv to form a new dual neural architecture: OctSqueezeNet. Our experiments, conducted using two well-known LiDAR datasets and several classical state-of-the-art classification methods, revealed that our proposed classification approach based on OctSqueezeNet is able to provide competitive advantages in terms of both classification accuracy and computational amount.

RESUMEN

Medical diagnosis judges the status of polyp from the size and the 3D shape of the polyp from its medical endoscope image. However the medical doctor judges the status empirically from the endoscope image and more accurate 3D shape recovery from its 2D image has been demanded to support this judgment. As a method to recover 3D shape with high speed, VBW (Vogel-Breuß-Weickert) model is proposed to recover 3D shape under the condition of point light source illumination and perspective projection. However, VBW model recovers the relative shape but there is a problem that the shape cannot be recovered with the exact size. Here, shape modification is introduced to recover the exact shape with modification from that with VBW model. RBF-NN is introduced for the mapping between input and output. Input is given as the output of gradient parameters of VBW model for the generated sphere. Output is given as the true gradient parameters of true values of the generated sphere. Learning mapping with NN can modify the gradient and the depth can be recovered according to the modified gradient parameters. Performance of the proposed approach is confirmed via computer simulation and real experiment.