RESUMEN
Retinopathy of prematurity (ROP) represents a vasoproliferative disease, especially in newborns and infants, which can potentially affect and damage the vision. Despite recent advances in neonatal care and medical guidelines, ROP still remains one of the leading causes of worldwide childhood blindness. The paper presents a unique dataset of 6,004 retinal images of 188 newborns, most of whom are premature infants. The dataset is accompanied by the anonymized patients' information from the ROP screening acquired at the University Hospital Ostrava, Czech Republic. Three digital retinal imaging camera systems are used in the study: Clarity RetCam 3, Natus RetCam Envision, and Phoenix ICON. The study is enriched by the software tool ReLeSeT which is aimed at automatic retinal lesion segmentation and extraction from retinal images. Consequently, this tool enables computing geometric and intensity features of retinal lesions. Also, we publish a set of pre-processing tools for feature boosting of retinal lesions and retinal blood vessels for building classification and segmentation models in ROP analysis.
Asunto(s)
Recien Nacido Prematuro , Retina , Retinopatía de la Prematuridad , Retinopatía de la Prematuridad/diagnóstico por imagen , Humanos , Recién Nacido , Retina/diagnóstico por imagen , República Checa , Procesamiento de Imagen Asistido por ComputadorRESUMEN
The paper focuses on the issue of collaborative control of a two quadrotor (Unmanned Aerial Vehicle QDR) system. In particular, two quadrotors perform the task of horizontally transporting a long payload along a predefined trajectory. A leader-follower method is used to synchronize the motion of both QDRs. Conventional PD controllers drive the motion of the leader QDR-L to follow a predefined trajectory. To control a follower QDR-F drive, in the case of indoor applications, a Position Feedback Controller approach (PFC) can be used. To control the QDR-F, the PFC system uses the position information of QDR-L and the required accurate tracking cameras. In our solution, outdoor applications are considered, and usage of the Global Positioning System (GPS) is needed. However, GPS errors can adversely affect the system's stability. The Force Feedback Controller approach (FFC) is therefore implemented to control the QDR-F motion. The FFC system assumes a rigid gripping of payload by both QDRs. The QDR-F collaborative motion is controlled using the feedback contact forces and torques acting on it due to the motion of the QDR-L. For FFC implementation, the principle of admittance control is used. The admittance controller simulates a virtual "mass-spring-damper" system and drives the motion of the QDR-F according to the contact forces. With the FFC control scheme, the follower QDR-F can be controlled without using the QDR-L positional feedback and the GPS. The contribution to the quality of payload transportation is the novelty of the article. In practice, one of the requirements may be to maintain the horizontal position of the payload. In this paper, an original solution is presented to minimize the horizontal position difference of both QDRs. A new procedure of the transfer admittance controller adaptation according to the mass of the transported payload is designed. The adaptive admittance FFC system is implemented in a Matlab-Simulink environment. The effectiveness of its trajectory tracking and horizontal stabilization functions for variations of the payload mass are demonstrated by numerical calculations.
RESUMEN
With the rapid growth of sensor networks and the enormous, fast-growing volumes of data collected from these sensors, there is a question relating to the way it will be used, and not only collected and analyzed. The data from these sensors are traditionally used for controlling and influencing the states and processes. Standard controllers are available and successfully implemented. However, with the data-driven era we are facing nowadays, there is an opportunity to use controllers, which can include much information, elusive for common controllers. Our goal is to propose a design of an intelligent controller-a conventional controller, but with a non-conventional method of designing its parameters using approaches of artificial intelligence combining fuzzy and genetics methods. Intelligent adaptation of parameters of the control system is performed using data from the sensors measured in the controlled process. All parts designed are based on non-conventional methods and are verified by simulations. The identification of the system's parameters is based on parameter optimization by means of its difference equation using genetic algorithms. The continuous monitoring of the quality control process and the design of the controller parameters are conducted using a fuzzy expert system of the Mamdani type, or the Takagi-Sugeno type. The concept of the intelligent control system is open and easily expandable.
RESUMEN
The article Medical Image Retrieval Using Vector Quantization and Fuzzy S-tree, written by Jana Nowaková, Michal Prílepok and Václav Snásel, was originally published electronically on the publisher's internet portal (currently SpringerLink) on December 15, 2016 without open access.
RESUMEN
The aim of the article is to present a novel method for fuzzy medical image retrieval (FMIR) using vector quantization (VQ) with fuzzy signatures in conjunction with fuzzy S-trees. In past times, a task of similar pictures searching was not based on searching for similar content (e.g. shapes, colour) of the pictures but on the picture name. There exist some methods for the same purpose, but there is still some space for development of more efficient methods. The proposed image retrieval system is used for finding similar images, in our case in the medical area - in mammography, in addition to the creation of the list of similar images - cases. The created list is used for assessing the nature of the finding - whether the medical finding is malignant or benign. The suggested method is compared to the method using Normalized Compression Distance (NCD) instead of fuzzy signatures and fuzzy S-tree. The method with NCD is useful for the creation of the list of similar cases for malignancy assessment, but it is not able to capture the area of interest in the image. The proposed method is going to be added to the complex decision support system to help to determine appropriate healthcare according to the experiences of similar, previous cases.
Asunto(s)
Lógica Difusa , Almacenamiento y Recuperación de la Información/métodos , Mamografía/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Algoritmos , Compresión de Datos , Sistemas de Apoyo a Decisiones Clínicas/organización & administración , HumanosRESUMEN
INTRODUCTION: The liver is the most common site of colorectal metastases (colorectal liver metastases - CLM). Surgical treatment in combination with oncological therapy is the only potentially curative method. Unfortunately, only 10-25% of patients are suitable for surgery. Traditionally, open liver resection (OLR) is usually performed. However, laparoscopic liver resection (LLR) has become popular worldwide in the last two decades. AIM: To evaluate the effectiveness and benefits of radiofrequency minor LLR of CLM in comparison with OLR. MATERIAL AND METHODS: The indication for surgery was CLM and the possibility to perform minor laparoscopic or OLR not exceeding two hepatic segments according to Couinaud's classification. RESULTS: Sixty-six minor liver resections for CLM were performed. Twenty-five (37.9%) patients underwent a laparoscopic approach and 41 (62.1%) patients underwent OLR. The mean operative time was 166.4 min for LLR and 166.8 min for OLR. Average blood loss was 132.3 ±218.0 ml during LLR and 149.5 ±277.5 ml during OLR. Length of hospital stay was 8.4 ±2.0 days for LLR and 10.5 ±5.8 days for OLR. All resections were R0. There was no case of mortality. Postoperative complications were recognized in 9 (13.6%) patients: 8 in the group of OLR patients and 1 in the LLR group. The median survival time for LLR was 70.5 months and for OLR 61.9 months. The 5-year overall survival rate was higher for LLR vs. OLR - 82.1% vs. 69.8%. The average length of disease-free interval after LLR was greater (52.2 months) in comparison with OLR (49.4%). The 5-year disease-free interval was 63.2% for LLR and 58% for OLR. CONCLUSIONS: Outcomes and oncological radicality of minor laparoscopic liver resections of CLM are comparable to outcomes of OLR.
RESUMEN
The aim of this study is to inform about the development of a new semispherical surgical instrument for the bipolar multielectrode radiofrequency liver ablation. Present tools are universal; however they have several disadvantages such as ablation of healthy tissue, numerous needle punctures, and, therefore, longer operating procedure. Our newly designed and tested semispherical surgical tool can solve some of these disadvantages. By conducting an in vivo study on a set of 12 pigs, randomly divided into two groups, we have compared efficiency of the newly developed instrument with the commonly used device. Statistical analysis showed that there were no significant differences between the groups. On average, the tested instrument RONJA had shorter ablation time in both liver lobes and reduced the total operating time. The depth of the thermal alteration was on average 4 mm larger using the newly tested instrument. The new radiofrequency method described in this study could be used in open liver surgery for the treatment of small liver malignancies (up to 2 cm) in a single application with the aim of saving healthy liver parenchyma. Further experimental studies are needed to confirm these results before clinical application of the method in the treatment of human liver malignancies.
Asunto(s)
Ablación por Catéter/instrumentación , Hígado/cirugía , Animales , Biopsia , Electrodos , Técnicas In Vitro , Hígado/patología , Sus scrofa , TermografíaRESUMEN
BACKGROUND/AIMS: After the first reported laparoscopic liver resection (LLR) twenty years ago, liver surgery still remains one of the last areas of resistance to the offensive of laparoscopy. Radiofrequency assisted laparoscopic liver resection has been recently developed technique for treatment of primary and secondary liver tumors. METHODOLOGY: Over a 5-year period, a total of 134 laparoscopic and open radiofrequency assisted operations were performed in a single institution. LLR was done in 47 patients, and open liver resection (OLR) in 87 patients. RESULTS: The study selection criteria were fulfilled by 134 patients. The mean blood loss for LLR was 68.7 mL, the difference between the groups was significant with lower median of blood loss using laparoscopy (p=0.046). The mean of length of hospital stay in LLR was 7.5 days versus 8.7 days in OLR (p=0.071). The 5-year survival rate was 67.0% after LLR and 63.8% after OLR. The 5-year disease-free survival rate was 59.4% after LLR, and 62.2% after OLR. The difference between groups was not statistically significant. CONCLUSIONS: Laparoscopic liver resection is safe and feasible procedure. The hand-assisted laparoscopic radiofrequency technique can be applied effectively for selected patients. Preliminary oncological results suggest non-inferiority of laparoscopic to open procedures.