OBJECTIVE. The aim of our article is to give an overview of the current and future possibilities of real-time image fusion involving ultrasound. We present a review of the existing English-language peer-reviewed literature assessing this technique, which covers technical solutions (for ultrasound and endoscopic ultrasound), image fusion in several anatomic regions, and electromagnetic needle tracking. CONCLUSION. The recent progress of real-time ultrasound in image fusion may provide several new possibilities, including diagnosis, treatment, and follow-up of oncologic patients.

Confocal laser endomicroscopy (CLE) is becoming a popular method for optical biopsy of digestive mucosa for both diagnostic and therapeutic procedures. Computer aided diagnosis of CLE images, using image processing and fractal analysis can be used to quantify the histological structures in the CLE generated images. The aim of this study is to develop an automatic diagnosis algorithm of colorectal cancer (CRC), based on fractal analysis and neural network modeling of the CLE-generated colon mucosa images. We retrospectively analyzed a series of 1035 artifact-free endomicroscopy images, obtained during CLE examinations from normal mucosa (356 images) and tumor regions (679 images). The images were processed using a computer aided diagnosis (CAD) medical imaging system in order to obtain an automatic diagnosis. The CAD application includes image reading and processing functions, a module for fractal analysis, grey-level co-occurrence matrix (GLCM) computation module, and a feature identification module based on the Marching Squares and linear interpolation methods. A two-layer neural network was trained to automatically interpret the imaging data and diagnose the pathological samples based on the fractal dimension and the characteristic features of the biological tissues. Normal colon mucosa is characterized by regular polyhedral crypt structures whereas malignant colon mucosa is characterized by irregular and interrupted crypts, which can be diagnosed by CAD. For this purpose, seven geometric parameters were defined for each image: fractal dimension, lacunarity, contrast correlation, energy, homogeneity, and feature number. Of the seven parameters only contrast, homogeneity and feature number were significantly different between normal and cancer samples. Next, a two-layer feed forward neural network was used to train and automatically diagnose the malignant samples, based on the seven parameters tested. The neural network operations were cross-entropy with the results: training: 0.53, validation: 1.17, testing: 1.17, and percent error, resulting: training: 16.14, validation: 17.42, testing: 15.48. The diagnosis accuracy error was 15.5%. Computed aided diagnosis via fractal analysis of glandular structures can complement the traditional histological and minimally invasive imaging methods. A larger dataset from colorectal and other pathologies should be used to further validate the diagnostic power of the method.

Aim: In this paper we proposed different architectures of convolutional neural network (CNN) to classify fatty liver disease in images using only pixels and diagnosis labels as input. We trained and validated our models using a dataset of 629 images consisting of 2 types of liver images, normal and liver steatosis. Material and methods: We assessed two pre-trained models of convolutional neural networks, Inception-v3 and VGG-16 using fine-tuning. Both models were pre-trained on ImageNet dataset to extract features from B-mode ultrasound liver images. The results obtained through these methods were compared for selecting the predictive model with the best performance metrics. We trained the two models using a dataset of 262 images of liver steatosis and 234 images of normal liver. We assessed the models using a dataset of 70 liver steatosis im-ages and 63 normal liver images. Results. The proposed model that used Inception v3 obtained a 93.23% test accuracy with a sensitivity of 89.9%% and a precision of 96.6%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.93. The other proposed model that used VGG-16, obtained a 90.77% test accuracy with a sensitivity of 88.9% and a precision of 92.85%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.91. Conclusion. The deep learning algorithms that we proposed to detect steatosis and classify the images in normal and fatty liver images, yields an excellent test performance of over 90%. However, future larger studies are required in order to establish how these algorithms can be implemented in a clinical setting.

Purpose To evaluate the accuracy of a 3-dimensional (3D) navigation system using electromagnetically tracked tools to explore its potential in patients. Methods The 3D navigation accuracy was quantified on a phantom and in a porcine model using the same setup and vascular interventional suite. A box-shaped phantom with 16 markers was scanned in 5 different positions using computed tomography (CT). The 3D navigation system registered each CT volume in the magnetic field. A tracked needle was pointed at the physical markers, and the spatial distances between the tracked needle positions and the markers were calculated. Contrast-enhanced CT images were acquired from 6 swine. The 3D navigation system registered each CT volume in the magnetic field. An electromagnetically tracked guidewire and catheter were visualized in the 3D image and navigated to 4 specified targets. At each target, the spatial distance between the tracked guidewire tip position and the actual position, verified by a CT control, was calculated. Results The mean accuracy on the phantom was 1.28±0.53 mm, and 90% of the measured distances were ≤1.90 mm. The mean accuracy in swine was 4.18±1.76 mm, and 90% of the measured distances were ≤5.73 mm. Conclusion This 3D navigation system demonstrates good ex vivo accuracy and is sufficiently accurate in vivo to explore its potential for improved endovascular navigation.

Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.