Deep Learning (DL) is the most widely used image-analysis process, especially in medical image processing. Though DL has entered image processing to solve Machine Learning (ML) problems, identifying the most suitable model based on evaluation of the epochs is still an open question for scholars in the field. There are so many types of function approximators like Decision Tree, Gaussian Processes and Deep Learning, used in multi-layered Neural Networks (NNs), which should be evaluated to determine their effectiveness. Therefore, this study aimed to assess an approach based on DL techniques for modern medical imaging methods according to Magnetic Resonance Imaging (MRI) segmentation. To do so, an experiment with a random sampling approach was conducted. One hundred patient cases were used in this study for training, validation, and testing. The method used in this study was based on full automatic processing of segmentation and disease classification based on MRI images. U-Net structure was used for the segmentation process, with the use of cardiac Right Ventricular Cavity (RVC), Left Ventricular Cavity (LVC), Left Ventricular Myocardium (LVM), and information extracted from the segmentation step. With train and using random forest classifier, and Multilayer Perceptron (MLP), the task of predicting the pathologic target class was conducted. Segmentation extracted information was in the form of comprehensive features handcrafted to reflect demonstrative clinical strategies. Our study suggests 92% test accuracy for cardiac MRI image segmentation and classification. As for the MLP ensemble, and for the random forest, test accuracy was equal to 91% and 90%, respectively. This study has implications for scholars in the field of medical image processing.

Background: Safe dose escalation is highly desirable in radiotherapy for prostate cancer. Prostate displacement due to bladder filling can be significant, so improved targeting of the prostate by ultrasound imaging potentially allows for a reduction in the target margin and consequently less toxicity. This study estimates the accuracy of ultrasound for prostate and bladder volume measurements by comparing ultrasound images taken immediately before and after magnetic resonance imaging to reduce the effect of organ filling on measurement accuracy.Methods: Three patients with a wide range of prostate sizes underwent pelvic magnetic resonance imaging and ultrasound imaging. We tested the correlation between the two measurements and the differences between the ultrasound measurements before and after magnetic resonance imaging using statistical analysis.Results: Based on a total number of 18 volume measurements, a strong linear correlation was found (r=0.95), but there were no significant differences between ultrasound imaging performed before and after magnetic resonance imaging (P=0.809).Conclusion: Our results provide additional evidence that ultrasound imaging measures bladder and prostate volumes in a reproducible and accurate manner over a wide range of volumes, which enables its use with different fractions of prostate radiotherapy.

Background and Objective: Early diagnosis of Alzheimer's disease (AD) seems necessary due to the high cost of care and treatment, the uncertainty of existing therapies, as well as the worrying future of the patient. This study was conducted to AD diagnosis by MRI images using artificial intelligence methods. Methods: In this research, a computer system for early detection of AD with using machine learning algorithms is presented in the framework of computer-aided process. Conditional random field and Inception deep neural network have been adapted for brain MR images to detect AD. Since hippocampal tissue is one of the first tissues to be affected by AD, hence for the early detection of this disease, the hippocampus was located from other brain tissues firstly and then due to the extent to which this tissue is affected, the diagnosis was made. Conditional random field could accurately extract hippocampal fragments of different shapes in all three brain planes. These components serve as the basis for feature extraction by the deep network. The proposed method was tested on standard ADNI dataset images and its performance was demonstrated. The used Inception network has been trained on the huge ImageNet dataset. One of the important steps is knowledge transfer of the problem under consideration. To facilitate this, data augmentation process was applied according to the shape and structure of the hippocampus. Results: The implemented method in this research, achieved to 98. 51% accuracy for two-class classification of "Alzheimer" versus "Normal control" and achieved to 93. 41% accuracy for two-class classification of "Mild cognitive impairment" versus "Normal control", which increased by 2. 56% and 8. 41%, compared with the rival methods, respectively. Conclusion: The achieved results of this study showed that the using of artificial intelligence techniques has highly accurate in diagnosing AD according to MRI images.

Breast cancer is the most common type of cancer that affects the female population. Early detection of cancer can increase the chance of treatment and is also the most effective way to fight the disease. The development of automated methods for the detection of cancer or tumor mass has been of interest to researchers. In this paper, a method based on deep convolutional neural networks for detecting tumor area from MRI images is introduced. The proposed method is to collect MRI images along with GT images from their tumor area and expand the data to train and test the neural network. The type of learning method used in this paper is supervised learning. The algorithm is tested on the RIDER breast dataset and the results show that the proposed method performs better than other image detection methods such as clustering methods. Benefits include high quality in tumor detection and acceptable speed at runtime.

Introduction & Background: Brain MR Findings in cerebral venous thrombosis (CVT) are mass effect, hyper intense parenchyma abnormalities on T2 weighted images, and intraparenchymal hematoma. Unlike conventional MR images, diffusion weighted (DW) MR is sensitive to water diffusion, and thus can differentiate cacogenic from toxic edema. In this study, we sought to characterize parenchyma changes associated with CVT on DW images and de-termini whether this technique could differentiate resolvable injuries from permanent ones. Patients & Methods: We reviewed patient charts and T2 weighted MR images of 20 patients with CVT complicated by intraparenchymal abnormality. DW and conventional MR images were evaluated for any change in the signal intensity, and the signal intensity of the normal appearing contra lateral brain was used for comparison. Results: DW images disclosed 3 lesion types: lesions with a high diffusion that resolved, consistent with cacogenic edema; lesions with a low diffusion that persisted, consistent with cytotoxic edema in patients without seizure activity; and lesions with low diffusion that resolved in patients with seizure activity. Conclusion: The DW imaging can help to prospectively determine the severity of irreversible brain in-jury, and have clinical implications in patient man-agreement. 

The image recognition and the classification of objects according to the images are more in focus of interests, especially in medicine. A mathematical procedure allows us, not only to evaluate the amount of data per se, but also ensures that each image is processed similarly. Here in this study, we propose the power of shape analysis, in conjunction with neural networks for reducing white noise instead of searching an optimal metric, to support the user in his evaluation of MRI of renal tumors. Therapy of renal tumors in childhood bases on therapy optimizing SIOP (Society of Pediatric Oncology and Hematology) -study protocols in Europe. The most frequent tumor is the nephroblastoma. Other tumor entities in the retro peritoneum are clear cell sarcoma, renal cell carcinoma and extrarenal tumors, especially neuroblastoma. Radiological diagnosis is produced with the help of cross sectional imaging methods (computer tomography CT or Magnetic Resonance images MRI). Our research is the first mathematical approach on MRI of retroperitoneal tumors (n=108). We use MRI in 3 planes and evaluate their potential to differentiate other types of tumor by Statistical Shape Analysis. Statistical shape Analysis is a methology for analyzing shapes in the presence of randomness. It allows to study two- or more dimensional objects, summarized according to key points called landmarks, with a possible correction of size and position of the object. To get the shape of an object without information about position and size, centralization and standardization procedures are used in some metric space. This approach provides an objective methodology for classification whereas even today in many applications the decision for classifying according to the appearance seems at most intuitive.We determine the key points or three dimensional landmarks of retroperitoneal tumors in childhood by using the edges of the platonic body (C60) and test the difference between the groups (nephroblastoma versus non-nephroblastoma).

Background: Identification and precise localization of the liver surface and its segments are essential for any surgical treatment. An algorithm of accurate liver segmentation simplifies the treatment planning for different types of liver diseases. Although liver segmentation turns researcher’ s attention, it still has some challenging problems in computer-aided diagnosis. Objective: This study aimed to extract the potential liver regions by an adaptive water flow model and perform the final segmentation by the classification algorithm. Material and Methods: In this experimental study, an automatic liver segmentation algorithm was introduced. The proposed method designed the image by a transfer function based on the probability distribution function of the liver pixels to enhance the liver area. The enhanced image is then segmented using an adaptive water flow model in which the rainfall process is controlled by the liver location in the training images and the gray levels of pixels. The candidate liver segments are classified by a Multi-Layer Perception (MLP) neural network considering some texture, area, and gray level features. Results: The proposed algorithm efficiently distinguishes the liver region from its surrounding organs, resulting in perfect liver segmentation over 250 Magnetic Resonance Imaging (MRI) test images. The accuracy of 97% was obtained by quantitative evaluation over test images, which revealed the superiority of the proposed algorithm compared to some evaluated algorithms. Conclusion: Liver segmentation using an adaptive water flow algorithm and classifying the segmented area in MRI images yields more robust and reliable results in comparison with the classification of pixels.