Current Medical Imaging - Volume 16, Issue 4, 2020

Background: Various kind of medical imaging modalities are available for providing noninvasive view and for analyzing any pathological symptoms of human beings. Different noise may appear in those modalities at the time of acquisition, transmission, scanning, or at the time of storing. The removal of noises from the digital medical images without losing any inherent features is always considered a challenging task because a successful diagnosis relies on them. Numerous techniques have been proposed to fulfill this objective, and each having their own benefits and limitations. Discussion: In this comprehensive review article, more than 65 research articles are investigated to illustrate the applications of Artificial Neural Networks (ANN) in the field of biomedical image denoising. In particular, the zest of this article is to highlight the hybridized filtering model using nature-inspired algorithms and artificial neural networks for suppression of noise. Various other techniques, such as fixed filter, linear adaptive filters and gradient descent learning based neural network filter are also included. Conclusion: This article envisages how to train ANN using derivative free nature-inspired algorithms, and its performance in various medical images modalities and noise conditions.

Background: Physical characteristics including body size and configuration, are considered as one of the key influences on the optimum performance in athletes. Despite several analyzing methods for modeling the slimming estimation in terms of reduction in anthropometric indices, there are still weaknesses of these models such as being very demanding including time taken for analysis and accuracy. Objectives: This research proposes a novel approach for determining the slimming effect of a herbal composition as a natural medicine for weight loss. Methods: To build an effective prediction model, a modern hybrid approach, merging adaptivenetwork- based fuzzy inference system and particle swarm optimization (ANFIS-PSO) was constructed for prediction of changes in anthropometric indices including waist circumference, waist to hip ratio, thigh circumference and mid-upper arm circumference, on female athletes after consumption of caraway extract during ninety days clinical trial. Results: The outcomes showed that caraway extract intake was effective on lowering all anthropometric indices in female athletes after ninety days trial. The results of analysis by ANFIS-PSO was more accurate compared to SPSS. Also, the efficiency of the proposed approach was confirmed using the existing data. Conclusion: It is concluded that a development in predictive accuracy and simplification capability could be attained by hybrid adaptive neuro-fuzzy techniques as modern approaches in detecting changes in body characteristics. These developed techniques could be more useful and valid than other conventional analytical methods for clinical applications.

Background: Considering the increasing volume of text document information on Internet pages, dealing with such a tremendous amount of knowledge becomes totally complex due to its large size. Text clustering is a common optimization problem used to manage a large amount of text information into a subset of comparable and coherent clusters. Aims: This paper presents a novel local clustering technique, namely, β-hill climbing, to solve the problem of the text document clustering through modeling the β-hill climbing technique for partitioning the similar documents into the same cluster. Methods: The β parameter is the primary innovation in β-hill climbing technique. It has been introduced in order to perform a balance between local and global search. Local search methods are successfully applied to solve the problem of the text document clustering such as; k-medoid and kmean techniques. Results: Experiments were conducted on eight benchmark standard text datasets with different characteristics taken from the Laboratory of Computational Intelligence (LABIC). The results proved that the proposed β-hill climbing achieved better results in comparison with the original hill climbing technique in solving the text clustering problem. Conclusion: The performance of the text clustering is useful by adding the β operator to the hill climbing.

Background: Cuckoo Search Algorithm (CSA) was introduced by Yang and Deb in 2009. It considers as one of the most successful in various fields compared with the metaheuristic algorithms. However, random selection is used in the original CSA which means there is no high chance for the best solution to select, also, losing the diversity. Methods: In this paper, the Modified Cuckoo Search Algorithm (MCSA) is proposed to enhance the performance of CSA for unconstrained optimization problems. MCSA is focused on the default selection scheme of CSA (i.e. random selection) which is replaced with tournament selection. So, MCSA will increase the probability of better results and avoid the premature convergence. A set of benchmark functions is used to evaluate the performance of MCSA. Results: The experimental results showed that the performance of MCSA outperformed standard CSA and the existing literature methods. Conclusion: The MCSA provides the diversity by using the tournament selection scheme because it gives the opportunity to all solutions to participate in the selection process.

Background: The extension of CPU schedulers with fuzzy has been ascertained better because of its unique capability of handling imprecise information. Though, other generalized forms of fuzzy can be used which can further extend the performance of the scheduler. Objectives: This paper introduces a novel approach to design an intuitionistic fuzzy inference system for CPU scheduler. Methods: The proposed inference system is implemented with a priority scheduler. The proposed scheduler has the ability to dynamically handle the impreciseness of both priority and estimated execution time. It also makes the system adaptive based on the continuous feedback. The proposed scheduler is also capable enough to schedule the tasks according to dynamically generated priority. To demonstrate the performance of proposed scheduler, a simulation environment has been implemented and the performance of proposed scheduler is compared with the other three baseline schedulers (conventional priority scheduler, fuzzy based priority scheduler and vague based priority scheduler). Results: Proposed scheduler is also compared with the shortest job first CPU scheduler as it is known to be an optimized solution for the schedulers. Conclusion: Simulation results prove the effectiveness and efficiency of intuitionistic fuzzy based priority scheduler. Moreover, it provides optimised results as its results are comparable to the results of shortest job first.

Background: The Gaussian and impulse noises corrupt the Computed Tomography (CT) images either individually or collectively, and the conventional fixed filters do not have the potential to suppress these noise. Objectives: These spurious noises affect the inherent features of CT image awkwardly. Hence, to handle such a situation adaptive Cat Swarm Optimization based Functional Link Multilayer Perceptron (CSO-FLMLP) has been proposed in this paper to get rid of unwanted noise from the CT images. Methods: Here, the nature-inspired CSO technique which is an optimization algorithm has been employed to assist in updating the weights of FLMLP network. In this work, the cost function considered for CSO is the error between noisy and contextual pixels of reference images which need to minimize. For examining the efficiency of CSO-FLMLP filter, it is compared with the other six competitive adaptive filters. Results: The performance of proposed approach and other state-of-the-art filters are compared on the basis of performance metrics like the structural similarity index (SSIM), peak signal to noise ratio (PSNR), computational time and convergence rate. Supremacy of CSO-FLMLP among the considered adaptive filters is validated through Friedman statistical test. Conclusion: The CSO-FLMLP adaptive filter could successfully re-move the dominant Gaussian, impulse or combination of both noises from the clinical CT images.

Background: In this era of cutting edge research, though one of the ubiquitous facilities accessible to modern man is state of the art medical care yet diabetes has emerged as one of the major ailments afflicting the present generation. So the prime necessity of this age has transformed into providing cheap and sustainable medical care against such major diseases like diabetes. In layman’s terms Diabetes may be defined as a physiological condition wherein the blood glucose level is more than the prescribed level on a regular basis. Objectives: So the prime objective of this work is to provide a novel classification technique for detection of diabetes in a timely and effective manner. Methods: The proposed work comprises of four phases: In the first phase a “Localized Diabetes Dataset” has been compiled and collected from Bombay Medical Hall, Mahabir Chowk, Pyada Toli, Upper Bazar, Jharkhand, Ranchi, India. In the second phase various classification techniques namely RBF NN, MLP NN, NBs, and J48graft DT have been applied on the Localized Diabetes Dataset. In the third phase, Genetic algorithm (GA) has been utilized as an attribute selection technique through which six attributes among twelve attributes have been filtered. Lastly in the fourth phase RBF NN, MLP NN, NBs and J48graft DT has been utilized for classification on relevant attributes obtained by GA. Results: In this study, comparative analysis of outcomes obtained by with and without the use of GA for the same set of classification technique has been done w.r.t performance assessment. It has been conclusively inferred that GA is helpful in removing insignificant attributes, reducing the cost and computation time while enhancing ROC and accuracy. Conclusion: The utilized strategy may likewise be executed for other medical issues.

Background: Biomedical data is filled with continuous real values; these values in the feature set tend to create problems like underfitting, the curse of dimensionality and increase in misclassification rate because of higher variance. In response, pre-processing techniques on dataset minimizes the side effects and have shown success in maintaining the adequate accuracy. Aims: Feature selection and discretization are the two necessary preprocessing steps that were effectively employed to handle the data redundancies in the biomedical data. However, in the previous works, the absence of unified effort by integrating feature selection and discretization together in solving the data redundancy problem leads to the disjoint and fragmented field. This paper proposes a novel multi-objective based dimensionality reduction framework, which incorporates both discretization and feature reduction as an ensemble model for performing feature selection and discretization. Selection of optimal features and the categorization of discretized and non-discretized features from the feature subset is governed by the multi-objective genetic algorithm (NSGA-II). The two objectives, minimizing the error rate during the feature selection and maximizing the information gain, while discretization is considered as fitness criteria. Methods: The proposed model used wrapper-based feature selection algorithm to select the optimal features and categorized these selected features into two blocks namely discretized and nondiscretized blocks. The feature belongs to the discretized block will participate in the binary discretization while the second block features will not be discretized and used in its original form. Results: For the establishment and acceptability of the proposed ensemble model, the experiment is conducted on the fifteen medical datasets, and the metric such as accuracy, mean and standard deviation are computed for the performance evaluation of the classifiers. Conclusion: After an extensive experiment conducted on the dataset, it can be said that the proposed model improves the classification rate and outperform the base learner.

Background: This work uses genetic algorithm (GA) for optimum design of patient specific spinal implants (pedicle screw) with varying implant diameter and bone condition. The optimum pedicle screw fixation in terms of implant diameter is on the basis of minimum strain difference from intact (natural) to implantation at peri-prosthetic bone for the considered six different peri-implant positions. Methods: This design problem is expressed as an optimization problem using the desirability function, where the data generated by finite element analysis is converted into an artificial neural network (ANN) model. The finite element model is generated from CT scan data. Thereafter all the ANN predictions of the microstrain in six positions are converted to unitless desirability value varying between 0 and 1, which is then combined to form the composite desirability. Maximization of the composite desirability is done using GA where composite desirability should be made to go up as close as possible to 1. If the composite desirability is 1, then all ‘strain difference values in 6 positions’ are 0. Results: The optimum solutions obtained can easily be used for making patient-specific spinal implants.

Background: Medical image authentication is an important area which attempts to establish ownership authentication and data authentication of medical images. Aims: In this paper, we propose a new reversible watermarking scheme based on a novel half difference expansion technique for medical image forensics. Methods: Conventional difference expansion based reversible watermarking scheme generates watermarked images with less visual quality, and the embedding rate was considerably less due to the high probability of overflow or underflow. In the proposed scheme, the quality of the watermarked image has been improved by modifying the traditional difference expansion based watermarking scheme, half of the difference between two pixels will be expanded during watermarking. The modification of pixels during watermarking is limited by expanding half of the pixel difference, which helps to obtain watermarked images with better visual quality and improved embedding rate due to less chance of overflow or underflow during watermarking. We also propose a tamper detection localization process to detect the tampered regions from the watermarked image. Results: Experimental study of the proposed scheme on the standard medical images from Osrix medical image data set shows that the proposed watermarking scheme outperforms the existing schemes in terms of visual quality of the watermarked image and embedding rate. Conclusion: The overhead related to location map and parity information need to be addressed in future works to improve the proposed scheme.

Diabetic Retinopathy (DR) is a major cause of blindness in diabetic patients. The increasing population of diabetic patients and difficulty to diagnose it at an early stage are limiting the screening capabilities of manual diagnosis by ophthalmologists. Color fundus images are widely used to detect DR lesions due to their comfortable, cost-effective and non-invasive acquisition procedure. Computer Aided Diagnosis (CAD) of DR based on these images can assist ophthalmologists and help in saving many sight years of diabetic patients. In a CAD system, preprocessing is a crucial phase, which significantly affects its performance. Commonly used preprocessing operations are the enhancement of poor contrast, balancing the illumination imbalance due to the spherical shape of a retina, noise reduction, image resizing to support multi-resolution, color normalization, extraction of a field of view (FOV), etc. Also, the presence of blood vessels and optic discs makes the lesion detection more challenging because these two artifacts exhibit specific attributes, which are similar to those of DR lesions. Preprocessing operations can be broadly divided into three categories: 1) fixing the native defects, 2) segmentation of blood vessels, and 3) localization and segmentation of optic discs. This paper presents a review of the state-of-the-art preprocessing techniques related to three categories of operations, highlighting their significant aspects and limitations. The survey is concluded with the most effective preprocessing methods, which have been shown to improve the accuracy and efficiency of the CAD systems.

Background: It was known that the response of tumor cells to radiation is closely related to tissue oxygen level and fractionated radiotherapy allows reoxygenation of hypoxic tumor cells. Non-invasive mapping of tissue oxygen level may hold great importance in clinic. Objective: The aim of this study is to evaluate the role of oxygen-enhanced MR imaging in the detection of tissue oxygen levels between fractionated radiotherapy. Methods: A cohort of 10 patients with brain metastasis was recruited. Quantitative oxygen enhanced MR imaging was performed prior to, 30 minutes and 22 hours after first fractionated radiotherapy. Results: The ΔR1 (the difference of longitudinal relaxivity between 100% oxygen breathing and air breathing) increased in the ipsilateral tumor site and normal tissue by 242% and 152%, respectively, 30 minutes after first fractionated radiation compared to pre-radiation levels. Significant recovery of ΔR1 in the contralateral normal tissue (p < 0.05) was observed 22 hours compared to 30 minutes after radiation levels. Conclusion: R1-based oxygen-enhanced MR imaging may provide a sensitive endogenous marker for oxygen changes in the brain tissue between fractionated radiotherapy.

Objectives: This study investigated the radiation dose and value of prospective dualenergy computed tomography (DECT) in the diagnosis of gastric cancer. Methods: Sixty patients scheduled for computed tomography (CT) for preoperative staging were divided into two groups. Thirty patients (Group A) underwent a single contrast-enhanced abdominal CT acquisition using a dual-source mode (100 kV/140 kV). Weighted average images of the two-kilovolt acquisitions and iodine maps were created. The remaining 30 patients underwent a standard CT scan (Group B). Two observers performed a blinded read of the images for gastric lesions, evaluating the image quality and recording effective dose. Results: During the blinded read, observers found 90% (27/30) of the cancers in both groups. The mean imaging quality scores were 2.1±0.9 for Group A, and 2.3±1.1 for Group B. The effective mean doses were 6.59±0.59 mSv and 25.86±0.44 mSv for Groups A and B, respectively. Compared with the control group (B), the imaging quality in the low-dose group decreased a little, but the radiation dose substantially decreased by 74.6%. Conclusion: The new DECT technique is valuable for examining gastric cancer patients. The dualkV scan mode can substantially reduce radiation dose while preserving good diagnostic image quality.

Objective: Isthmuses are narrow communications between root canals, and form as the result of the merging of the two root canals widening in a buccolingual direction. This widening causes the high ovality of isthmuses. The shaping and cleaning of all root canal systems are regarded as one of the major difficulties in long-oval shaped root canals. This study aims to make quantitative analysis of Vertucci type II root canal systems following preparation with Self- Adjusting file (SAF), Reciproc or Revo-S. Methods: Major diameter and roundness values were measured at the level 1.2 mm from apical foramen before and after preparation. A ‘post-preparation node’ point was described when the minimum minor diameter value was smaller than major diameter of apical 1.2 mm. Data were analysed using one-way ANOVA, Tukey and Chi-square tests. Results: Preparation resulted in a significant increase in the major diameter values regardless of the instrumentation (p = 0.000). Preparation with Reciproc led to the significant increase in roundness values (p = 0.000), whereas no significant difference was detected in specimens prepared with SAF (p = 0.21) and Revo-S (p = 0.15). Conclusion: Root canal preparation with SAF, Reciproc and Revo-S led to a significant increase in the major diameter of apical 1.2 mm and resulted in high frequencies of the post-preparation node.

Background: Frontotemporal dementia (FTD) represents the second most frequent early onset of dementia in people younger than 65 years. The main syndromes encompassed by the term FTD are behavioral variant of Frontotemporal dementia (bvFTD), non-fluent variant primary progressive aphasia (nfvPPA) and semantic variant (SD). Aims: To assess the bvFTD and SD, which represent the most common subtypes of FTD, using visual rating scales. Methods: Brain MRI exams of 77 patients either with bvFTD (n=43) or SD (n=34) were evaluated. The rating scales used were: Global cortical atrophy (GCA), Fazekas Scale: periventricular (PV) and white matter (WM) changes, Koedam rating scale and visual scales regarding specific cortical regions: dorsofrontal (DF), orbitofrontal (OF), anterior cingulate (AC), basal ganglia (BG), anterior- temporal (AT), insula, lateral-temporal (LT), entorhinal (ERC), perirhinal (PRC), anterior fusiform( AF), anterior hippocampus (AHIP) and posterior hippocampus (PHIP). Both Left (L) and Right (R) hemispheres were evaluated. Results: R-OF (p=0.059), L-OF (p<0.0005), L-AT (p=0.047) and L-AHIP (p=0.007) have a statistically significant effect on the variable occurrence of SD compared to bvFTD. The indicators with the highest value of the area under the curve (AUC) were R-AC (0.829), L-OF (0.808), L-AC (0.791) and L-AF (0.778). Highest sensitivity was achieved by R-OF (97%) and L-AF (75%). Highest specificity was achieved by L-OF (95%), L-AT (91%) followed by R-AC (84%). Best combination of sensitivity and specificity was achieved by L-AF (74%-79%), L-OF (56%-95%) and R-OF (97%-42%). Best combination of PPV and NPV was achieved by L-OF (90%-73%), LAT (83%-72%) and R-AC (77%-77%). Conclusion: Visual rating scales can be a practical diagnostic tool in the characterization of patterns of atrophy in FTLD and may be used as an alternative to highly technical methods of quantification.

Objective: The aim of the study was to evaluate hepatic steatosis in an asymptomatic group of patients with unenhanced abdominal computed tomography (CT) and to compare the results with anthropometric measurements. Methods: The study included 617 patients aged 18-93 years, who underwent unenhanced abdominopelvic CT between January 2016 and December 2017. Three imaging criteria were used in the assessment of hepatic steatosis on CT: mean region of interest (ROI) value of measured liver lobe (40 HU ≥), mean ROI value of measured liver lobe / measured spleen mean ROI value (1 ≥), mean ROI value of measured liver lobe - mean ROI value of spleen (10 HU≥). The liver fat was quantitatively assessed both visually and using multidetector CT grading. The anthropometric measurements used were the size of the liver and spleen, abdominal anterior-posterior diameter, abdominal transverse diameter, abdominal circumference, subcutaneous adipose tissue area, and anterior, posterior, and posterolateral subcutaneous adipose tissue thickness. Results: The prevalence of hepatic steatosis was 29.3% according to the visual evaluation, 29.8% according to the quantitative evaluation, 67.1% according to at least one criterion and 23.3% according to at least two criteria. A positive correlation was determined between hepatic steatosis and anthropometric measurements. Differences between the genders were observed in both hepatic steatosis and anthropometric measurements. Conclusion: By setting more objective criteria for evaluation, with the possibility of quantitative analysis in particular, non-contrast CT will have a more important role in assessing liver fat in the future.

Aims: To evaluate the diagnostic accuracy of ultrasound (US) assessing the lateral compartment lymph node metastasis in patients with primary papillary thyroid carcinoma (PTC), and to demonstrate the incidence and patterns of the lateral lymph node metastasis. Methods: We retrospectively reviewed 198 patients with primary PTC who underwent thyroidectomy in addition to modified lateral neck dissections (MLND) involving level II to level V due to clinically positive lateral neck disease. A skilled and experienced single operator performed all US examinations. Surgical pathology results were accepted as the reference method and sensitivity, specificity, and diagnostic accuracy of US in detecting metastatic lymph nodes established using level-by-level analysis. Results: In the study cohort, 10.1% of the patients had lateral compartment lymph node metastases without any central compartment involvement. For the lateral compartment, 48.5% had level II, 74.7% had level III, 64.6% had level IV, and 29.3% of the patients had level V metastasis. None of the patients had isolated level V metastasis. The sensitivity, specificity, and diagnostic accuracy of US in identifying lateral lymph compartment metastasis ranged from 87% to 91.4%, 92% to 98.6% 92.4% to 96%, respectively. However, the sensitivity (74.7%) and diagnostic accuracy (76.2%) of US significantly decreased for the central compartment while specificity (90%) remained similar. Conclusion: US performed by a skilled operator has an excellent diagnostic accuracy for the evaluation of lateral cervical lymph nodes in primary PTC; thus, might enable precise tailoring of the management strategies. Moreover, the high incidence of level V involvement favors MLND over selective approaches.