Current Medical Imaging - Volume 16, Issue 10, 2020

Breast Cancer is a common dangerous disease for women. Around the world, many women have died due to Breast cancer. However, in the initial stage, the diagnosis of breast cancer can save women's life. To diagnose cancer in the breast tissues, there are several techniques and methods. The image processing, machine learning, and deep learning methods and techniques are presented in this paper to diagnose the breast cancer. This work will be helpful to adopt better choices and reliable methods to diagnose breast cancer in an initial stage to save a women's life. To detect the breast masses, microcalcifications, and malignant cells,different techniques are used in the Computer-Aided Diagnosis (CAD) systems phases like preprocessing, segmentation, feature extraction, and classification. We have reported a detailed analysis of different techniques or methods with their usage and performance measurement. From the reported results, it is concluded that for breast cancer survival, it is essential to improve the methods or techniques to diagnose it at an initial stage by improving the results of the Computer-Aided Diagnosis systems. Furthermore, segmentation and classification phases are also challenging for researchers for the diagnosis of breast cancer accurately. Therefore, more advanced tools and techniques are still essential for the accurate diagnosis and classification of breast cancer.

Diabetes occurs due to the excess of glucose in the blood that may affect many organs of the body. Elevated blood sugar in the body causes many problems including Diabetic Retinopathy (DR). DR occurs due to the mutilation of the blood vessels in the retina. The manual detection of DR by ophthalmologists is complicated and time-consuming. Therefore, automatic detection is required, and recently different machine and deep learning techniques have been applied to detect and classify DR. In this paper, we conducted a study of the various techniques available in the literature for the identification/classification of DR, the strengths and weaknesses of available datasets for each method, and provides the future directions. Moreover, we also discussed the different steps of detection, that are: segmentation of blood vessels in a retina, detection of lesions, and other abnormalities of DR.

A huge amount of medical data is generated every second, and a significant percentage of the data are images that need to be analyzed and processed. One of the key challenges in this regard is the recovery of the data of medical images. The medical image recovery procedure should be done automatically by the computers that are the method of identifying object concepts and assigning homologous tags to them. To discover the hidden concepts in the medical images, the lowlevel characteristics should be used to achieve high-level concepts and that is a challenging task. In any specific case, it requires human involvement to determine the significance of the image. To allow machine-based reasoning on the medical evidence collected, the data must be accompanied by additional interpretive semantics; a change from a pure data-intensive methodology to a model of evidence rich in semantics. In this state-of-art, data tagging methods related to medical images are surveyed which is an important aspect for the recognition of a huge number of medical images. Different types of tags related to the medical image, prerequisites of medical data tagging, different techniques to develop medical image tags, different medical image tagging algorithms and different tools that are used to create the tags are discussed in this paper. The aim of this state-of-art paper is to produce a summary and a set of guidelines for using the tags for the identification of medical images and to identify the challenges and future research directions of tagging medical images.

Recent facts and figures published in various studies in the US show that approximately 27,510 new cases of gastric infections are diagnosed. Furthermore, it has also been reported that the mortality rate is quite high in diagnosed cases. The early detection of these infections can save precious human lives. As the manual process of these infections is time-consuming and expensive, therefore automated Computer-Aided Diagnosis (CAD) systems are required which helps the endoscopy specialists in their clinics. Generally, an automated method of gastric infection detections using Wireless Capsule Endoscopy (WCE) is comprised of the following steps such as contrast preprocessing, feature extraction, segmentation of infected regions, and classification into their relevant categories. These steps consist of various challenges that reduce the detection and recognition accuracy as well as increase the computation time. In this review, authors have focused on the importance of WCE in medical imaging, the role of endoscopy for bleeding-related infections, and the scope of endoscopy. Further, the general steps and highlighting the importance of each step have been presented. A detailed discussion and future directions have been provided at the end.

Background: Medical image fusion is very important for the diagnosis and treatment of diseases. In recent years, there have been a number of different multi-modal medical image fusion algorithms that can provide delicate contexts for disease diagnosis more clearly and more conveniently. Recently, nuclear norm minimization and deep learning have been used effectively in image processing. Methods: A multi-modality medical image fusion method using a rolling guidance filter (RGF) with a convolutional neural network (CNN) based feature mapping and nuclear norm minimization (NNM) is proposed. At first, we decompose medical images to base layer components and detail layer components by using RGF. In the next step, we get the basic fused image through the pretrained CNN model. The CNN model with pre-training is used to obtain the significant characteristics of the base layer components. And we can compute the activity level measurement from the regional energy of CNN-based fusion maps. Then, a detail fused image is gained by NNM. That is, we use NNM to fuse the detail layer components. At last, the basic and detail fused images are integrated into the fused result. Results: From the comparison with the most advanced fusion algorithms, the results of experiments indicate that this fusion algorithm has the best effect in visual evaluation and objective standard. Conclusion: The fusion algorithm using RGF and CNN-based feature mapping, combined with NNM, can improve fusion effects and suppress artifacts and blocking effects in the fused results.

Background: The dural venous sinuses (DVS), in general, are frequently asymmetrical and display far more anatomical variations than arterial systems. A comprehensive study of the anatomy and variants of the DVS can help surgeons in the preoperative evaluation and management as well as minimizing possible complications in the following treatment.

Methods: The current review was designed to provide a general overview of the normal anatomy and notable variants of the cerebral venous system as surveyed from the available literature. The pros and cons of different multimodal imaging methods for investigating DVS are also outlined. Finally, cases of various pathological entities are illustrated from our clinical practice.

Conclusion: There are many anatomical variations and lesions involving the DVS. MRI examination can provide essential information both on anatomical variation and morphological or functional change of the offending DVS in most circumstances. Multimodal non-invasive venography protocols may become a feasible alternative to the classical digital subtraction angiography and would improve the diagnostic accuracy in future studies.

Background: This study aims to investigate the existence of any Diffusion Tensor Imaging (DTI) value differences in Brain Metastases (BM) due to lung adenocarcinoma based on the Epidermal Growth Factor Receptor (EGFR) gene mutation status. Material and Methods: 17 patients with 32 solid intracranial metastatic lesions from lung adenocarcinoma were included prospectively. Patients were divided according to the EGFR mutation status as EGFR (+) (group 1, n:8) and EGFR wild type (group 2, n:9). The Fractional Anisotropy (FA), apparent diffusion coefficient (ADC), normalized ADC (nADC), Axial Diffusivity (AD), and Radial Diffusivity (RD) values were measured from the solid component of the metastatic lesions and nADC values were calculated. DTI values were compared between group 1 and group 2. The receiver-operating characteristic analysis was used to obtain cut-off values for the parameters presenting a statistical difference between the EGFR gene mutation-positive and wild type group. Results: There were statistically significant differences in measured ADC, nADC, AD, and RD values between group 1 and group 2. The ADC, nADC, AD, and RD values were significantly lower in group 1. There was no significant difference in FA values between the two groups. Analysis by the ROC curve method revealed a cut-off value of ≤721 x 10^-6 mm²/s for ADC (Sensitivity= 72.7, Specificity=85.7); ≤0.820 for nADC (Sensitivity=72.7, Specificity=90.5), ≤ 886 for AD (Sensitivity=81.8, Specificity=81.0), and ≤588 for RD (Sensitivity=63.6, Specificity=90.5) in differentiating EGFR mutation (+) group from wild type group. Conclusion: A combination of the decreased ADC, nADC, AD, and RD values in BM due to lung adenocarcinoma can be important for predicting the EGFR gene mutation status. DTI features of the brain metastases from lung adenocarcinoma may be utilized to provide insight into the EGFR mutation status and guide the clinicians for the initiation of targeted therapy.

Background: The apparent diffusion coefficient (ADC), the quantitative parameter of diffusion-weighted magnetic resonance imaging (DW-MRI), is a measure for this restricted diffusion, and its role in gastric cancer (GC) including distinguishing malignant segments from healthy gastric wall, metastatic perigastric lymph nodes from benign nodes and evaluating response of GC to neoadjuvant chemotherapy has been investigated in previous studies. Evidence suggests that ADC may also be of help in assessment of aggressiveness and preoperative staging of gastric cancer, which needs to be explored in further studies.

Objective: To investigate the role of DW-MRI and its quantitative parameter, ADC in staging of gastric cancer.

Methods: Forty-six patients (28 male, 18 female, mean age 62 years) with non-metastatic biopsy- proven GC who underwent abdominal DW-MRI before surgery were included in this retrospective study. Tumor invasion depth (T-stage) and nodal involvement (N-stage) were evaluated using signal increase on DW-MRI, and tumor ADC was measured. Diagnostic performance of these results was assessed by comparing them with postsurgical histopathology based on 8th TNM classification.

Results: Sensitivity, specificity, and accuracy of DW-MRI in T-staging were 92.1%, 75%, 89.1% for ≤T2 vs. ≥T3; and 75%, 88.5%, 82.6% for ≤T3 vs. T4. However, sensitivity, specificity, and accuracy of DW-MRI in N-staging were 89.3%, 88.9%, 89.1% for ≤N1 vs. ≥N2; and 73.7%, 96.3%, 86.9% for ≤N2 vs. N3, respectively. Relative preoperative ADC values correlated with pT staging (r=-0.397, p=0.006). There was also a statistically significant difference of relative ADC values between ≤T3 and T4 stages, and a cut-off of 0.64 s/mm2 could differentiate these stages with an odds ratio of 7.714 (95% confidence interval, 1.479-40.243). The area under the receiver operating characteristic curve for differentiating ≤T3 and T4 stages was 0.725.

Conclusion: DW-MRI may contribute to the clinical staging of non-metastatic GC. In particular, relative ADC of DW-MRI can distinguish T4 gastric cancer from less advanced T-stages.

Background: In patients with Alzheimer’s disease (AD), cerebral blood flow (CBF) is decreased from the early stages. CBF in AD is currently estimated from Z-scores using statistical analysis. However, the Z-score is not considered the impaired area ratio. Methods: In the present study, a novel indicator, ΣzS, associated with brain surface area and Zscores, is defined and the association with regional CBF has been estimated using Mini-Mental State Examination (MMSE) scores, which indicate the severity of cognitive impairment in patients with AD. Results: A negative correlation was detected between ΣzS in the posterior cingulate gyrus and the subset numbers 1, 2, and 5 of the total MMSE scores. Furthermore, a negative correlation was detected between the total MMSE score and ΣzS in Brodmann area 30, which is a subdivided area of the brain. Conclusion: These results suggest that ΣzS may be a useful indicator of CBF metabolism, and thus may improve the current understanding of cognitive function in patients with AD.

Background: Accuracy of Joint British Society calculator3 (JBS3) cardiovascular (CV) risk assessment tool may vary across the Indian states, which is not verified in south Indian, Kerala based population. Objectives: To evaluate the traditional risk factors (TRFs) based CV risk estimation done in Kerala based population. Methods: This cross-sectional study uses details of 977 subjects aged between 30 and 80 years, recorded from the medical archives of clinical locations at Ernakulum district, in Kerala. The risk categories used are Low (<7.5%), Intermediate (≥7.5% and <20%), and High (≥20%) 10-year risk classifications. The lifetime classifications are Low lifetime (≤39%) and High lifetime (≥40%) are used. The study evaluated using statistical analysis; the Chi-square test was used for dependent and categorical CV risk variable comparisons. A multivariate ordinal logistic regression analysis for the 10-year risk and odds logistic regression analysis for the lifetime risk model identified the significant risk variables. Results: The mean age of the study population is 52.56±11.43 years. With 39.1% in low, 25.0% in intermediate, and 35.9% has high 10-year risk. Low lifetime risk with 41.1%, the high lifetime risk has 58.9% subjects. The intermediate 10-year risk category shows the highest reclassifications to High lifetime risk. The Hosmer-Lemeshow goodness-of-fit statistics indicates a good model fit. Conclusion: Timely interventions using risk predictions can aid in appropriate therapeutic and lifestyle modifications useful for primary prevention. Precaution to avoid short-term incidences and reclassifications to a high lifetime risk can reduce the CVD related mortality rates.

Background: Osteonecrosis of Femoral Head (ONFH) is a common complication in orthopaedics, wherein femoral structures are usually damaged due to the impairment or interruption of femoral head blood supply. Aim: In this study, an automatic approach for the classification of the early ONFH with deep learning has been proposed. Methods: All femoral CT slices according to their spatial locations with the Convolutional Neural Network (CNN) are first classified. Therefore, all CT slices are divided into upper, middle or lower segments of femur head. Then the femur head areas can be segmented with the Conditional Generative Adversarial Network (CGAN) for each part. The Convolutional Autoencoder is employed to reduce dimensions and extract features of femur head, and finally K-means clustering is used for an unsupervised classification of the early ONFH. Results: To invalidate the effectiveness of the proposed approach, the experiments on the dataset with 120 patients are carried out. The experimental results show that the segmentation accuracy is higher than 95%. The Convolutional Autoencoder can reduce the dimension of data, the Peak Signal- to-Noise Ratios (PSNRs) are better than 34dB for inputs and outputs. Meanwhile, there is a great intra-category similarity, and a significant inter-category difference. Conclusion: The research on the classification of the early ONFH has a valuable clinical merit, and hopefully it can assist physicians to apply more individualized treatment for patient.

Background: Impacted teeth are commonly asymptomatic and not associated with any pathologic lesions for years. Any change in the size of the follicle associated with impacted teeth may result in odontogenic cysts or tumors. CBCT plays an important role in determining the radiographic features of a lesion and therefore, is very helpful for accurate diagnosis and treatment planning. Objective: This study aims to evaluate radiolucent lesions associated with impacted teeth in terms of age and sex distribution, localization, and comparison with the pathological diagnosis. Methods: In this retrospective study, out of 6758 CBCT images, 400 images revealing radiolucent lesions were detected. The study included only 190 cases (regarding 180 patients) which had a matching histopathological evaluation. Data related to the age and sex of the patients, localization of the lesions, and their comparison with the pathological diagnosis were recorded and analyzed. Results: The most encountered lesions were dentigerous cysts (60%) and odontogenic keratocysts (26.3%). Males were the most affected (63.3%). Most of the lesions were found in the left and right posterior mandible and mostly (66.8 %) associated with third molars. Out of 123 radiological diagnoses of dentigerous cyst cases, histopathological diagnoses confirmed 108 cases. Regarding odontogenic keratocyst, histopathological diagnosis confirmed 40 cases out of 48. Conclusion: Radiological diagnoses of the lesions mostly match with their pathological diagnosis unless their characteristics are changed due to infection. CBCT, as a technique enabling detailed imaging of the involved dental structures, is a helpful instrument for differential diagnosis.