Current Medical Imaging Reviews (v.13, #1)
Meet Our Editorial Board Member by Keon W. Kang (1-1).
Preface by E. Edmund Kim (2-2).
Recent Developments in Computer Aided Diagnosis for Lung Nodule Detection from CT images: A Review by Syed M. Naqi, Muhammad Sharif (3-19).
A Computer Aided Diagnosis (CAD) system has a significant importance and key role in cancer detection especially from lungs by using medical imaging modalities. It is much helpful to the radiologists by providing a second opinion regarding diagnosis which improves their performance in terms of time and precision. This work examines the effectiveness of automatic cancer detection methods from lungs using Computed Tomography (CT) images and provides a detailed survey of different techniques, algorithms which are used in nodule detection in recent years. We intend to give the readers a comprehensive view of existing research and a range of feature extraction, classification, and segmentation algorithms. We have also assessed some performance measures used to evaluate the correctness of a CAD system including sensitivity; specificity, accuracy, and false positive rate. This review will give a detailed picture and provides insight into the current developments in the field of Computer Aided Diagnosis.
A Review of Ground Glass Opacity Detection Methods in Lung CT Images by Lv Linying, Liu Xiabi, Zhou Chunwu, Zhao Xinming, Zhao Yanfeng (20-31).
The automatic detection of Ground-Glass Opacity (GGO) in lung CT images is very useful for early diagnosis of lung cancers. In this paper, we present a study of previous GGO detection methods and summarize a common algorithm framework, which includes three components: preprocessing, candidate extraction and GGO identification. For each component, we discuss the main methods. Also we further describe the evaluation criterion and provide a comparison of the performance of the existing approaches.
Role of Ultrasonography in Acute Appendicitis of the Elderly. A Pictorial Essay by Marco Tana, Claudio Tana, Giovanni Iannetti, Marcello Romano, Mauro Silingardi, Cosima Schiavone (32-37).
Acute appendicitis in the elderly represents an emerging problem. Although it has been considered for a long time an exclusive disease of the second and third decades of life, the increase of life expectancy has resulted in an increasing number of cases found in the elderly. While the key element for the diagnosis in the young is represented by typical history and symptoms, the diagnosis is more difficult in the elderly mostly due to atypical and paucysymtomatic presentation and high rate of complications. Therefore, the need of imaging techniques such as computed tomography to achieve a correct diagnosis is higher in the elderly than in the young patients, but the risk of nephrotoxicity using iodine contrast agents, the need to move the patient to the Radiology Department with consequent time delay and the difficulty in acquisition of the informed consent in urgent conditions are some of the main limits of this technique. In this context, ultrasound (US) represents a good imaging modality to achieve a correct and rapid diagnosis. Furthermore, the emerging role of contrastenhanced ultrasound has expanded the diagnostic scenarios in the assessment of this disease. In this short pictorial essay, we would like to report main US features of acute appendicitis in the elderly, highlighting the advantages of US assessment in comparison to other imaging techniques.
Role of Imaging in Testicular Cancer by Mandip Dulal, Jing Lei, She-Wei Dou, Shao-Cheng Zhu (38-49).
Testicular malignancy is the most common nonhematologic malignancy in young men. Around 95% of them are germ cell tumors (GCTs), and with correct assessment of the disease and application of chemotherapy and radiotherapy survival rates of more than 90% can be achieved. Imaging studies not only aid in the diagnosis of testicular cancer but also help determine the tumor extent and site of metastatic disease, in monitoring treatment response, surgical planning and detecting sites of relapse and residual disease. Scrotal sonography combined with clinical examination has a high sensitivity for diagnosing testicular cancer and thus is often the first imaging modality to be performed on patients presenting with testicular mass. Abdominal and pelvic CT and chest CT remain the preferred techniques for staging, monitoring of treatment response, and detecting relapse and residual disease in patients with testicular cancer but MRI, PET with 18F-FDG (fluorodeoxyglucose) and sonography also show promises in certain situations. This article reviews the literatures on the role of imaging in the management of testicular germ cell cancer.
Harnessing the Power of Cerenkov Luminescence Imaging for Gastroenterology: Cerenkov Luminescence Endoscopy by Xin Cao, Yonghua Zhan, Xu Cao, Jimin Liang, Xueli Chen (50-57).
The Cerenkov luminescence imaging (CLI) has built a bridge between the nuclear and optical imaging, and opened a new direction of optical imaging in clinic translation. However, the wide applications of CLI are limited by the weak intensity and poor penetration capacity. By coupling highly sensitive charged coupled device camera with optical fiber bundle based endoscope, Cerenkov luminescence endoscopy (CLE) has recently been developed to overcome these limitations. Using the CLE, diseases deep buried in the body, such as the gastrointestinal (GI) tract cancer, can be identified by radiotracer, which can hardly be detected by CLI from the surface of the body. Here, we review recent progress on CLI and CLE, including the principle, imaging instrument, as well as applications. In addition, the intensity enhanced strategies for Cerenkov luminescence are presented, which may provide an ideal solution to the obstacle of CLE in the translation studies. In the end, we present possible future directions of the CLE technology.
An Edge Preservation Index for Evaluating Nonlinear Spatial Restoration in MR Images by Justin Joseph, Sivaraman Jayaraman, Rajadurai Periyasamy, Simi V. Renuka (58-65).
Background: Edge preserving filters are widely preferred for medical image denoising as they do not degrade the morphological edges during smoothing. Even though, the operational parameters of these filters have crucial influence on their performance, the parameters are selected subjectively. The optimum values of the operational parameters can be selected objectively with the help of edge quality indices. The available edge quality indices either do not comply with the subjective quality ratings or they are prone to noise level. Objectives: (a) To formulate an edge preservation metric which has good correlation with subjective fidelity ratings and is robust to noise (b) To demonstrate an objective method for the selection of optimum values of the operational parameters of the non-linear spatial filters using the newly formulated edge preservation metric. Methods: Pratt's Figure of Merit (PFOM) between the binary edge maps of the original and restored images, extracted via gradient based threshold, is used as the measure of extent to which edges are preserved during restoration. Magnetic Resonance (MR) images filtered by anisotropic diffusion for different values of number of iterations are used as ground truth images. The PFOM is compared with existing edge quality indices in terms of robustness to noise and correlation with subjective fidelity ratings. Results: PFOM exhibits a correlation of 0.9998 with the subjective edge quality rating which is only 0.9802 for Edge Preservation Index (EPI). Conclusion: The proposed index is robust to noise level and useful for optimizing the performance of non-linear spatial filters.
Dual Energy Computed Tomography Angiography in the Peripheral Arterial Imaging: A Systematic Review of Image Quality, Radiation Dose and Diagnostic Value by Abdulrahman Almutairi, Zhonghua Sun (66-72).
To perform a systematic review of the diagnostic value of dual energy computed tomography angiography (DECTA) in peripheral arterial disease (PAD). PubMed, ProQuest, Medline and ScienceDirect were searched for studies evaluating DECTA compared to conventional computed tomography angiography (CTA) and digital subtraction angiography (DSA) in patients with PAD. Diagnostic value, image quality and radiation dose were analysed and compared. Nine studies comprising a total of 286 patients were found to meet selection criteria where DECTA was used to evaluate lower extremities. The mean estimates of sensitivity and specificity of DECTA were 95.8% (95% CI: 84 to 97.2%) and 79.8% (95% CI: 78 to 97%). Reduction of the contrast medium volume up to 50% was found to achieve an adequate image quality at the optimal keV setting. The mean effective dose for DECTA was 9.51 mSv (95% CI: 7.56 to 11.18 mSv). DECTA is a non-invasive and an accurate diagnostic procedure in the diagnostic assessment of peripheral arterial disease with high diagnostic value.
A Novel EIAC and Rule Based Region Map Algorithms for Text Detection, Localization and Character Recognition by Manoharan Sudha, Sankaran Palani (73-82).
Background: Generally, the texture information stored in the natural scene images provide some vital clues to the image based on the applications include Content Based Image Retrieval (CBIR), scene understanding, assistive navigation and automatic coding. Still locating the text from complex background and recognizing the characters with different colors are the major issues in image processing applications. Methods: To overcome these problems, a new structure is proposed in this paper for detecting and recognizing the text strings present in the natural scene images. To execute an efficient framework, the preparation of an input image is necessary that contains two preliminary tasks. It includes preprocessing based on Gaussian filtering and preprocessing based on Histogram equalization. Moreover, an Edge based Intensity Aided Clustering (EIAC) is introduced to detect the text by using the Sobel operator. Then, the neuro-fuzzy algorithm is used classify the text and non-text portions. A new Rule-based Region Map algorithm is introduced for text segmentation, where the necessary features are extracted based on the Local Tetra Patterns (LTrPs). Finally, the characters are recognized with the help of Fuzzy based Relevance Vector Machine (RVMs) classification algorithm. Results: The simulation results obtained by the proposed method are compared with the existing techniques for proving the better performance. The results are analyzed in terms of sensitivity, specificity, accuracy, precision, recall, recognition rate and F-Measure. Conclusion: The proposed framework is fully based on the combination of text detection, classification, segmentation, feature extraction and character recognition. The major advantages of this paper are, accuracy, simplicity and easy to use. Moreover, it provides the best classification results, when compared to the existing techniques.
CT and CT-guided Percutaneous Needle Biopsy in Diagnosis of Primary Pulmonary Cryptococcosis in Immunocompetent Patients by Jibo Hu, Hongjie Hu, Susu Xie, Xiaoming Yang, Yaoying Zhong, Yijie Shi (83-88).
Objective: Primary pulmonary cryptococcosis in immunocompetent patients is very easily misdiagnosed or even missed. Accurate diagnosis of this disease is critical for a timely and proper treatment. This study aims to address the importance of computed tomography (CT) and CT-guided percutaneous needle biopsy for primary pulmonary cryptococcosis in immunocompetent patients. Methods: We retrospectively analyzed clinical features and CT findings of 36 immunocompetent patients with pathologically confirmed primary pulmonary cryptococcosis. CT-guided percutaneous pulmonary needle biopsies were performed in 25 of these patients. Results: Nineteen patients were symptomatic, including cough, chest pain, expectoration, bloody sputum or hemoptysis, and fatigue. Seventeen patients were asymptomatic. CT examinations displayed a single-lobe lesion in 29 cases and multiple-lobe lesions in 7 cases. Lesions were located in the outer zone in 33 cases, and in the middle zone in 3 cases. CT findings were primarily classified into 2 types: solitary nodule (10 cases, 27.8%) and localized multiple miscellaneous nodule or consolidation (26 cases, 72.2%). In addition, air-bronchograms within the lesions, irregular cavitations and halo signs were found in 21, 8 and 10 cases, respectively. Twenty two (88%) of 25 CT-guided percutaneous pulmonary needle biopsies were confirmed to be pulmonary cryptococcosisby pathology. Conclusions: CT findings of localized multiplemiscellaneous nodules or consolidations with airbronchograms, or cavitations, or halo signs, strongly support the presence of primary pulmonary cryptococcosis. CT-guided percutaneous needle biopsy helps with the accurate diagnosis of this disease.
Decision Support System for Lymphoma Classification by Ahmed E-S. Negm, Ahmed H. Kandil, Osama A. E-F. Hassan (89-98).
The diffuse lymphoma is a malignant tumor of lymphoid tissues. It is associated with abnormal, unlimited and uncontrolled proliferation of lymphoid cells. Until now, expert pathologists have identified diffuse lymphoma cells disease manually. This paper introduces automatic system with a friendly user interface to differentiate between the categories of the diffuse lymphoma cells. This research is based on the morphological features such as size, perimeter and circularity. The cell size is a critical element in the classification of diffuse lymphoma according to international formulation standards. Therefore, the applied procedures identify lymphoid cell population in digital microscopic images. The cells are classified using their morphological data according to the characteristics of each cell such as: circularity, perimeter, area, and color density. The number of cells is taken into consideration in the developed approach. Image processing techniques are applied to digital microscopic images to measure morphological parameters and to overcome image problems such as overlapping and cell distortion that affect the sensitivity of the measured data. The developed procedures help the pathologists to come to a decision regarding the classification of diffuse lymphoma. Moreover, it can be used to train medical students and young pathologists.
Clustering Based Approach for Segmentation of Optic Cup and Optic Disc for Detection of Glaucoma by Niharika Thakur, Mamta Juneja (99-105).
Glaucoma is a disease in which damage of the optic nerve of eye leads to progressive and irreversible vision loss. It is caused due to enlargement of the optic cup present inside the optic disc. It can be detected by calculating the CDR value which is the ratio of segmented optic cup to the segmented optic disc. Optic disc is the point from where various ganglion cells exit from eye to form an optic nerve. On the other hand, optic cup is a depression of the variable size present inside the optic disc. This paper initially presents a review analysis of existing techniques followed by a novel approach with improved accuracy.