scholarly journals Computational intelligence for the detection and classification of malignant lesions in screening mammography

2006 ◽  
Author(s):  
Evangelia Panourgias ◽  
Athanasios Tsakonas ◽  
Georgios Dounias ◽  
Georgia Panagi
Keyword(s):  
Computational Intelligence ◽  
Screening Mammography ◽  
Malignant Lesions

Increse of newly - detected in situ cancers in non-palpable breast lesions

2006 ◽  
Vol 53 (1) ◽  
pp. 73-75
Author(s):  
N. Miletic ◽  
D. Stojiljkovic ◽  
M. Inic ◽  
M. Prekajski ◽  
A. Celebic ◽  
...  
Keyword(s):  
Breast Tissue ◽  
Malignant Disease ◽  
Clinical Stage ◽  
Diagnostic Procedures ◽  
Basal Membrane ◽  
Needle Aspiration ◽  
Screening Mammography ◽  
Significant Difference ◽  
Malignant Lesions

Great importance in detecting cancer in the phase of in situ lays in the fact that the epithelial layer is deprived of blood and lymph vessels, so metastases may develop only when basal membrane has been broken. This paper includes 46 operated women in whom it preoperatively had been verified suspect non-palpable lesion. The preoperative diagnostics included use of high- resolution mammography, aimed mammography, palpatory examination, as well as fine-needle aspiration (FNA), biopsy and cytologic analysis of the sample. The methodology of this work implies the use of stereotaxic marking, specimen mammography and ex-tempore pathohistology analysis. Out of 46 investigated patients in clinical stage T0N0M0, in whom there were no signs of malignant disease, and according to suspect lesion of initial screening mammography, malignant lesions of breast tissue were diagnosed in 19 patients (41%) intraoperatively. Three of these lesions (15,8%) were histopathologically verified as in situ. Comparing our results with data of the Institute of oncology and radiology of Serbia hospital registry (IORS) for the year 2001, from 1173 patients registered with malignant lesions, only 16 ones (1,4%) had in situ cancer, operated on the basis of the suspect mammography of clinical stage T0N0M0. Statistically significant difference was found related to the number of detected cancers in this early phase of the breast malignant disease. This limits surgical intervention to tumorectomy, with preservation of the remaining breast tissue, what brings to healing, justifying in that way, screening examinations and routine application of the most contemporary diagnostic procedures.

scholarly journals Manual versus Automatic Classification of Laryngeal Lesions based on Vascular Patterns in CE+NBI Images

2020 ◽  
Vol 6 (3) ◽  
pp. 70-73
Author(s):  
Nazila Esmaeili ◽  
Alfredo Illanes ◽  
Axel Boese ◽  
Nikolaos Davaris ◽  
Christoph Arens ◽  
...  
Keyword(s):  
Vocal Fold ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Automatic Classification ◽  
Vascular Pattern ◽  
Objective Interpretation ◽  
Laryngeal Lesions ◽  
Malignant Lesions ◽  
Manual Classification

AbstractLongitudinal and perpendicular changes in the blood vessels of the vocal fold have been related to the advancement from benign to malignant laryngeal cancer stages. The combination of Contact Endoscopy (CE) and Narrow Band Imaging (NBI) provides intraoperative realtime visualization of vascular pattern in Larynx. The evaluation of these vascular patterns in CE+NBI images is a subjective process leading to differentiation difficulty and subjectivity between benign and malignant lesions. The main objective of this work is to compare multi-observer classification versus automatic classification of laryngeal lesions. Six clinicians visually classified CE+NBI images into benign and malignant lesions. For the automatic classification of CE+NBI images, we used an algorithm based on characterizing the level of the vessel’s disorder. The results of the manual classification showed that there is no objective interpretation, leading to difficulties to visually distinguish between benign and malignant lesions. The results of the automatic classification of CE+NBI images on the other hand showed the capability of the algorithm to solve these issues. Based on the observed results we believe that, the automatic approach could be a valuable tool to assist clinicians to classifying laryngeal lesions.

scholarly journals Classification of Asphalt Pavement Cracks Using Laplacian Pyramid-Based Image Processing and a Hybrid Computational Approach

2018 ◽  
Vol 2018 ◽  
pp. 1-16 ◽  
Author(s):  
Nhat-Duc Hoang
Keyword(s):  
Image Processing ◽  
Computational Intelligence ◽  
Asphalt Pavement ◽  
Classification Model ◽  
Laplacian Pyramid ◽  
Pavement Condition ◽  
Crack Patterns ◽  
Image Processing Techniques ◽  
Processing Techniques

To improve the efficiency of the periodic surveys of the asphalt pavement condition, this study puts forward an intelligent method for automating the classification of pavement crack patterns. The new approach relies on image processing techniques and computational intelligence algorithms. The image processing techniques of Laplacian pyramid and projection integral are employed to extract numerical features from digital images. Least squares support vector machine (LSSVM) and Differential Flower Pollination (DFP) are the two computational intelligence algorithms that are employed to construct the crack classification model based on the extracted features. LSSVM is employed for data classification. In addition, the model construction phase of LSSVM requires a proper setting of the regularization and kernel function parameters. This study relies on DFP to fine-tune these two parameters of LSSVM. A dataset consisting of 500 image samples and five class labels of alligator crack, diagonal crack, longitudinal crack, no crack, and transverse crack has been collected to train and verify the established approach. The experimental results show that the Laplacian pyramid is really helpful to enhance the pavement images and reveal the crack patterns. Moreover, the hybridization of LSSVM and DFP, named as DFP-LSSVM, used with the Laplacian pyramid at the level 4 can help us to achieve the highest classification accuracy rate of 93.04%. Thus, the new hybrid approach of DFP-LSSVM is a promising tool to assist transportation agencies in the task of pavement condition surveying.

Tumors of the Liver

2018 ◽  
Author(s):  
Alex C Kim ◽  
Hari Nathan
Keyword(s):  
Imaging Techniques ◽  
Future Liver Remnant ◽  
Hepatic Tumors ◽  
Liver Remnant ◽  
Future Liver Remnant Volume ◽  
Malignant Lesions ◽  
Eighth Edition ◽  
Tumors Of The Liver

Tumors in the liver arise from either the underlying hepatic parenchyma, resulting in benign or malignant lesions, or as metastatic deposit from extrahepatic malignancies. Treatment of these tumors is complex and requires a careful clinical evaluation. Recent improvement in diagnostic imaging techniques and reporting facilitates for appropriate characterization of hepatic tumors. In addition, utilization of genetics allows for careful classification of malignant potential in certain hepatic tumors. This chapter discusses several different types of hepatic tumors and examines the underlying etiologies, clinical presentation, diagnostic studies, staging, treatment, and prognosis. The staging of the malignant lesions is updated to reflect the American Joint Committee on Cancer’s eighth edition system. This review contains 7 figures, 4 tables and 82 references. Key Words: Barcelona Clinic Liver Cancer system, CAPOX, future liver remnant volume, FOLFOX, LI-RADS, stereotactic body radiation therapy, transarterial chemoembolization, transarterial radioembolization, β-catenin

Computational Intelligence Approach for Classification of Diabetes Mellitus Using Decision Tree

2020 ◽  
pp. 87-103
Author(s):  
Engin Pekel ◽  
Ebru Pekel Özmen
Keyword(s):  
Diabetes Mellitus ◽  
Computational Intelligence ◽  
Elevated Blood ◽  
Algorithm Efficiency ◽  
Chronic Hyperglycemia ◽  
Classification And Regression ◽  
Cart Algorithm ◽  
Intelligence Approach ◽  
Common Manifestation

Diabetes mellitus (DM) is a group of metabolic disorders with one common manifestation: elevated blood sugar or hyperglycemia. The diagnosis of diabetes is the most crucial point due to chronic hyperglycemia. This chapter improves the performance of the Classification and Regression Trees (CART) algorithm because the accurate classification of diabetes depends on the algorithm efficiency. Authors use the accuracy rate for the objective function in the prediction process by Genetic Algorithm (GA). The proposed GA-CART algorithm provides the best performance at 96.05%.

Application of Computational Intelligence Techniques in Wireless Sensor Networks the State of the Art

2020 ◽  
pp. 1580-1600
Author(s):  
Subhendu Kumar Pani
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Computational Intelligence ◽  
State Of The Art ◽  
Area Coverage ◽  
Wireless Sensor ◽  
Coverage Problem ◽  
Sensor Devices ◽  
Huge Variety

A wireless sensor network may contain hundreds or even tens of thousands of inexpensive sensor devices that can communicate with their neighbors within a limited radio range. By relaying information on each other, they transmit signals to a command post anywhere within the network. Worldwide market for wireless sensor networks is rapidly growing due to a huge variety of applications it offers. In this chapter, we discuss application of computational intelligence techniques in wireless sensor networks on the coverage problem in general and area coverage in particular. After providing different types of coverage encountered in WSN, we present a possible classification of coverage algorithms. Then we dwell on area coverage which is widely studied due to its importance. We provide a survey of literature on area coverage and give an account of its state-of-the art and research directions.

Application of Computational Intelligence Techniques in Wireless Sensor Networks the State of the Art

2016 ◽  
pp. 441-461
Author(s):  
Subhendu Kumar Pani
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Computational Intelligence ◽  
State Of The Art ◽  
Area Coverage ◽  
Wireless Sensor ◽  
Coverage Problem ◽  
Sensor Devices ◽  
Huge Variety

A wireless sensor network may contain hundreds or even tens of thousands of inexpensive sensor devices that can communicate with their neighbors within a limited radio range. By relaying information on each other, they transmit signals to a command post anywhere within the network. Worldwide market for wireless sensor networks is rapidly growing due to a huge variety of applications it offers. In this chapter, we discuss application of computational intelligence techniques in wireless sensor networks on the coverage problem in general and area coverage in particular. After providing different types of coverage encountered in WSN, we present a possible classification of coverage algorithms. Then we dwell on area coverage which is widely studied due to its importance. We provide a survey of literature on area coverage and give an account of its state-of-the art and research directions.

scholarly journals Malignant Gastrointestinal Stromal Tumour with Metastasis

2015 ◽  
Vol 01 (01) ◽  
pp. 031-033
Author(s):  
Bhushita Lakhar ◽  
Nilesh Guru
Keyword(s):  
Gastrointestinal Stromal Tumors ◽  
Gastrointestinal Stromal Tumour ◽  
Anatomic Site ◽  
Stromal Tumors ◽  
Mesenchymal Neoplasms ◽  
Imaging Characteristics ◽  
The World ◽  
Mitotic Frequency ◽  
Malignant Lesions

AbstractGastrointestinal stromal tumors (GISTs) are the most usual mesenchymal neoplasms of the gastrointestinal tract. Ever since the classification of GIST as an entity distinct from leiomyoma's, leiomyosarcomas, etc., there has been an increased concern in defining their imaging characteristics. It is estimated that approximately 5000-10,000 people are affected per year by this tumor all over the world. Most GISTs are benign (70-80%). However, these tumors have a spectrum ranging from benign to malignant lesions, depending on its anatomic site, tumor size, and mitotic frequency. We report a case of multiple malignant GIST with metastasis into Liver.

Sign in / Sign up

Export Citation Format

Share Document