Multiresolution-Based Singular Value Decomposition Approach for Breast Cancer Image Classification.

Breast cancer is the most prevalent form of cancer that can strike at any age; the higher the age, the greater the risk. The presence of malignant tissue has become more frequent in women. Although medical therapy has improved breast cancer diagnostic and treatment methods, still the death rate remains high due to failure of diagnosing breast cancer in its early stages. A classification approach for mammography images based on nonsubsampled contourlet transform (NSCT) is proposed in order to investigate it. The proposed method uses multiresolution NSCT decomposition to the region of interest (ROI) of mammography images and then uses Z-moments for extracting features from the NSCT-decomposed images. The matrix is formed by the components that are extracted from the region of interest and are then subjected to singular value decomposition (SVD) in order to remove the essential features that can generalize globally. The method employs a support vector machine (SVM) classification algorithm to categorize mammography pictures into normal, benign, and malignant and to identify and classify the breast lesions. The accuracy of the proposed model is 96.76 percent, and the training time is greatly decreased, as evident from the experiments performed. The paper also focuses on conducting the feature extraction experiments using morphological spectroscopy. The experiment combines 16 different algorithms with 4 classification methods for achieving exceptional accuracy and time efficiency outcomes as compared to other existing state-of-the-art approaches.

Outcome of surgery for operable supratentorial mass lesions in patients presenting with decerebration following severe head injury: A retrospective analysis of factors affecting outcome.

AIM: Abnormal motor response in the form of decerebration signifies either injury or compression of brain stem. The presence of decerebrate rigidity following head injury is a grave prognostic sign. Mortality may increase up to 70% in patients showing signs of decerebration. Although many studies have identified the prognostic factors in severe head injuries, few studies have focused on the operated patients with decerebration in predicting the long-term outcome. This study was planned to determine the outcome in this group of patients for prognostication and to help plan further line of management. MATERIALS AND METHODS: All the patients admitted with severe head injury with decerebration (M2 motor response) admitted in neurosurgery department from September 2009 to January 2011 were included in the study. All the patients had operable supratentorial mass lesions with no direct evidence of brain stem damage. Patients with penetrating injury and diffuse injury with no operative mass lesions were excluded from the study. Clinical and computerized tomography (CT) data were correlated with outcome retrospectively. Glasgow outcome scale (GOS) was used as a measure of functional outcome. RESULTS: The patients admitted with decerebration (M2 motor response) comprised 8% of the total head injury related operative procedures performed at our institute during the period. Of the 72 patients, 14 (19%) patients were more than 60 years old and 21% (15) were females. The surgical mass lesions comprised extradural hematoma in 27 (38%), cerebral contusions in 19 (26%), acute Subdural Hematoma alone in 7 (10%), and acute Subdural Hematoma (SDH) with cerebral contusion in 19 (26%) of the patients. Of the 72 patients, 36(50%) were operated within 24 hours of injury Follow-up of all, but 2 (3%) was obtained. Favorable outcome (GOS 4 and 5) was obtained in 14% (n = 10) of the patients with 83% (n = 60) mortality rate. The favorable outcome rate among the patients operated for Extradural Hematoma was 26% and for cerebral contusions was 11%. Only 5% of the patients operated for acute SDH survived. CONCLUSION: Radiological diagnosis (type of lesion), followed by duration of decerebration and age of the patient are the most important prognostic factors determining the outcome of surgery in decerebrating patients. Our results confirm that despite the poor prognosis in decerebrate patients, a significant number of patients may still survive and have a good outcome.

Comparative evaluation of 3-dimensional pseudocontinuous arterial spin labeling with dynamic contrast-enhanced perfusion magnetic resonance imaging in grading of human glioma.

INTRODUCTION: The study was performed to compare dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) with 3-dimensional (3D) pseudocontinuous arterial spin labeling (PCASL) MRI in gliomas with an aim to see whether arterial spin labeling (ASL)-derived cerebral blood flow (CBF) values can be used as an alternative to DCE-MRI for its grading. MATERIALS AND METHODS: Sixty-four patients with glioma (37 male; mean age, 43 years; 38 high grade and 26 low grade) underwent 3D-PCASL and DCE-MRI. The DCE indices (relative cerebral blood volume, rCBV; relative CBF, rCBF; permeability, k and kep; and leakage, ve) and ASL (absolute and rCBF) values were quantified from the tumors. Student independent t test was used to compare ASL and DCE-MRI indices. Pearson correlation was used to see correlation between DCE- and ASL-derived CBF values in tumor and normal parenchyma. RESULTS: On Student t test, neither ASL-derived absolute CBF (P = 0.78) nor rCBF (P = 0.12) values were found to be significantly different in 2 groups, whereas DCE indices except ve were significantly higher in high-grade gliomas. Arterial spin labeling-derived rCBF values weakly correlated with DCE-derived rCBF values, whereas these did not show correlation in normal grey (P = 0.12, r = 0.2) and white (P = 0.26, r = 0.14) matter regions. CONCLUSIONS: Three-dimensional pseudocontinuous arterial spin labeling does not appear to be a reliable technique in the current form and may not be a suitable replacement for DCE in grading of glioma.