Predicting Malignant Cancer Using Machine Learning

One of the primary concerns that is also a demanding issue within the realm of medical specialism is the detection and removal of tumours. Because visualisation approaches had the drawback of being adversarial, doctors relied heavily on MRI images to provide a superior result. Pre-processing, tumour segmentation, and tumour operations are the three stages in which tumour image processing takes place. Following the acquisition of the source image, the original image is converted to grayscale. Additionally, a noise removal filter and a median filter for quality development are provided, followed by an exploration stage that yields hits orgasmic identical images. Finally, the watershed algorithm is used to complete the segmentation. This proposed methodology is useful in automatically organising reports in a short amount of time, and exploration has resulted in the removal of many less tumour parameters. Keywords: MRI Imaging, Segmentation, Watershed Algorithm.

TO ASSESS VARIOUS BRAIN LESIONS ON MRI

Background- The danger of intracranial pathology is that expansion in an enclosed space leads to brain compression causing ischemia, swelling and loss of function that can be permanent and possibly fatal. Methods- This was a simple observational prospective study carried out at the Department Of Radio-Diagnosis And Modern Imaging, S.P.M.C. & A.G. Of P.B.M. Hospitals, Bikaner. All the patients presented for MR brain study with some neurological complaints and showed positive findings on MRI were included in this study. Results- out of total 120 stroke cases, there were 33 cases of acute arterial infarct, 4 of HIE, 6 cases of ICH, 76 of subacute arterial infarct and 1 case of venous infarct. Similarly, out of total 17 cases of tumors, 9 cases were of meningioma, 4 of lymphoma, 2 of glioma and metastasis each. Out of total 9 cases of infections, there were 3 cases of abscess, 2 of encephalitis and 4 of tubercular meningitis. There were 1 case of pontine myelinolysis, 2 cases of ADEM and 1 cases of diffuse axonal injury in this study. Conclusion- Stroke comprised the majority of lesions at 120 cases (80% of the total cases studied). Keywords: MRI, Brain, lesion.

TO CORRELATE THE MRI FINDINGS WITH THAT OF TRANSVAGINAL ULTRASOUND

This Study was done in the Department of Radio diagnosis of Amaltas Institute of Medical Sciences, Dewas, Madhya Pradesh, A total of 65 patients who were referred to our department with clinical suspicion of endometrial lesions and incidentally detected endometrial lesions on ultrasonography underwent transvaginal ultrasound. Result:On TVS 29% cases were diagnosed as endometrial hyperplasia. 25% cases were diagnosed as malignantetiology. Overall benign lesions predominated comprising of 75% of total lesions. Other benign lesions identified on TVS were endometrial polyp,endometritis,submucosal fibroid ,adenomyosis and synechiae. Conclusion: TVS should be used as the primary imaging modality in endometrial lesions as it is dynamic, widely available and less expensive. But it is less sensitive in diagnosing malignant endometrial lesions and there extend. Accuracy of TVS is 82% in detecting malignant endometrial lesions. All patients with even slight suspicion of malignancy based on clinical features, age and TVS findings should be subjected to pelvic MRI. Keywords: MRI, Transvaginal, Ultrasound & Endometrial lesions