The Impact of Post-Operative Radiotherapy in Early Stage (pT1-pT2N0M0) Oral Tongue Squamous Cell Carcinoma in Era of DOI

Background: This study investigated the role of depth of infiltration (DOI) as an independent prognosticator in early stage (T1-T2N0M0) oral cavity tumors and to evaluate the need of postoperative radiotherapy in the case of patients upstaged to pT3 for DOI > 10 mm in the absence of other risk factors. Methods: We performed a retrospective analysis on patients treated with surgery and re-staged according to the 8th edition of malignant tumors classification (TNM). The role of DOI as well as other clinical/pathological features was investigated at both univariable and multivariable analyses on overall survival (OS), disease free survival (DFS), relapse free survival (RFS), and local RFS. Results: Among the 94 included patients, 23 would have been upstaged to pT3 based on DOI. Multivariable analysis showed that DOI was not an independent prognostic factor for any of the considered outcomes. The presence of perineural invasion was associated with a significant worse RFS (p = 0.02) and LRFS (p = 0.04). PORT was found to be significantly associated with DFS (p = 0.04) and RFS (p = 0.06). Conclusions: The increasing DOI alone was not sufficient to impact the prognosis, and therefore, should not be sufficient to dictate PORT indications in early-stage patients upstaged on the sole basis of DOI.

Benign and malignant breast tumors classification based on texture analysis and backpropagation neural network

Breast cancer is a leading cause of death in women due to cancer. According to WHO in 2018, it is estimated that 627.000 women died from breast cancer, that is approximately 15 % of all cancer deaths among women [3]. Early detection is a very important factor to reduce mortality by 25-30 %. Mammography is the most commonly used technique in detecting breast cancer using a low-dose X-ray system in the examination of breast tissue that can reduce false positives. A Computer-Aided Detection (CAD) system has been developed to effectively assist radiologists in detecting masses on mammograms that indicate the presence of breast tumors. The type of abnormality in mammogram images can be seen from the presence of microcalcifications and the presence of mass lesions. In this research, a new approach was developed to improve the performance of CAD System for classifying benign and malignant tumors. Areas suspected of being masses (RoI) in mammogram images were detected using an adaptive thresholding method and mathematical morphological operations. Wavelet decomposition is performed on the Region of Interest (RoI) and the feature extraction process is performed using a GLCM method with 4 statistical features, namely, contrast, correlation, entropy, and homogeneity. Classification of benign and malignant tumors using the MIAS database provided an accuracy of 95.83 % with a sensitivity of 95.23 % and a specificity of 96.49 %. A comparison with other methods illustrates that the proposed method provides better performance.

Brain Tumors Classification System Using Convolutional Recurrent Neural Network

The brain is a body organ that controls exercise of the relative multitude of parts of the body. Conceding robotized mind tumors in MRI (Magnetic Reverberation Imaging) is a confounded assignment given size and area variety. This strategy decides a wide range of malignancies in the body. Past techniques devour additional time with less accuracy. A manual assessment can be mistaken because of the degree of intricacies engaged with cerebrum tumors and their properties. However, the above proposition isn’t appropriate for mind tumors because of colossal varieties in size and shape. Our proposed strategy to magnify arrangement performance. First, the expanded tumor district using picture enlargement is utilized to return for capital invested rather than the unique tumor area since it can give hints for tumor types. Second, expanded tumor locale split into progressively refined ring structure subregions. With three-component extraction approaches, employing photographs for information augmentation and rotating photographs at various angles, evaluate the performance of the suggested strategy on a large dataset. Utilizing Convolutional Recurrent Neural Network (CRNN), grouping of the tumor into three categories and thus give a virtual portrayal of exact value.

Morphology classification of liver tumors (comparison of the last and previous WHO classifications 2010 and 2019)

Some changes and details of the last WHO liver tumors classification (2019) in comparison with the previous WHO classification (2010) are being discussed. Using different methods of investigations allow us to get better understanding of pathologic processes and their evolution. It is highly recommended to use WHO classification of tumours. 5th Edition. Digestive System Tumours. Еdited by the WHO Classification of Tumours Editorial Board. Lyon, IARC Press, 2019 in everyday clinical practice and scientific activity.