Medical Imaging through Machine Learning Technique

In this analysis propose and evaluate the convolution neural network designed for classification of ILD patterns. The 7outputs of ILD patterns: healthy, ground glass opacity (GGO), micro nodules, consolidation, reticulation, honeycombing and a combination of GGO/reticulation. To train and evaluate the CNN, we used rst deep CNN designed for the specic problem. Finally we classify the performance (91 %) demonstrated the potential of CNNs in analyzing lung patterns. We proposed a deep CNN to classify lung CT image patches into7classes, including 6 different ILD pattern sand healthy tissue. The method can be easily trained on additional textural lung patterns while performance could be further improved. The slight punctuation of the results, for the same input, due to the random initialization of the weights. Data or class imbalance in the training set is also a significant issue in medical image analysis this refers to the number of images in the training data being skewed towards normal and non-pathological images. Rare diseases are an extreme example of this and can be missed without adequate training examples. This data imbalance effect can be ameliorated by using data augmentation to generate more training images of rare or abnormal data, though there is risk of over fitting. Aside from data-level strategies, algorithmic modification strategies and cost sensitive learning have also been Analysis.