A hybrid DenseNet121-UNet model for brain tumor segmentation from MR Images

•Since we train the images by dividing them into small-sized pieces, the training time is relatively short.•We propose a hybrid model by preprocessing the dataset, critical in im-balanced label distributions.•A hybrid algorithm for brain tumor segmentation is proposed by using DenseNet121-UNet architecture.•We achieve better results than other studies in detecting whole tumor, core tumor, and enhancing tumor by improving low DSC accuracy rate.•We ensure unnecessary areas for feature extraction and remove them by cropping images, which improves the accuracy of the segmentation process and shortens the training time of the model.