Over the past decade, deep learning has significantly impacted medical imaging, particularly in segmentation tasks. Encoder-decoder methods have advanced medical image segmentation by restoring feature map resolution and minimizing information loss during decoding. This paper introduces three key contributions: a method for region of interest (RoI) detection that isolates the lung region by classifying CT scan slices using two convolutional neural networks—one for slices above the lungs; an architecture inspired by U-Net, which employs a convolutional Encoder-Decoder-Encoder-Decoder pattern to enhance learning by feeding output feature maps from the first decoder into the second encoder; and concatenation layers between the encoder-decoder networks that reintroduce important features lost in the initial structure, improving the learning of complex features. Evaluation results demonstrate the effectiveness of these methods for lung segmentation, achieving an average DSC of 92.68%.