This paper presents a novel deep learning model for skin disease diagnosis, focusing on multi-feature fusion. The authors propose a Fully Fused Network (FFN) that combines an Improved Single Block (ISB) and an Improved Fusion Block (IFB) to enhance the accuracy of skin disease identification. The model is implemented using a convolutional neural network (CNN) and is evaluated on proprietary and publicly available datasets, including ISIC2016, ISIC2017, and HAM10000. The highest accuracy achieved was 86% for ISB, 90% for IFB, and 92% for FFN using HAM10000 with different ResNet configurations. These results represent improvements of 9.2%, 13.2%, and 15.2% over state-of-the-art methods, respectively. The paper also reviews existing approaches, such as MFF-Net, HAC-LF, co-attention blocks, and GFANet, highlighting their contributions to skin disease classification and segmentation.This paper presents a novel deep learning model for skin disease diagnosis, focusing on multi-feature fusion. The authors propose a Fully Fused Network (FFN) that combines an Improved Single Block (ISB) and an Improved Fusion Block (IFB) to enhance the accuracy of skin disease identification. The model is implemented using a convolutional neural network (CNN) and is evaluated on proprietary and publicly available datasets, including ISIC2016, ISIC2017, and HAM10000. The highest accuracy achieved was 86% for ISB, 90% for IFB, and 92% for FFN using HAM10000 with different ResNet configurations. These results represent improvements of 9.2%, 13.2%, and 15.2% over state-of-the-art methods, respectively. The paper also reviews existing approaches, such as MFF-Net, HAC-LF, co-attention blocks, and GFANet, highlighting their contributions to skin disease classification and segmentation.