The early detection of diseases such as brain tumor and lung cancer is achieved through segmenting these images. As these images are typified to contain obscure structures, a precise segmentation method needs to be evolved. The principal idea is to devise an unsupervised segmentation technique for medical images involving a partial fractional derivative (PFD)-dependent texture extraction model and an unsupervised clustering algorithm. Basically, image segmentation process allocates different tags to diverse image regions. In this chapter, the process is considered to be texture-based segmentation by representing every tag with an exclusive texture label. The textural features are extorted using PFD-based model. The ISODATA clustering is suggested for segmentation through pixel-based classification. This process is experimented on different test cases such as images of lung cancer detection and brain tumor detection and is able to produce higher accuracy than existing methods. © Springer Nature Singapore Pte Ltd. 2018.