This paper presents an observation of improving clinical picture classification via transfer getting to know and meta-studying. Switching getting-to-know and meta-learning methods are usually employed in medical imaging class tasks. Transfer studying objectives to switch information and illustration from a properly-trained version and mildew that expertise to higher healthy the problem at hand, while meta-gaining knowledge is a version of switch gaining knowledge of which targets to seize and adapt the generalizable expertise of a project domain, and to allow a progressed impact for the goal tasks. Inside the clinical imaging scenario, the two procedures can dig deeper into the several layers which might be involved in gaining deep knowledge of algorithms. The authors compare the effectiveness of the proposed strategies in five publicly available medical imaging datasets. Effects have shown that the proposed techniques notably advanced the usual type accuracy for a few datasets. Furthermore, it was found that the 2-step technique showed higher performance than the one-step technique. This study presents a higher understanding of the efficacy of transfer learning and meta-mastering techniques for clinical photo-type tasks.