Early cancer screening is crucial for both survival time and quality of life of patients, and the use of algorithmic techniques can provide rapid feedback to doctors on auxiliary screening results. Based on this, this paper proposes a tumor cell detection method based on the combination of Whale Optimization Improvement Algorithm and Support Vector Machine. For the problem of low accuracy of WOA-SVM algorithm under 10-fold cross-validation, the support vector machine recursive feature elimination method SVM-RFE is used to reduce the dimensionality of the original dataset, and then the WOA algorithm is improved by introducing the idea of dynamically increasing the high-quality operators and obtaining the MWOA algorithm. In order to verify the effectiveness of the method proposed in this article, multiple methods are designed for comparison. The example results show that the accuracy of the improved model proposed in this essay is improved by 5% compared with the traditional support vector machine algorithm model, and the accuracy is improved by about 0.5% compared with the WOA-SVM model, which verifies the effectiveness of the improved model in the field of tumor cell detection.