Histopathologic analysis through biopsy has been one of the most useful methods for the assessment of malignant neoplasms. However, some aspects of the analysis such as invasiveness, evaluation range, and turnaround time from biopsy to report could be improved. Here, we report a novel method for visualizing human cervical tissue three-dimensionally, without biopsy, fixation, or staining, and with sufficient quality for histologic diagnosis. Near-infrared excitation and nonlinear optics were employed to visualize unstained human epithelial tissues of the cervix uteri by constructing images with third-harmonic generation (THG) and second-harmonic generation (SHG). THG images enabled evaluation of nuclear morphology in a quantitative manner with six parameters after image analysis using deep learning. It was also possible to quantitatively assess intraepithelial fibrotic changes based on SHG images and another deep learning analysis. Using each analytical procedure alone, normal and cancerous tissue were classified quantitatively with an AUC ≥0.92. Moreover, a combinatory analysis of THG and SHG images with a machine learning algorithm allowed accurate classification of three-dimensional image files of normal tissue, intraepithelial neoplasia, and invasive carcinoma with a weighted kappa coefficient of 0.86. Our method enables real-time noninvasive diagnosis of cervical lesions, thus constituting a potential tool to dramatically change early detection. Significance: This study proposes a novel method for diagnosing cancer using nonlinear optics, which enables visualization of histologic features of living tissues without the need for any biopsy or staining dye.

Histopathological diagnosis is the ultimate method of attaining the final diagnosis; however, the observation range is limited to the two‐dimensional plane, and it requires thin slicing of the tissue, which limits diagnostic information. To seek solutions for these problems, we proposed a novel imaging‐based histopathological examination. We used the multiphoton excitation microscopy (MPM) technique to establish a method for visualizing unfixed/unstained human breast tissues. Under near‐infrared ray excitation, fresh human breast tissues emitted fluorescent signals with three major peaks, which enabled visualizing the breast tissue morphology without any fixation or dye staining. Our study using human breast tissue samples from 32 patients indicated that experienced pathologists can estimate normal or cancerous lesions using only these MPM images with a kappa coefficient of 1.0. Moreover, we developed an image classification algorithm with artificial intelligence that enabled us to automatically define cancer cells in small areas with a high sensitivity of ≥0.942. Taken together, label‐free MPM imaging is a promising method for the real‐time automatic diagnosis of breast cancer.