Nonlinear optical microscopy (NLOM) emerged as a powerful imaging modality in cancer diagnosis, offering unparalleled capabilities for label-free, high-resolution visualization of tissue architecture and cellular dynamics with minimal invasion. By leveraging nonlinear optical phenomena, techniques such as two-photon fluorescence (TPF), second harmonic generation (SHG), third harmonic generation (THG), and coherent anti-Stokes Raman scattering (CARS) enable detailed imaging of the tumor microenvironment (TME), extracellular matrix (ECM), and cellular interactions at subcellular resolution without the requirement for external contrast agents. These techniques are particularly effective for assessing the ECM structure, collagen organization, and tumor-associated features critical to cancer progression. This chapter systematically examines specific applicationsApplications of NLOM across major cancer types, including breast, skin, brain, and gastrointestinal (GI) cancers. For breast cancerBreast cancer, NLOM excels in detecting tumor-associated collagen signatures (TACSTumour-associated collagen signature (TACS)) and monitoring collagenCollagen reorganization. In skin cancer, it enables detailed imaging of tissue morphology and assessment of tumor margins, supporting both diagnosticDiagnostics accuracy and surgical precision, while in brain cancers, it delineates tumor boundaries and cellular infiltration patterns. The NLOM also facilitates early detection of GI malignancies and accurate evaluation of surgical margins. A comparative analysis with conventional optical imaging modalities, such as confocal microscopy, optical coherence tomography (OCT), and Raman microspectroscopy, underscores NLOM’s superior imaging depth, resolution, and intrinsic label-free imaging capabilities. Challenges related to depth penetration, signal-to-noise ratio (SNR) optimization, and miniaturization for clinical translation are discussed alongside strategies to overcome them. This chapter highlights advancements in hardware, software, and artificial intelligence (AI), emphasizing their role in real-time, in vivo cancer detectionCancer detection and monitoring. This extensive review is a valuable resource for researchers and clinicians interested in understanding the principles, applications, and future directions of NLOM in cancer diagnosisCancer diagnosis.