**8. Conclusions**

AI applications in prostate mpMRI are promising tools for more effective and efficient image interpretation, leading to improved care. In pure image interpretation, ML has shown noteworthy progress in prostate organ segmentation and volume estimation. As better-curated data becomes available for prostate lesions, ML will likely become more successful at lesion detection, volume estimation, and characterization. As ML evolves, it will indisputably change radiologists' workflow by performing many of the simple tasks in image interpretation. However, ML will not replace the role of radiologists, who are critical to solving complex clinical problems [104]. AI is poised to enhance the decisions made by radiologists. It will enable radiologists to better care for their patients rather than supersede the need for radiologists.

Similarly, ML's ability to evaluate complex datasets across different domains suggests this technique may facilitate the bridging of advanced imaging, such as mpMRI, with emerging biomarker analysis or tumor genetics. Thus, ML may form the underpinnings of radiogenomics, allowing for the integration of imaging data, blood chemistry analysis, and pathologic evaluation in forming complex models that can predict treatment response. Enabled by larger datasets and more sophisticated mathematical techniques, ML could progress to creating completely automated tools that receive a patient's prostate mpMRI images and then delineate a range of desired features, as well as giving likelihood metrics for an array of pathologies.

**Funding:** This review was partially funded by the Radiological Society of North America Medical Student Research Grant RMS1902 and the Alpha Omega Alpha Carolyn L. Kuckein Student Research Fellowship.

**Conflicts of Interest:** Author Peter D. Chang, MD, is a co-founder and shareholder of Avicenna.ai, a medical imaging startup. Author Daniel S. Chow, MD, is a shareholder of Avicenna.ai, a medical imaging startup, and a grant recipient from Cannon Inc. The other authors declare no conflicts of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.
