Advances in digitizing tissue slides and the fast-paced progress in
artificial intelligence, including deep learning, have boosted the field of
computational pathology. This field holds tremendous potential to automate
clinical diagnosis, predict patient prognosis and response to therapy, and
discover new morphological biomarkers from tissue images. Some of these
artificial intelligence-based systems are now getting approved to assist
clinical diagnosis; however, technical barriers remain for their widespread
clinical adoption and integration as a research tool. This Review consolidates
recent methodological advances in computational pathology for predicting
clinical end points in whole-slide images and highlights how these developments
enable the automation of clinical practice and the discovery of new biomarkers.
We then provide future perspectives as the field expands into a broader range
of clinical and research tasks with increasingly diverse modalities of clinical
data.
Advances in digitizing tissue slides and artificial intelligence, including deep learning, have revolutionized the field of computational pathology. This remarkable combination of technologies has unlocked the potential to automate clinical diagnosis, predict patient prognosis and response to therapy, and discover new morphological biomarkers from tissue images. These developments have not only improved the accuracy and efficiency of pathology analysis but also opened up exciting possibilities for personalized medicine and precision healthcare.
One of the most significant achievements in this field is the approval of artificial intelligence-based systems to assist clinical diagnosis. These systems have shown impressive performance in accurately identifying abnormalities and classifying different types of diseases from whole-slide images. However, despite their promising results, there are still technical barriers that need to be overcome for their widespread adoption and integration into clinical practice. These barriers include challenges related to standardization, scalability, interpretability, and regulatory compliance.
This Review aims to consolidate recent methodological advances in computational pathology for predicting clinical endpoints in whole-slide images. By summarizing and analyzing these advancements, we can gain a deeper understanding of how computational pathology can automate clinical practice and enable the discovery of new biomarkers. The multi-disciplinary nature of this field is evident, as it combines expertise from pathology, computer science, machine learning, and biomedical engineering.
Looking ahead, there are exciting future perspectives for computational pathology. The field is rapidly expanding into a broader range of clinical and research tasks, encompassing not only histopathology but also other modalities of clinical data such as radiology, genomics, and proteomics. Integrating these diverse sources of data will enable more comprehensive and holistic patient assessment, leading to improved diagnostics, treatment planning, and outcomes.
Moreover, as artificial intelligence algorithms become more sophisticated and capable of handling complex medical data, computational pathology holds great potential for personalized medicine. The ability to predict patient prognosis and response to therapy with high accuracy will revolutionize treatment strategies, allowing for targeted therapies and personalized interventions. Additionally, automated analysis of tissue images can uncover novel morphological biomarkers that may serve as important prognostic indicators or therapeutic targets.
In conclusion, the field of computational pathology has witnessed significant advancements in recent years, fueled by developments in digitization and artificial intelligence. The integration of these technologies has not only improved diagnostic accuracy and efficiency but also paved the way for personalized medicine and the discovery of new biomarkers. As the field expands into new domains and incorporates diverse clinical data modalities, there is immense potential for transforming clinical practice and advancing our understanding of disease mechanisms.