DIGITAL PATHOLOGY
Harnessing AI for digital pathology in clinical and diagnostic workflows
With digital equipment and workflows now proliferating in pathology laboratories, the next technological leap is the introduction of artificial intelligence. Here, Dr Kayla Hackman MD, Benjamin Dyer and Hallie Rane look at the roles for AI in clinical and diagnostic workflows.
Anatomic pathology is undergoing a significant transformation with the advent of artificial intelligence (AI). Advances in computer vision and deep-learning methodologies have resulted in AI tools capable of performing tasks traditionally completed by humans, such as slide quality control, immunohistochemistry (IHC) expression analysis, cancer diagnosis and grading, and tumour estimation for slide macrodissection. The increasing adoption of digital pathology scanners in clinical and research laboratories, the availability of AI tools in the life sciences, and the decreasing cost of storing whole-slide image (WSI) data have facilitated the creation of large, diverse data sets suited for AI analysis. At the same time, the growing complexity of pathology cases and the worsening shortage of pathologists have created a pressing need for methods that automate and expedite the diagnostic process; a problem AI is uniquely situated to address.1
This article discusses some of the
current and potential applications of AI in the field of clinical and diagnostic digital pathology and makes the case for an AI-augmented pathologist empowered to do more through AI assistance.
Fig 1. Haematoxylin and eosin (H&E) images analysed with a slide quality control AI algorithm. H&E images are shown in the left-hand column and the image analysis markup is shown in the right- hand column. Artefact is shown in magenta and acceptable tissue is shown in cyan.
WWW.PATHOLOGYINPRACTICE.COM FEBRUARY 2025 Benefits of AI
The incidence of cancer is expected to increase, with total global cases predicted to double between 2020 and 2070.2 With a shortage of trained pathologists, methods to alleviate the increased case burden are essential to maintain high-quality and timely diagnostics. Research increasingly demonstrates that AI tools can significantly enhance the accuracy and efficiency of pathological evaluation.3,4 AI offers numerous benefits within the context of digital pathology, including
45
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60
