search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
DIGITAL PATHOLOGY


there is sufficient tumour cell content to successfully analyse the entire sample, the slide can be automatically marked for whole-slide scrape.


Future applications in digital pathology


Although it is impossible to correctly forecast which of a myriad of AI applications will advance the fastest towards mass adoption in the clinic, possibilities include adoption of AI tools for tumour detection, slide quality control, IHC scoring, tumour grading, macrodissection, and novel applications. As well as assisting pathologists with their diagnostic workload for high volume cases, such as for breast and colorectal cancers, AI tools will become available for diagnosing rare diseases, assisting pathologists in clinics which do not have specialists for such diseases. Only a few commercially available tools have been approved in the EU and UK for predicting biomarker status from H&E images in a diagnostic setting, and this novel application has not yet been widely translated to the clinic.18,19 Given advancements in life sciences applications, adoption could increase after more in-depth validation studies are performed.20


AI can ‘see’ and analyse


patterns and visual indicators within patient tissue samples that are either too nuanced to reproducibly report and be included in standardised clinical guidelines, or are in fact invisible to the human eye.20


Using such complex


morphological information, AI algorithms will be able to perform as yet unidentified diagnostic and prognostic analysis and suggest biomarker expression scores from H&E images, reducing the need for additional tests, preserving patient tissue, and creating a new method of evaluating pathology slides.21


A challenge remains in


using this information to create human- interpretable features so they can be properly quantified and used in clinical diagnosis. An alternative realisation of this technology could include routine scanning of H&E slides with an algorithm capable of flagging those that are likely to have a genetic mutation present, something already possible for common aberrations like microsatellite instability.19,20


Another potential novel application involves AI review of patient information and charts and incorporating that information into the analysis of pathology images. With AI tools collecting data from patient history files, information about lifestyle choices, prescription medications, and other clinically relevant information could be used to adjust evaluation and render more accurate and


48 LIS | LIMS VNA OME.TIFF PACS


Clinical Data Systems


Scanners


20+ Image Formats (Brightfield and Fluorescence)


DICOM


HALO Link


3rd Party AI


HALO


Other IMS


Research & Admin Data Systems


AI and IA


Clinical AI HALO®


& HALO AI


Fig 4. HALO AP is compatible with a wide range of brightfield and fluorescent image file formats, including DICOM and OME.TIFF and is compatible with a diverse array of scanners, including Hamamatsu and Leica scanners. Bidirectional connectivity via API enables seamless integration with existing laboratory systems including the Xyall Tissector for automated macrodissection workflows.


precise clinical diagnoses and prognoses. For instance, someone who has a lung cancer biopsy could have their smoking history considered while the presence of anthracotic pigment on the biopsy could be automatically removed because they are a known smoker. This would both improve patient care and provide an additional metric for quality control, enhancing patient safety and treatment outcomes. The future also holds the possibility of algorithms and tools being used together in advanced digital pathology workflows. Slides could be automatically scanned using AI-powered slide quality control tools, have their tumour content and IHC expression analysed, and be triaged based on clinical priority before the pathologist ever receives the case. To realise this future, enterprise digital pathology platforms that centralise AI


algorithms for clinical use must be highly flexible and interoperable, enabling laboratories to adapt and work with their laboratory information system or laboratory information management system (LIS | LIMS) of choice. The digital pathology platform must also be user- friendly, intuitive, and accessible to all skill levels.


In summary, the future AI-assisted pathologist will be enabled to work remotely while expediting diagnostic workflows through automated quantification of biomarkers and grading of malignancies, improved slide quality control, AI-powered tumour quantification, and more. With a diverse array of AI applications that could democratise molecular testing, improve patient chart management, and more, the pathologist will increasingly be at the centre of a cockpit of data, enabling them


The process of digitisation and deploying AI-based automated artefact detection algorithms introduces an opportunity to simultaneously scan each slide for artefacts


FEBRUARY 2025 WWW.PATHOLOGYINPRACTICE.COM


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