Dr. Yuri Tolkach (DE) presented a lecture on ‘AI in genitourinary cancer pathology’, focusing on the clinical relevance. He emphasised that there is work to be done before using AI tools for pathology, and even though digital pathology uses 50% less time, there are a lot of costs involved in the setup, the integration can be very difficult, and there are no reimbursement mechanisms for AI tools. “We need some support from clinical disciplines as this is something that urologists can help us with a lot, and other colleagues from oncology, because the application of AI tools brings a lot of benefits to the patients.”

According to Dr. Tolkach, “AI has virtually no limits in pathology but there is still only a handful of tools (which is the same as 3 to 4 years ago), there is still very limited use, mostly because we are not digitalised enough yet. There is a lot of ‘AI hype’ and lots of studies that have no clinical application.”

He cites the results of his digital pathology validation study (Tolkach Y, et. al. NPJ Precision Oncology, 2023). From over 7,000 biopsy cores, there was no 100% accuracy, but the sensitivity of the tools was very high, which is useful for alerting pathologists to areas considered suspicious, rather than the obvious.

A new access to tumour complexity?

“There are huge efforts ongoing, especially in the industry,” stated pathologist Dr. Markus Eckstein (DE) in his lecture on ‘Spatial transcriptomics/proteomics: How AI could improve our understanding of tumour complexity.’ He shared several methods with a review of their resolution, complexity and price, including array-based transcriptome, digital microdissection, mass spectrometry, CyTOF, High Plex ISH and RNA Scope. “All of these methods have pros and cons. You must know what spatial biology study you want to perform and then you can choose the best option.”

Dr. Eckstein was enthusiastic about the discovery earlier this year of the spatial niche interactions from Cellcharter (Varrone et al, Nature Genetics 2024). Cellcharter is an algorithmic framework to identify, characterise, and compare cellular niches in spatially resolved datasets.

Extending diagnostic capabilities

“There is promise in AI and pathology but there are also barriers to overcome, but they are not brick walls,” explained Dr. Gladell Paner (US) in his lecture on ‘Artificial intelligence in grading of urological cancers.’ Firstly, he clarified that “AI in the grading of prostate cancer is architecture-based and AI grading of bladder cancer is cytomorphology-based.” Dr. Paner shared several research studies with results indicating “AI has a comparable accuracy and reproductivity in the grading of PCa with uropathologists. It can be used to enhance the grading of PCa by assisting pathologists, and can identify other grade-derived elements, such as cribriform pattern. For BCa, AI can help identify objective morphometric features for grading BCa.”

According to Dr. Paner there are still challenges in the advancement of AI-based histopathology, and a lengthy list of limitations. “None of the current available AI algorithms are 100% perfect and they need human supervision. It is not superior to a specialist GU pathologist, and the digital pathology workflow for integration of AI-based diagnostics is a costly set up.”

You can watch the full ESUP presentations on the EMUC24 Resource Centre.

The post Pathology: Is AI progressing in clinical application? appeared first on EMUC25.

Taking place on day one of EMUC23 in Marseille, the symposium was co-chaired by Prof. Maurizio Colecchia (IT), Prof. Kerstin Junker (DE) and Dr. Gladell Paner (US).

Dr. Markus Eckstein (DE) presented his lecture ‘Molecular differences between primary bladder tumours and metastasis and differences in PDL – 1 expression’. He began by explaining the metastatic evolution from stem(s) to branches. “Tumour properties driving clonal evolution include genetic alterations, cell cycle alterations, DNA-repair alterations, cell mortality and EMT/MET.”

He stated that metabolic effects include the environment such as oxygen, nutrients and hormones. Immunological selection pressure includes immune invasion and immune suppression. Niche properties include nutrient/oxygen supply, immune surveillance (liver, brain and bone), and stroma conditions.

With this highly complex interaction between many cell populations and environmental factors, Prof. Eckstein concluded with the question, “Can we go on testing biomarkers in primary tumours for precision oncology?”

Middle-grade NMIBC?

A case study was shared by pathologist Prof. Colecchia (IT) during his lecture ‘Proposal of a new grading in non-muscle invasive bladder cancer’. He took a deep dive into explaining how the grading recommendations for NMIBC could be improved, as well as the reproducibility of the grading system.

Prof. Colecchia sited several studies that tried to correlate outcomes between heterogeneous grades. “There were different thresholds for the fraction of high-grade cells. If it is a <10% of a high-grade tumour cell, there was no change in clinical outcomes of low-grade carcinoma. Distinction between low-risk and intermediate-to-high-risk carcinoma can provide the basis for adjuvant intravesical instillation and regimen of BCG (Bacillus Calmette-Guerin) [with its significant side effects].”

Prof. Colecchia reported that in 2022, the WHO proposed criteria for reporting papillary tumours as high-grade as long as the high-grade component represents >5% of the tumour. Moreover, tumours with <5% high-grade component should be reported as ‘low-grade with <5% high-grade component’.

To watch the full presentation, visit the EMUC23 Resource Centre.

The post ESUP: A review of biomarkers and molecular tests in bladder urothelial carcinoma appeared first on EMUC25.

In her lecture “The new WHO classification of renal tumours”, Pathologist Dr. Maria Rosaria Raspollini (IT) shared an update on the 2022 classification changes, addressing the concept of molecularly defined renal tumour entities in particular. According to Dr. Raspollini, traditionally, renal tumour subtypes have been named on the basis of predominant cytoplasmic features (clear cells/pink cells RCC) and chromophobe RCC. Now there are renal tumour subtypes named on the basis of architectural features (papillae RCC).

Dr. Raspollini stated: “Clear cell RCC account for 60-75% of all RCC’s and are characterised by neoplastic cells with predominantly clear and occasionally eosinophilic cytoplasm, accompanied by an abundant network of blood vessels and associated with biallelic VHL inactivation. Chromophobe RCC accounts for 5-7% of cases and are characterised by large pale and/or smaller eosinophilic tumour cells with wrinkled nuclei and perinuclear haloes. The WHO 2022 papillary RCC is characterised by papillary and tubular structures lined by cuboidal cells with scant or lightly basophilic cytoplasm with an overall basophilic appearance. Foamy histiocytes and psammoma bodies may also be present.”

On the topic of new renal tumour entities, Dr. Raspollini stated that clear cell papillary renal cell carcinoma has been reclassified as clear papillary renal cell tumour, because there is not a described metastatic event. “These tumours are mainly pT1 well-circumscribed, encapsulated and cystic change can occur. Specific molecular pathological features that it lacked were chromosome 3p loss and alterations of VHL, as well as mutations in TSC1, TSC2, MTOR or ELOC (TCBE1).”

According to Dr. Raspollini, another new entity is Eosinophilic solid and cystic renal cell carcinoma (ESC-RCC). “These are typically well-circumscribed, tan, solid and cystic, with reported sizes ranging from <10 to 135mm. ESC-RCC is characterised by solid and cystic architecture, eosinophilic cytoplasm and coarsely granular, basophilic cytoplasmic stippling. The majority of ESC-RCC’s appear to have been cured by resection. Rare cases with metastases have been reported.”

Morphological and molecular reporting strategy

During his lecture “The new WHO classification of bladder tumours – why the morphology is important in the molecular age”, Prof. Antonio Lopez-Beltran (PT) shared details on non-invasive urothelial neoplasms, points of practice and novelties, including urothelial papilloma and inverted urothelial papilloma.

“The classification papillary urothelial hyperplasia has disappeared” stated Prof. Lopez-Beltran. “We should report cases even if the WHO does not recognise it”.

Prof. Lopez-Beltran questions the correctness of the newly classified urothelial carcinoma “subtypes”, which were previously “variants”. The term “variant” has been exclusively reserved for genomic alternations. In his opinion, they are genetic variations.

Looking at what lies ahead in the future, Prof. Lopez-Beltran voiced the proposal of a combined morphological and molecular reporting strategy.  “This is an evolving process from WHO in 1973 to WHO 2002/2016 to molecular subtyping using immunohistochemistry. Advantages of combined reports include providing the clinician with more information sooner, leading ultimately to a more personalised approach to current therapies.”

Prof. Lopez-Beltran ended his lecture with the comment “classifications are getting more difficult and more complicated, but we need to tell clinicians that we are going forward. We are driving towards a new time for pathology”.

The post What’s new in GU Pathology and WHO classification? appeared first on EMUC25.

The symposium was chaired by pathologists Prof. Maurizio Colecchia (IT) and Prof. Dr. Antonio Lopez-Beltran (PT), together with Chairman of the EAU Policy Office, Prof. Hein Van Poppel (BE).

In his lecture “Towards a new WHO classification of genitourinary tumours, with emphasis on kidney cancer”, pathologist Dr. Gladell Paner (US) provided a summary of three papers (1) published after the publication of The 2016 WHO Classification of Tumours of the Urinary System and Male Genital Organs. His lecture focused on its updates on renal cell neoplasms and novel renal cell carcinoma (RCC) types.

The updates were as follows:

1. Dividing papillary RCC as subtypes 1 and 2 is no longer recommended.
2. Drop “carcinoma” in clear cell papillary RCC due to low malignant potential.
3. New subset of TFEB RCC defined by amplification not by translocation; this group of tumours is aggressive.
4. Group of SMARCB1-deficient RCCs includes mainly medullary carcinoma.
5. “FH-deficient RCC” (fumarate hydratase–deficient renal cell carcinoma) is the preferred term over hereditary leiomyomatosis and renal cell carcinoma (HLRCC)-associated RCC.
6. Collecting duct RCC with FH-deficient RCC and medullary carcinoma
7. Update on grading chromophobe RCC
8. Proposed terminology “Oncocytic renal neoplasm of low malignant potential, not further classified” to replace “Hybrid oncocytic/chromophobe tumor” proposed for sporadic cases.

Dr. Paner also enumerated the novel entities such as eosinophilic solid and cystic RCC; anaplastic lymphoma kinase (ALK) rearrangement associated RCC; and RCC with fibromyomatous stroma.

Future directions of prostate cancer grading

During her lecture “Prostate cancer grading: Will ‘Gleason’ survive?”, Dr. Alessia Cimadamore (IT) shared the evolution of prostate cancer (PCa) grading, GUPS and ISUP recommendations, and future directions of PCa grading such as 3D architecture reconstruction of PCa growth patterns, which can show two morphological subgroups:

1. The first subgroup comprises Gleason pattern 3, poorly formed and fused Gleason pattern 4, and Gleason pattern 5 cords wherein the vast majority of the tumour cells make direct contact with the surrounding stroma.
2. The second subgroup is comprised of cribriform Gleason pattern 4 and solid Gleason pattern 5 wherein the vast majority of the tumour cells do not make contact with the surrounding stroma.

Dr. Cimadamore also discussed the role of computational pathology and AI. She stated, “AI-based algorithms can perform grading at the level of experienced subspecialised uropathologists. There is a potential avenue for improving inter- and intra-observer variability. Additionally, AI-based algorithms could lead to more accurate quantification of patterns. However, more extensive prospective validation is needed in applying AI in routine practice.”

Another innovation Dr. Cimadamore mentioned was radiomics, which she defined as a method based on the extraction of quantitative features from radiological images that cannot be seen by a radiologist’s naked eye and on the use of these data for the creation of clinical decision support systems.

She stated, “There are several papers published illustrating radiomics is able to distinguish prostate biopsy with cancer with another which has no cancer, grade the prostate cancer, and to perform Gleason grading accurately as a pathologist would.”

Dr. Cimadamore concluded that there is a continuous histologic spectrum of gradual changes in prostate cancer. Although histologic grading of PCa is not fully optimised, AI and radiomics will help pathologists in the near future.

She dedicated her lecture to EAU Section of Uropathology (ESUP) Chair Prof. Rodolfo Montironi, whom she considers her mentor.

Watch the full presentations of Dr. Paner and Dr. Cimadamore as webcasts, as well as, other presentations during the symposium via the Resource Centre.

References:

• “New developments in existing WHO entities and evolving molecular concepts: The Genitourinary Pathology (GUPS) update on renal neoplasia” (Trpkov et al., Mod Pathol 2021;34:1392-1424)
• “Report from the International Society of Urological Pathology (ISUP) Consultation Conference on Molecular Pathology of Urogenital Cancers: III: Molecular Pathology of Kidney Cancer” (Williamson et al., Am J Surg Pathol 2020;44:e15-e86)
• “Novel, emerging and provisional entities: The Genitourinary Pathology Society (GUPS) update on renal neoplasia” (Trpkov et al., Mod Pathol 2021;34:1167-84).

The post Expectations for new WHO classification and what’s next in PCa grading appeared first on EMUC25.

The symposium is co-organised by the EAU Sections of Uro-Pathology (ESUP) and Urological Research (ESUR) and the Uropathology Working Group of the European Society of Pathology. Expert speakers were drawn from these bodies, with speakers of a variety of pathology-related backgrounds.

This year, the ESUP Symposium examined the current state of liquid biopsies in uro-oncology, and it possible future applications. What emerged over the course of the afternoon was a future with a promising perspective, but still a lot of work to be done for researchers and pathologists.

Dr. Michelangelo Fiorentino (Bologna, IT), a clinical pathologist, gave an introductory talk on the current applications, and what uro-oncologists should know before using them. Liquid biopsies refers to the use of blood and other bodily fluids as an alternative to tissue samples for diagnostic purposes.

The potential of liquid biopsies is significant, according to Fiorentino: “The major advantages are the non-invasiveness, removing the need for biopsies. Also, liquid biopsies can give a better representation of all the tumour profiles and genetic mutations. Finally, liquid biopsies can give a better indication on the extent of tumour burden.”

In theory, any lab test for tissue can be used to analyse liquids, but they have to be adapted for much lower concentrations of tumour cells. Some tests can require up to 80ml of blood. As it stands, liquid biopsy is currently much more expensive than conventional histology. The reliability of diagnostic accuracy is also inferior. It is also not entirely clear which professional should be in charge of liquid biopsies: pathologists, biochemists, geneticists or (uro-)oncologists.

Potential for BCa

Following talks on kidney cancer (by ESUR Chairwoman Prof. Kerstin Junker, pictured) and prostate cancer and the potential suitability of liquid biopsies for those urological cancers, Prof. Thomas Gevaert (Leuven, BE) spoke on bladder cancer. “In contrast to other urological cancers, BCa has advantage: we can look at blood as well as urine. By combining analysis of the liquids, and with a variety of techniques we can investigate different substances.”

“The majority of patients with metastatic BCa have circulating tumour DNA. This means there is potential value to stratify patients for clinical trials, as well as potential value in diagnostic and follow-up flowcharts. cfDNA/ctDNA is a very sensitive tool to detect early recurrence and minimal residual disease.”

Gevaert postulated that by combining analysis of cfDNA (mutational landscape) and CTC’s (protein expresession), these could be complementary tools with even better results.

Despite aforementioned advantages of liquid biopsies, particularly for BCa, like its non-invasiveness, the combination of urine and blood, and the pre-screening and monitoring, Gevaert pointed out certain hurdles that need to be cleared before liquid biopsies are adopted.

“As with many new techniques, we are still waiting for prospective validation. We also need standardization in our approach. Crucially, we should not be using liquid biopsies unless there is a clear superiority when compared to traditional biopsies. Sensitivity and specificity of liquid biopsies also need to be determined.”

The post ESUP Symposium examines the potential of liquid biopsies in uro-oncology appeared first on EMUC25.