Interoperability Showcase by Aiforia, Philips, and Software Point: End-to-End Integrated AI Workflow at Fimlab

Friday, June 19th | at 16:20 CEST

Main Auditorium

Join this Interoperability Showcase session featuring Aiforia (by Darshan Kumar, Director of the Global FAS team), Philips (by Ruud Roelofsen, Product Marketing Manager), and Software Point (by Lisbeth Finstad, Solution Specialist) integration at Fimlab (by Lasse Nieminen, MD, Pathologist) to learn how an end-to-end AI-driven diagnostic workflow is brought to life in a clinical diagnostics laboratory. This presentation demonstrates the seamless ecosystem uniting Philips slide digitalization, the Software Point LIS (LVMS), and Aiforia® Breast Cancer Suite. We showcase how scanned slides and metadata are automatically synced to trigger automated AI analysis, enabling pathologists to efficiently prioritize cases directly from their LIS interface and to streamline case review and reporting. Attendees will discover the practical benefits of full digital pathology deployment for clinical diagnostics at Fimlab, including key operational advantages.

Posters and presentations

(Abstract presentation) A Novel Prediction tool (AIFORIA) for Classifying Spindle Cell Lesion subtypes using Deep Learning on H&E Sections
Kristijan Skok (Austria) et al.

June 19 at 14:30 CEST

During the “Machine Learning and Algorithm Development II" session

In this proof-of-concept study, Skok et al. evaluated the performance of two AI models developed with Aiforia® Create, using standard CNNs and Aiforia's proprietary Foundation Engine, to classify complex spindle cell lesion subtypes from routine H&E slides via a weakly supervised approach. The standard CNN-based AI model showed strong sensitivity for solitary fibrous tumors (SFT) but struggled with class imbalance. The AI model built on Foundation Engine provided a more balanced predictive approach, achieving an overall concordance of 64.9% while maintaining solid detection rates for Synovial Sarcoma (66.2% recall). However, accurately identifying MPNST cases remains a complex challenge across all tested architectures, highlighting the need for further dataset expansion and targeted model optimization to enhance clinical applicability.

Check the video to hear Dr. Kristijan Skok and Prof. Dr. Bernadette Liegl-Atzwanger discuss their research and the use of AI in clinical pathology ⬇️

(P147) CAD-assisted histological diagnosis in prostate mapping: a multicentric Italian experience of the AI-FLOPP study
Moira Ragazzi (Italy) et al.

In this study, Ragazzi et al. evaluated the performance of the Aiforia® Prostate Cancer Biopsy AI solution in two Italian hospitals. The results demonstrate that the AI algorithm achieves pathologist-level accuracy, with a sensitivity of approximately 99% (~97% in Reggio Emilia and ~99% in San Raffaele), demonstrating exceptional consistency across different scanning ecosystems. The findings indicate that the AI algorithm serves as a valuable tool for screening negative slides, while a pathologist review remains required for positive cases.

Check our interview with Dr. Moira Ragazzi to discover more about the study. ⬇️

(P132) The Impact of Artificial Intelligence Assistance on Interobserver Agreement in ER, PR, HER2, and Ki-67 Assessment
Fadime Gul Salman (Turkiye) et al.

In this study, Salman et al. evaluated how the Aiforia® Breast Suite affects agreement among pathologists scoring breast cancer biomarkers in 296 cases. The use of AI increased diagnostic consistency and reduced scoring discrepancies for ER, PR, and HER2, notably decreasing complete disagreement for HER2 from 21% to 14%.

Check our interview with Dr. Serdar Balcı from Turkey Memorial Hospital to discover more about the study. ⬇️

Aiforia Foundation Engine Technology

Aiforia incorporates foundation models into the semantic segmentation, object detection, and instance segmentation workflows in Aiforia® Create, Aiforia’s versatile tool for developing AI models for image analysis in digital pathology.

Foundation models can be used to reduce the annotation workload, speeding up the AI training. Learn more about their use at the Aiforia's booth, or download our whitepaper below.

Download whitepaper >

Watch webinar > 

Read press release >

Most recent CE-IVD-marked AI solutions based on Aiforia's Foundation Engine

Aiforia® Clinical Suites deliver integrated workflows to enhance efficiency, consistency, and diagnostic accuracy. Come see a demo of Aiforia’s clinical AI solutions, including the most recent CE-IVD marked solutions for gastric and prostate cancer diagnostics built on Aiforia’s Foundation Engine technology, and more. 

The next generation of the clinical AI solution for prostate cancer diagnostics - Aiforia® Prostate Cancer Biopsy AI application is designed to enhance pathologists’ diagnostic workflow by providing world-class tools for comprehensive analysis and reporting of prostate needle biopsies.

More about Aiforia® Prostate Suite >

Aiforia® Gastric Cancer solution is designed to support a high-sensitivity diagnostic approach, helping pathologists focus their attention on suspicious areas and reducing the risk that cancerous regions go unnoticed. The AI solution supports detection across all major types of gastric cancer, including hard-to-identify forms, where tumor cells can be sparse and difficult to see. 

More about Aiforia® Gastric Suite >

Explore the full portfolio of Aiforia's clinical AI solutions here >>>