Stratipath Breast

Stratipath Breast is the first EU regulatory compliant solution for risk stratification of breast cancer using AI-based precision diagnostics to analyse cancer tissue, and enabling identification of patients with increased risk of disease progression.

In contrast to traditional molecular tests, AI-based risk stratification enables faster turnaround times for results, provides new information at the point of diagnosis and reduces the need for expensive molecular testing, allowing for wider use and benefit to more patients.

Stratipath Breast is the first EU regulatory compliant solution for risk stratification of breast cancer using AI-based precision diagnostics to analyse cancer tissue, and enabling identification of patients with increased risk of disease progression.

In contrast to traditional molecular tests, AI-based risk stratification enables faster turnaround times for results, provides new information at the point of diagnosis and reduces the need for expensive molecular testing, allowing for wider use and benefit to more patients.

Addresses the over 50% of breast cancers that are diagnosed as intermediate risk

Deep learning analysis of routine HE-stained histopathology images from resected breast tumours

Rapid analysis can shorten time to treatment

Contributes to reduced costs, time and workload

“Stratipath Breast offers a faster and cheaper alternative to molecular assays, allowing more patients to have access to precision diagnostics. By using Stratipath Breast, clinicians can diagnose with support from prognostic information, while reducing laboratory time and costs.”

Johan Hartman

Professor of pathology at Karolinska Institutet, Stockholm and co-founder of Stratipath

How Stratipath breast works

The system measures risk-associated morphological patterns locally in the image and aggregates this information across the analysed tissue area to establish whether the tumour belongs to high- or low-risk groups. Results from Stratipath Breast provide prognostic information and are intended to be used as a decision support tool, together with other clinical and pathological information.

 

THE AI ANALYSIS IS CARRIED OUT IN PARALLEL WITH THE EXISTING DIAGNOSTIC WORKFLOW

Stratipath Breast provides an optimal workflow through integration with leading digital pathology solutions. It can also be used on its own, via the Stratipath customer web portal. Access to Stratipath Breast will be provided as a Software as a Service solution, by a subscription model.

THE CLASSIFICATION OF INTERMEDIATE RISK TUMOURS INTO LOW- AND HIGH-RISK GROUPS

Histological tumour grade is a strong prognostic factor in breast cancer 1 2. Grading of invasive breast cancer is performed on all invasive breast cancers based on morphological assessment, according to the Nottingham Histologic Grade (NHG), resulting in the low- to high-risk categories NHG 1, 2 or 3 3. But currently, more than 50% of all breast cancer patients are categorised as of intermediate risk (i.e. NHG 2) 4, which provides little clinical utility for treatment decision-making. The consequential over- and undertreatment of patients with early breast cancer has become one of the main challenges for treating physicians, and clinical decisions are often dependent on expensive molecular assays that are not accessible to the majority of patients. Computer-based image analysis enables precise and reproducible classification of digitised histopathology images, and has shown to be able to divide NHG 2 tumours into a low- and high-risk group based on grade-related morphology 5.

Using deep learning, Stratipath Breast enables cancer detection and classification of intermediate risk tumours into low- and high-risk groups, based on grade-related tumour morphology. The stratification comes from a rigorous scientific development process and validation using multi-source real-world datasets, comprising histopathology images and associated clinical outcome data.

1↑ Rakha EA, El-Sayed ME, Lee AH, Elston CW, Grainge MJ, Hodi Z, et al. Prognostic significance of Nottingham histologic grade in invasive breast carcinoma. J Clin Oncol. 2008;26(19):3153-8.
2↑ Rakha EA, Reis-Filho JS, Baehner F, Dabbs DJ, Decker T, Eusebi V, et al. Breast cancer prognostic classification in the molecular era: the role of histological grade. Breast Cancer Res. 2010;12(4):207.
3↑ Elston CW, Ellis IO. Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long-term follow-up. Histopathology. 1991;19(5):403-10.
4↑ Acs B, Rönnlund C, Hagerling C, Ehinger A, Kovács A, Røge R, et al. Variability in breast cancer biomarkerassessment and the effect on oncological treatment decisions: A nationwide 5-year population-based study. Cancers. 2021;13(5):1166.
5↑ Wang Y, Acs B, Robertson S, Liu B, Solorzano L, Wählby C, et al. Improved breast cancer histological grading using deep learning. Ann Oncol. 2022;33(1):89-98.