Back

Deep Learning-Based Screening for POLE mutations on Histopathology Slides in Endometrial Cancer

van den Berg, N.; Schoenpflug, L.; Horeweg, N.; Volinsky-Fremond, S.; Barkey-Wolf, J.; Andani, S.; Lafarge, M. W.; Oertft, G.; Jobsen, J. J.; Razack, R.; Gerestein, K.; Jonges, T.; de Kroon, C. D.; Nout, R.; Tseng, D.; Kuijsters, N.; Powell, M. E.; Khaw, P.; Shepherd, L.; Leary, A.; de Boer, S. M.; Kommoss, S.; van den Heerik, A. S. V. M.; Haverkort, M. A. D.; Church, D.; de Bruyn, M.; Smit, V. T. H. B. M.; Steyerberg, E.; Creutzberg, C. L.; Koelzer, V. H.; Bosse, T.

2026-02-09 pathology
10.64898/2026.02.06.26345335 medRxiv
Show abstract

POLE sequencing for somatic mutations (POLEmut) guides adjuvant therapy in endometrial cancer (EC), but cost and infrastructural considerations lead to limited uptake. Omission of POLE testing leads to unnecessary exposure to radiotherapy and/or chemotherapy. We developed POLARIX, a multiple instance deep learning model with attention pooling, which predicts POLE mutation status from routine hematoxylin and eosin whole-slide images (WSIs). Trained on 2,238 cases from eleven EC cohorts, POLARIX showed clinical-grade discrimination across three external cohorts (Pooled: AUC=0.95, 95% CI: 0.91-0.98; n=68/481 POLEmut/POLEwt). Attention maps highlight POLE morphologies. Clinical applicability is demonstrated using predefined thresholds based on three resource scenarios. The most sensitive threshold ("Low") yields a test reduction of 77% (73%-81%) (sensitivity: 93% (85%-99%), specificity: 89% (87%-92%)). POLARIX is an interpretable and cost-efficient approach to reduce POLE testing in women with endometrial cancer, broadening access to precision oncology.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
Nature Communications
4913 papers in training set
Top 9%
14.9%
2
Modern Pathology
21 papers in training set
Top 0.1%
12.6%
3
Clinical Cancer Research
58 papers in training set
Top 0.1%
10.2%
4
Cancer Research
116 papers in training set
Top 0.4%
4.9%
5
The Lancet Digital Health
25 papers in training set
Top 0.1%
4.9%
6
Cell Reports Medicine
140 papers in training set
Top 1%
4.0%
50% of probability mass above
7
The Lancet Infectious Diseases
71 papers in training set
Top 0.7%
3.7%
8
eBioMedicine
130 papers in training set
Top 0.5%
2.6%
9
npj Precision Oncology
48 papers in training set
Top 0.3%
2.4%
10
npj Digital Medicine
97 papers in training set
Top 2%
2.1%
11
British Journal of Cancer
42 papers in training set
Top 0.6%
2.1%
12
Science Translational Medicine
111 papers in training set
Top 2%
2.1%
13
Nature Cancer
35 papers in training set
Top 0.7%
1.7%
14
Journal of Pathology Informatics
13 papers in training set
Top 0.2%
1.7%
15
JNCI Cancer Spectrum
10 papers in training set
Top 0.3%
1.3%
16
Annals of Oncology
13 papers in training set
Top 0.6%
1.2%
17
Nature Medicine
117 papers in training set
Top 3%
1.2%
18
Scientific Reports
3102 papers in training set
Top 66%
1.2%
19
PLOS ONE
4510 papers in training set
Top 64%
0.9%
20
ACS Nano
99 papers in training set
Top 3%
0.9%
21
Clinical Infectious Diseases
231 papers in training set
Top 4%
0.9%
22
Journal of Clinical Investigation
164 papers in training set
Top 5%
0.9%
23
Cancers
200 papers in training set
Top 5%
0.8%
24
EMBO Molecular Medicine
85 papers in training set
Top 4%
0.8%
25
JCO Clinical Cancer Informatics
18 papers in training set
Top 0.8%
0.8%
26
Breast Cancer Research
32 papers in training set
Top 0.5%
0.7%
27
Cancer Medicine
24 papers in training set
Top 2%
0.7%
28
Nature Machine Intelligence
61 papers in training set
Top 4%
0.5%
29
Biomedicines
66 papers in training set
Top 5%
0.5%
30
Experimental & Molecular Medicine
14 papers in training set
Top 0.4%
0.5%