Enabling clinical use of foundation models for computational pathology

Audun L Henriksen; Ole-Johan Skrede; Lisa van der Schee; Enric Domingo; Karolina Cyll; Sepp de Raedt; Ilyá Kostolomov; Jennifer Hay

cs.CVFeb 25, 2026

Enabling clinical use of foundation models for computational pathology

Authors: Audun L Henriksen, Ole-Johan Skrede, Lisa van der Schee, Enric Domingo, Karolina Cyll, Sepp de Raedt, Ilyá Kostolomov, Jennifer Hay, +26 more

Organizations: Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway · Department of Pathology, University Medical Center Utrecht, Utrecht, The Netherlands · Department of Oncology, University of Oxford, Oxford, UK · CRUK Beatson Institute of Cancer Research, Garscube Estate, Glasgow, UK · Glasgow Tissue Research Facility, University of Glasgow, Queen Elizabeth University Hospital, Glasgow, UK · Area for Improvement and Digital Transformation, Norwegian Offshore Directorate, Stavanger, Norway · Pathology Department, Hospital Clínic, Barcelona, Spain · Institut d’Investigacions Biomèdiques August Pi I Sunyer (IDIBAPS), Barcelona, Spain · Department of Clinical Foundations, Universitat de Barcelona, Barcelona, Spain · School of Cancer Sciences, Wolfson Wohl Cancer Research Centre, University of Glasgow, Glasgow, UK · Institute of Clinical Medicine, University of Oslo, Oslo, Norway · Department of Gastrointestinal Surgery, Oslo University Hospital, Oslo, Norway · Gloucestershire Cellular Pathology Laboratory, Cheltenham General Hospital, Cheltenham, UK · Institute of Pathology, University Medical Center, Mainz, Germany · Department of Gastrointestinal Oncology, National Cancer Center Hospital East, Kashiwa, Japan · Translational Research Support Office, National Cancer Center Hospital East, Kashiwa, Japan · Department of Cancer Biology and Pathology, University College London, London, UK · Department of Gastroenterological Surgery, Osaka International Cancer Institute, Osaka, Japan · Centre for Human Genetics, University of Oxford, Oxford, UK · Oxford NIHR Comprehensive Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK · Nuffield Division of Clinical Laboratory Sciences, University of Oxford, Oxford, UK · Department of Informatics, University of Oslo, Oslo, Norway · Centre for Research-based Innovation Visual Intelligence, UiT The Arctic University of Norway, Tromsø, Norway

Abstract

Foundation models for computational pathology are expected to facilitate the development of high-performing, generalisable deep learning systems. However, in addition to biologically relevant features, current foundation models also capture pre-analytic and scanner-specific variation that bias the predictions made by downstream task-specific models trained on these features. Here we show that introducing novel robustness losses during downstream model training reduces sensitivity to technical variability. A purpose-designed comprehensive experimentation setup with 27,042 whole-slide images from 6,155 patients is used to train thousands of models from the features of eight well-known foundation models for computational pathology. In addition to a substantial improvement in robustness, our approach improves classification accuracy by focusing on biologically relevant features. It mitigates robustness limitations of foundation models for computational pathology without retraining the foundation models themselves, enabling development of models that are more suitable in real-world clinical use.

Figures & tables

Figure 2: Foundation model robustness issue

Figure 6: Prediction of lymph node metastasis

	Ahus		Aker		Gloucester		VICTOR		Training		QUASAR 2		TransSCOT
Patient count	58		388		265		427		1138		1112		2856
Age
Years	71	(64–77)	70	(60–77)	68	(62–75)	64	(57–71)	67	(59–75)	65	(59–71)	65	(58–70)
Sex
Female	34	(59%)	195	(50%)	144	(54%)	149	(35%)	522	(46%)	474	(43%)	1126	(39%)
Male	24	(41%)	193	(50%)	121	(46%)	278	(65%)	616	(54%)	638	(57%)	1730	(61%)

Table 1: Baseline characteristics for included cohorts in CRC outcome prediction. Data are given as median (interquartile range) or count (percentage) . Time to event statistics are based only on patients with the respective event. CSD: cancer-specific death.

	Aker		Ahus		Gloucester		VICTOR		Mainz		DENEB		Training		Dutch T1
Patient count	69		243		444		282		135		61		1234		290
Age
Years	71	(59–77)	73	(63–79)	70	(64–77)	64	(58–71)	73	(66–79)	61	(52–72)	69	(61–77)	68	(63–74)
Sex
Female	36	(52%)	128	(53%)	182	(41%)	102	(36%)	60	(44%)	31	(51%)	539	(44%)	126	(43%)
Male	33	(48%)	115	(47%)	262	(59%)	180	(64%)	75	(56%)	30	(49%)	695	(56%)	164	(57%)

Table 2: Baseline characteristics for included cohorts in CRC T1 LNM prediction. Data are given as median (interquartile range) or count (percentage) . Time to event statistics are based only on patients with the respective event.

Figure 1: WSI prediction score comparison between tissue sections. Comparison of model score between different tissue sections from the same patient. Each dot represents one tissue section. For each patient, the x-axis is the prediction score on a tissue section scanned at ICGI, on 5 different scanners, and the y-axis is the score of a original tissue section. For each scatterplot, kernel density estimates are shown for both the original tissue sections and the tissue sections scanned at ICGI.

	Model	No robustness loss	Embedding loss		Score loss		Both losses
c-index	H-optimus-0	0.661 $\pm$ 0.014	0.682 $\pm$ 0.013	(6%)	0.689 $\pm$ 0.005	(7%)	0.694 $\pm$ 0.006	(10%)
	H-optimus-1	0.692 $\pm$ 0.011	0.689 $\pm$ 0.009	(-2%)	0.695 $\pm$ 0.004	(1%)	0.699 $\pm$ 0.005	(2%)
	Hibou-L	0.654 $\pm$ 0.012	0.678 $\pm$ 0.007	(7%)	0.672 $\pm$ 0.005	(6%)	0.680 $\pm$ 0.004	(7%)
	Phikon-v2	0.654 $\pm$ 0.017	0.668 $\pm$ 0.014	(4%)	0.666 $\pm$ 0.004	(4%)	0.678 $\pm$ 0.006	(7%)
	Prov-GigaPath	0.662 $\pm$ 0.013	0.676 $\pm$ 0.008	(1%)	0.673 $\pm$ 0.004	(0%)	0.680 $\pm$ 0.007	(5%)
	UNI	0.681 $\pm$ 0.010	0.680 $\pm$ 0.012	(0%)	0.670 $\pm$ 0.005	(0%)	0.683 $\pm$ 0.005	(0%)

Table 3: Performance comparison between different loss terms in survival prediction. Metric summary results are given as mean

\pm

standard deviation ( relative improvement ). For all columns with robustness loss, the best weight (

\lambda

) is used, and improvement is relative to no robustness loss (

\lambda

= 0).

	Model	No robustness loss	Embedding loss		Score loss		Both losses
Balanced accuracy	H-optimus-0	0.611 $\pm$ 0.014	0.608 $\pm$ 0.014	(0%)	0.647 $\pm$ 0.014	(10%)	0.620 $\pm$ 0.019	(2%)
	H-optimus-1	0.631 $\pm$ 0.009	0.638 $\pm$ 0.011	(5%)	0.628 $\pm$ 0.018	(2%)	0.612 $\pm$ 0.026	(-5%)
	Hibou-L	0.661 $\pm$ 0.013	0.655 $\pm$ 0.013	(2%)	0.662 $\pm$ 0.013	(6%)	0.688 $\pm$ 0.016	(8%)
	Phikon-v2	0.618 $\pm$ 0.011	0.617 $\pm$ 0.014	(6%)	0.625 $\pm$ 0.015	(8%)	0.620 $\pm$ 0.008	(0%)
	Prov-GigaPath	0.635 $\pm$ 0.011	0.620 $\pm$ 0.009	(0%)	0.654 $\pm$ 0.011	(10%)	0.651 $\pm$ 0.015	(4%)
	UNI	0.636 $\pm$ 0.011	0.640 $\pm$ 0.014	(8%)	0.653 $\pm$ 0.014	(14%)	0.605 $\pm$ 0.013	(-8%)

Table 4: Performance comparison between different loss terms in prediction of lymph node metastasis. Metric summary results are given as mean

\pm

standard deviation ( relative improvement ). For all columns with robustness loss, the best weight (

\lambda

) is used, and improvement is relative to no robustness loss (

\lambda

= 0).

Figure 2: Performance vs robustness weight for outcome prediction. Effect of varying $\lambda$ in eq. 1 on inconsistency and c-index. Statistics are gathered from 20 models per value of $\lambda$ per foundation model.

Figure 3: Performance vs robustness weight for LNM prediction. Effect of varying $\lambda$ in eq. 1 on inconsistency and AUC. Statistics are gathered from 20 models per value of $\lambda$ per foundation model.

Figure 4: Effect of different robustness loss terms on robustness and classification performance in survival prediction. Box plots show the distribution of metric values for each foundation model when downstream models are trained without robustness loss, with the embedding loss alone, with the score loss alone, or with both loss terms combined. P values indicate comparisons of each loss setting with conventional training without robustness loss.

Figure 5: Effect of different robustness loss terms on robustness and classification performance in prediction of lymph node metastasis. Box plots show the distribution of metric values for each foundation model when downstream models are trained without robustness loss, with the embedding loss alone, with the score loss alone, or with both loss terms combined. P values indicate comparisons of each loss setting with conventional training without robustness loss.

Figure 6: Scanner prediction with linear probing. A single-layer linear classifier was trained to predict which scanner was used to form the input WSI, using tile feature vectors extracted with foundation models. Input is a WSI feature vector that is the average of its tile feature vectors, and the task was to predict whether a WSI had been imaged with one of the following five scanners: Aperio AT2, Aperio GT 450 DX, NanoZoomer XR, KF-PRO-400, Pannoramic 1000. We trained nine classifiers for each of the eight foundation models on WSIs from QUASAR 2 and show the average accuracy over all scanners on WSIs from TransSCOT in this figure. We used PyTorch’s implementation of the LBFGS optimisation algorithm with a learning rate of 1.0, 1000 as the maximum number of iterations, a history size of 50, with strong wolfe as the solver, and CrossEntropyLoss as the loss function. Prior to feeding each feature vector into the linear classifier, we normalise it based on mean and standard deviation calculated on the QUASAR 2 dataset.

Explore similar work

Robustifying pathology foundation models via fine-tuning
Jul 24, 2026Alexandre Filiot, Oskar Thaeter, Benoit Schmauch +1Computational Pathology Fine-Tuning
1Waiv · Institute of Pathology, Technical University of Munich · School of Computation, Information and Technology, Technical University of Munich
The Good, the Bad, and the Brittle: Benchmarking Robustness and Generalisation of Histopathology Foundation Models
Jul 5, 2026Dhyey Yajnik, Amina Asif, Fayyaz MinhasDistribution Shift Robustness Neural Network Robustness
Predictive Systems in Biomedicine Lab, Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, United Kingdom
HERO: Histology Encoder for Robust Representation in Oncology
Sep 28, 2026Zhi Li, Eghbal Amidi, Yating Cheng +11Computational Pathology Domain Generalization
Caris Life Sciences, Irving, TX, United States

Jul 24, 2026J/K move · Enter open · S save

Robustifying pathology foundation models via fine-tuning

Alexandre Filiot, Oskar Thaeter, Benoit Schmauch, Lionel Guillou

1Waiv · Institute of Pathology, Technical University of Munich · School of Computation, Information and Technology, Technical University of Munich

Computational Pathology Fine-Tuning Pathology Foundation Models

Open paper AskPDF arXiv

Pathology foundation models (FMs) produce powerful tile-level representations which remain sensitive to scanner and staining variability, undermining deployment across laboratories. We develop a novel fine-tuning recipe that improves the robustness of pathology FMs to acquisition factors. Applied to ten different FMs, our fine-tuning strategy consistently improves robustness for every model as well as downstream performance, with no observed trade-off. On average, it raises the PathoROB robustness index by 23% (from 0.72 to 0.87) and increases the overall cross-benchmark performance by 43% on Patho-Bench, HEST and THUNDER combined, with individual gains reaching up to 72% in robustness (Phikon-v2) and 76% in performance (Midnight-12k). We publicly release the fine-tuned versions of Phikon-v2 (Phaet) and Midnight-12k (Mascaret) at https://huggingface.co/wearewaiv/models.

Abstract

Explore similar work

Robustifying pathology foundation models via fine-tuning

The Good, the Bad, and the Brittle: Benchmarking Robustness and Generalisation of Histopathology Foundation Models

HERO: Histology Encoder for Robust Representation in Oncology