Back

Associations between spatial distribution of immune cell subsets and clinical outcomes in patients with advanced melanoma treated with immune checkpoint inhibitors: results from the PUMA challenge

Schuiveling, M.; Liu, H.; Eek, D.; Hanusov, M.; van Duin, I.; ter Maat, L. S.; van der Weerd, J. C.; van den Berkmortel, F. W. P. J.; Blank, C. U.; Breimer, G. E.; Burgers, F. H.; Boers-Sonderen, M.; van den Eertwegh, A. J. M.; de Groot, J. W.; Haanen, J. B. A. G.; Hospers, G. A. P.; Kapiteijn, E.; Piersma, D.; Simkens, L. H. J.; Westgeest, H. M.; Schrader, A. M. R.; van Diest, P. J.; Lv, J.; Zhu, Y.; Tenorio, C. G. C.; Chohan, B. S.; Eastwood, M.; Raza, S. E. A.; Torbati, N.; Meshcheryakova, A.; Mechtcheriakova, D.; Mahbod, A.; Adams, D.; Galdran, A.; Pluim, J. P. W.; Blokx, W. A. M.; Suijker

2026-03-10 oncology
10.64898/2026.03.09.26347935 medRxiv
Show abstract

Patients with advanced melanoma are treated with immune checkpoint inhibitors (ICIs), yet less than 50% of patients achieve a durable response while all patients are exposed to the risk of severe side effects. Tumor-infiltrating lymphocytes (TILs) in pathology images are associated with ICI outcomes, but manual assessment is subjective. In addition, the predictive value of other immune cell subsets, including plasma cells, neutrophils, histiocytes, and melanophages, remains unclear. We organized the Panoptic segmentation of nUclei and tissue in advanced MelanomA (PUMA) challenge to evaluate whether the spatial localization of TILs and other immune cell subsets on melanoma H&E slides collected before start of treatment was associated with treatment outcomes. Algorithm performance was evaluated on a hidden test set, after which top-ranked algorithms were applied to pre-treatment metastatic whole-slide images from a large, multicenter cohort of patients with advanced melanoma treated with first-line ICIs (n=1102). Automatically quantified tissue features and immune cell subsets were then associated with clinical outcomes. Top-performing algorithms improved detection of immune cell subsets, although accuracy for rare classes remained limited. Across challenge participants, TIL density showed the most consistent association with treatment response and survival. Associations for stromal TILs were weaker, while plasma cells, histiocytes, melanophages, neutrophils, necrosis and blood vessels did not show independent associations with outcomes. Overall, the results from the PUMA challenge improved the state of the art of immune cell detection in melanoma histopathology and show that intra-tumoral lymphocytes are the immune cell subset most consistently associated with treatment response and survival. HighlightsO_LIWe organized the first melanoma-specific tissue and nuclei segmentation competition C_LIO_LIWinning algorithms were applied to 1102 whole-slide images for biomarker analysis C_LIO_LIIntra-tumoral TILs were associated with response to immune checkpoint inhibitors C_LIO_LIOther immune cell subsets showed no independent association with treatment outcomes C_LIO_LITissue segmentation on WSIs was limited by low heterogeneity in training data. C_LI Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=140 SRC="FIGDIR/small/26347935v1_ufig1.gif" ALT="Figure 1"> View larger version (39K): org.highwire.dtl.DTLVardef@13838e4org.highwire.dtl.DTLVardef@1f34a6org.highwire.dtl.DTLVardef@b9a65borg.highwire.dtl.DTLVardef@58d300_HPS_FORMAT_FIGEXP M_FIG C_FIG

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

1
Nature Communications
4913 papers in training set
Top 23%
8.3%
2
European Journal of Cancer
10 papers in training set
Top 0.1%
8.1%
3
PLOS Computational Biology
1633 papers in training set
Top 6%
6.2%
4
iScience
1063 papers in training set
Top 2%
6.2%
5
Frontiers in Bioinformatics
45 papers in training set
Top 0.1%
4.8%
6
eLife
5422 papers in training set
Top 25%
3.6%
7
Journal of Translational Medicine
46 papers in training set
Top 0.2%
3.5%
8
Cell Reports Medicine
140 papers in training set
Top 2%
3.5%
9
Cancers
200 papers in training set
Top 2%
3.5%
10
Briefings in Bioinformatics
326 papers in training set
Top 3%
2.3%
11
Cancer Cell
38 papers in training set
Top 0.8%
2.0%
50% of probability mass above
12
npj Digital Medicine
97 papers in training set
Top 2%
2.0%
13
Patterns
70 papers in training set
Top 0.7%
1.9%
14
British Journal of Cancer
42 papers in training set
Top 0.8%
1.8%
15
JAMA Network Open
127 papers in training set
Top 2%
1.8%
16
BMJ Open
554 papers in training set
Top 9%
1.7%
17
JCO Clinical Cancer Informatics
18 papers in training set
Top 0.5%
1.7%
18
Scientific Reports
3102 papers in training set
Top 60%
1.7%
19
Cell Reports
1338 papers in training set
Top 25%
1.7%
20
Clinical Cancer Research
58 papers in training set
Top 1%
1.5%
21
eBioMedicine
130 papers in training set
Top 2%
1.5%
22
npj Precision Oncology
48 papers in training set
Top 0.7%
1.5%
23
Cancer Epidemiology, Biomarkers & Prevention
17 papers in training set
Top 0.4%
1.3%
24
Frontiers in Immunology
586 papers in training set
Top 6%
1.2%
25
GigaScience
172 papers in training set
Top 2%
0.9%
26
Communications Medicine
85 papers in training set
Top 0.8%
0.9%
27
Frontiers in Pharmacology
100 papers in training set
Top 4%
0.9%
28
The Journal of Pathology
22 papers in training set
Top 0.4%
0.8%
29
Breast Cancer Research
32 papers in training set
Top 0.5%
0.7%
30
JCO Precision Oncology
14 papers in training set
Top 0.4%
0.7%