Tarjei S. Hveem
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tarjei S. Hveem has a total of 73 co-authors. Here are the top co-authors by number of shared publications:
- Andreas Kleppe
Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway; Department of Informatics, Faculty of Mathematics and Natural Sciences, University of Oslo, Oslo, Norway; Centre for Research-based Innovation Visual Intelligence, UiT The Arctic University of Norway, Tromsø, Norway
3 shared publications - Gunnar Balle Kristensen
Oslo University Hospital, Division of Cancer Medicine, Institute for Cancer Genetics and Informatics, Oslo, Norway; Oslo University Hospital, Department of Surgical Oncology, Section for Gynecological Oncology, Oslo, Norway
2 shared publications - Hanne A. Askautrud
Division of Cancer Medicine, Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
2 shared publications - Kari Anne R. Tobin
Division of Cancer Medicine, Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
2 shared publications - Kristina Lindemann
Oslo University Hospital, Department of Surgical Oncology, Section for Gynecological Oncology, Oslo, Norway; University of Oslo, Faculty of Medicine, Institute of Clinical Medicine, Oslo, Norway
2 shared publications - Ljiljana Vlatkovic
Division of Cancer Medicine, Institute for Cancer Genetics and Informatics, Oslo University Hospital, Oslo, Norway
2 shared publications
Latest Publications
- Open Access
- 12 February 2026
- Published by Wiley in FEBS Open Bio
- Vol. 16 (7) , 1259-1270
Applicability of mitotic figure counting by deep learning: a development and pan‐cancer validation study
Mitotic figure counting is an established measure of cell proliferation that is included in grading systems. We developed a deep learning method for mitotic figure counting and evaluated its prognostic impact in multiple external validation datasets. The deep learning method was trained in whole slide images of tissue sections stained with haematoxylin and eosin from a publicly available breast cancer dataset where mitotic figures have been annotated by expert pathologists. The final model was externally validated according to a protocol with predefined analyses of 14 571 patient samples from 13 patient cohorts from seven different cancer types. The predefined primary analysis was univariable Cox survival analysis of the number of mitotic figures detected per mm 2 . Automatic mitotic figure counting correlated well with known proliferation rates, and patients with more mitotic figures per mm 2 had significantly worse patient outcome in all the studied cancer types except colorectal cancer. This study demonstrates the practical potential of automated, deep learning‐based mitotic figure counting, both by automating pathology work and by suggesting expanded use in more cancer types, such as prostate cancer.
- 12 February 2026
- Published by Wiley in FEBS Open Bio
- Vol. 16 (7) , 1259-1270
Open AccessApplicability of mitotic figure counting by deep learning: a development and pan‐cancer validation study
Mitotic figure counting is an established measure of cell proliferation that is included in grading systems. We developed a deep learning method for mitotic figure counting and evaluated its prognostic impact in multiple external validation datasets. The deep learning method was trained in whole slide images of tissue sections stained with haematoxylin and eosin from a publicly available breast cancer dataset where mitotic figures have been annotated by expert pathologists. The final model was externally validated according to a protocol with predefined analyses of 14 571 patient samples from 13 patient cohorts from seven different cancer types. The predefined primary analysis was univariable Cox survival analysis of the number of mitotic figures detected per mm 2 . Automatic mitotic figure counting correlated well with known proliferation rates, and patients with more mitotic figures per mm 2 had significantly worse patient outcome in all the studied cancer types except colorectal cancer. This study demonstrates the practical potential of automated, deep learning‐based mitotic figure counting, both by automating pathology work and by suggesting expanded use in more cancer types, such as prostate cancer.
- Open Access
- 6 December 2025
- Published by Elsevier in European Journal of Cancer
- Vol. 233, 116164
Surgical stage in the era of molecular profiling of endometrial cancer
- 6 December 2025
- Published by Elsevier in European Journal of Cancer
- Vol. 233, 116164
Open AccessSurgical stage in the era of molecular profiling of endometrial cancer
- Open Access
Endometrial Carcinoma: Molecular Cytogenetics and Transcriptomic Profile
Endometrial carcinomas (ECs) are histologically classified as endometrioid and nonendometrioid tumors, with each subgroup displaying different molecular profiles and clinical outcomes. Considerable biological and clinical heterogeneity exists within this scheme, however, reflecting its imperfection. We aimed to gather additional data that might help clarify the tumors’ pathogenesis and contribute toward a more meaningful classification scheme. In total, 33 ECs were examined for the presence of chromosomal aberrations, genomic imbalances, pathogenic variants, microsatellite instability, and expression profiles at both gene and miRNA levels. Chromosome 1 was the most frequently rearranged chromosome, showing a gain of all or part of the long arm. Pathogenic variants were found for PTEN (53%), PDGFRA (37%), PIK3CA (34%), and KIT (31%). High microsatellite instability was identified in 15 ECs. Comparing tumors and controls, we identified 23 differentially expressed genes of known importance in carcinogenesis, 15 genes involved in innate and adaptative immune responses, and altered expression of 7 miRNAs. miR-32-5p was the most upregulated. Our series showed a high degree of heterogeneity. Tumors were well-separated from controls, but there was no clear-cut separation between endometrioid and nonendometrioid ECs. Whether this means that the current phenotypic classification is of little relevance or if one still has not detected which genomic parameters to enter into correlation analyses remains unknown.
Open AccessEndometrial Carcinoma: Molecular Cytogenetics and Transcriptomic Profile
Endometrial carcinomas (ECs) are histologically classified as endometrioid and nonendometrioid tumors, with each subgroup displaying different molecular profiles and clinical outcomes. Considerable biological and clinical heterogeneity exists within this scheme, however, reflecting its imperfection. We aimed to gather additional data that might help clarify the tumors’ pathogenesis and contribute toward a more meaningful classification scheme. In total, 33 ECs were examined for the presence of chromosomal aberrations, genomic imbalances, pathogenic variants, microsatellite instability, and expression profiles at both gene and miRNA levels. Chromosome 1 was the most frequently rearranged chromosome, showing a gain of all or part of the long arm. Pathogenic variants were found for PTEN (53%), PDGFRA (37%), PIK3CA (34%), and KIT (31%). High microsatellite instability was identified in 15 ECs. Comparing tumors and controls, we identified 23 differentially expressed genes of known importance in carcinogenesis, 15 genes involved in innate and adaptative immune responses, and altered expression of 7 miRNAs. miR-32-5p was the most upregulated. Our series showed a high degree of heterogeneity. Tumors were well-separated from controls, but there was no clear-cut separation between endometrioid and nonendometrioid ECs. Whether this means that the current phenotypic classification is of little relevance or if one still has not detected which genomic parameters to enter into correlation analyses remains unknown.
- Open Access
PTEN and DNA Ploidy Status by Machine Learning in Prostate Cancer
Machine learning (ML) is expected to improve biomarker assessment. Using convolution neural networks, we developed a fully-automated method for assessing PTEN protein status in immunohistochemically-stained slides using a radical prostatectomy (RP) cohort (n = 253). It was validated according to a predefined protocol in an independent RP cohort (n = 259), alone and by measuring its prognostic value in combination with DNA ploidy status determined by ML-based image cytometry. In the primary analysis, automatically assessed dichotomized PTEN status was associated with time to biochemical recurrence (TTBCR) (hazard ratio (HR) = 3.32, 95% CI 2.05 to 5.38). Patients with both non-diploid tumors and PTEN-low had an HR of 4.63 (95% CI 2.50 to 8.57), while patients with one of these characteristics had an HR of 1.94 (95% CI 1.15 to 3.30), compared to patients with diploid tumors and PTEN-high, in univariable analysis of TTBCR in the validation cohort. Automatic PTEN scoring was strongly predictive of the PTEN status assessed by human experts (area under the curve 0.987 (95% CI 0.968 to 0.994)). This suggests that PTEN status can be accurately assessed using ML, and that the combined marker of automatically assessed PTEN and DNA ploidy status may provide an objective supplement to the existing risk stratification factors in prostate cancer.
Open AccessPTEN and DNA Ploidy Status by Machine Learning in Prostate Cancer
Machine learning (ML) is expected to improve biomarker assessment. Using convolution neural networks, we developed a fully-automated method for assessing PTEN protein status in immunohistochemically-stained slides using a radical prostatectomy (RP) cohort (n = 253). It was validated according to a predefined protocol in an independent RP cohort (n = 259), alone and by measuring its prognostic value in combination with DNA ploidy status determined by ML-based image cytometry. In the primary analysis, automatically assessed dichotomized PTEN status was associated with time to biochemical recurrence (TTBCR) (hazard ratio (HR) = 3.32, 95% CI 2.05 to 5.38). Patients with both non-diploid tumors and PTEN-low had an HR of 4.63 (95% CI 2.50 to 8.57), while patients with one of these characteristics had an HR of 1.94 (95% CI 1.15 to 3.30), compared to patients with diploid tumors and PTEN-high, in univariable analysis of TTBCR in the validation cohort. Automatic PTEN scoring was strongly predictive of the PTEN status assessed by human experts (area under the curve 0.987 (95% CI 0.968 to 0.994)). This suggests that PTEN status can be accurately assessed using ML, and that the combined marker of automatically assessed PTEN and DNA ploidy status may provide an objective supplement to the existing risk stratification factors in prostate cancer.