Kari Anne Tobin

Kari Anne Tobin


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 August 2021 in Cancers
Verified
Journal Article
Open access
PDF file
KCKarolina Cyll
Karolina Cyll
AKAndreas Kleppe
Andreas Kleppe
JKJoakim Kalsnes
Joakim Kalsnes
LVLjiljana Vlatkovic
Ljiljana Vlatkovic
MPManohar Pradhan
Manohar Pradhan
HDHåvard Danielsen
Håvard Danielsen
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.

6 December 2025 in European Journal of Cancer
Verified
Journal Article
Open access
JKJenneke Kasius
Jenneke Kasius
WKWanja Kildal
Wanja Kildal
SVS.W. Vrede
S.W. Vrede
HAH.A. Askautrud
H.A. Askautrud
MPManohar Pradhan
Manohar Pradhan
AKA. Kleppe
A. Kleppe
Molecular classification has reshaped risk stratification in endometrial cancer (EC), yet the relevance of tumor spread within molecular subgroups has not been reported so far. This multicenter retrospective study included 2056 EC patients treated between 1994 and 2018 across 11 European centers. All histopathological subtypes and FIGO stages were included. Tumors were classified into four molecular subgroups: POLE-mutated (POLEmut), mismatch repair deficient (MMRd), no specific molecular profile (NSMP), and TP53/p53 abnormal (p53abn). Clinical and pathological data were extracted from existing cohort databases. Patients were diagnosed with FIGO stage I (69 %), II (9 %), III (16 %), and IV (6 %), and classified into: POLEmut (8 %), MMRd (28 %), NSMP (44 %), and p53abn (21 %). The overall 5-year cancer-specific death (CSD) and recurrence rates were 16.5 % (95 % CI, 14.9 %-18.2 %) and 23.8 % (95 % CI, 22.0 %-25.7 %), respectively. In multivariable analysis cancer-specific survival (CSS) was independently associated with molecular subtype, FIGO stage, age, histopathological type, grade, lymphovascular space invasion, adjuvant therapy, residual tumor, and lymphadenectomy. FIGO stage was significantly associated with CSD also in within each molecular subgroup (p < 0.001). Patients with tumors confined to the uterus had the most favourable prognosis. Lymph node metastases significantly decreased CSS in POLEmut, MMRd, and p53abn groups. Within FIGO stage IV, molecular subtype was not significantly related to outcome. Surgical stage remains a strong prognostic factor across molecular subtypes and should be considered alongside molecular classification when tailoring adjuvant treatment in EC.