Carolin Stürenberg

Carolin Stürenberg

Auto-generated profile, based on publicly available information

Carolin Stürenberg

Department of Pathology University of Helsinki and Helsinki University Hospital Helsinki Finland

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 November 2021 in European Urology Focus
Verified
Journal Article
Closed access
JEJuho T. Eineluoto
Juho T. Eineluoto
KSKevin Sandeman
Kevin Sandeman
JPJoona Pohjonen
Joona Pohjonen
KSKonrad Sopyllo
Konrad Sopyllo
SNStig Nordling
Stig Nordling
TMTuomas Mirtti
Tuomas Mirtti

3 July 2019
Verified
Book Chapter
Open access
PDF file
UKUmair Akhtar Hasan Khan
Umair Akhtar Hasan Khan
CSCarolin Stürenberg
Carolin Stürenberg
Oguzhan GencogluOguzhan Gencoglu
Oguzhan Gencoglu
KSKevin Sandeman
Kevin Sandeman
THTimo Heikkinen
Timo Heikkinen
TMTuomas K. Mirtti
Tuomas K. Mirtti
Deep neural networks have introduced significant advancements in the field of machine learning-based analysis of digital pathology images including prostate tissue images. With the help of transfer learning, classification and segmentation performance of neural network models have been further increased. However, due to the absence of large, extensively annotated, publicly available prostate histopathology datasets, several previous studies employ datasets from well-studied computer vision tasks such as ImageNet dataset. In this work, we propose a transfer learning scheme from breast histopathology images to improve prostate cancer detection performance. We validate our approach on annotated prostate whole slide images by using a publicly available breast histopathology dataset as pre-training. We show that the proposed cross-cancer approach outperforms transfer learning from ImageNet dataset.

18 March 2021 in The Prostate
Verified
Journal Article
Open access
PDF file
TLTimo‐Pekka K. Lehto
Timo‐Pekka K. Lehto
CSCarolin Stürenberg
Carolin Stürenberg
AMAdrian Malén
Adrian Malén
AEAndrew Erickson
Andrew Erickson
HKHannu Koistinen
Hannu Koistinen
TMTuomas K. Mirtti
Tuomas K. Mirtti
Background: Improved prognostication is needed to minimize overtreatment in grade group (GG) 2–4 prostate cancer. Our aim was to determine, at messenger RNA (mRNA) level, the performance of the genes in the commercial panels Decipher, Oncotype DX, Prolaris, and mutational panel MSK‐IMPACT to predict metastasis‐free and prostate cancer‐specific death (PCSD) in patients with GG 2–4 prostate cancer at radical prostatectomy.Methods: The retrospective cohort consisted of GG 2–4 patients treated with radical prostatectomy (median follow‐up 10.4 years). Seventy‐six cases with postoperative metastasis or PCSD and 84 controls with similar clinical baseline risk, but without progression, were analyzed. Index lesion mRNA transcripts were analyzed using NanoString technology. Random forest models were trained using panel gene sets to predict clinical endpoints and area under the curve (AUC), sensitivity, specificity, Youden index, and number needed to diagnose (NND) was measured. Survival probability was assessed with Kaplan–Meier estimator.Results: All gene sets outperformed clinical parameters and predicted metastasis‐free and prostate cancer‐specific survival. However, there were significant differences between the panels. In metastasis prediction, the genes in Oncotype DX had inferior performance (area under the curve [AUC] = 0.65) compared to other panels (AUC = 0.73–0.74). Decipher, MSK‐IMPACT and Prolaris showed similar NND (2.83–3.12) with Oncotype DX having highest NND (4.79). In PCSD prediction, the Prolaris gene set performed worse (AUC = 0.66) than MSK‐IMPACT or Decipher (AUC = 0.72). Oncotype DX performed similarly to other panels (AUC = 0.69, p > .05). Oncotype DX demonstrated lowest NND (2.79) compared to other panels (4.22–5.66).Conclusion: Transcript analysis of genes included in commercial panels is feasible in survival prediction of GG 2‐4 patients after radical prostatectomy and may aid in clinical decision making. There were significant differences between the panels, and overall stronger predictive gene sets are needed. Prospective investigation is warranted in biopsy materials.

4 May 2023 in International Journal of Cancer
Verified
Journal Article
Open access
TLTimo‐Pekka K. Lehto
Timo‐Pekka K. Lehto
RKRuusu‐Maaria Kovanen
Ruusu‐Maaria Kovanen
SLSusanna Lintula
Susanna Lintula
AMAdrian Malén
Adrian Malén
CSCarolin Stürenberg
Carolin Stürenberg
HKHannu Koistinen
Hannu Koistinen
We aimed to study mRNA levels and prognostic impact of all 15 human kallikrein‐related peptidases ( KLK s) and their targets, proteinase‐activated receptors ( PAR s), in surgically treated prostate cancer (PCa). Seventy‐nine patients with localized grade group 2‐4 PCas represented aggressive cases, based on metastatic progression during median follow‐up of 11 years. Eighty‐six patients with similar baseline characteristics, but no metastasis during follow‐up, were assigned as controls. Transcript counts were detected with nCounter technology. KLK12 protein expression was investigated with immunohistochemistry. The effects of KLK12 and KLK15 were studied in LNCaP cells using RNA interference. KLK3 , ‐ 2 , ‐ 4 , ‐ 11 , ‐ 15 , ‐ 10 and ‐ 12 mRNA, in decreasing order, were expressed over limit of detection (LOD). The expression of KLK2 , ‐ 3 , ‐ 4 and ‐ 15 was decreased and KLK12 increased in aggressive cancers, compared to controls ( P < .05). Low KLK2 , ‐ 3 and ‐ 15 expression was associated with short metastasis‐free survival ( P < .05) in Kaplan‐Meier analysis. PAR1 and ‐ 2 were expressed over LOD, and PAR1 expression was higher, and PAR2 lower, in aggressive cases than controls. Together, KLKs and PARs improved classification of metastatic and lethal disease over grade, pathological stage and prostate‐specific antigen combined, in random forest analyses. Strong KLK12 immunohistochemical staining was associated with short metastasis‐free and PCa‐specific survival in Kaplan‐Meier analysis ( P < .05). Knock‐down of KLK15 reduced colony formation of LNCaP cells grown on Matrigel basement membrane preparation. These results support the involvement of several KLKs in PCa progression, highlighting, that they may serve as prognostic PCa biomarkers.

17 December 2021 in arXiv
Verified
Preprint
Open access
PDF file
JPJoona Pohjonen
Joona Pohjonen
CSCarolin Stürenberg
Carolin Stürenberg
ARAntti Rannikko
Antti Rannikko
TMTuomas K. Mirtti
Tuomas K. Mirtti
EPEsa Pitkänen
Esa Pitkänen
Many current neural networks for medical imaging generalise poorly to data unseen during training. Such behaviour can be caused by networks overfitting easy-to-learn, or statistically dominant, features while disregarding other potentially informative features. For example, indistinguishable differences in the sharpness of the images from two different scanners can degrade the performance of the network significantly. All neural networks intended for clinical practice need to be robust to variation in data caused by differences in imaging equipment, sample preparation and patient populations. To address these challenges, we evaluate the utility of spectral decoupling as an implicit bias mitigation method. Spectral decoupling encourages the neural network to learn more features by simply regularising the networks' unnormalised prediction scores with an L2 penalty, thus having no added computational costs. We show that spectral decoupling allows training neural networks on datasets with strong spurious correlations and increases networks' robustness for data distribution shifts. To validate our findings, we train networks with and without spectral decoupling to detect prostate cancer tissue slides and COVID-19 in chest radiographs. Networks trained with spectral decoupling achieve up to 9.5 percent point higher performance on external datasets. Our results show that spectral decoupling helps with generalisation issues associated with neural networks, and can be used to complement or replace computationally expensive explicit bias mitigation methods, such as stain normalization in histological images. We recommend using spectral decoupling as an implicit bias mitigation method in any neural network intended for clinical use.