Tapahtumakalenteri (vanha)
kesäkuu
13
Dissertation: Laura Mannismäki
Laura Mannismäki, University of Helsinki, Faculty of Medicine, Doctoral Programme in Clinical Research
Selected aspects of acute stroke treatment in the scope of computed tomographic perfusion imaging : From extended time window to acute treatment and functional outcome
Opponent: Docent Jori Ruuskanen, University of Turku
Aloitusaika: 13.06.2025 12:00
Lopetusaika: 13.06.2025 14:00
Kesto: 2 hours
Sijainti: HUS SIltasairaala, Töölö luentosali STB3.03, Haartmaninkatu 4
Tyyppi: Dissertation
Organisaatio: UH, Faculty of Medicine
Yhteyshenkilö: laura.mannismaki@hus.fi
kesäkuu
13
Dissertation: Juan Serna Santos
Juan Serna Santos, University of Helsinki, Faculty of Medicine, Doctoral Program in Clinical Research
The hybrid operating room : revascularization outcomes and radiation safety
Opponent: Professor of Vascular Surgery Bijan Modarai, King's College London
Aloitusaika: 13.06.2025 13:00
Lopetusaika: 13.06.2025 15:00
Kesto: 2 hours
Sijainti: HUS Siltasairaala, Kruunuhakasali, Haartmaninkatu 4
Tyyppi: Dissertation
Organisaatio: UH, Faculty of Medicine
Yhteyshenkilö: juan.sernasantos@helsinki.fi
Online-kokouslinkki:
kesäkuu
13
Dissertation: Zhiyang Wang
Zhiyang Wang, University of Helsinki, Faculty of Medicine, Doctoral Program in Population Health
The effect of the environment on depression and underlying genetic influence in adolescents and young adults
Opponent: Professor Sylvain Sebert, University of Oulu
Aloitusaika: 13.06.2025 14:00
Lopetusaika: 13.06.2025 16:00
Kesto: 1 hour
Sijainti: Biomedicum1, lecture hall 2, Haartmaninkatu 8, 00290 Helsinki
Tyyppi: Dissertation
Organisaatio: UH, Faculty of Medicine
Yhteyshenkilö: zhiyang.wang@helsinki.fi
Online-kokouslinkki:
https://video.helsinki.fi/unitube/live-stream.html?room=l43
kesäkuu
16
Dissertation: Feiyi Wang
Feiyi Wang, University of Helsinki, Faculty of Medicine, Doctoral Programme in Clinical Research
Familial and genetic risk factors for autoimmune diseases
Opponent: Professor Ingrid Kockum, Karolinska Institutet
Aloitusaika: 16.06.2025 13:00
Lopetusaika: 16.06.2025 15:00
Kesto: 2 hours
Sijainti: Biomedicum1, lecture hall 2, Haartmaninkatu 8, 00290 Helsinki
Tyyppi: Dissertation
Organisaatio: UH, Faculty of Medicine
Yhteyshenkilö: feiyi.wang@helsinki.fi
Online-kokouslinkki:
https://video.helsinki.fi/unitube/live-stream.html?room=l43
kesäkuu
17
iCAN Science Seminar on Bridging the radiology-pathology gap for prostate cancer characterization with Mirabela Rusu
Welcome to the iCAN science
seminar with Assistant Professor Mirabela Rusu (Stanford University) on on Bridging the radiology-pathology gap for prostate
cancer characterization!
Radiology imaging is an essential non-invasive tool for cancer care, facilitating diagnosis and treatment planning. Yet, despite technological advancements in imaging, radiologists still miss 12-36% of aggressive prostate cancers due to their subtle radiologic features. Some patients undergo surgery as cancer treatment and thus have rich data comprised of high-resolution pathology images showing the extent, heterogeneity, and aggressiveness of cancer. In this context, Prof. Rusu’s team develops advanced deep learning methods to assist radiologists in their image interpretation. The approaches are split between two categories. First, the team developed registration methods that align radiology and pathology images, e.g., in the prostate or breast, using both traditional and deep-learning based registration methods. Second, they developed radiology-pathology fusion strategies by constructing pathology-derived radiology (rad-pathomic) biomarkers. When included in deep learning models, these biomarkers improved by 7% the detection of aggressive vs indolent cancers on prostate MRI or kidney CT. While this cancer detection methods are trained when both radiology and pathology images are available, they only use radiology images at inference time in new unseen patients, rendering then useful to guide biopsy or local treatment procedures.
Radiology imaging is an essential non-invasive tool for cancer care, facilitating diagnosis and treatment planning. Yet, despite technological advancements in imaging, radiologists still miss 12-36% of aggressive prostate cancers due to their subtle radiologic features. Some patients undergo surgery as cancer treatment and thus have rich data comprised of high-resolution pathology images showing the extent, heterogeneity, and aggressiveness of cancer. In this context, Prof. Rusu’s team develops advanced deep learning methods to assist radiologists in their image interpretation. The approaches are split between two categories. First, the team developed registration methods that align radiology and pathology images, e.g., in the prostate or breast, using both traditional and deep-learning based registration methods. Second, they developed radiology-pathology fusion strategies by constructing pathology-derived radiology (rad-pathomic) biomarkers. When included in deep learning models, these biomarkers improved by 7% the detection of aggressive vs indolent cancers on prostate MRI or kidney CT. While this cancer detection methods are trained when both radiology and pathology images are available, they only use radiology images at inference time in new unseen patients, rendering then useful to guide biopsy or local treatment procedures.
Hosts: Prof. Tuomas Mirtti and Doctoral Researcher Tolou Shabdah
Bio: Dr. Rusu is an Assistant Professor, in the Department of Radiology, and, by courtesy, Department of Urology and Biomedical Data Science, at Stanford University, California, where she leads the Personalized Integrative Medicine Laboratory (PIMed). The PIMed Laboratory has a multi-disciplinary direction and focuses on developing analytic methods for biomedical data integration, with a particular interest in multimodal fusion, e.g., radiology-pathology fusion to facilitate radiology image labeling, or MRI-ultrasound for guiding procedure. These fusion approaches allow the downstream training of advanced multimodal machine learning for cancer detection and subtype identification at pixel-level. Our approaches have been applied in oncologic applications (prostate, breast, kidney).Aloitusaika: 17.06.2025 11:45
Lopetusaika: 17.06.2025 12:45
Kesto:
Sijainti: HUS Siltasairaala, Ullanlinnasali, Haartmaninkatu 4
Tyyppi: Seminar
Organisaatio: iCAN Flagship Team
Yhteyshenkilö: ican-comms@helsinki.fi
Online-kokouslinkki:
https://helsinki.zoom.us/j/69887400500