Artificial intelligence-based image analysis can predict outcome in high-grade serous carcinoma via histology alone

Autor: Sami Blom, Anni Virtanen, Anna Ray Laury, Olli Carpén, Tuomas Ropponen
Přispěvatelé: Research Program in Systems Oncology, Research Programs Unit, HUSLAB, HUS Diagnostic Center, Department of Pathology, Precision Cancer Pathology, Olli Mikael Carpen / Principal Investigator, Digital Precision Cancer Medicine (iCAN), Faculty of Medecine [Helsinki], University of Helsinki, HUS Medical Imaging Center [Helsinki] (HUS-MIC), HiLIFE - Neuroscience Center (NC), Helsinki Institute of Life Science (HiLIFE), University of Helsinki-University of Helsinki-Helsinki Institute of Life Science (HiLIFE), University of Helsinki-University of Helsinki
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Oncology
Serous carcinoma
Colorectal cancer
Platinum Compounds
0302 clinical medicine
MUTATION-STATUS
Peritoneal Neoplasms
Ovarian Neoplasms
0303 health sciences
Multidisciplinary
Melanoma
LONG-TERM SURVIVORS
WOMEN
Middle Aged
3. Good health
Treatment Outcome
Chemotherapy
Adjuvant
030220 oncology & carcinogenesis
Medicine
[SDV.IB]Life Sciences [q-bio]/Bioengineering
Female
Breast carcinoma
Adult
medicine.medical_specialty
Science
3122 Cancers
[SDV.CAN]Life Sciences [q-bio]/Cancer
OVARIAN-CANCER
Article
03 medical and health sciences
Text mining
Ovarian cancer
Artificial Intelligence
Internal medicine
CLINICOPATHOLOGICAL FEATURES
medicine
Carcinoma
Fallopian Tube Neoplasms
Humans
030304 developmental biology
Aged
Retrospective Studies
business.industry
Histology
Translational research
medicine.disease
BRCA1
Cystadenocarcinoma
Serous
PATTERNS
3111 Biomedicine
Neural Networks
Computer
business
Zdroj: Scientific Reports
Scientific Reports, Nature Publishing Group, 2021, 11 (1), pp.19165. ⟨10.1038/s41598-021-98480-0⟩
Scientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
ISSN: 2045-2322
Popis: High-grade extrauterine serous carcinoma (HGSC) is an aggressive tumor with high rates of recurrence, frequent chemotherapy resistance, and overall 5-year survival of less than 50%. Beyond determining and confirming the diagnosis itself, pathologist review of histologic slides provides no prognostic or predictive information, which is in sharp contrast to almost all other carcinoma types. Deep-learning based image analysis has recently been able to predict outcome and/or identify morphology-based representations of underlying molecular alterations in other tumor types, such as colorectal carcinoma, lung carcinoma, breast carcinoma, and melanoma. Using a carefully stratified HGSC patient cohort consisting of women (n = 30) with similar presentations who experienced very different treatment responses (platinum free intervals of either ≤ 6 months or ≥ 18 months), we used whole slide images (WSI, n = 205) to train a convolutional neural network. The neural network was trained, in three steps, to identify morphologic regions (digital biomarkers) that are highly associating with one or the other treatment response group. We tested the classifier using a separate 22 slide test set, and 18/22 slides were correctly classified. We show that a neural network based approach can discriminate extremes in patient response to primary platinum-based chemotherapy with high sensitivity (73%) and specificity (91%). These proof-of-concept results are novel, because for the first time, prospective prognostic information is identified specifically within HGSC tumor morphology.
Databáze: OpenAIRE
Externí odkaz: