Ovarian carcinoma is the most lethal cancer of the female reproductive system. There are five common subtypes of ovarian cancer: high-grade serous carcinoma, clear-cell ovarian carcinoma, endometrioid, low-grade serous, and mucinous carcinoma. Additionally, there are several rare subtypes ("Outliers"). These are all characterized by distinct cellular morphologies, etiologies, molecular and genetic profiles, and clinical attributes. Subtype-specific treatment approaches are gaining prominence, though first requires subtype identification, a process that could be improved with data science.

Currently, ovarian cancer diagnosis relies on pathologists to assess subtypes. However, this presents several challenges, including disagreements between observers and the reproducibility of diagnostics. Furthermore, underserved communities often lack access to specialist pathologists, and even well-developed communities face a shortage of pathologists with expertise in gynecologic malignancies. 

Deep learning models have exhibited remarkable proficiency in analyzing histopathology images. Yet challenges still exist, such as the need for a significant amount of training data, ideally from a single source. Technical, ethical, and financial constraints, as well as confidentiality concerns, make training a challenge. In this competition, you will have access to the most extensive and diverse ovarian cancer dataset of histopathology images from more than 20 centers across four continents.

![](https://storage.googleapis.com/kaggle-media/competitions/UBC/OCEAN-Optional-Figure.png)

Competition host University of British Columbia (UBC) is a global center for teaching, learning, and research, consistently ranked among the top 20 public universities in the world. UBC embraces innovation and transforms ideas into action. Since 1915, UBC has been opening doors of opportunity for people with the curiosity, drive, and vision to shape a better world. Joining UBC is the BC Cancer, part of the Provincial Health Services Authority and its world-renowned Ovarian Cancer Research (OVCARE) team whose discoveries have led to progressive prevention strategies and improved diagnostics and treatments. BC Cancer provides a comprehensive cancer control program for the people of British Columbia in partnership with regional health authorities.  We have also partnered with the Ovarian Tumour Tissue Analysis (OTTA) consortium, an international multidisciplinary network of investigators from more than 65 international teams across the globe. Finally, the OCEAN challenge is made possible through a generous donation from TD Bank Group through the BC Cancer Foundation.

Your work could yield improved accuracy in identifying ovarian cancer subtypes. Better classification would enable clinicians to formulate personalized treatment strategies regardless of geographic location. This targeted approach has the potential to enhance treatment efficacy, reduce adverse effects, and ultimately contribute to better patient outcomes for those diagnosed with this deadly cancer.

##Using the data outside of the competition
Should you choose to utilize this dataset in your studies, please ensure to follow the citation guidelines listed in the **How to Cite This Challenge in Publications** section found in the **Overview** section of the competition page.