Cancer grading is important for therapeutic decision making and prognosis prediction. Pathologists grade tumors based on the morphology of cells within tissue and state in the pathology reports in addition to some other clinical parameters, like stage, size of the tumor, and anatomical position. In retrospective studies, extracting these information from unstructured text in pathology reports is crucial for sample selection and experiment design.

**Aim:** To design deep learning models extracting Fuhrman grade from pathology reports of renal cell carcinoma patients  in [The Cancer Genome Atlas (TCGA)](https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga).

**Dataset:** Consisting of pathology reports and corresponding Fuhrman grades of renal cell carcinoma patients in The Cancer Genome Atlas. The dataset is modified from the dataset provided in [1].

**Task:** Given text in a patient's pathology report, extract the Fuhrman grade of renal cell carcinoma.


## Example from the dataset

**Pathology report text:**
```
procedure: right radical nephrectomy tumor type: papillary renal cell carcinoma nuclear grade: grade iii tumor size: 12 x 11.5 x 9 cm renal vein invasion: not present lymph nodes: not examined phthologic stage: t2 nx mx
```

**Fuhrman grade:**
```
G3
```

## Acknowledgements

We thank Hakan Kıymaz (graduate student, BAU) for preparing the competition's dataset from the one published in [1]

[1] Wu, J., Tang, K., Zhang, H., Wang, C., & Li, C. (2020, December). Structured information extraction of pathology reports with attention-based graph convolutional network. In *2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)* (pp. 2395-2402). IEEE.