Goldgof Dmitry, Hall Lawrence, Hawkins Samuel, Schabath Matthew, Stringfield Olya, Garcia Alberto, Balagurunathan Yoganand, Kim Jongphil, Eschrich Steven, Berglund Anders, Gatenby Robert, Gillies Robert. (2017) Long and Short Survival in Adenocarcinoma Lung CTs. The Cancer Imaging Archive. http://doi.org/10.7937/K9/TCIA.2017.0tv7b9x1
The dataset consists of pre-surgical chest CT images of 40 subjects from the H. Lee Moffitt Cancer Center & Research Institute, Tampa, Florida. The CT images were acquired by standard-of-care, contrast-enhanced CT scans among patients who had non-small cell cancer with biopsy-verified adenocarcinoma with 2 years of follow-up. A region-growing algorithm segmented the tumor with seed points that were chosen by radiologists.
The adenocarcinoma cases are divided into the upper and lower quartiles of survival. Both the lower and upper quartiles have 20 cases. The lower quartile survival timeline is 103 to 498 days while the upper quartile timeline is 1351 to 2163 days. The average survival of the lower and upper quartiles is 288 days and 1569 days respectively. The median survival for the lower and upper quartiles is 289 and 1551 days respectively. The overall mean survival time is 879 days and median survival time is 925 days. Three of these cases, QIN-LSC-0009, QIN-LSC-0014, and QIN-LSC-0064 appear in LungCT-Diagnosis collection, while the remaining 37 cases are from the QIN Lung CT collection.
Image data is available in DICOM format. Segmentation data is available in .nii format. Labels are available in .csv format. The first column is subject identification. The second column is survival class. Subsequent columns are computed image features which are described in the following publications.
Hawkins, Samuel H., John N. Korecki, Yoganand Balagurunathan, Yuhua Gu, Virendra Kumar, Satrajit Basu, Lawrence O. Hall, Dmitry B. Goldgof, Robert A. Gatenby, and Robert J. Gillies. "Predicting Outcomes of Nonsmall Cell Lung Cancer using CT Image Features." IEEE Access 2 (2014): 1418-1426. DOI: 10.1109/ACCESS.2014.2373335
Paul, Rahul, Samuel H. Hawkins, Yoganand Balagurunathan, Matthew B. Schabath, Robert J. Gillies, Lawrence O. Hall, and Dmitry B. Goldgof. "Deep Feature Transfer Learning in Combination with Traditional Features Predicts Survival Among Patients with Lung Adenocarcinoma." Tomography: a journal for imaging research 2, no. 4 (2016): 388. DOI:10.18383/j.tom.2016.00211
Note: This data is restricted against commercial use. Please contact firstname.lastname@example.org with any questions on usage.
- DICOM Image Data:
- Click the Download button above to save a ".tcia" manifest file to your computer, which you must open with the NBIA Data Retriever.
- Segmentations (NIFTI)
- Patient Survival & Image Features