search

ku-milab / MGICNN

Implementation of "Multi-scale Gradual Itegration Convolutional Neural Network for False Positive Reduction in Pulmonary Nodule Detection"
34 stars 19 forks source link

Mis-matching Total number of candidates #8

Closed MjdMahasneh closed 3 years ago

MjdMahasneh commented 4 years ago

Hello,

after evaluating the predictions file (i.e. METU_VISION_FPRED.csv) using the LUNA16 official script (i.e. noduleCADEvaluationLUNA16.py), I get an output (CADAnalysis.txt) like this :

CADAnalysis.txt

CAD Analysis: METU_VISION_FPRED

Candidate detection results: True positives: 1128 False positives: 81706 False negatives: 58 True negatives: 0 Total number of candidates: 87794 Total number of nodules: 1186 Ignored candidates on excluded nodules: 4600 Ignored candidates which were double detections on a nodule: 360 Sensitivity: 0.951096121 Average number of candidates per scan: 98.867117117

From what I understand, the the Total number of candidates should be 754,975 according to https://luna16.grand-challenge.org/Evaluation/

Even though METU_VISION_FPRED.csv has 754,975 candidates!! the CADAnalysis.txt still says Total number of candidates: 87794 !!!!!

Looking forward to hearing back from you. Any help is extremely appreciated.

Many thanks.

Any idea why that happens?? Am I missing something?

torki-hossein commented 3 years ago

I think you run the model with 10 fold cross validation and also you just did 1 fold train-test phase. In the 5-fold cross validation (as said in the paper) each fold contain almost 149248 candidates, and if you run all of validation folds, you can reach near to 754975 candidates.