Back

AI-VDT can Help in Detecting Primary Lung Cancer

Suzuki, K.; Otsuka, Y.; Imashimizu, K.; Hata, K.; Suzuki, K.

2022-04-28 radiology and imaging
10.1101/2022.04.26.22274299 medRxiv
Show abstract

The current study shows that measuring volume doubling time could accelerate the detection of primary lung cancer in chest CT imaging. Thirty tumors were selected from surgical cases of primary lung cancer at a university hospital in Japan, and the CT scan data and radiology reports were extracted retrospectively. The CT scan data were processed by a commercial pulmonary nodule AI and volume doubling time was calculated for each historical study time point. 43% of the 30 tumors had an VDT below 400 days in earlier study than the tumor was reported as a nodule on the radiology report. The average days of earlier detection was 299 days. Interpolation of the detailed mortality reduction data from the NELSON study predicted a 5.6% reduction in 10-year mortality from lung cancer.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.