Masahiro Yakami MD, PhD, Presenter: Nothing to Disclose

Masami Kawagishi, Abstract Co-Author: Nothing to Disclose

Gakuto Aoyama, Abstract Co-Author: Nothing to Disclose

Hiroyuki Yamamoto, Abstract Co-Author: Nothing to Disclose

Takeshi Kubo MD, Abstract Co-Author: Nothing to Disclose

Kaori Togashi MD, PhD, Abstract Co-Author: Research Grant, Bayer AG Research Grant, DAIICHI SANKYO Group Research Grant, Eisai Co, Ltd Research Grant, FUJIFILM Holdings Corporation Research Grant, Nihon Medi-Physics Co, Ltd Research Grant, Shimadzu Corporation Research Grant, Toshiba Corporation Research Grant, Covidien AG

Yoshio Iizuka, Abstract Co-Author: Nothing to Disclose

Ryo Sakamoto, Abstract Co-Author: Nothing to Disclose

Koji Sakai, Abstract Co-Author: Nothing to Disclose

Koji Fujimoto MD, PhD, Abstract Co-Author: Nothing to Disclose

Hiroyuki Sekiguchi, Abstract Co-Author: Nothing to Disclose

Yutaka Emoto MD, PhD, Abstract Co-Author: Nothing to Disclose

In the process of determining diagnosis at a clinical conference, each physician explains one’s differential diagnoses including their possibilities. This study proposes a computer simulation of clinical conference to evaluate the effect of increasing the number of the participant and joining a CADx as a participant.

With the approval of the institutional review board, we built a database on 491 lung nodules on which diagnoses were clinically confirmed as primary lung cancer, metastatic nodules or other benign nodules. This database consisted of CT images, image findings on the nodules, the confirmed diagnosis, clinical information such as laboratory data and patient history. The image findings were described by consensus of two board-certified radiologists. The CADx was trained and evaluated by using 179 and 312 nodules in the database, respectively. The CADx derived a list of possibilities for differential diagnoses on each nodule using a Bayesian network. Eleven radiologists, with five years’ experience in diagnostic imaging, interpreted the 312 nodules. Each radiologist inputted the possibilities for differential diagnoses, which in total should be 100%, on each nodule. Among all possible diagnoses, the one with the highest total possibility in all participants was defined as the diagnosis at a conference. The average accuracy in the simulated conference among each combination of 2 to 11 (N) radiologists (R-Only), and that among all the combinations generated by replacing any radiologist in the combination with the CADx (R+C) were calculated for evaluation. The radiologists interpreted the same nodules referring CADx later with more than one month interval.

The average accuracies by each radiologist without/with CADx were 71.4% and 76.3%, respectively. Those by RadOnly (N=2 to 11) were 73.5%, 75.6%, 76.4%, 76.9%, 77.2%, 77.4%, 77.5%, 77.5%, 77.8% and 77.9%, respectively. Those by R+C (N=2 to 11) were 77.2%, 78.3%, 79.1%, 79.3%, 79.4%, 79.4%, 79.4%, 79.4%, 79.3% and 79.3%, respectively.

Increasing the number of participant improved the diagnostic accuracy, and joining CADx as a participant showed relatively higher improvement.

Yakami, M, Kawagishi, M, Aoyama, G, Yamamoto, H, Kubo, T, Togashi, K, Iizuka, Y, Sakamoto, R, Sakai, K, Fujimoto, K, Sekiguchi, H, Emoto, Y, Computer Simulation of Clinical Conference: Evaluation of the Effect of Increasing Number of Participant and Joining Computer-aided Differential Diagnosis (CADx) as a Participant.  Radiological Society of North America 2013 Scientific Assembly and Annual Meeting, December 1 - December 6, 2013 ,Chicago IL. http://archive.rsna.org/2013/13016993.html