Medical treatment for cancer is performed in thefollowing order: detection of the lesion, differential diagnosis, andtreatment. Radiomics can be considered as an artificial intelligence systemthat supports the second half of medical treatment. In radiomic studies, it isimportant to develop interactive tools for decision support because thetreatment is determined by a counterbalance between doctor’s discretion andpatient choice. The purpose of this study is to propose tools for visualanalytics in the estimation of 1p/19q codeletion of brain tumor. We collected81 MR images from the LGG-1p19q deletion database in the Cancer ImagingArchive. We calculated 740 radiomic features from the tumor region. Logisticregression with 6 radiomic features selected by Lasso was employed forestimating the presence or absence of 1p/19q codeletion. Multidimensionalscaling and nomogram were also used for visual analytics. Since we were able tovisualize the reason for determining the output of logistic regression, ourproposed methods are considered to be useful as a tool for the decision supportin treatment strategy.

It is very difficult for radiologist to correctly detect small calcifications and lesions hidden in dense breast tissue on mammography. There are previous papers that detect lesions of the observer’s eye-tracking information in chest radiography etc. by CNN. Therefore, we investigated in 3ch convLSTM, Autoencoding convLSTM, and U-net convLSTM for deep learning, and aimed to predict the eye-tracking movement in mammography with high accuracy. We obtained gaze-tracking data for four mammography expert radiologists and 15 mammography technologists on 15 abnormal and 15 normal mammographies published by the MIAS. Next, a heat map was created at 4-second intervals, and 3ch convLSTM, Autoencoding convLSTM, and U-net convLSTM was used to predict the heat map image 4 seconds ahead from the temporal two heat map images. In the SSIM in U-net convLSTM, 4-8 seconds to 16-20 seconds was 0.96±0.01. In all 4-8 seconds to 16-20 seconds, the SSIM in U-net convLSTM was higher than this in 3ch convLSTM, Autoencoder convLSTM and there was a statistically significant difference (P<0.05). In the future, it will be necessary to increase the number of cases and further improve the prediction.