Publications by authors named "H Kamezawa"
Article Synopsis
- - The study developed a deep learning model to predict the volume of lung tissue receiving at least 20 Gy during radiation therapy, using 91 chest X-ray images from lung cancer patients treated between 2018-2022.
- - A convolutional neural network was employed to create the model, which was evaluated using statistical measures like RMSE and MAE, resulting in a median prediction error of -1.8% and a Pearson correlation coefficient of 0.40 between actual and predicted values.
- - The model showed strong performance as a binary classifier for V <20% with a sensitivity of 75.0% and an accuracy of 80.6%, indicating its potential for assisting in patient treatment strategies.
Purpose: The malignancy grades of parotid gland cancer (PGC) have been assessed for a decision of treatment policies. Therefore, we have investigated the feasibility of topology-based radiomic features for the prediction of parotid gland cancer (PGC) malignancy grade in magnetic resonance (MR) images.
Materials And Methods: Two-dimensional T1- and T2-weighted MR images of 39 patients with PGC were selected for this study.
We investigated an approach for predicting recurrence after radiation therapy using local binary pattern (LBP)-based dosiomics in patients with head and neck squamous cell carcinoma (HNSCC). Recurrence/non-recurrence data were collected from 131 patients after intensity-modulated radiation therapy. The cases were divided into training (80%) and test (20%) datasets.
View Article and Find Full Text PDF[6. Imaging Biopsy for Assisting Cancer Precision Therapy -Information Extracted from Radiomics].
Nihon Hoshasen Gijutsu Gakkai Zasshi
March 2022
Peroxisome proliferator-activated receptor (PPAR) γ1, a nuclear receptor, is abundant in the murine placenta during the late stage of pregnancy (E15-E16), although its functional roles remain unclear. PPARγ1 is encoded by two splicing isoforms, namely Pparγ1 and Pparγ1sv, and its embryonic loss leads to early (E10) embryonic lethality. Thus, we generated knockout (KO) mice that carried only one of the isoforms to obtain a milder phenotype.
View Article and Find Full Text PDF