Prediction of liver Dmean for proton beam therapy using deep learning and contour-based data augmentation

The prediction of liver Dmean with 3-dimensional radiation treatment planning (3DRTP) is time consuming in the selection of proton beam therapy (PBT), and deep learning prediction generally requires large and tumor-specific databases. We developed a simple dose prediction tool (SDP) using deep learning and a novel contour-based data augmentation (CDA) approach and assessed its usability. We trained the SDP to predict the liver Dmean immediately. Five and two computed tomography (CT) data sets of actual patients with liver cancer were used for the training and validation. Data augmentation was performed by artificially embedding 199 contours of virtual clinical target volume (CTV) into CT images for each patient. The data sets of the CTVs and OARs are labeled with liver Dmean for six different treatment plans using two-dimensional calculations assuming all tissue densities as 1.0. The test of the validated model was performed using 10 unlabeled CT data sets of actual patients. Contouring only of the liver and CTV was required as input. The mean relative error (MRE), the mean percentage error (MPE) and regression coefficient between the planned and predicted Dmean was 0.1637, 6.6%, and 0.9455, respectively. The mean time required for the inference of liver Dmean of the six different treatment plans for a patient was 4.47±0.13 seconds. We conclude that the SDP is cost-effective and usable for gross estimation of liver Dmean in the clinic although the accuracy should be improved further if we need the accuracy of liver Dmean to be compatible with 3DRTP.

Effect of laser diode light irradiation on growth capability of human hair follicle dermal papilla cells

Low level laser therapy is widely used to relieve pain and inflammation, and to restore cellular functions. The photons of light are absorbed by mitochondria in cells, leading to an increase in the production of adenosine triphosphate (ATP), nitric oxide release, blood flow, and reactive oxygen species (ROS). This study proposed the use of a laser diode array at 808 nm to stimulate the proliferation and to activate the functions of dermal papilla cells, which were an important part of the hair growth cycle. These cells were isolated from human hair follicles and were exposed to 808 nm light at various doses from 0.5, 1, 2.5, 4, and 6 J/cm². The rate of cell proliferation and the gene expression profile of dermal papilla cells were investigated and compared with the control in which the cells did not received any light treatment. The growth curves of the dermal papilla cells were used to determine the specific growth rates. Higher specific growth rates were observed in the cells exposed to laser at doses higher than 0.5 J/cm². The effect of the laser light treatment on several gene markers, specifically for dermal papilla cells, was evaluated using real-time polymerase chain reaction (qPCR). Our result shows that collagen type 1 (Col1), alkaline phosphatase (Alp), and versican (Vcan) did not increase when the cells were irradiated by the laser light. Interestingly, sex determining region y-box 2 (Sox2) gene was up-regulated when 0.5 J/cm², and 1 J/cm² light was used, while an increase in the level of fibroblast growth factor 7 (Fgf7) gene was observed with light irradiation at 0.5 J/cm², 1 J/cm², 2.5 J/cm², and 4 J/cm². Too high irradiation dose was shown to yield no effect on the gene expression of dermal papilla cells.