A modified deep learning method for Alzheimer's disease detection based on the facial submicroscopic features in mice.

Alzheimer's disease (AD) is a chronic disease among people aged 65 and older. As the aging population continues to grow at a rapid pace, AD has emerged as a pressing public health issue globally. Early detection of the disease is important, because increasing evidence has illustrated that early diagnosis holds the key to effective treatment of AD.

Nanodosimetric quantity-weighted dose optimization for carbon-ion treatment planning.

Dose verification of treatment plans is an essential step in radiotherapy workflows. In this work, we propose a novel method of treatment planning based on nanodosimetric quantity-weighted dose (NQWD), which could realize biological representation using pure physical quantities for biological-oriented carbon ion-beam treatment plans and their direct verification. The relationship between nanodosimetric quantities and relative biological effectiveness (RBE) was studied with the linear least-squares method for carbon-ion radiation fields.

DR-only Carbon-ion radiotherapy treatment planning via deep learning.

Purpose: To evaluate the feasibility of patient-specific digital radiography (DR)-only treatment planning for carbon ion radiotherapy in anthropomorphic thorax-and-abdomen phantom and head-and-neck patients.

Methods: The study was conducted on the anthropomorphic phantom and head-and-neck patients. We collected computed tomography (CT) and DR images of the phantom and cone beam CT (CBCT) and DR images of the patients, respectively.

Validation and testing of a novel pencil-beam model derived from Monte Carlo simulations in carbon-ion treatment planning for different scenarios.

Purpose: The calculation ability of the newly-proposed accurate beam model, the double Gaussian-logistic (DG-L) model, was validated in both homogeneous and heterogeneous phantoms to provide helpful information for its future application in clinical carbon-ion treatment planning system (TPS).

Methods: MatRad was used as the new algorithm test platform. Based on Monte Carlo (MC) method, the basic database in matRad was generated, then comparative dosimetric analyses between the single Gaussian (SG), double Gaussian (DG) and DG-L models against the MC recalculations were performed on the treatment plans of a cubic water phantom, a TG119 phantom and a liver patient scenario.

Artificial Intelligence Radiotherapy Planning: Automatic Segmentation of Human Organs in CT Images Based on a Modified Convolutional Neural Network.

Objective: Precise segmentation of human organs and anatomic structures (especially organs at risk, OARs) is the basis and prerequisite for the treatment planning of radiation therapy. In order to ensure rapid and accurate design of radiotherapy treatment planning, an automatic organ segmentation technique was investigated based on deep learning convolutional neural network.

Method: A deep learning convolutional neural network (CNN) algorithm called BCDU-Net has been modified and developed further by us.

Nanodosimetric understanding to the dependence of the relationship between dose-averaged lineal energy on nanoscale and LET on ion species.

With the extension of ion species in ion-beam radiotherapy, the sole dependence of relative biological effectiveness (RBE) on linear energy transfer (LET) is insufficient when comparing RBE for ion beams with the same LET value. The aim of the present study was to provide a systematic study of the nanodosimetry for ion beams with the same LET value. Based on the calculated LET profiles of ion beams with range about 130 mm, lineal energy spectra and dose-averaged lineal energy [Formula: see text] on 4 nm site for various clinical ion beams were obtained.

Nanodosimetric quantities and RBE of a clinically relevant carbon-ion beam.

Purpose: Although carbon-ion therapy is becoming increasingly attractive to the treatment of tumors, details about the ionization pattern formed by therapeutic carbon-ion beam in tissue have not been fully investigated. In this work, systematic calculations for the nanodosimetric quantities and relative biological effectiveness (RBE) of a clinically relevant carbon-ion beam were studied for the first time.

Methods: The method combining both track structure and condensed history Monte Carlo (MC) simulations was adopted to calculate the nanodosimetric quantities.

Technical Note: Effect of magnetic fields on the microdosimetry of carbon-ion beams.

Purpose: To investigate the influence of magnetic fields on the microdosimetry of carbon-ion beams and the scaling effect of tissue equivalent proportional counter (TEPC) defined as the change of energy deposition in a TEPC from that in a microscopic scale region of interest due to the presence of a magnetic field in combination with the TEPC larger physical dimensions.

Methods: Geant4-based Monte Carlo simulations were conducted to calculate the microdosimetric quantities for carbon-ion beams with different initial energies (10-290 MeV/u) under magnetic fields of various strengths (0.5-3 T).

A novel pencil beam model for carbon-ion dose calculation derived from Monte Carlo simulations.

An accurate kernel model is of vital importance for pencil-beam dose algorithm in charged particle therapy using precise spot-scanning beam delivery, in which an accurate depiction of the low dose envelope is especially crucial. Based on the Monte Carlo method, we investigated the dose contribution of secondary particles to the total dose and proposed a novel beam model to depict the lateral dose distribution of carbon-ion pencil beam in water. We demonstrated that the low dose envelope in single-spot profiles in water could be adequately modelled with the addition of a logistic distribution to a double Gaussian one, which was verified in both single carbon-ion pencil beam and superposed fields of different sizes with multiple pencil beams.

Fragmentation level determines mitochondrial damage response and subsequently the fate of cancer cells exposed to carbon ions.

Objectives: Although mitochondria are known to play an important role in radiation-induced cellular damage response, the mechanisms of how radiation elicits mitochondrial responses are largely unknown.

Materials And Methods: Human cervical cancer cell line HeLa and human breast cancer cell lines MCF-7 and MDA-MB-231 were irradiated with high LET carbon ions at low (0.5 Gy) and high (3 Gy) doses.

Evaluation of mesh- and binary-based contour propagation methods in 4D thoracic radiotherapy treatments using patient 4D CT images.

Based on four dimensional (4D) computed tomography (CT) images, mesh- and binary-based contour propagation algorithms for 4D thoracic radiotherapy treatments were evaluated. Gross tumor volumes (GTVs), lungs, hearts and spinal cords on the CT images at the end-exhale and end-inhale phases for six patients were delineated by the physician. All volumes of interest (VOIs) were automatically propagated from the end-exhale phase to the end-inhale phase using two propagation methods.

Respiratory motion management using audio-visual biofeedback for respiratory-gated radiotherapy of synchrotron-based pulsed heavy-ion beam delivery.

Purpose: To efficiently deliver respiratory-gated radiation during synchrotron-based pulsed heavy-ion radiotherapy, a novel respiratory guidance method combining a personalized audio-visual biofeedback (BFB) system, breath hold (BH), and synchrotron-based gating was designed to help patients synchronize their respiratory patterns with synchrotron pulses and to overcome typical limitations such as low efficiency, residual motion, and discomfort.

Methods: In-house software was developed to acquire body surface marker positions and display BFB, gating signals, and real-time beam profiles on a LED screen. Patients were prompted to perform short BHs or short deep breath holds (SDBH) with the aid of BFB following a personalized standard BH/SDBH (stBH/stSDBH) guiding curve or their own representative BH/SDBH (reBH/reSDBH) guiding curve.