Prediction of toxicity outcomes following radiotherapy using deep learning-based models: A systematic review

PURPOSE

This study aims to perform a comprehensive systematic review of deep learning (DL) models in predicting RT-induced toxicity.

MATERIALS AND METHODS

A literature review was performed following the PRISMA guidelines. Systematic searches were performed in PubMed, Scopus, Cochrane and Embase databases from the earliest record up to September 2022. Related studies on deep learning models for radiotherapy toxicity prediction were selected based on predefined PICOS criteria.

RESULTS

Fourteen studies of radiotherapy-treated patients on different types of cancer [prostate (n=2), HNC (n=4), liver (n=2), lung (n=4), cervical (n=1), and oesophagus (n=1)] were eligible for inclusion in the systematic review. Information regarding patient characteristics and model development was summarized. Several approaches, such as ensemble learning, data augmentation, and transfer learning, that were utilized by selected studies were discussed.

CONCLUSION

Deep learning techniques are able to produce a consistent performance for toxicity prediction. Future research using large and diverse datasets and standardization of the study methodologies are required to improve the consistency of the research output.

The impact of ZnO configuration as an external layer on the sensitivity of a bi-layer coated polymer optical fiber probe

Salinity magnitude changes are a critical factor for determining the chemistry of natural water bodies and biological processes. Label-free refractive index sensors are promising devices for detecting these changes. A polymer optical fiber (POF) sensor modified with cladding treatment and a bi-layer zinc oxide/silver (ZnO/Ag) nanostructure coating to determine sodium chloride concentration changes through refractive index variations in water is experimentally demonstrated. The use of three ZnO nanostructure shapes, nanoparticles and horizontally and vertically oriented nanorods, as an external layer and a broad spectrum light source from the visible (Vis) to the near infrared (NIR) region are investigated to achieve optimum sensitivity. The rms roughness, optical band-gap and zeta potential (ZP) value for the vertically oriented sample are 148 nm, 3.19 eV and 5.96 mV, respectively. In the NIR region the wavelength–intensity sensitivity values of probes coated with ZnO nanoparticles and horizontally and vertically oriented nanorods are 104 nm RIU⁻¹–12 dB RIU⁻¹, 63 nm RIU⁻¹–10 dB RIU⁻¹ and 146 nm RIU⁻¹–22 dB RIU⁻¹, respectively, and in the Vis area the values are 65 nm RIU⁻¹–14 dB RIU⁻¹, 58 nm RIU⁻¹–11 dB RIU⁻¹ and 89 nm RIU⁻¹–23 dB RIU⁻¹, respectively. The maximum amplitude sensitivity is obtained for the probe coated with vertically aligned ZnO nanorods in the NIR area due to the deeper penetration of evanescent waves, a higher surface-volume ratio, better crystallinity, more adhesive interactions with salt molecules, larger surface roughness and higher-order dispersion compared to the other coated ZnO nanostructures.

Detecting the salinity magnitude changes as a predominant factor for determining the chemistry of natural water bodies and biological process via label-free refractive index modified optical fiber sensors.

An FBG magnetic sensor for oil flow monitoring in sandstone core

Monitoring the oil movement using a non-contact optical fiber probe during enhanced oil recovery is a novel technique to increase the efficiency of the process by distinguishing the oil position in the reservoir. A partially unclad fiber Bragg grating (FBG) coated with Fe₃O₄ nanoparticles as a magnetic field sensor is experimentally demonstrated. A series of six FBGs reflecting different wavelengths are fixed on the surface of sandstone. Nanofluids containing magnetite nanoparticles and alkaline-surfactant-polymer are injected continuously in two separate steps into the sandstone, which is saturated with 20% oil and 80% brine. The chamber is equipped with a solenoid that acts as a magnetic field generator. The changes in the magnetic field strength depended on the FBG-solenoid distance and the density of localized injected nanoparticles near the FBGs leads to a shift of the reflected wavelength of each single FBG accordingly. The shift is caused by the interference of different propagating modes reflected from the core-cladding and cladding-magnetite layer interfaces. The intensity of the FBG spectra decreases by injecting the nanofluid and vice versa for surfactant injection. The sensor response time of ∼21 s confirms the high reliability and repeatability of the sensing scheme. Movement of oil along the sandstone alters the wavelength shift in the FBG spectra.

Monitoring the oil movement using a non-contact optical fiber probe during enhanced oil recovery is a novel technique to increase the efficiency of the process by distinguishing the oil position in the reservoir.

Nanostructured Pd-Based Electrocatalyst and Membrane Electrode Assembly Behavior in a Passive Direct Glycerol Fuel Cell

The aim of this study was to synthesize, characterize, and observe the catalytic activity of Pd₁Au₁ supported by vapor-grown carbon nanofiber (VGCNF) anode catalyst prepared via the chemical reduction method. The formation of the single-phase compounds was confirmed by X-ray diffraction (XRD) and Rietveld refinement analysis, which showed single peaks corresponding to the (111) plane of the cubic crystal structure. Further analysis was carried out by field emission scanning emission microscopy (FESEM), energy dispersive X-ray analysis (EDX), nitrogen adsorption/desorption measurements, and X-ray photoelectron spectroscopy (XPS). The electrochemical performance was examined by cyclic voltammetry tests. The presence of mesoporous VGCNF as support enables the use of a relatively small amount of metal catalyst that still produces an excellent current density (66.33 mA cm^-2). Furthermore, the assessment of the kinetic activity of the nanocatalyst using the Tafel plot suggests that Pd₁Au₁/VGCNF exerts a strong electrocatalytic effect in glycerol oxidation reactions. The engineering challenges are apparent from the fact that the application of the homemade anode catalyst to the passive direct glycerol fuel cell shows the power density of only 3.9 mW cm^-2. To understand the low performance, FESEM observation of the membrane electrode assembly (MEA) was carried out, examining several morphological defects that play a crucial role and affect the performance of the direct glycerol fuel cell.

Enhanced performance of a novel anodic PdAu/VGCNF catalyst for electro-oxidation in a glycerol fuel cell

This study presents a novel anodic PdAu/VGCNF catalyst for electro-oxidation in a glycerol fuel cell. The reaction conditions are critical issues affecting the glycerol electro-oxidation performance. This study presents the effects of catalyst loading, temperature, and electrolyte concentration. The glycerol oxidation performance of the PdAu/VGCNF catalyst on the anode side is tested via cyclic voltammetry with a 3 mm2 active area. The morphology and physical properties of the catalyst are examined using X-ray diffraction (XRD), field emission scanning electron microscopy (SEM) and energy dispersive X-ray (EDX) spectroscopy. Then, optimization is carried out using the response surface method with central composite experimental design. The current density is experimentally obtained as a response variable from a set of experimental laboratory tests. The catalyst loading, temperature, and NaOH concentration are taken as independent parameters, which were evaluated previously in the screening experiments. The highest current density of 158.34 mAcm-2 is obtained under the optimal conditions of 3.0 M NaOH concentration, 60 °C temperature and 12 wt.% catalyst loading. These results prove that PdAu-VGCNF is a potential anodic catalyst for glycerol fuel cells.

Occupational radiation exposure to anesthetists from fluoroscopic projections during orthopedic operative procedures

PURPOSE

The role of anesthetists during orthopedic fluoroscopic procedures exposes them to radiation. We conducted a prospective, descriptive study to estimate the radiation exposure to anesthetists during procedures over a six-month period in the orthopedic trauma operating theatres which had the most fluoroscopic usage.

MATERIALS AND METHODS

Thermoluminescent dosimeter (TLD) chips were placed two metres away from the radiation source, in three positions to simulate the anesthetist's position in the operating theatre during the fluoroscopic procedures as well as their radiation safety practices. The three positions were above the lead gown, behind the lead gown and behind the protective lead screen. The fourth TLD chip was assigned as a control measure to account for background radiation. The radiation exposure was measured at every end of each month during the period of six consecutive months. The TLD chips were sent to the Malaysian Institute for Nuclear Technology (MINT) for the analysis.

RESULTS

From the study, the annual exposure without a protective shield at a 2 metre distance from the projection source was estimated to be 0.70 milliSievert (mSv)/year. With the use of lead gowns and protective lead screens, the annual exposure was estimated to be 0.08 mSv / year. All the radiation levels measured were within the maximum permissible dose of 50 mSv / year.

CONCLUSIONS

During fluoroscopic assisted orthopedic procedures, the anesthetists in UKMMC are exposed to a small amount of radiation which is well below the annual maximum permissible limit as determined by local and international regulatory bodies.

Ambulatory surgery and anaesthesia in HUKM, a teaching hospital in Malaysia: the first two years experience

Ambulatory or day care surgery is still in its infancy in this part of the world. Our newly built university affiliated hospital started its Day Surgery Centre in February 1998. It is the first multidisciplinary ambulatory surgery centre in a teaching hospital in the country. It caters for Orthopaedic surgery, Urology, Plastic surgery, Otorhinolaryngology, General surgery, Paediatric surgery and Ophthalmology. We have done 2,604 cases and our unanticipated admission rate is less than 2%. There has been no major morbidity or mortality. The problems of setting up a multidisciplinary ambulatory centre in a teaching hospital are discussed.