Low-cost flexible thin-film detector for medical dosimetry applications

Abstract

The purpose of this study is to characterize dosimetric properties of thin film photovoltaic sensors as a platform for development of prototype dose verification equipment in radiotherapy. Towards this goal, flexible thin-film sensors of dose with embedded data acquisition electronics and wireless data transmission are prototyped and tested in kV and MV photon beams. Fundamental dosimetric properties are determined in view of a specific application to dose verification in multiple planes or curved surfaces inside a phantom. Uniqueness of the new thin-film sensors consists in their mechanical properties, low-power operation, and low-cost. They are thinner and more flexible than dosimetric films. In principle, each thin-film sensor can be fabricated in any size (mm² - cm² areas) and shape. Individual sensors can be put together in an array of sensors spreading over large areas and yet being light. Photovoltaic mode of charge collection (of electrons and holes) does not require external electric field applied to the sensor, and this implies simplicity of data acquisition electronics and low power operation. The prototype device used for testing consists of several thin film dose sensors, each of about 1.5 cm × 5 cm area, connected to simple readout electronics. Sensitivity of the sensors is determined per unit area and compared to EPID sensitivity, as well as other standard photodiodes. Each sensor independently measures dose and is based on commercially available flexible thin-film aSi photodiodes. Readout electronics consists of an ultra low-power microcontroller, radio frequency transmitter, and a low-noise amplification circuit implemented on a flexible printed circuit board. Detector output is digitized and transmitted wirelessly to an external host computer where it is integrated and processed. A megavoltage medical linear accelerator (Varian Tx) equipped with kilovoltage online imaging system and a Cobalt source are used to irradiate different thin-film detector sensors in a Solid Water phantom under various irradiation conditions. Different factors are considered in characterization of the device attributes: energies (80 kVp, 130 kVp, 6 MV, 15 MV), dose rates (different ms × mA, 100-600 MU/min), total doses (0.1 cGy-500 cGy), depths (0.5 cm-20 cm), irradiation angles with respect to the detector surface (0°-180°), and IMRT tests (closed MLC, sweeping gap). The detector response to MV radiation is both linear with total dose (~1-400 cGy) and independent of dose rate (100-600 Mu/min). The sensitivity per unit area of thin-film sensors is lower than for aSi flat-panel detectors, but sufficient to acquire stable and accurate signals during irradiations. The proposed thin-film photodiode system has properties which make it promising for clinical dosimetry. Due to the mechanical flexibility of each sensor and readout electronics, low-cost, and wireless data acquisition, it could be considered for quality assurance (e.g., IMRT, mechanical linac QA), as well as real-time dose monitoring in challenging setup configurations, including large area and 3D detection (multiple planes or curved surfaces).

Figure 1

An array of eight sensors (a) mounted on flexible PCB; MSP430 USB‐receiver (b) for wireless data transmission; schematic diagrams of the principle of operation of thin‐film photocell (c); and the analog amplification circuit (d). X‐rays incident on thin‐film photocell can directly produce electron‐hole pairs, which are separated in the semiconductor junction and processed by additional amplification electronics. Transimpedance amplification and buffer circuit before digitalization of the separated charge of the photocell leads to a current in photovoltaic mode, which is amplified by a transimpedance amplifier.

Figure 2

Total photocell response ${\mathrm{S}}_{\text{tot}}\left(\mathrm{D}\right)$ [ADC] vs. ionization chamber dose D [cGy]. The integrated ADC units scale linearly with applied dose, as measured by the reference ion chamber. As one can see. different detector cells have different linear response, which can be calibrated to rsult in dose (6 MV).

Figure 3

Normalized photocell and ion chamber response per monitor unit (R(m) / m) as a function of monitor unit $({\mathrm{m}}_{\text{ref}}=100,6\hspace{0.17em}\text{MV})$.

Figure 4

Normalized response ${\mathrm{R}}_{\text{FTF}-\text{PV}}(\varphi )/{\mathrm{R}}_{\text{ion}}(\varphi )$ as a function of the irradiation angle $\varphi ({\varphi }_{\text{ref}}=0^{\circ },6\hspace{0.17em}\text{MV})$.

Figure 5

Dose rate dependence of photocells in comparison to ionization chamber reference measurements. The responses are normalized to dose rate ${\mathrm{r}}_{\text{ref}}=600\hspace{0.17em}\text{MU}/min$ (6 MV).

Figure 6

Attenuation profile R(d) with ${\mathrm{d}}_{\text{ref}}=1.5\hspace{0.17em}\text{cm}\hspace{0.17em}(\text{SDD}=100\hspace{0.17em}\text{cm})$ for measured response vs. dose calculated by Eclipse TPS (6 MV).

Figure 7

Raw data (a) for 80 kVp and 130 kVp and various values of mAs. The maximal sampling frequency in the current system is applied here, because the pulses are within 4‐25 milliseconds; time dependence of sensor signal (b) for 6 MV and $\mathrm{m}=50$ and different dose rates. The raw data was rescaled to show differences in the Moiré‐aliasing patterns. Sampling rate was $\mathrm{f}=268\text{Hz}$ in all cases.

Figure 8

Normalized photocell and ion chamber response per monitor unit (R(m,f) / m) as a function of monitor unit $({\mathrm{m}}_{\text{ref}}=100,6\hspace{0.17em}\text{MV})$. Different sampling frequencies affect the total sensibility of the detector cell. Dose rate was ${\mathrm{r}}_{\text{ref}}=400\hspace{0.17em}\text{MU}/min$.

Figure 9

Energy dependence for various detectors including a‐Si FTF‐PV normalized to the Cobalt source energy 1.25 MeV Energies in keV range represent average energies of kVp spectra (integrated energy fluence divided bv integrated fluence) generated by an X‐ray tube.

Figure 10

Raw signal of FTF‐PV (a) in hardware‐integration mode for two open beam and three 20 mm sweeping gap irradiations: ${\mathrm{e}}_{\text{ref}}=6\hspace{0.17em}\text{MV},{\mathrm{r}}_{\text{ref}}=400\hspace{0.17em}\text{MU}/min,{\mathrm{m}}_{\text{ref}}=100\hspace{0.17em}\text{MU}$ and 200 MU, 6 MV; response (b) of sweeping gap and closed MLC as a function of gap size. For closed MLC pattern, gap size was assumed to be zero.