目的:為7使軟片適用於強度調控放射治療(IMRT)多重角度入射，及動態性照野蠻化的劑量驗體特性，本研究針對射東與敵片平行排列時，照野與深度改變的情況下，如何正確將軟片光密度值正確轉換劑量，提供一套可行的辦法。

材料與方法:利用數種材質的濾片與軟片之組合接受X光的照射，再以類神經網路將不同能贈與劑量之間的關係找出來，可以得到實際的劑量。

結果:經本系統"換的劑量值，在深度及�ij野蠻化的情況下，仍能有效轉換劑量至最大誤差小於±4% '平掏蜈差2%左右，此為臨床上司接受之誠差Iif!I圈。

結論:本實驗所提出之劑量鞠換方式，已能正確轉換劑量於射東和軟片平行排列及照野蠻化的情況，進一步將實際評估本系統在鷗床應用及多重照野(multiple field)下的義現。

Purpose:Intensity Modulation Radiation Therapy (IMRT) is implemented using multiple beam orientations and varius field sizes. X-ray film can't be used as a dosimetry tool in such situation because of its serious energy dependent problem. We present and develop an improved method to overcome the cIrcumstances.

Materials and Methods : We used the combination of film with various filters (None， Pb， Cu， and AI) so that each film is irradiated to di仔erent energy sp凹trum. A neural-network is employed to relate the actual dose and energy spectra. After calibration and training， the optical densities of the four films can be input to the network to yield the actual dose at any location.

Results:The PDD of a 20 x 20 field size and the dose distribution of an off-axis location at 5cm are estimated using this trained neural network. The maximum differences between the measurements of this film system and ionization chamber were less than ±4%， and less than 2% for the mean error in our InvestigatIOn

Conclusion: Optical density and dose relationship can be found and converted by our neural-net systern. For the future studies， we will focus on clinical application of these experimental results and extend the concept to multiple beam orientations.