X-ray　spectrum　plays　a　very　important　role　in　dual　energy　computed　tomography　(DECT)　reconstruction.　Because　it　is　difficult　to　measure　x-ray　spectrum　directly　in　practice,　efforts　have　been　devoted　into　spectrum　estimation　by　using　transmission　measurements.　These　measurement　methods　are　independent　of　the　image　reconstruction,　which　bring　extra　cost　and　are　time　consuming.　Furthermore,　the　estimated　spectrum　mismatch　would　degrade　the　quality　of　the　reconstructed　images.　In　this　paper,　we　propose　a　spectrum　estimation-guided　iterative　reconstruction　algorithm　for　DECT　which　aims　to　simultaneously　recover　the　spectrum　and　reconstruct　the　image.　The　proposed　algorithm　is　formulated　as　an　optimization　framework　combining　spectrum　estimation　based　on　model　spectra　representation,　image　reconstruction,　and　regularization　for　noise　suppression.　To　resolve　the　multi-variable　optimization　problem　of　simultaneously　obtaining　the　spectra　and　images,　we　introduce　the　block　coordinate　descent　(BCD)　method　into　the　optimization　iteration.　Both　the　numerical　simulations　and　physical　phantom　experiments　are　performed　to　verify　and　evaluate　the　proposed　method.　The　experimental　results　validate　the　accuracy　of　the　estimated　spectra　and　reconstructed　images　under　different　noise　levels.　The　proposed　method　obtains　a　better　image　quality　compared　with　the　reconstructed　images　from　the　known　exact　spectra　and　is　robust　in　noisy　data　applications.