As　bridges　increasingly　serve　not　only　to　meet　traffic　demands　but　also　to　fulfill　aesthetic　expectations,　ensuring　high　aesthetic　quality　in　bridge　design　has　become　more　important.　This　paper　proposes　a　deep-learning-based　aesthetic　evaluation　network　for　the　automatic　assessment　of　bridge　pylon　aesthetics　and　elaborates　on　a　design　method　that　integrates　this　network　with　topology　optimization.　Firstly,　a　standardized　database　and　anaesthetic　quality　evaluation　framework　specifically　for　bridge　pylons　of　long-span　cable-supported　bridges　were　developed.　High-quality　bridge　pylon　data　were　acquired　through　a　series　of　image　processing　methods,　followed　by　an　extensive　questionnaire　to　gather　aesthetic　quality　labels　for　each　pylon.　Then,　different　kinds　of　base　models　were　designed　and　trained　with　the　labeled　dataset,　with　comparisons　made　across　accuracy　and　complexity　indicators　to　establish　the　Pylon　Aesthetic　Evaluation　Network　(PAENet).　Finally,　anaesthetics-　oriented　bridge　pylon　design　method　is　proposed　which　integrates　the　PAENet　with　topology　optimization,　and　the　design　of　suspension　bridge　pylons　were　given　as　examples.　Through　this　study,　a　high-quality　database　for　bridge　pylon　aesthetics　quality　evaluation　was　constructed.　Results　indicate　that　the　PAENet,　using　ShuffleNet　v2x1　as　the　base　model　and　enhanced　through　transfer　learning,　achieved　the　highest　accuracy　in　assessing　the　aesthetic　quality　of　bridge　pylons,　in　alignment　with　human　evaluations.　Moreover,　the　integration　of　topology　optimization　and　aesthetic　evaluation　facilitates　designs　that　balance　mechanical　performance　with　aesthetic　appeal.　The　proposed　method　promotes　the　practical　incorporation　of　aesthetics　into　bridge　design,　contributing　to　the　conceptual　design　of　future　bridges.