We report the development of a cost-effective, automated parasite diagnostic system that does not require special sample preparation or a trained user. It is composed of a cost-effective, portable microscope that can automatically auto-focus and scan over the size of an entire McMaster chamber (100 mm2) and capture high resolution (~1 µm) bright field images without need for user intervention. Fecal samples prepared using the McMaster flotation method were imaged, with the imaging region comprising the entire McMaster chamber. A convolutional neural network (CNN) automatically segments and analyzes the images to robustly separate eggs from background debris. The performance of the CNN is high despite the challenging, unbalanced nature of the images, where >95% of images contain no eggs and thus the potential for false-positives is high. Simple post-processing of the CNN output yields both egg species and egg counts. The system was validated by comparing hand counts with automated counts of samples containing eggs from ascarid, strongyle, and Trichuris nematodes, along with Eimeria oocysts. The system shows excellent performance, even on challenging Eimeria parasites whose small size is similar to fecal debris. The R2 values between hand and automated counts are >0.95 for both Eimeria and nematode parasites. Further, the diagnostic accuracy of our system for recommending antibiotic treatment is 100% for nematode parasites and 96% for Eimeria. As a further demonstration of utility, the system was used to conveniently quantify drug response over time, showing residual disease due to antibiotic resistance after 2 weeks.