摘要：Tzanck smear test is a low-cost, rapid and reliable tool which can be used for the diagnosis of many erosive-vesiculobullous, tumoral and granulomatous diseases. Currently its use is limited mainly due to lack of experience in interpretation of the smears. We developed a deep learning model, TzanckNet, that can identify cells in Tzanck smear test findings. TzanckNet was trained on a retrospective development dataset of 2260 Tzanck smear images collected between December 2006 and December 2019. The finalized model was evaluated using a prospective validation dataset of 359 Tzanck smear images collected from 15 patients during January 2020. It is designed to recognize six cell types (acantholytic cells, eosinophils, hypha, multinucleated giant cells, normal keratinocytes and tadpole cells). For 359 images and 6 cell types, TzanckNet made 2154 predictions. The accuracy was 94.3% (95% CI 93.4–95.3), the sensitivity was 83.7% (95% CI 80.3–87.0) and the specificity was 97.3% (95% CI 96.5–98.1). The area under the receiver operating characteristic curve was 0.974. Our results show that TzanckNet has the potential to lower the experience barrier needed to use this test, broadening its user base, and hence improving patient well-being.
其他摘要：Abstract Tzanck smear test is a low-cost, rapid and reliable tool which can be used for the diagnosis of many erosive-vesiculobullous, tumoral and granulomatous diseases. Currently its use is limited mainly due to lack of experience in interpretation of the smears. We developed a deep learning model, TzanckNet, that can identify cells in Tzanck smear test findings. TzanckNet was trained on a retrospective development dataset of 2260 Tzanck smear images collected between December 2006 and December 2019. The finalized model was evaluated using a prospective validation dataset of 359 Tzanck smear images collected from 15 patients during January 2020. It is designed to recognize six cell types (acantholytic cells, eosinophils, hypha, multinucleated giant cells, normal keratinocytes and tadpole cells). For 359 images and 6 cell types, TzanckNet made 2154 predictions. The accuracy was 94.3% (95% CI 93.4–95.3), the sensitivity was 83.7% (95% CI 80.3–87.0) and the specificity was 97.3% (95% CI 96.5–98.1). The area under the receiver operating characteristic curve was 0.974. Our results show that TzanckNet has the potential to lower the experience barrier needed to use this test, broadening its user base, and hence improving patient well-being.
