Yunmin Zou

Yunmin Zou

Auto-generated profile, based on publicly available information

Yunmin Zou

Department of Dermatology

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 February 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HLHui Liu
Hui Liu
YDYibo Dou
Yibo Dou
KWKai Wang
Kai Wang
YZYunmin Zou
Yunmin Zou
GSGan Sen
Gan Sen
HLHuling Li
Huling Li
Skin diseases, a significant category in the medical field, have always been challenging to diagnose and have a high misdiagnosis rate. Deep learning for skin disease classification has considerable value in clinical diagnosis and treatment. This study proposes a skin disease classification model based on multi-scale channel attention. The network architecture of the model consists of three main parts: an input module, four processing blocks, and an output module. Firstly, the model has improved the pyramid segmentation attention module to extract multi-scale features of the image entirely. Secondly, the reverse residual structure is used to replace the residual structure in the backbone network, and the attention module is integrated into the reverse residual structure to achieve better multi-scale feature extraction. Finally, the output module consists of an adaptive average pool and a fully connected layer, which convert the aggregated global features into several categories to generate the final output for the classification task. To verify the performance of the proposed model, this study used two commonly used skin disease datasets, ISIC2019 and HAM10000, for validation. The experimental results showed that the accuracy of this study was 77.6\(\%\) on the ISIC2019 skin disease series dataset and 88.2\(\%\) on the HAM10000 skin disease dataset. External validation data was added for evaluation to validate the model further, and the comprehensive evaluation results proved the effectiveness of the proposed model in this paper.

7 November 2022 in The American Journal of Dermatopathology
Verified
Journal Article
Closed access
JGJing Gu
Jing Gu
RXRushan Xia
Rushan Xia
YZYunmin Zou
Yunmin Zou
Lichen sclerosus et atrophicus (LSA) is a chronic inflammatory disease. The clinical presentation is clustered distribution of porcelain white spots that can be fused together. Early diagnosis of LSA is difficult, especially in the vulva, where it is difficult to distinguish from vitiligo. Traditional diagnostic methods mainly rely on histopathology. In this study, we used reflectance confocal microscopy (RCM) to study the characteristics of LSA and vitiligo. We investigated the clinical and confocal features of 40 cases of histopathologically proven genital LSA or vitiligo, and correlated the features with histopathologic findings. Through the analysis of the results, by RCM, we can easily distinguish genital LSA from vitiligo, which are clinically indistinguishable. This can reduce the number of unnecessary biopsies, and help with early diagnosis and timely treatment.

10 January 2024 in Skin Research and Technology
Verified
Journal Article
Open access
YZYunmin Zou
Yunmin Zou
XZXiaohong Zhu
Xiaohong Zhu
RXRushan Xia
Rushan Xia
Background: Acral lentiginous melanoma (ALM) is a highly malignant and invasive type of melanoma with unique locations of onset. Its incidence is increasing and early diagnosis is challenging. Reflectance confocal microscopy (RCM) is a non‐invasive technique that provides an accurate image of tissue pathology. There are few reports on the use of RCM for the assessment of ALM.Materials and methods: In this retrospective study, data from 31 patients with a clinical diagnosis of ALM were collected. RCM image features were compared with histopathological findings to determine the concordance between the two methods. The sensitivity, specificity, positive predictive value, and negative predictive value of RCM for the diagnosis of ALM were evaluated.Results: RCM and histopathology findings were concordant in 29 of 31 patients (93.5%). There were no false‐negative results, although there were two false positives in RCM diagnosis. The sensitivity of RCM for diagnosing ALM was 100%, specificity was 50%, positive predictive value was 93.1%, and negative predictive value was 100%.Conclusions: RCM showed substantial concordance with histopathology in the diagnosis of ALM. It is a reliable and valuable non‐invasive diagnostic tool that holds promise for the early diagnosis of ALM.

1 October 2022 in Dermatology Practical & Conceptual
Verified
Journal Article
Open access
PDF file
YZYun-Min Zou
Yun-Min Zou
XZXiaohong Zhu
Xiaohong Zhu
RXRushan Xia
Rushan Xia
Background: Patients with multifocal superficial basal cell carcinomas (sBCC) require a non-invasive treatment and follow-up with a non-invasive technique. Imiquimod 5% cream is a new non-invasive therapy for BCC. Reflectance confocal microscopy (RCM) is a non-invasive, real-time imaging technique. Methods:The efficacy of imiquimod 5% cream for the treatment of multifocal sBCC was evaluated, as well as the potential of RCM for assessing therapeutic effects. We reported four patients with 34 sBCC lesions were treated with imiquimod 5% cream. RCM was performed in the baseline and at 12 weeks, 24 weeks and 52 weeks after starting treatment. Results: Of 34 lesions treated with imiquimod 5%, 32 responded to the treatment and showed complete clinical clearing. Two subclinical BCC lesions were identified by RCM. The complete tumor clearance rate was 88.2%, and the efficiency rate was 97.1%. No lesion recurred at 24-month follow-up. RCM identified previously described confocal features of BCC and was more sensitive than clinical examination. Local skin reactions were relieved after expectant treatment. Conclusions: Imiquimod 5% cream may be useful for the treatment of multifocal sBCC, and its side effects are easy to manage. RCM can be used for non-invasive monitoring of treatment response and improved the tumor clearance rate.

18 June 2020 in Skin Research and Technology
Verified
Journal Article
Closed access
PDF file
YZYunmin Zou
Yunmin Zou
XZXiaohong Zhu
Xiaohong Zhu
LYLijia Yang
Lijia Yang
JGJing Gu
Jing Gu
RXRushan Xia
Rushan Xia