Assessment of Skin Toxicity in an in Vitro Reconstituted Human Epidermis Model Using Deep Learning
Open accessAbstract
Skin toxicity is a common safety concern associated with drugs that inhibit epidermal growth factor receptors as well as other targets involved in epidermal growth and differentiation. Recently, the use of a three-dimensional reconstructed human epidermis model enabled large-scale drug screening and showed potential for predicting skin toxicity. Although a decrease in epidermal thickness was often observed when the three-dimensional reconstructed tissues were exposed to drugs causing skin toxicity, the thickness evaluation of epidermal layers from a pathologist was subjective and not easily reproducible or scalable. In addition, the subtle differences in thickness among tissues, as well as the large number of samples tested, made cross-study comparison difficult when a manual evaluation strategy was used. The current study used deep learning and image-processing algorithms to measure the viable epidermal thickness from multiple studies and found that the measured thickness was not only significantly correlated with a pathologist's semi-quantitative evaluation but was also in close agreement with the quantitative measurement performed by pathologists. Moreover, a sensitivity of 0.8 and a specificity of 0.75 were achieved when predicting the toxicity of 18 compounds with clinical observations with these epidermal thickness algorithms. This approach is fully automated, reproducible, and highly scalable. It not only shows reasonable accuracy in predicting skin toxicity but also enables cross-study comparison and high-throughput compound screening.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · see citing works
Improved protein structure prediction using potentials from deep learning
Senior, A. W., Evans, R., Jumper, J., Kirkpatrick, J., Sifre, L., Green, T., Qin, C., Žídek, A., Nelson, A. W. R., Bridgland, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1923-7 · Cited by 3,378 · see citing works
Principles for Valid Histopathologic Scoring in Research
Gibson-Corley, K. N., Olivier, A. K., & Meyerholz, D. K. (2013) · Veterinary Pathology · doi:10.1177/0300985813485099 · Cited by 965 · see citing works
Mechanisms of cutaneous toxicities to EGFR inhibitors
Lacouture, M. E. (2006) · Nature reviews. Cancer · doi:10.1038/nrc1970 · Cited by 792 · see citing works
Artificial Intelligence and Digital Pathology: Challenges and Opportunities
Tizhoosh, H. R., & Pantanowitz, L. (2018) · Journal of Pathology Informatics · doi:10.4103/jpi.jpi_53_18 · Cited by 544 · see citing works
Peng, B., Hayes, M., Resta, D. J., Racine-Poon, A., Druker, B. J., Talpaz, M., Sawyers, C. L., Rosamilia, M., Ford, J., Lloyd, P. M., et al. (2004) · Journal of Clinical Oncology · doi:10.1200/jco.2004.03.050 · Cited by 471 · see citing works
The Epidermal Growth Factor Receptor System in Skin Repair and Inflammation
Pastore, S., Mascia, F., Mariani, V., & Girolomoni, G. (2007) · Journal of Investigative Dermatology · doi:10.1038/sj.jid.5701184 · Cited by 441 · see citing works
Sarker, D., Ang, J. E., Baird, R. D., Kristeleit, R. S., Shah, K. J., Moreno, V., Clarke, P. A., Raynaud, F. I., Levy, G. G., Ware, J. A., et al. (2014) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-14-0947 · Cited by 361 · see citing works
The EGF receptor - an essential regulator of multiple epidermal functions.
Jost, M., Kari, C., & Rodeck, U. (2000) · PubMed · Cited by 298 · see citing works
Age-dependent HLA genetic heterogeneity of type 1 insulin-dependent diabetes mellitus.
Caillat‐Zucman, S., Garchon, H., Timsit, J., Assan, R., Boîtard, C., Djilali-Saiah, I., Bougneres, P. F., & Bach, J. (1992) · Journal of Clinical Investigation · doi:10.1172/jci116110 · Cited by 286 · see citing works
Scope, A., Agero, A. L. C., Dusza, S. W., Myskowski, P. L., Lieb, J., Saltz, L. B., Kemeny, N. E., & Halpern, A. C. (2007) · Journal of Clinical Oncology · doi:10.1200/jco.2007.12.6987 · Cited by 277 · see citing works
Hanker, A. B., Kaklamani, V., & Arteaga, C. L. (2019) · Cancer Discovery · doi:10.1158/2159-8290.cd-18-1175 · Cited by 256 · see citing works
IL-23–Mediated Psoriasis-Like Epidermal Hyperplasia Is Dependent on IL-17A
Rizzo, H. L., Kagami, S., Phillips, K. G., Kurtz, S. E., Jacques, S. L., & Blauvelt, A. (2010) · The Journal of Immunology · doi:10.4049/jimmunol.1001001 · Cited by 239 · see citing works
The Next Era: Deep Learning in Pharmaceutical Research
Ekins, S. (2016) · Pharmaceutical Research · doi:10.1007/s11095-016-2029-7 · Cited by 237 · see citing works
Clinical Pharmacokinetics and Pharmacodynamics of Afatinib
Wind, S., Schnell, D., Ebner, T., Freiwald, M., & Stopfer, P. (2017) · Clinical Pharmacokinetics · doi:10.1007/s40262-016-0440-1 · Cited by 206 · see citing works
Cutaneous adverse effects of targeted therapies
Macdonald, J. B., Macdonald, B., Golitz, L. E., LoRusso, P. M., & Sekulić, A. (2015) · Journal of the American Academy of Dermatology · doi:10.1016/j.jaad.2014.07.033 · Cited by 178 · see citing works
Schneider, M. R., Werner, S., Paus, R., & Wolf, E. (2008) · American Journal Of Pathology · doi:10.2353/ajpath.2008.070942 · Cited by 161 · see citing works
Faller, C., Bracher, M. G., Dami, N., & Roguet, R. (2002) · Toxicology in Vitro · doi:10.1016/s0887-2333(02)00053-x · Cited by 137 · see citing works
Management of toxicity to isoform α-specific PI3K inhibitors
Nunnery, S. E., & Mayer, I. A. (2019) · Annals of Oncology · doi:10.1093/annonc/mdz440 · Cited by 137 · see citing works
Ibragimov, B., Toesca, D. A. S., Chang, D. T., Yuan, Y., Koong, A. C., & Xing, L. (2018) · Medical Physics · doi:10.1002/mp.13122 · Cited by 125 · see citing works
Kanďárová, H., Liebsch, M., Spielmann, H., Genschow, E., Schmidt, E., Traue, D., Guest, R. L., Whittingham, A., Warren, N., Gamer, A. O., et al. (2006) · Toxicology in Vitro · doi:10.1016/j.tiv.2005.11.008 · Cited by 122 · see citing works
Minami, H., Kawada, K., Ebi, H., Kitagawa, K., Kim, Y., Araki, K., Mukai, H., Tahara, M., Nakajima, H., & Nakajima, K. (2008) · Cancer Science · doi:10.1111/j.1349-7006.2008.00837.x · Cited by 119 · see citing works
Shilling, A. D., Nedza, F. M., Emm, T., Diamond, S., McKeever, E., Punwani, N., Williams, W., Arvanitis, A., Galya, L. G., Li, M., et al. (2010) · Drug Metabolism and Disposition · doi:10.1124/dmd.110.033787 · Cited by 111 · see citing works
Cutaneous side effects of inhibitors of the RAS/RAF/MEK/ERK signalling pathway and their management
Manousaridis, I., Mavridou, S., Goerdt, S., Leverkus, M., & Utikal, J. S. (2012) · Journal of the European Academy of Dermatology and Venereology · doi:10.1111/j.1468-3083.2012.04546.x · Cited by 99 · see citing works
Pharmacokinetics and pharmacodynamics: Maximizing the clinical potential of Erlotinib (Tarceva)
Hidalgo, M. M., & Bloedow, D. C. (2003) · Seminars in Oncology · doi:10.1016/s0093-7754(03)70012-8 · Cited by 99 · see citing works
Schwartz, G. K., Robertson, S., Shen, A., Wang, E., Pace, L., Dials, H. J., Mendelson, D. S., Shannon, P., & Gordon, M. S. (2009) · Journal of Clinical Oncology · doi:10.1200/jco.2009.27.15_suppl.3513 · Cited by 95 · see citing works
Hilton, C. B., Milinovich, A., Felix, C., Vakharia, N., Crone, T., Donovan, C., Proctor, A. W., & Nazha, A. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0249-z · Cited by 93 · see citing works
Phase I study of palbociclib, a cyclin‐dependent kinase 4/6 inhibitor, in Japanese patients
Tamura, K., Mukai, H., Naito, Y., Yonemori, K., Kodaira, M., Tanabe, Y., Yamamoto, N., Osera, S., Sasaki, M., Mori, Y., et al. (2016) · Cancer Science · doi:10.1111/cas.12932 · Cited by 92 · see citing works
Lolkema, M. P., Bohets, H., Arkenau, H., Lampo, A., Barale-Thomas, E., de Jonge, M. J. A., van Doorn, L., Hellemans, P., Bono, J. S. D., & Eskens, F. A. L. M. (2015) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-14-3258 · Cited by 87 · see citing works
Tox_(R)CNN: Deep learning-based nuclei profiling tool for drug toxicity screening
Jiménez‐Carretero, D., Abrishami, V., Fernández-de-Manúel, L., Palacios, I., Quílez-Álvarez, A., Díez-Sánchez, A., del Pozo, M. Á., & Montoya, M. C. (2018) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1006238 · Cited by 84 · see citing works
Yamazaki, S., Skaptason, J., Romero, D., Vekich, S., Jones, H., Tan, W.-W., Wilner, K., & Koudriakova, T. (2011) · Drug Metabolism And Disposition · doi:10.1124/dmd.110.035857 · Cited by 69 · see citing works
Kanďárová, H., Liebsch, M., Gerner, I., Schmidt, E., Genschow, E., Traue, D., & Spielmann, H. (2005) · Alternatives to Laboratory Animals · doi:10.1177/026119290503300408 · Cited by 68 · see citing works
Hou, D., Di, Z., Qi, R., Wang, H., Zheng, S. G., Hong, Y., Guo, H., Chen, H., & Gao, X. (2017) · Skin Pharmacology and Physiology · doi:10.1159/000479528 · Cited by 67 · see citing works
EGFR regulation of epidermal barrier function
Tran, Q. T., Kennedy, L. H., Carrion, S. L., Bodreddigari, S., Goodwin, S. B., Sutter, T. R., & Sutter, T. R. (2012) · Physiological Genomics · doi:10.1152/physiolgenomics.00176.2011 · Cited by 66 · see citing works
Mitra, A. D., Raychaudhuri, S. P., Abria, C. J., Mitra, A., Wright, R., Ray, R., & Kundu‐Raychaudhuri, S. (2013) · Journal of Investigative Dermatology · doi:10.1038/jid.2013.3 · Cited by 52 · see citing works
Hardwick, R. N., Betts, C. J., Whritenour, J., Sura, R., Thamsen, M., Kaufman, E. H., & Fabre, K. (2020) · Lab on a Chip · doi:10.1039/c9lc00519f · Cited by 48 · see citing works
Hand-Foot and Stump Syndrome to Sorafenib
Lai, S. E., Kuzel, T., & Lacouture, M. E. (2007) · Journal of Clinical Oncology · doi:10.1200/jco.2006.08.9565 · Cited by 47 · see citing works
Danilenko, D. M., Phillips, G. D. L., & Diaz, D. (2016) · Toxicologic Pathology · doi:10.1177/0192623316632074 · Cited by 40 · see citing works
Self-citationCada, D. J., Demaris, K., Levien, T. L., & Baker, D. E. (2013) · Hospital Pharmacy · doi:10.1310/hpj4805-413 · Cited by 40 · see citing works
Maddah, M., Mandegar, M. A., Dame, K., Grafton, F., Loewke, K. E., & Ribeiro, A. J. S. (2020) · Journal of Pharmacological and Toxicological Methods · doi:10.1016/j.vascn.2020.106895 · Cited by 38 · see citing works
Dickson, M. A., Gordon, M. S., Edelman, G. M., Bendell, J. C., Kudchadkar, R. R., LoRusso, P. M., Johnston, S. H., Clary, D. O., & Schwartz, G. K. (2014) · Investigational New Drugs · doi:10.1007/s10637-014-0191-5 · Cited by 32 · see citing works
Cutaneous toxicities of BRAF inhibitors: Clinical and pathological challenges and call to action
Mandalà, M., Massi, D., & GIORGI, V. D. (2013) · Critical Reviews in Oncology/Hematology · doi:10.1016/j.critrevonc.2013.06.002 · Cited by 31 · see citing works
Tokarz, D. A., Steinbach, T., Lokhande, A., Srivastava, G., Ugalmugle, R., Co, C. A., Shockley, K. R., Singletary, E., Cesta, M. F., Thomas, H. C., et al. (2020) · Toxicologic Pathology · doi:10.1177/0192623320972614 · Cited by 27 · see citing works
Salphati, L., Pang, J., Plise, E. G., Chou, B., Halladay, J. S., Olivero, A. G., Rudewicz, P. J., Tian, Q., Wong, S., & Zhang, X. (2011) · Xenobiotica · doi:10.3109/00498254.2011.603386 · Cited by 24 · see citing works
Pharmacokinetic Study of Osimertinib in Cancer Patients with Mild or Moderate Hepatic Impairment
Grande, E., Harvey, R. D., You, B., Batlle, J. F., Galbraith, H., Sarantopoulos, J., Ramalingam, S. S., Mann, H., So, K., Johnson, M. G., et al. (2019) · Journal of Pharmacology and Experimental Therapeutics · doi:10.1124/jpet.118.255919 · Cited by 24 · see citing works
PathML: A unified framework for whole-slide image analysis with deep learningPreprint
Berman, A. G., Orchard, W. R., Gehrung, M., & Markowetz, F. M. (2021) · medRxiv · doi:10.1101/2021.07.07.21260138 · Cited by 24 · see citing works
Doma, E., Rupp, C., Varga, A., Kern, F., Riegler, B., & Baccarini, M. (2013) · Cancer Research · doi:10.1158/0008-5472.can-13-0748 · Cited by 21 · see citing works
Park, S. R., Ryu, M., Ryoo, B., Beck, M. Y., Lee, I. S., Choi, M., Lee, M. W., & Kang, Y. (2015) · Cancer Research and Treatment · doi:10.4143/crt.2015.017 · Cited by 20 · see citing works
Żuraw, A., Staup, M. A., Klopfleisch, R., Aeffner, F., Brown, D. L., Westerling, T., & Rudmann, D. G. (2020) · Toxicologic Pathology · doi:10.1177/0192623320980310 · Cited by 20 · see citing works
Turin, S. Y., Ledwon, J. K., Bae, H., Tepole, A. B., Topczewska, J. M., & Gosain, A. K. (2018) · Experimental Dermatology · doi:10.1111/exd.13534 · Cited by 18 · see citing works
Ovarian Toxicity Assessment in Histopathological Images Using Deep Learning
Hu, F., Schutt, L., Kozlowski, C., Regan, K. S., Dybdal, N. O., & Schutten, M. M. (2019) · Toxicologic Pathology · doi:10.1177/0192623319877871 · Cited by 18 · see citing works
Self-citationNoh, Y.-H., Lim, H.-S., Jung, J.-A., Song, T. H., & Bae, K.-S. (2015) · Cancer Chemotherapy and Pharmacology · doi:10.1007/s00280-014-2621-7 · Cited by 15 · see citing works
Deep Learning in Toxicologic Pathology: A New Approach to Evaluate Rodent Retinal Atrophy
Mudry, M. C. D. V., Martin, J. C., Schumacher, V. L., & Venugopal, R. (2020) · Toxicologic Pathology · doi:10.1177/0192623320980674 · Cited by 15 · see citing works
Quantitative neurotoxicology: Potential role of artificial intelligence/deep learning approach
Srivastava, A., & Hanig, J. P. (2020) · Journal of Applied Toxicology · doi:10.1002/jat.4098 · Cited by 13 · see citing works
Marinis, E. D., Ceccherelli, A., Quattrocchi, A., Leboffe, L., Polticelli, F., Nervi, C., & Ascenzi, P. (2019) · Scientific Reports · doi:10.1038/s41598-019-52852-9 · Cited by 10 · see citing works
Hu, F., Martin, H., Martinez, A. F., Everitt, J. I., Erkanli, A., Lee, W. T., Dewhirst, M. W., & Ramanujam, N. (2017) · Cancer Research · doi:10.1158/0008-5472.can-17-1058 · Cited by 9 · see citing works
Self-citationHu, F., Morhard, R., Murphy, H. A., Zhu, C., & Ramanujam, N. (2016) · Biomedical Optics Express · doi:10.1364/boe.7.003247 · Cited by 7 · see citing works
Self-citationDrug Monographs: Belinostat and Idelalisib
Piper, W. L., Waddell, J. A., & Solimando, D. A. (2014) · Hospital Pharmacy · doi:10.1310/hpj4911-1009 · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Artificial Intelligence for Drug Discovery: Are We There Yet?
Hasselgren, C., & Oprea, T. I. (2024) · Annual Review of Pharmacology and Toxicology · doi:10.1146/annurev-pharmtox-040323-040828 · Cited by 236 · see citing works
Machine Learning and Artificial Intelligence in Toxicological Sciences
Lin, Z., & Chou, W. (2022) · Toxicological Sciences · doi:10.1093/toxsci/kfac075 · Cited by 204 · see citing works
Artificial Intelligence in Cosmetic Dermatology: A Systematic Literature Review
Vatiwutipong, P., Vachmanus, S., Noraset, T., & Tuarob, S. (2023) · IEEE Access · doi:10.1109/access.2023.3295001 · Cited by 67 · see citing works
Artificial intelligence in cosmetic dermatology
Kania, B., Montecinos, K., & Goldberg, D. J. (2024) · Journal of Cosmetic Dermatology · doi:10.1111/jocd.16538 · Cited by 38 · see citing works
Complex in vitro models positioned for impact to drug testing in pharma: a review
Kang, S., Chen, E. C., Cifuentes, H., Co, J. Y., Cole, G., Graham, J. C., Hsia, I., Kiyota, T., Klein, J. A., Kroll, K. T., et al. (2024) · Biofabrication · doi:10.1088/1758-5090/ad6933 · Cited by 21 · see citing works
Self-citationFrontiers in Topical Photoprotection
Sullivan, M., Obezo, C. G., Lipsky, Z. W., Panchal, A., & Jensen, J. (2025) · Cosmetics · doi:10.3390/cosmetics12030096 · Cited by 20 · see citing works
In vitro 3D skin culture and its sustainability in toxicology: a narrative review
Masri, S., Fauzi, M. B., Rajab, N. F., Lee, W.-H., Zainal Abidin, D. A., & Siew, E. L. (2024) · Artificial Cells, Nanomedicine, and Biotechnology · doi:10.1080/21691401.2024.2407617 · Cited by 15 · see citing works
Zhao, H., Chen, Z., Kang, X., Yang, B., Luo, P., Li, H., & He, Q. (2023) · Toxicological Sciences · doi:10.1093/toxsci/kfad093 · Cited by 14 · see citing works
Liu, L., Zhang, Q., Guo, Y., Chen, E., Li, Z., Li, Y., Wang, B., & Ri, A. (2023) · Remote Sensing · doi:10.3390/rs15051235 · Cited by 10 · see citing works
Fujimura, T., Furugaki, K., Mizuta, H., Muraoka, S., Nishio, M., Adachi, J., Uchibori, K., Miyauchi, E., Hayashi, H., Katayama, R., et al. (2024) · npj Precision Oncology · doi:10.1038/s41698-024-00757-w · Cited by 8 · see citing works
Zhong, M., He, H., Wang, L., Pu, L., Liu, Z., Wang, J., Zhang, Y., Wang, S., Sun, B., Li, X., et al. (2024) · Colloids and Surfaces B Biointerfaces · doi:10.1016/j.colsurfb.2024.114378 · Cited by 3 · see citing works
Toxicokinetics and organ-specific toxicity
Dixit, P. V., Mishra, D. K., Rajpoot, K., Tekade, M., Achanta, N. S. K., Anup, N., & Tekade, R. K. (2023) · Elsevier eBooks · doi:10.1016/b978-0-443-15840-7.00016-6
MACHINE LEARNING APPLICATIONS IN TOXICOLOGY: CURRENT APPROACHES AND FUTURE PERSPECTIVES
Yaşar, S., Çetin, R., & Kızılkaya, M. B. (2026) · Ankara Universitesi Eczacilik Fakultesi Dergisi · doi:10.33483/jfpau.1655343
- Authors
- Hu, F., Santagostino, S. F., Danilenko, D. M., Tseng, M., Brumm, J., Zehnder, P., & Wu, K. C.
- Affiliations
- Genentech (US)
- Corresponding author
- Hu, Fangyao
- Wu, Kai Connie
- Venue
- The American Journal of Pathology
- Publisher
- Elsevier BV
- Published
- 2022-04
- Volume
- 192
- Issue
- 4
- Pages
- 687-700
- ISSN
- 0002-9440 (ISSN-L)
- OpenAlex
- W4205571820
- Cited by
- 13
- References
- 59
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 5 · 2023: 5 · 2022: 1
- FWCI
- 1.33
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- American Journal Of Pathology (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Biophysics › Cell Image Analysis Techniques
- Health Sciences › Medicine › Dermatology › Chemotherapy-related skin toxicity
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Keywords
- skin toxicity, reconstructed human epidermis, deep learning, image analysis, EGFR inhibitors, high-throughput drug screening
- MeSH terms
- Deep Learning, Algorithms, Epidermis, Humans, Image Processing, Computer-Assisted, Skin, Skin Diseases
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
