TY - JOUR
T1 - NSCLC Subtyping in Conventional Cytology
T2 - Results of the International Association for the Study of Lung Cancer Cytology Working Group Survey to Determine Specific Cytomorphologic Criteria for Adenocarcinoma and Squamous Cell Carcinoma
AU - IASLC Pathology Committee
AU - Jain, Deepali
AU - Nambirajan, Aruna
AU - Chen, Gang
AU - Geisinger, Kim
AU - Hiroshima, Kenzo
AU - Layfield, Lester
AU - Minami, Yuko
AU - Moreira, Andre L.
AU - Motoi, Noriko
AU - Papotti, Mauro
AU - Rekhtman, Natasha
AU - Russell, Prudence A.
AU - Prince, Spasenija Savic
AU - Schmitt, Fernando
AU - Yatabe, Yasushi
AU - Eppenberger-Castori, Serenella
AU - Bubendorf, Lukas
AU - Beasley, Mary Beth
AU - Berezowska, Sabina
AU - Borczuk, Alain
AU - Brambilla, Elizabeth
AU - Chou, Teh Ying
AU - Chung, Jin Haeng
AU - Cooper, Wendy
AU - Dacic, Sanja
AU - Chan, Yuchen
AU - Hirsch, Fred R.
AU - Hwang, David
AU - Joubert, Philippe
AU - Kerr, Keith
AU - Lantuejoul, Sylvie
AU - Lin, Dongmei
AU - Lopez-Rios, Fernando
AU - Matsubara, Daisuke
AU - Mino-Kenudson, Mari
AU - Nicholson, Andrew
AU - Poleri, Claudia
AU - Roden, Anja
AU - Schalper, Kurt
AU - Sholl, Lynette
AU - Thunnissen, Erik
AU - Travis, William D.
AU - Tsao, Ming
AU - Wistuba, Ignacio
N1 - Publisher Copyright:
© 2022 International Association for the Study of Lung Cancer
PY - 2022/6
Y1 - 2022/6
N2 - Introduction: Accurate subtyping of NSCLC into lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) is the cornerstone of NSCLC diagnosis. Cytology samples reveal higher rates of classification failures, that is, subtyping as non–small cell carcinoma—not otherwise specified (NSCC-NOS), as compared with histology specimens. This study aims to identify specific algorithms on the basis of known cytomorphologic features that aid accurate and successful subtyping of NSCLC on cytology. Methods: A total of 13 expert cytopathologists participated anonymously in an online survey to subtype 119 NSCLC cytology cases (gold standard diagnoses being LUAD in 80 and LUSC in 39) enriched for nonkeratinizing LUSC. They selected from 23 predefined cytomorphologic features that they used in subtyping. Data were analyzed using machine learning algorithms on the basis of random forest method and regression trees. Results: From 1474 responses recorded, concordant cytology typing was achieved in 53.7% (792 of 1474) responses. NSCC-NOS rates on cytology were similar among gold standard LUAD (36%) and LUSC (38%) cases. Misclassification rates were higher in gold standard LUSC (17.6%) than gold standard LUAD (5.5%; p < 0.0001). Keratinization, when present, recognized LUSC with high accuracy. In its absence, the machine learning algorithms developed on the basis of experts’ choices were unable to reduce cytology NSCC-NOS rates without increasing misclassification rates. Conclusions: Suboptimal recognition of LUSC in the absence of keratinization remains the major hurdle in improving cytology subtyping accuracy with such cases either failing classification (NSCC-NOS) or misclassifying as LUAD. NSCC-NOS seems to be an inevitable morphologic diagnosis emphasizing that ancillary immunochemistry is necessary to achieve accurate subtyping on cytology.
AB - Introduction: Accurate subtyping of NSCLC into lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) is the cornerstone of NSCLC diagnosis. Cytology samples reveal higher rates of classification failures, that is, subtyping as non–small cell carcinoma—not otherwise specified (NSCC-NOS), as compared with histology specimens. This study aims to identify specific algorithms on the basis of known cytomorphologic features that aid accurate and successful subtyping of NSCLC on cytology. Methods: A total of 13 expert cytopathologists participated anonymously in an online survey to subtype 119 NSCLC cytology cases (gold standard diagnoses being LUAD in 80 and LUSC in 39) enriched for nonkeratinizing LUSC. They selected from 23 predefined cytomorphologic features that they used in subtyping. Data were analyzed using machine learning algorithms on the basis of random forest method and regression trees. Results: From 1474 responses recorded, concordant cytology typing was achieved in 53.7% (792 of 1474) responses. NSCC-NOS rates on cytology were similar among gold standard LUAD (36%) and LUSC (38%) cases. Misclassification rates were higher in gold standard LUSC (17.6%) than gold standard LUAD (5.5%; p < 0.0001). Keratinization, when present, recognized LUSC with high accuracy. In its absence, the machine learning algorithms developed on the basis of experts’ choices were unable to reduce cytology NSCC-NOS rates without increasing misclassification rates. Conclusions: Suboptimal recognition of LUSC in the absence of keratinization remains the major hurdle in improving cytology subtyping accuracy with such cases either failing classification (NSCC-NOS) or misclassifying as LUAD. NSCC-NOS seems to be an inevitable morphologic diagnosis emphasizing that ancillary immunochemistry is necessary to achieve accurate subtyping on cytology.
KW - Cytology
KW - IASLC
KW - Machine learning
KW - Non–small cell lung carcinoma
KW - Regression tree
KW - Subtyping
UR - http://www.scopus.com/inward/record.url?scp=85131108275&partnerID=8YFLogxK
U2 - 10.1016/j.jtho.2022.02.013
DO - 10.1016/j.jtho.2022.02.013
M3 - Article
C2 - 35331963
AN - SCOPUS:85131108275
SN - 1556-0864
VL - 17
SP - 793
EP - 805
JO - Journal of Thoracic Oncology
JF - Journal of Thoracic Oncology
IS - 6
ER -