Detection of malignant mesothelioma using nuclear structure of mesothelial cells in effusion cytology specimens

Our plain-English summary of Detection of malignant mesothelioma using nuclear structure of mesothelial cells in effusion cytology specimens, by A.B. Tosun, O. Yergiyev, S. Kolouri, et al (Cytometry. Part a, 2015).

The study

• Authors: A.B. Tosun, O. Yergiyev, S. Kolouri, J.F. Silverman, G.K. Rohde
• Journal: Cytometry. Part a
• Published: 2015;87(4):326-33
• Cited by: 26 articles, as counted by NIH iCite
• Read it: PubMed · Publisher · Free full text

Abstract

Mesothelioma is a form of cancer generally caused from previous exposure to asbestos. Although it was considered a rare neoplasm in the past, its incidence is increasing worldwide due to extensive use of asbestos. In the current practice of medicine, the gold standard for diagnosing mesothelioma is through a pleural biopsy with subsequent histologic examination of the tissue. The diagnostic tissue should demonstrate the invasion by the tumor and is obtained through thoracoscopy or open thoracotomy, both being highly invasive surgical operations. On the other hand, thoracocentesis, which is removal of effusion fluid from the pleural space, is a far less invasive procedure that can provide material for cytological examination. In this study, we aim at detecting and classifying malignant mesothelioma based on the nuclear chromatin distribution from digital images of mesothelial cells in effusion cytology specimens. Accordingly, a computerized method is developed to determine whether a set of nuclei belonging to a patient is benign or malignant. The quantification of chromatin distribution is performed by using the optimal transport-based linear embedding for segmented nuclei in combination with the modified Fisher discriminant analysis. Classification is then performed through a k-nearest neighborhood approach and a basic voting strategy. Our experiments on 34 different human cases result in 100% accurate predictions computed with blind cross validation. Experimental comparisons also show that the new method can significantly outperform standard numerical feature-type methods in terms of agreement with the clinical diagnosis gold standard. According to our results, we conclude that nuclear structure of mesothelial cells alone may contain enough information to separate malignant mesothelioma from benign mesothelial proliferations.

© 2015 International Society for Advancement of Cytometry.

In plain English

This study developed and tested a computer method for telling malignant mesothelioma from benign conditions using microscope images of cells in pleural effusion fluid. This fluid is collected less invasively than a biopsy. The authors used archived slides from 34 patients: 16 with malignant mesothelioma and 18 with benign pleural effusions. Each patient's diagnosis had been checked by pleural biopsy. They outlined 1,080 nuclei, and the computer analysed how chromatin (material inside the nucleus) was spread in each. Single nuclei were classified correctly 73.3% of the time; each patient was then classified by a majority vote of their nuclei. Leaving each patient out of training in turn, the method classified all 34 patients correctly. A standard feature-based computer method misclassified seven patients (79% accuracy). On average, malignant cells had more chromatin toward the centre of the nucleus. The authors concluded that the approach can reliably tell malignant from benign sets of mesothelial cells using effusion cytology alone, and that, if successful, it could eliminate or reduce the need for tissue biopsy. They planned to expand the dataset. The study did not examine asbestos exposure.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Development and testing of a computerized diagnostic method on archived cytology slides, evaluated with leave-one-patient-out cross validation against biopsy diagnosis
• Who was studied: 34 patients (16 with malignant mesothelioma, 18 with benign pleural effusions) from the pathology archives of Allegheny General Hospital and the West Penn Hospital. All had pleural effusion cytology and a concurrent or subsequent pleural biopsy, which was used as the gold standard. 1,080 nuclei were analysed (590 from benign cases, 490 from malignant cases).
• Exposure: Not studied: the article analysed cell images and did not report the patients' asbestos exposure
• Main results:
  • The transport-based (LOT) method correctly classified all 34 patients (all 18 benign and all 16 malignant), 100% accuracy
  • The standard numerical feature-based comparison method misclassified 7 of 34 patients (2 of 18 benign called malignant, 5 of 16 malignant called benign), 79% accuracy
  • For individual nuclei (rather than whole patients), accuracy was 73.3% with the LOT method and 59.8% with the feature-based method
  • On the most discriminating direction, nuclei from benign and malignant patients differed with a P-value of 0.0004 (test data only). Malignant cells tended to have chromatin toward the centre of the nucleus, benign cells toward the border.
  • According to the authors' pathologist reports, the five malignant patients misclassified by the feature-based method had also been misdiagnosed by cytopathologists looking at effusion cytology alone, and were malignant on biopsy
• The authors' conclusion: The authors concluded that the transport-based morphometry approach can reliably distinguish malignant from benign sets of mesothelial cells from effusion cytology specimens alone. They also wrote that, if successful, the technique has the potential to eliminate or reduce the need for tissue biopsy.
• Limitations the authors state:
  • The dataset needs to be expanded to better assess the method's robustness and reliability
  • Selection of mesothelial cells and the start of nuclear segmentation were guided by a pathologist rather than automated
  • The method was not tested on distinguishing mesothelioma from adenocarcinoma involving the pleura; the authors plan this for future work

Topics

The National Library of Medicine indexes this study under subjects our site covers: Lung cancer, Mesothelioma.

Medical terms in this study, explained in our Lexicon: Malignant Mesothelioma, Mesothelial Cells, Cytology, Mesothelioma, Neoplasm, Pleural Biopsy, Thoracoscopy, Thoracotomy.

Related studies

• Comparison of antibodies to HBME-1 and calretinin for the detection of mesothelial cells in effusion cytology — P.A. Fetsch, A. Simsir, et al. (2001)
• Diagnostic usefulness of EMA, IMP3, and GLUT-1 for the immunocytochemical distinction of malignant cells from reactive mesothelial cells in effusion cytology using cytospin preparations — K. Ikeda, G. Tate, et al. (2011)
• Investigating unilateral pleural effusions: the role of cytology — D.T. Arnold, D. De Fonseka, et al. (2018)
• Ancillary studies in pleural, pericardial, and peritoneal effusion cytology — K.E. Sundling, E.S. Cibas (2018)
• Categorical systems for reporting of cytology specimens: Following the footsteps of Bethesda-like reporting systems — L.J. Layfield, Z. Baloch (2020)
• Utility of BAP1 Immunohistochemistry and p16 (CDKN2A) FISH in the Diagnosis of Malignant Mesothelioma in Effusion Cytology Specimens — H.C. Hwang, B.S. Sheffield, et al. (2016)

Browse return to medical research.