Image analysis of peripheral compression artefacts of ThinPrep(®) liquid-based cytology preparations

Cytomorphological comparison of ThinPrep and SurePath liquid-based cytology in thyroid fine-needle aspiration

BACKGROUND

The two widely established systems for liquid-based cytology (LBC), ThinPrep and SurePath, employ different principles. The aim of this study was to compare the cytomorphology of thyroid lesions prepared by the two techniques.

METHODS

We retrospectively reviewed 44 thyroid FNA specimens prepared by LBC, including 20 ThinPrep and 22 SurePath. Cytologic diagnoses were made according to the Bethesda system and cytomorphologic parameters were evaluated.

RESULTS

Acellular smears were significantly frequent in ThinPrep than SurePath (10% vs. 0%). Both techniques produced a clean background, well cell preservation, and not apparent cell shrinkage. ThinPrep showed significantly lower cellularity than SurePath (25% vs. 4.3%). ThinPrep produced considerable flattening and fragmented clusters, while SurePath contained larger clusters in a three-dimensional configuration. Colloid was significantly reduced in amount and fragmented in ThinPrep, and was easily observed in SurePath. In cases of Hashimoto's thyroiditis, ThinPrep produced much less leukocytes in background than SurePath. Aggregates of fibrin and leukocytes were frequently present in 10/16 cases (62.5%) processed by ThinPrep. Air-dry artifact at periphery of the ring was present in 6/16 cases (37.5%) processed by ThinPrep. The nuclear features of papillary carcinoma were similarly evident in both LBC preparations.

CONCLUSION

SurePath seems to be superior to ThinPrep for diagnosing benign entities based on adequate representation of colloid and lymphocytes. The cell quality of both techniques in thyroid FNA was comparable, while each method introduces its own unique cytologic artifacts related to its methodology. We should recognize the cytomorphologic alterations to avoid misinterpretations.

Annotation-Free Deep Learning-Based Prediction of Thyroid Molecular Cancer Biomarker BRAF (V600E) from Cytological Slides

Thyroid cancer is the most common endocrine cancer. Papillary thyroid cancer (PTC) is the most prevalent form of malignancy among all thyroid cancers arising from follicular cells. Fine needle aspiration cytology (FNAC) is a non-invasive method regarded as the most cost-effective and accurate diagnostic method of choice in diagnosing PTC. Identification of BRAF (V600E) mutation in thyroid neoplasia may be beneficial because it is specific for malignancy, implies a worse prognosis, and is the target for selective BRAF inhibitors. To the authors' best knowledge, this is the first automated precision oncology framework effectively predict BRAF (V600E) immunostaining result in thyroidectomy specimen directly from Papanicolaou-stained thyroid fine-needle aspiration cytology and ThinPrep cytological slides, which is helpful for novel targeted therapies and prognosis prediction. The proposed deep learning (DL) framework is evaluated on a dataset of 118 whole slide images. The results show that the proposed DL-based technique achieves an accuracy of 87%, a precision of 94%, a sensitivity of 91%, a specificity of 71% and a mean of sensitivity and specificity at 81% and outperformed three state-of-the-art deep learning approaches. This study demonstrates the feasibility of DL-based prediction of critical molecular features in cytological slides, which not only aid in accurate diagnosis but also provide useful information in guiding clinical decision-making in patients with thyroid cancer. With the accumulation of data and the continuous advancement of technology, the performance of DL systems is expected to be improved in the near future. Therefore, we expect that DL can provide a cost-effective and time-effective alternative tool for patients in the era of precision oncology.

A diagnostic head and neck fine needle aspiration service can be provided using liquid-based cytology only

OBJECTIVE

Liquid-based cytology (LBC) has been used for non-gynaecological specimens since its introduction into routine use in cervical cytology in the mid-1990s. There are still relatively few large studies comparing performance in reporting the head and neck fine-needle aspirations (H&N FNA) processed by LBC only to conventional direct smears (CDS).

METHODS

This study compared 686 H&N FNAs processed by LBC only with 3719 CDS. All were taken under ultrasound (US) guidance by a small cohort of three consultant radiologists and reported by the author.

RESULTS

The (smaller) LBC sample was statistically representative of the larger CDS population at an alpha level of 0.05. There was no difference between CDS and LBC at a 95% confidence interval (CI) when comparing specificity and sensitivity (specificity: 94.8-96.5% versus 90.2-95.4%; sensitivity: 91.4-94.1% versus 86.8-93.4%). The inadequate rate between the two techniques was similar, 0.5-1.0% for CDS versus 0.7-2.5% for LBC. The significance difference was in the suspicious rate which was greater at 2.8-5.8% for LBC versus 1.7-2.6% for CDS. Consequently, there was a slight but non-significant difference between the two populations with respect to the overall accuracy: 93.5-95.1% for CDS versus 89.4-93.7% for LBC.

CONCLUSIONS

While there are morphological differences between LBC and CDS in H&N FNAs, once a degree of familiarity is achieved, the two techniques have equivalent sensitivity, specificity and inadequate rates.