Machine learning algorithm improved automated droplet classification of ddPCR for detection of BRAF V600E in paraffin-embedded samples.

Somatic mutations in cancer driver genes can help diagnosis, prognosis and treatment decisions. Formalin-fixed paraffin-embedded (FFPE) specimen is the main source of DNA for somatic mutation detection. To overcome constraints of DNA isolated from FFPE, we compared pyrosequencing and ddPCR analysis for absolute quantification of BRAF V600E mutation in the DNA extracted from FFPE specimens and compared the results to the qualitative detection information obtained by Sanger Sequencing. Sanger sequencing was able to detect BRAF V600E mutation only when it was present in more than 15% total alleles. Although the sensitivity of ddPCR is higher than that observed for Sanger, it was less consistent than pyrosequencing, likely due to droplet classification bias of FFPE-derived DNA. To address the droplet allocation bias in ddPCR analysis, we have compared different algorithms for automated droplet classification and next correlated these findings with those obtained from pyrosequencing. By examining the addition of non-classifiable droplets (rain) in ddPCR, it was possible to obtain better qualitative classification of droplets and better quantitative classification compared to no rain droplets, when considering pyrosequencing results. Notable, only the Machine learning k-NN algorithm was able to automatically classify the samples, surpassing manual classification based on no-template controls, which shows promise in clinical practice.

Revised criteria for diagnosis of NIFTP reveals a better correlation with tumor biological behavior.

The recent reclassification of a follicular variant of papillary thyroid carcinoma (FVPTC), subset as noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP), aims to avoid overtreatment of patients with an indolent lesion. The diagnosis of NIFTP has recently been revisited using more rigid criteria. This study presents histological and molecular findings and a long clinical follow-up of 94 FVPTC, 40 cases of follicular adenoma (FTA) and 22 cases of follicular carcinoma (FTC) that were classified before the advent of the NIFTP reclassification. All slides were reviewed using these rigid criteria and analysis of numerous sections of paraffin blocks and reclassified as 7 NIFTPs, 2 EFVPTCs, 29 infiltrative FVPTC (IFVPTCs), 57 invasive EFVPTC (I-EFVPTCs), 39 FTAs and 22 FTCs. Remarkably, EFVPTC and NIFTP patients were all free of disease at the end of follow-up and showed no BRAF mutation. Only one NIFTP sample harbored mutations, an NRAS Q61R. PAX8/PPARG fusion was found in I-EFVPTCs and FTC. Although additional studies are needed to identify a specific molecular profile to aid in the diagnosis of lesions with borderline morphological characteristics, we confirmed that the BRAF V600E mutation is an important tool to exclude the diagnosis of NIFTP. We also show that rigorous histopathological criteria should be strongly followed to avoid missing lesions in which more aggressive behavior is present, mainly via the analysis of capsule or vascular invasion and the presence of papillary structures.