Stromal tissue as an adjunct tool in the diagnosis of follicular thyroid lesions by fine-needle aspiration biopsy

Machine learning-based image analysis for accelerating the diagnosis of complicated preneoplastic and neoplastic ductal lesions in breast biopsy tissues

PURPOSE

Diagnosis of breast preneoplastic and neoplastic lesions is difficult due to their similar morphology in breast biopsy specimens. To diagnose these lesions, pathologists perform immunohistochemical analysis and consult with expert breast pathologists. These additional examinations are time-consuming and expensive. Artificial intelligence (AI)-based image analysis has recently improved, and may help in ordinal pathological diagnosis. Here, we showed the significance of machine learning-based image analysis of breast preneoplastic and neoplastic lesions for facilitating high-throughput diagnosis.

METHODS

Images were obtained from normal mammary glands, hyperplastic lesions, preneoplastic lesions and neoplastic lesions, such as usual ductal hyperplasia (UDH), columnar cell lesion (CCL), ductal carcinoma in situ (DCIS), and DCIS with comedo necrosis (comedo DCIS) in breast biopsy specimens. The original enhanced convoluted neural network (CNN) system was used for analyzing the pathological images.

RESULTS

The AI-based image analysis provided the following area under the curve values (AUC): normal lesion versus DCIS, 0.9902; DCIS versus comedo DCIS, 0.9942; normal lesion versus CCL, 0.9786; and UDH versus DCIS, 1.000. Multiple comparison analysis showed precision and recall scores similar to those of single comparison analysis. Based on the gradient-weighted class activation mapping (Grad-CAM) used to visualize the important regions reflecting the result of CNN analysis, the ratio of stromal tissue in the whole weighted area was significantly higher in UDH and CCL than that in DCIS.

CONCLUSIONS

These analyses may provide a more accurate and rapid pathological diagnosis of patients. Moreover, Grad-CAM identifies uncharted important histological characteristics for newer pathological findings and targets of research for understanding diseases.

RET-mediated modulation of tumor microenvironment and immune response in multiple endocrine neoplasia type 2 (MEN2)

Medullary thyroid carcinomas (MTC) arise from thyroid parafollicular, calcitonin-producing C-cells and can occur either as sporadic or as hereditary diseases in the context of familial syndromes, including multiple endocrine neoplasia 2A (MEN2A), multiple endocrine neoplasia 2B (MEN2B) and familial MTC (FMTC). In a large fraction of sporadic cases, and virtually in all inherited cases of MTC, activating point mutations of the RET proto-oncogene are found. RET encodes for a receptor tyrosine kinase protein endowed with transforming potential on thyroid parafollicular cells. As in other cancer types, microenvironmental factors play a critical role in MTC. Tumor-associated extracellular matrix, stromal cells and immune cells interact and influence the behavior of cancer cells both in a tumor-promoting and in a tumor-suppressing manner. Several studies have shown that, besides the neoplastic transformation of thyroid C-cells, a profound modification of tumor microenvironment has been associated to the RET FMTC/MEN2-associated oncoproteins. They influence the surrounding stroma, activating cancer-associated fibroblasts (CAFs), promoting cancer-associated inflammation and suppressing anti-cancer immune response. These mechanisms might be exploited to develop innovative anti-cancer therapies and novel prognostic tools in the context of familial, RET-associated MTC.