Deep learning as a new tool in the diagnosis of mycosis fungoides.

Mycosis Fungoides (MF) makes up the most of the cutaneous lymphomas. As a malignant disease, the greatest diagnostical challenge is to timely differentiate MF from inflammatory diseases. Contemporary computational methods successfully identify cell nuclei in histological specimens. Deep learning methods are especially favored for such tasks. A deep learning model was used to detect nuclei Hematoxylin-Eosin(H-E) stained micrographs. Nuclear properties are extracted after detection. A multi-layer perceptron classifier is used to detect lymphocytes specifically among the detected nuclei. The comparisons for each property between MF and non-MF were carried out using statistical tests the results are compared with the findings in the literature to provide a descriptive analysis as well. Random forest classifier method is used to build a model to classify MF and non-MF lymphocytes. 10 nuclear properties were statistically significantly different between MF and non-MF specimens. MF nuclei were smaller, darker and more heterogenous. Lymphocyte detection algorithm had an average 90.5% prediction power and MF detection algorithm had an average 94.2% prediction power. This project aims to fill the gap between computational advancement and medical practice. The models could make MF diagnoses easier, more accurate and earlier. The results also challenge the manually examined and defined nuclear properties of MF with the help of data abundance and computer objectivity.

The role of COL6A1and PD-1 expressions in renal cell carcinoma.

OBJECTIVE: The COL6A1 is a gene encoding the alpha 1 polypeptide subunit of collagen 6 (COL6A1), an extracellular matrix protein subunit. Programmed cell death receptor-1 (PD-1) and its ligand, programmed cell death receptor ligand-1 (PD-L1) have been shown to have a prognostic significance in clear cell renal cell carcinomas (RCCs). In this study, we evaluated the expressions of COL6A1 and PD-1 in four different RCC subtypes. MATERIALS AND METHODS: A total of 161 radical nephrectomy and nephron-sparing surgery cases with RCCs from five different health care centers were included in this study. Clinical data of the cases were taken from electronic records of the institutions. The pathological data were collected by an expert uropathologist and re-evaluated with slides obtained from paraffin blocks of the cases. The correlation of COL6A1 and PD-1 expression with sex, age, tumor type, lymphovascular invasion (LVI), World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade, and tumor stage (pT) was analyzed with the Pearson chi-squared test. RESULTS: Patients with sarcomatoid RCC and clear cell RCC had significantly higher COL6A1 scores and intensities than in other types of RCC (p=0.004 and p=0.002, respectively). WHO/ISUP grade and, COL6A1 and PD-1 staining scores also showed positive correlation (r=0.230, p=0.004 and r=0.277, p=0.001, respectively for COL6A1 and r=0.191, p=0.018 and r=0.166, p=0.041, respectively for PD-1). The staining scores and intensities of COL6A1 and PD-1 were not different between the patients with positive and negative LVI (p>0.05). CONCLUSION: In high-grade RCCs, we found the relationship between immunohistochemical staining scores of COL6A1 and PD-1 proteins and clinical, demographic, and histopathological parameters. Our results proved that COL6A1 and PD-1 are really promising proteins as prognostic parameters and for targeted immunotherapy.