DiagSet: a dataset for prostate cancer histopathological image classification.

Cancer diseases constitute one of the most significant societal challenges. In this paper, we introduce a novel histopathological dataset for prostate cancer detection. The proposed dataset, consisting of over 2.6 million tissue patches extracted from 430 fully annotated scans, 4675 scans with assigned binary diagnoses, and 46 scans with diagnoses independently provided by a group of histopathologists can be found at https://github.com/michalkoziarski/DiagSet . Furthermore, we propose a machine learning framework for detection of cancerous tissue regions and prediction of scan-level diagnosis, utilizing thresholding to abstain from the decision in uncertain cases. The proposed approach, composed of ensembles of deep neural networks operating on the histopathological scans at different scales, achieves 94.6% accuracy in patch-level recognition and is compared in a scan-level diagnosis with 9 human histopathologists showing high statistical agreement.

The number of CD163 positive macrophages is associatedwith more advanced skin melanomas, microvessels density and patient prognosis.

The study was aimed to evaluate the number of TAMs and to investigate whether they have association with microvessels density and patients' survival times. 46 cases of melanomas, divided into four groups according to the Breslow scale, were tested immunohistochemically with antibodies anti-CD68, CD163, iNOS to vizualized macrophages and anti-CD34 antibody to stain microvessels. The number of macrophages and the microvessels density were counted by hotspot analysis using an image analysis system. The study revealed increased numbers of CD68 and CD163 positive macrophages in successive stages of Breslow scale, but statistically significant differences were observed only between I and IV group for CD68 positive macrophages, and between I and III, IV group for CD163 positive macrophages. The mean number of the microvessels was significantly increased in group II, III, IV compared to group I. The correlative study showed significant positive correlations between the mean number of CD68 and CD163 positive macrophages and microvessels density. Moreover, the number of CD163 positive macrophages was associated inversely with patient's survival time. The results of our study may indicate that higher infiltration of macrophages, especially CD163 positive cells, is associated with more advanced melanomas, microvessels density and worse patient's prognosis.

Retroperitoneal "ancient" Schwannoma - a rare case of rare location: case report and literature review.

Schwannomas are benign tumors derived from glial cells of peripheral nerve sheaths. They usually occur in association with Von Recklinghausen's disease and most commonly are observed on the head, neck, and upper extremities. Rare morphological variants may be misinterpreted as a malignancy under microscopic examination. The study presented a case of a sporadic "ancient" Schwannoma cell tumor located in the retroperitoneum. Literature data concerning diagnosis and treatment of the above-mentioned pathology was also reviewed.

[Rhabdomyosarcoma embryonale of the middle ear at 55-year-old women]. / Rhabdomyosarcoma embryonale ucha srodkowego u.55-letniej chorej.

The study presents extremely rare of the middle ear rhabdomyosarcoma embryonale at 55-year women. Authors showed untypical clinical process and own suspect of neoplasm illness. In difficult cases of the middle ear chronic granulomatosis, classical HE histological method maybe not enough and should be extended as an immunohistochemical examination.

Antigen levels of urokinase type plasminogen activator and its inhibitors in primary breast cancer.

Primary Breast Cancer, Urokinase-Type Plasminogen Activator, Inhibitors The aim of the study was to monitor urokinase plasminogen activator antigen concentrations and its type 1 (PAI-1) and type 2 (PAI-2) inhibitors in histologically defined forms of primary breast cancer and a comparison with these antigens levels in normal tissue. Another goal was a search for a relationship/or its lack/between the occurrence of the new generation markers of neoplastic disease and a presence/or absence/of lymph node metastases. U-PA, PAI-1 and PAI-2 antigen levels were determined by ELISA tests in protein extracts of breast cancer tissues. Among the studied breast tumors 32 specimens were ductal carcinomas, 15 specimens were lobular carcinomas and the remaining 13 were other rare histological forms. In comparison to the obtained values of u-PA antigen levels in normal tissue, the values in neoplastic tissues were elevated several times: 11-fold, 6-fold and 15-fold in ductal c., lobular c. and other rare neoplasms. The values of PAI-1 antigen levels were about 20-fold higher for all studied, histologically defined primary breast cancers. The greatest differences of PAI-2 antigen levels growth was observed in histologically defined primary breast cancer forms. It was augmented 10-fold, 40-fold and 20-fold, respectively, for ductal carcinoma, lobular carcinoma and rare forms of neoplasms. In various forms of invasive breast cancer and those without lymph node metastases the content of u-PA, PAI-1 and PAI-2 were also significantly elevated. Among the new generation of independent markers of the neoplastic process, PAI-2 seems to be the most reliable marker for the identification of primary breast cancer. The goal of the present study was to evaluate a possible combined prognostic value of the three major components of the u-PA system (u-PA, PAI-1 and PAI-2) in patients with defined histopathological forms of primary breast cancer.