Araştırma Çıktıları

Permanent URI for this communityhttps://hdl.handle.net/11443/931

Browse

Author: search.filters.author.Tokat, FatmaSubject: search.filters.subject.Breast cancer

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    MITNET: a novel dataset and a two-stage deep learning approach for mitosis recognition in whole slide images of breast cancer tissue
    (SPRINGER LONDON LTD, 2022-01-01) Cayir, Sercan; Solmaz, Gizem; Kusetogullari, Huseyin; Tokat, Fatma; Bozaba, Engin; Karakaya, Sencer; Iheme, Leonardo Obinna; Tekin, Eren; Yazici, Cisem; Ozsoy, Gulsah; Ayalti, Samet; Kayhan, Cavit Kerem; Ince, Umit; Uzel, Burak; Kilic, Onur
    Mitosis assessment of breast cancer has a strong prognostic importance and is visually evaluated by pathologists. The inter, and intra-observer variability of this assessment is high. In this paper, a two-stage deep learning approach, named MITNET, has been applied to automatically detect nucleus and classify mitoses in whole slide images (WSI) of breast cancer. Moreover, this paper introduces two new datasets. The first dataset is used to detect the nucleus in the WSIs, which contains 139,124 annotated nuclei in 1749 patches extracted from 115 WSIs of breast cancer tissue, and the second dataset consists of 4908 mitotic cells and 4908 non-mitotic cells image samples extracted from 214 WSIs which is used for mitosis classification. The created datasets are used to train the MITNET network, which consists of two deep learning architectures, called MITNET-det and MITNET-rec, respectively, to isolate nuclei cells and identify the mitoses in WSIs. In MITNET-det architecture, to extract features from nucleus images and fuse them, CSPDarknet and Path Aggregation Network (PANet) are used, respectively, and then, a detection strategy using You Look Only Once (scaled-YOLOv4) is employed to detect nucleus at three different scales. In the classification part, the detected isolated nucleus images are passed through proposed MITNET-rec deep learning architecture, to identify the mitosis in the WSIs. Various deep learning classifiers and the proposed classifier are trained with a publicly available mitosis datasets (MIDOG and ATYPIA) and then, validated over our created dataset. The results verify that deep learning-based classifiers trained on MIDOG and ATYPIA have difficulties to recognize mitosis on our dataset which shows that the created mitosis dataset has unique features and characteristics. Besides this, the proposed classifier outperforms the state-of-the-art classifiers significantly and achieves a 68.7\% F1-score and 49.0\% F1-score on the MIDOG and the created mitosis datasets, respectively. Moreover, the experimental results reveal that the overall proposed MITNET framework detects the nucleus in WSIs with high detection rates and recognizes the mitotic cells in WSI with high F1-score which leads to the improvement of the accuracy of pathologists' decision.
  • Thumbnail Image
    Item
    Favorable locoregional control in clinically node-negative hormone-receptor positive breast cancer with low 21-gene recurrence scores: a single-institution study with 10-year follow-up
    (BMC, 2022-01-01) Uras, Cihan; Cabioglu, Neslihan; Tokat, Fatma; Er, Ozlem; Kara, Halil; Korkmaz, Taner; Bese, Nuran; Ince, Umit
    Background Recent studies have shown a lower likelihood of locoregional recurrences in patients with a low 21-gene recurrence score (RS). In this single-institution study, we investigated whether there are any associations between different cutoff values of 21-gene RS, histopathological factors, and outcome in patients with long-term follow-up. Methods The study included 61 patients who had early-stage (I-II) clinically node-negative hormone receptor-positive and HER2-negative breast cancer and were tested with the 21-gene RS assay between February 2010 and February 2013. Demographic, clinicopathological, treatment, and outcome characteristics were analyzed. Results The median age was 48 years (range, 29-72 years). Patients with high histologic grade (HG), Ki-67 >= 25\%, or Ki-67 >= 30\% were more likely to have intermediate/high RS (>= 18). Based on the 21-gene RS assay, only 19 patients (31\%) received adjuvant chemotherapy. At a median follow-up of 112 months, 3 patients developed locoregional recurrences (4.9\%), which were treated with endocrine therapy alone. Among patients treated with endocrine treatment alone (n = 42), the following clinicopathological characteristics were not found to be significantly associated with 10-year locoregional recurrence free survival (LRRFS): age < 40 years, age < 50 years, high histological or nuclear grade, high Ki-67-scores (>= 15\%, >= 20\%, >= 25\%, >= 30\%), presence of lymphovascular invasion, luminal-A type, multifocality, lymph node positivity, tumor size more than 2 cm, RS >= 18, and RS > 11. However, patients with RS >= 16 had significantly poorer 10-year LRRFS compared to those with RS < 16 (75\% vs. 100\%, respectively