Tubule-U-Net: a novel dataset and deep learning-based tubule segmentation framework in whole slide images of breast cancer.

The tubule index is a vital prognostic measure in breast cancer tumor grading and is visually evaluated by pathologists. In this paper, a computer-aided patch-based deep learning tubule segmentation framework, named Tubule-U-Net, is developed and proposed to segment tubules in Whole Slide Images (WSI) of breast cancer. Moreover, this paper presents a new tubule segmentation dataset consisting of 30820 polygonal annotated tubules in 8225 patches. The Tubule-U-Net framework first uses a patch enhancement technique such as reflection or mirror padding and then employs an asymmetric encoder-decoder semantic segmentation model. The encoder is developed in the model by various deep learning architectures such as EfficientNetB3, ResNet34, and DenseNet161, whereas the decoder is similar to U-Net. Thus, three different models are obtained, which are EfficientNetB3-U-Net, ResNet34-U-Net, and DenseNet161-U-Net. The proposed framework with three different models, U-Net, U-Net++, and Trans-U-Net segmentation methods are trained on the created dataset and tested on five different WSIs. The experimental results demonstrate that the proposed framework with the EfficientNetB3 model trained on patches obtained using the reflection padding and tested on patches with overlapping provides the best segmentation results on the test data and achieves 95.33%, 93.74%, and 90.02%, dice, recall, and specificity scores, respectively.

Managing Bronchiectasis: 13 Years of Experience from Sputum to Lung Transplantation.

OBJECTIVES: Bronchiectasis and especially related mortality has gained growing interest in recent years. The aim of our retrospective study was to determine the factors which may influence and indicate mortality in our bronchiectasis patients throughout 13 years. MATERIAL AND METHODS: Patients with ICD-10 code J47 depicting bronchiectasis between 1.1.2003 to 31.12.2015 were evaluated using database of our hospital.694 out of 1470 patients who had high-resolution computed tomography (HRCT) scan confirming the presence of bronchiectatic lesions were included. RESULTS: Female/male ratio was 1.09. Mean age of the patients was 45.9±15.7 years. Sputum culture results were available in 365 (52.6%)of the patients. Pseudomonas aeruginosa was the leading pathogen, which was found in 68 (20.7%) patients. 28 (4%) patients have died during the 13 year period, and the overall survival was 125,3 months. In general 5 (4.4%) out of 112 patients who underwent surgery were lost, 3 of them belonging to the transplantation group. 3 out of 9 patients (33%) who underwent lung transplantation were lost within 3 years. There was no statistically significant difference in survival between patients who underwent surgery or not (p>0.05).In univariate Cox regression mortality analysis age, FEV1, P. aeruginosa, E.coli, hospitalisation and ICU admission had p value <0.01. When these factors were evaluated in the multivariate analysis, only P.aeruginosa reached statistical significance in predicting mortality. CONCLUSION: Isolation of P.aeruginosa in a patient with bronchiectasis should be taken seriously. It can be suggested that eradication treatment according to guidelines will help reduce mortality of bronchiectasis worldwide. Surgery is still an option of treatment in severe bronchiectasis and lung transplantation may be a life-saving way of managing end-stage disease.

The role of preoperative radiotherapy in nonmetastatic high-grade osteosarcoma of the extremities for limb-sparing surgery.

PURPOSE: To assess the role of preoperative radiotherapy in patients with nonmetastatic high-grade osteosarcoma of the extremities for limb-sparing surgery and to compare the response of neoadjuvant therapies, local control, and survival with the literature results. METHODS AND MATERIALS: Forty-six patients with osteosarcoma of the limbs who were treated within a limb salvage protocol including preoperative radiotherapy and chemotherapy between 1987 and 2002, were retrospectively analyzed. Median age was 17 years (range, 14-66 years). Treatment was started with neoadjuvant chemotherapy. Cisplatin, epidoxorubicin, ifosfamide, and methotrexate were used in different combinations. Preoperative radiotherapy was applied, usually between the second and third cycle of chemotherapy. Radiotherapy was given (35 Gy in 10 fractions) to 44 patients. Two patients were treated with 46 Gy at 2 Gy/day. Definitive surgery was administered after the third course of chemotherapy. Chemotherapy was complete 6 courses postsurgery. RESULTS: Median follow-up time was 44 months (range, 2-154 months). Forty-four patients had limb-sparing surgery, whereas 2 had amputation. Tumor necrosis rate was >/=90% in 87% of the patients (Huvos Grade 3-4). Two patients had local failures, and 26 patients (56.5%) had distant metastases. The 5-year local control and overall survival rates were 97.5% and 48.4%, respectively. On univariate analysis, age

Intrathoracic extravasation of antineoplastic agents: case report and systematic review.

A case history is presented of a 34-year-old woman who was treated postoperatively for breast cancer with combination chemotherapy including epirubicin. The catheter of the port penetrated the wall of the superior vena cava, and extravasation in the mediastinum occurred. Severe pain, fever, and bilateral pleural effusion developed that necessitated two drainage procedures. She recovered well without sequelae. A comprehensive search of the medical literature was conducted using MEDLINE including bibliographies of all selected articles. Six additional cases of intrathoracic cytostatic agent extravasation were identified and the etiologic factors, clinical course, treatment strategy, and outcome were reviewed for each case.