Federated Learning Approach with Pre-Trained Deep Learning Models for COVID-19 Detection from Unsegmented CT images.

(1) Background: Coronavirus disease 2019 (COVID-19) is an infectious disease caused by SARS-CoV-2. Reverse transcription polymerase chain reaction (RT-PCR) remains the current gold standard for detecting SARS-CoV-2 infections in nasopharyngeal swabs. In Romania, the first reported patient to have contracted COVID-19 was officially declared on 26 February 2020. (2) Methods: This study proposes a federated learning approach with pre-trained deep learning models for COVID-19 detection. Three clients were locally deployed with their own dataset. The goal of the clients was to collaborate in order to obtain a global model without sharing samples from the dataset. The algorithm we developed was connected to our internal picture archiving and communication system and, after running backwards, it encountered chest CT changes suggestive for COVID-19 in a patient investigated in our medical imaging department on the 28 January 2020. (4) Conclusions: Based on our results, we recommend using an automated AI-assisted software in order to detect COVID-19 based on the lung imaging changes as an adjuvant diagnostic method to the current gold standard (RT-PCR) in order to greatly enhance the management of these patients and also limit the spread of the disease, not only to the general population but also to healthcare professionals.

Imaging Features of Rare Breast Lesions in Young Women.

Rare breast tumors, such as, pseudoangiomatous stromal hyperplasia, granulomatous mastitis, tubular adenoma, myofibroblastoma and xanthogranulomatous mastitis, sarcomas, neuroendocrine tumors can sometimes be misdiagnosed because of the similarities in their imagistic characteristics. The main objective of our report is to emphasize the importance of performing ultrasound-guided breast biopsies of suspect lesions in young patients. We performed an US-guided breast biopsy instead of an excisional biopsy because breast surgery has a huge psychological impact. We selected 3 atypical breast tumors in young women, with different clinical signs and symptoms, some of which similar to other breast lesions, but with rapid growth, which needed a different and multiple imaging approach.

Deep Learning: a Promising Method for Histological Class Prediction of Breast Tumors in Mammography.

The objective of the study was to determine if the pathology depicted on a mammogram is either benign or malignant (ductal or non-ductal carcinoma) using deep learning and artificial intelligence techniques. A total of 559 patients underwent breast ultrasound, mammography, and ultrasound-guided breast biopsy. Based on the histopathological results, the patients were divided into three categories: benign, ductal carcinomas, and non-ductal carcinomas. The mammograms in the cranio-caudal view underwent pre-processing and segmentation. Given the large variability of the areola, an algorithm was used to remove it and the adjacent skin. Therefore, patients with breast lesions close to the skin were removed. The remaining breast image was resized on the Y axis to a square image and then resized to 512 × 512 pixels. A variable square of 322,622 pixels was searched inside every image to identify the lesion. Each image was rotated with no information loss. For data augmentation, each image was rotated 360 times and a crop of 227 × 227 pixels was saved, resulting in a total of 201,240 images. The reason why our images were cropped at this size is because the deep learning algorithm transfer learning used from AlexNet network has an input image size of 227 × 227. The mean accuracy was 95.8344% ± 6.3720% and mean AUC 0.9910% ± 0.0366%, computed on 100 runs of the algorithm. Based on the results, the proposed solution can be used as a non-invasive and highly accurate computer-aided system based on deep learning that can classify breast lesions based on changes identified on mammograms in the cranio-caudal view.

Covid-19 Pandemic Impact on Breast Cancer Detection-The Major Effects Over an Early Diagnosis.

The COVID-19 pandemic has disrupted medical care systems, by decreasing patient addressability to outpatient care. The main objective of this study was to compare the patient's addressability to breast imaging techniques for diagnosis, and follow-up in the Clinical Emergency County Hospital of Craiova, Romania. We selected the mammographies performed over a period of 4 years (2018-2021) in our clinic. We divided the patients into four groups, one for each year (2018, 2019, 2020, 2021). Furtherly, we merged the data into two groups, one group for the pre-pandemic years (2018 and 2019) and one for the pandemic years (2020 and 2021). In our clinic, the number of mammographies plummeted to 0 during the month of April 2020 due to the lockdown and closure of non-urgent outpatient services in hospitals treating COVID-19 patients, and slowly creeped to 11 in the month of May and peaked to 160 in July (for the rest of the year). There was a huge difference regarding the patient's addressability to mammography immediately after the lockdown, with a 95.2% less addressability compared to the pre-pandemic period (May 2020 compared to May 2018). As an overall, by comparing both pre-pandemic years included in the study with the pandemic years, we obtained an addressability reduced with 37.3% suggesting the possible future delays in diagnosing breast tumors.