A5022671908- Ultrasound Imaging and Elastography
- AI in cancer detection
- Breast Lesions and Carcinomas
- Thyroid Cancer Diagnosis and Treatment
- Breast Cancer Treatment Studies
- Ultrasound and Hyperthermia Applications
- Radiomics and Machine Learning in Medical Imaging
- Thyroid and Parathyroid Surgery
- Photoacoustic and Ultrasonic Imaging
- Ultrasonics and Acoustic Wave Propagation
- MRI in cancer diagnosis
- Head and Neck Anomalies
- Gene expression and cancer classification
- Cancer and Skin Lesions
- Medical Imaging and Pathology Studies
- Infrared Thermography in Medicine
- Parathyroid Disorders and Treatments
- Medical Imaging Techniques and Applications
- Salivary Gland Tumors Diagnosis and Treatment
- Global Cancer Incidence and Screening
- Cancer Risks and Factors
- Cancer Diagnosis and Treatment
- Image and Signal Denoising Methods
- HER2/EGFR in Cancer Research
- Breast Implant and Reconstruction
The Maria Sklodowska-Curie National Research Institute of Oncology
2015-2024
Institute of Fundamental Technological Research
2015-2024
National Institute of Oncology
2024
Polish Academy of Sciences
2015-2024
QT Ultrasound (United States)
2022
Medical University of Warsaw
2019
Polish Academy of Learning
2017
Międzyleski Szpital Specjalistyczny w Warszawie
2014
Centrum Onkologii
2012-2013
Akademia Sztuk Pięknych w Gdańsku
2013
The aim of this paper is to provide access a database consisting the raw radio-frequency ultrasonic echoes acquired from malignant and benign breast lesions. freely available for study signal analysis.The were recorded focal lesions patients Institute Oncology in Warsaw. data collected between 11/2013 10/2015. Patients examined by radiologist with 18 yr' experience examination set includes scans 52 48 group 78 women. For each lesion, two individual orthogonal pathological region Ultrasonix...
The guidelines Thyroid Cancer 2022 are prepared based on previous Polish recommendations updated in 2018. They consider international - American Association (ATA) 2015 and National Comprehensive Network (NCCN); however, they adapted according to the ADAPTE process. strength of quality scientific evidence assessed GRADE system ATA NCCN recommendations. core changes made is inclusion results those studies that have already proven themselves prospectively. These extensions allow de-escalation...
Abstract The presented studies evaluate for the first time efficiency of tumour classification based on quantitative analysis ultrasound data originating from tissue surrounding tumour. 116 patients took part in study after qualifying biopsy due to suspicious breast changes. RF signals collected and tumour-surroundings were processed determine measures consisting Nakagami distribution shape parameter, entropy, texture parameters. utility parameters benign malignant lesions was assessed...
Early prediction of response to neoadjuvant chemotherapy (NAC) in breast cancer is crucial for guiding therapy decisions. In this work, we propose a deep learning based approach the early NAC ultrasound (US) imaging. We used transfer with convolutional neural networks (CNNs) develop models. The usefulness two techniques was examined. First, CNN pre-trained on ImageNet dataset utilized. Second, applied double learning, additionally fine-tuned mass US images differentiate malignant and benign...
Statistical modeling of an ultrasound backscattered echo envelope is used for tissue characterization. However, in the presence complex structures within analyzed area, estimation parameters disturbed and unreliable, e.g., case breast tumor classification. In order to improve differentiation lesions, authors proposed a method based on segmentation homodyned K distribution parameter maps. Regions lesions different scattering properties were extracted analyzed. classification, best-performing...
Numerous scientific societies around the world have published their TIRADS (Thyroid Imaging Reporting and Data System) classifications that evaluate risk of malignancy focal thyroid lesions, presenting different ultrasound features for each category lesion size thresholds to determine eligibility biopsy. The use such estimation systems in lesions facilitates reporting findings improves qualification fine-needle aspiration biopsy (FNAB). In this publication, three most popular...
Monitoring Neoadjuvant chemotherapy (NAC) effects is necessary to capture resistant patients and stop or change treatment. The aim of this study was assess the tumor response at an early stage, after first doses NAC, based on variability backscattered ultrasound energy, backscatter statistics. statistics has not previously been used monitor NAC effects. B-mode images raw radio frequency data from breast tumors were obtained using scanner before 1 week each cycle. Twenty-four malignant...
Computer-aided diagnosis (CAD) and other risk stratification systems may improve ultrasound image interpretation. This prospective study aimed to compare the diagnostic performance of CAD European Thyroid Imaging Reporting Data System (EU-TIRADS) classification applied by physicians with S-Detect 2 software based on Korean (K-TIRADS) combinations both methods (MODELs 1 5). In all, 133 nodules from 88 patients referred thyroidectomy available histopathology or unambiguous results cytology...
Background: Ultrasonography is a primary method used in the evaluation of thyroid nodules, but no single feature this predicts malignancy with high accuracy. Therefore, paper aims to assess utility contrast-enhanced ultrasound (CEUS) differential diagnosis nodules. Methods: The study group comprised 188 adult patients (155 women and 33 men) who preoperatively underwent CEUS nodule classified as Bethesda categories II–VI after fine-needle aspiration biopsy. During examination, 1.5 mL SonoVue...
In this paper we propose a computer-aided diagnosis system for the breast lesion classification. Our approach is based on quantitative ultrasound and deep learning. We used Nakagami imaging to create parametric maps of lesions that illustrate tissue scattering properties. For task sliding window technique was applied. The parameter calculated using maximum likelihood estimator. Next, train convolutional neural network. Classification performance evaluated by 5-fold cross-validation. obtained...
To validate the European Thyroid Imaging and Reporting Data System EU-TIRADS classification in a multi-institutional database of thyroid nodules by analyzing obtained scores histopathology results.A total 842 lesions (613 benign, 229 malignant) were identified 428 patients (mean age 62.7 years) scored according to EU-TIRADS, using ultrasound examination. In all tumors, histopathological verification was performed.In 2 (154 nodules) benign; 3, only 3/93 malignancies identified. 4, 12/103...
The quantitative ultrasound (QUS) imaging provides additional information on tissue properties in comparison to standard ultrasonography. In this paper we use the Nakagami address problem of breast lesion classification. Images lesions may contain areas with calcifications or/and necrosis. These are visible maps and their presence make classification more difficult; efficient texture features for harder estimate. As a remedy, propose convolutional neural network which automatically learn...
To investigate the performance of multiparametric ultrasound for evaluation treatment response in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). The IRB approved this prospective study. Breast who were scheduled to undergo NAC invited participate Changes tumour echogenicity, stiffness, maximum diameter, vascularity and integrated backscatter coefficient (IBC) assessed prior 7 days after four consecutive cycles. Residual malignant cell (RMC) measurement at surgery was...
Deep neural networks have achieved good performance in breast mass classification ultrasound imaging. However, their usage clinical practice is still limited due to the lack of explainability decisions conducted by networks. In this study, address problem, we generated saliency maps indicating image regions important for network's decisions.Ultrasound images were collected from 272 masses, including 123 malignant and 149 benign. Transfer learning was applied develop a deep network...
Shear wave elastography (SWE) is a modern method for the assessment of tissue stiffness.There has been growing interest in use this technique characterizing thyroid focal lesions, including preoperative diagnostics.Aim: The aim study was to assess clinical usefulness SWE medullary carcinoma (MTC) diagnostics.Materials and methods: A total 169 lesions were identifi ed group (139 patients), 6 MTCs 4 patients (mean age: 45 years).B-mode ultrasound performed using Aixplorer (SuperSonic,...