Article
Radiology, Nuclear Medicine & Medical Imaging
Phuong Dung (Yun) Trieu, Jennie Noakes, Tong Li, Natacha Borecky, Patrick C. Brennan, Melissa L. Barron, Sarah J. Lewis
Summary: This study evaluated the diagnostic efficacy of radiologists and radiology trainees in using DBT alone or DBT plus SV for identifying breast cancer lesions. The results showed no significant difference in specificity, sensitivity, and ROC AUC between the two reading modes for both radiologists and trainees. The cancer detection rate also did not differ significantly between the two modes for different breast densities, lesion types, and sizes. Therefore, DBT alone could be considered as a sole modality without SV.
BRITISH JOURNAL OF RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jung Hyun Yoon, Eun-Kyung Kim, Ga Ram Kim, Kyunghwa Han, Hee Jung Moon
Summary: This study assessed the impact of adding DBT or AI-CAD on recall rate and diagnostic performance in women undergoing mammographic surveillance after BCT. The results showed that adding DBT or AI-CAD reduced recall rates and improved diagnostic accuracy.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2022)
Article
Oncology
Takayoshi Uematsu, Kazuaki Nakashima, Taiyo Leopoldo Harada, Hatsuko Nasu, Tatsuya Igarashi
Summary: This study compared the performance of synthesized mammograms (AI CAD SM) with full-field digital mammograms (DM) and digital breast tomosynthesis (DBT) images. The results showed that AI CAD SM had better diagnostic performance than DM. AI CAD SM + DBT also performed better than DM + DBT, but the difference was not statistically significant.
Review
Oncology
Tong Li, Nehmat Houssami, Naomi Noguchi, Aileen Zeng, M. Luke Marinovich
Summary: Digital breast tomosynthesis (DBT) has differential incremental cancer detection and recall rates based on breast density. While the incremental cancer detection rate is higher in high-density screens, a substantial number of additional cancers can also be detected in low-density screens.
BRITISH JOURNAL OF CANCER
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Alistair Mackenzie, Emma L. Thomson, Melissa Mitchell, Premkumar Elangovan, Chantal van Ongeval, Lesley Cockmartin, Lucy M. Warren, Louise S. Wilkinson, Matthew G. Wallis, Rosalind M. Given-Wilson, David R. Dance, Kenneth C. Young
Summary: For calcification clusters, there were no significant differences in FoM or LDF. For masses, the FoM and LDF were significantly improved in the arms using DBT compared to DM alone. On average, both calcification clusters and masses were more visible on DBT than on DM and SM images.
EUROPEAN RADIOLOGY
(2022)
Article
Computer Science, Information Systems
Bahareh Salafian, Eyal Fishel Ben-Knaan, Nir Shlezinger, Sandrine De Ribaupierre, Nariman Farsad
Summary: We propose a hybrid model-based data-driven seizure detection algorithm called MICAL, which utilizes neural MI estimators, 1D CNN, and factor graph inference to improve the detection of seizures from EEG signals. The method successfully captures inter-channel statistical dependence and temporal correlation, leading to state-of-the-art performance.
Article
Radiology, Nuclear Medicine & Medical Imaging
Krithika Rangarajan, Pranjal Agarwal, Dhruv Kumar Gupta, Rohan Dhanakshirur, Akhil Baby, Chandan Pal, Arun Kumar Gupta, Smriti Hari, Subhashis Banerjee, Chetan Arora
Summary: This study analyzed the performance of deep learning in isodense/obscure masses in dense breasts. A deep learning model was built and validated using core radiology principles, and its performance in isodense/obscure masses was analyzed. The results showed improved sensitivity in cancer detection in dense breasts using the proposed deep learning model.
EUROPEAN RADIOLOGY
(2023)
Review
Oncology
Ioannis Sechopoulos, Jonas Teuwen, Ritse Mann
Summary: Screening for breast cancer has evolved rapidly over the past 30 years, with the introduction of digital technology and artificial intelligence becoming mainstream in breast cancer detection. Studies have shown that artificial intelligence performs on par with experienced radiologists in breast cancer screening.
SEMINARS IN CANCER BIOLOGY
(2021)
Article
Computer Science, Interdisciplinary Applications
Rebecca Sawyer Lee, Jared A. Dunnmon, Ann He, Siyi Tang, Christopher Re, Daniel L. Rubin
Summary: This study compared machine learning methods for classifying mass lesions on mammography images and found that a common segmentation-free CNN model substantially outperforms other methods. This indicates that representation learning techniques are advantageous for mammogram analysis.
JOURNAL OF BIOMEDICAL INFORMATICS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Alistair Mackenzie, Sukhmanjit Kaur, Emma L. Thomson, Melissa Mitchell, Premkumar Elangovan, Lucy M. Warren, David R. Dance, Kenneth C. Young
Summary: The study aimed to measure the threshold diameter of calcifications and masses under different breast glandularities for various imaging modalities, revealing the strengths and weaknesses of each technology in visualizing small cancer features. The results showed that glandularity has a minor effect on calcification detection but significantly impacts the threshold diameter of masses across all tested modalities.
Article
Engineering, Biomedical
Hossein Ketabi, Ali Ekhlasi, Hessam Ahmadi
Summary: The study proposes a method for detecting breast masses using a CAD system, automatically detecting breast ROIs, selecting features, and classifying mass tissues accurately. Sensitivity, specificity, and accuracy measures of the proposed approach are 89.5%, 91.2%, and 90%, respectively.
PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE
(2021)
Article
Engineering, Biomedical
Yue Li, Zilong He, Jiawei Pan, Weixiong Zeng, Jialing Liu, Zhaodong Zeng, Weimin Xu, Zeyuan Xu, Sina Wang, Chanjuan Wen, Hui Zeng, Jiefang Wu, Xiangyuan Ma, Weiguo Chen, Yao Lu
Summary: This study develops a deep learning-based CADe model with an adaptive receptive field to detect atypical architectural distortions (ADs) in digital breast tomosynthesis (DBT). The results show a significant improvement in AD detection performance, especially for atypical ADs.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Review
Biology
Kosmia Loizidou, Rafaella Elia, Costas Pitris
Summary: Cancer, particularly breast cancer, is a significant global health concern and major cause of morbidity and mortality. Mammography is effective for early detection and management, but accurately identifying and interpreting breast lesions is challenging. Computer-Aided Diagnosis (CAD) systems have been developed to assist radiologists in detecting and classifying breast cancer. This review examines recent literature on the use of both traditional feature-based machine learning and deep learning algorithms for automatic detection and classification of breast cancer in mammograms, as well as FDA-approved CAD systems and potential future opportunities in this field.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Review
Oncology
Nehmat Houssami, Sophia Zackrisson, Katrina Blazek, Kylie Hunter, Daniela Bernardi, Kristina Lang, Solveig Hofvind
Summary: Digital breast tomosynthesis (DBT) has been shown to significantly increase cancer detection rate (CDR) compared with mammography in breast cancer screening, but there is little difference in interval cancer rate (ICR) between DBT and mammography.
EUROPEAN JOURNAL OF CANCER
(2021)
Article
Multidisciplinary Sciences
Andria Hadjipanteli, Petros Polyviou, Ilias Kyriakopoulos, Marios Genagritis, Natasa Kotziamani, Demetris Moniatis, Anne Papoutsou, Anastasia Constantinidou
Summary: This study found no significant differences in sensitivity, specificity, and AUC between the 2-view 2D digital mammography and 2-view DBT implementation and the 1-view (cranial-caudal) DM and 1-view (mediolateral-oblique) DBT implementation in breast cancer surveillance imaging. Considering the radiation dose, using 1-view DM and 1-view DBT may be worth considering, but larger studies are needed to draw a final conclusion.
Article
Critical Care Medicine
Ehsan Abadi, Giavanna Jadick, David A. Lynch, W. Paul Segars, Ehsan Samei
Summary: This study investigates the impact of CT scan imaging parameters on the accuracy of emphysema-based quantifications and biomarkers, finding that the choice of imaging conditions can significantly affect accuracy. The study uses digital phantoms in a simulated trial platform, providing a reliable method for evaluating CT scan methods.
Article
Radiology, Nuclear Medicine & Medical Imaging
Moiz Ahmad, Xinming Liu, Ajaykumar C. Morani, Dhakshinamoorthy Ganeshan, Marcus R. Anderson, Ehsan Samei, Corey T. Jensen
Summary: This study provides reference levels for image noise and radiation dose in oncology-specific adult abdominal-pelvic CT examinations. The results showed that the radiation dose was higher and the image noise level was lower compared to non-oncology-specific CT examinations.
Review
Radiology, Nuclear Medicine & Medical Imaging
Fides Regina Schwartz, Ehsan Samei, Daniele Marin
Summary: Photon-counting computed tomography (PCCT) uses new detector technology to provide additional information compared to current CT and MR technologies. This review focuses on PCCT of the abdomen and its applications. It discusses the requirements and challenges for successful abdominal PCCT acquisition and highlights recent developments and protocols tested in clinical settings. PCCT has applications in imaging cystic lesions, identifying sources of bleeding, and staging cancers. It has the potential to advance beyond disease detection to quantitative staging and treatment response measurement.
INVESTIGATIVE RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Fides R. Schwartz, Melissa A. Daubert, Lior Molvin, Juan C. Ramirez-Giraldo, Ehsan Samei, Daniele Marin, Tina D. Tailor
Summary: A prospective comparison between standard computed tomography (CT) and photon-counting CT for coronary calcium scores showed no significant differences, but photon-counting CT had substantially lower radiation dose.
JOURNAL OF THORACIC IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Thomas J. Sauer, Adrian Bejan, Paul Segars, Ehsan Samei
Summary: This study aimed to compare the new anatomically-informed lesion model with a previous lesion model for use in computed tomography (CT) imaging and simulated CT imaging. Using cellular simulation techniques, the lesions generated by this model were indistinguishable from clinical lesions in CT images and superior to the previous image-based lesion model.
Article
Engineering, Biomedical
Fariba Azizmohammadi, Inaki Navarro Castellanos, Joaquim Miro, Paul Segars, Ehsan Samei, Luc Duong
Summary: This study proposes a novel patient-specific cardio-respiratory motion prediction approach using a simple LSTM model. The motion behavior in an X-ray angiography time series is represented as a sequence of 2D affine transformation matrices, and a LSTM model is used to predict future frames based on previously generated images. The method achieves small prediction errors in both simulated and patient datasets.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Multidisciplinary Sciences
Ilian Haeggmark, Kian Shaker, Sven Nyren, Bariq Al-Amiry, Ehsan Abadi, William P. Segars, Ehsan Samei, Hans M. Hertz
Summary: Respiratory X-ray imaging enhanced by phase contrast has shown improved airway visualization in animal models, but limitations in current technology hinder its clinical translation, making its potential impact uncertain.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Fides Regina Schwartz, Jeffrey Ashton, Benjamin Wildman-Tobriner, Lior Molvin, Juan Carlos Ramirez-Giraldo, Ehsan Samei, Mustafa Rifaat Bashir, Daniele Marin
Summary: This study compared liver fat quantification between MRI and photon-counting CT (PCCT). The results showed promising accuracy of liver fat fraction quantification for PCCT in obese patients, which may have potential application in opportunistic screening for CT in the future.
EUROPEAN JOURNAL OF RADIOLOGY
(2023)
Editorial Material
Computer Science, Information Systems
Sergio Cerutti, Bjoern Eskofier, Georgia Tourassi
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Faraz Farhadi, Pooyan Sahbaee, Jayasai R. Rajagopal, Moozhan Nikpanah, Babak Saboury, Ralf Gutjahr, Nadia M. Biassou, Ritu Shah, Thomas G. Flohr, Ehsan Samei, William F. Pritchard, Ashkan A. Malayeri, David A. Bluemke, Elizabeth C. Jones
Summary: This study reports the image quality metrics of virtual monoengetic images (VMI) in photon-counting (PCCT) angiography of the head and neck, expanding the evaluation of anatomical regions and qualitative methods. The study found that the preferred energy levels and quality ratings of VMI varied by anatomical location.
Article
Radiology, Nuclear Medicine & Medical Imaging
Megan K. Russ, Nicole M. Lafata, Scott H. Robertson, Ehsan Samei
Summary: This study aimed to evaluate the accuracy, reproducibility, and inter-scanner variability of ultrasound flow velocity measurements using a flow phantom. The impact of systematic acquisition parameters on measured flow velocity accuracy was also investigated.
Article
Radiology, Nuclear Medicine & Medical Imaging
Jayasai R. Rajagopal, Faraz Farhadi, Moozhan Nikpanah, Pooyan Sahbaee, Babak Saboury, William F. Pritchard, Elizabeth C. Jones, Marcus Y. Chen, Ehsan Samei
Summary: The study demonstrates that photon-counting CT can achieve higher spatial resolution, which helps improve cardiac imaging quality and reduce motion artifacts. High-resolution images perform better in vessel diameter and circularity compared to standard resolution, with slightly lower mutual information but still acceptable similarity.
PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Francesca Rigiroli, Jocelyn Hoye, Reginald Lerebours, Peijie Lyu, Kyle J. Lafata, Anru R. Zhang, Alaattin Erkanli, Niharika B. Mettu, Desiree E. Morgan, Ehsan Samei, Daniele Marin
Summary: This study developed and evaluated task-based radiomic features extracted from the mesenteric-portal axis for prediction of survival and response to neoadjuvant therapy in patients with pancreatic ductal adenocarcinoma (PDAC). The results suggest that task-based shape radiomic features can predict survival in PDAC patients.
EUROPEAN RADIOLOGY
(2023)
Letter
Oncology
Cynthia H. McCollough, Mahadevappa Mahesh, Ehsan Samei
Article
Radiology, Nuclear Medicine & Medical Imaging
Alan A. Peters, Justin B. Solomon, Oyunbileg von Stackelberg, Ehsan Samei, Njood Alsaihati, Waldo Valenzuela, Manuel Debic, Christian Heidt, Adrian T. Huber, Andreas Christe, Johannes T. Heverhagen, Hans-Ulrich Kauczor, Claus P. Heussel, Lukas Ebner, Mark O. Wielpuetz
Summary: This study aimed to determine the influence of dose reduction on a commercially available lung cancer prediction convolutional neuronal network (LCP-CNN). The results showed that CT dose reduction may affect the classification of pulmonary malignancies and potentially alter pulmonary nodule management.
EUROPEAN RADIOLOGY
(2023)