Review
Engineering, Biomedical
Haizhe Jin, Cheng Yu, Zibo Gong, Renjie Zheng, Yinan Zhao, Quanwei Fu
Summary: This study systematically analyzed and compared the performance of machine learning algorithms using the same dataset in the diagnosis of pulmonary nodules through a literature review.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Mario Silva, Giulia Picozzi, Nicola Sverzellati, Sandra Anglesio, Maurizio Bartolucci, Edoardo Cavigli, Annalisa Deliperi, Massimo Falchini, Fabio Falaschi, Domenico Ghio, Paola Gollini, Anna Rita Larici, Alfonso Marchiano, Stefano Palmucci, Lorenzo Preda, Chiara Romei, Carlo Tessa, Cristiano Rampinelli, Mario Mascalchi
Summary: Smoking is the main risk factor for lung cancer, and low dose computed tomography (LDCT) screening has been proven to reduce lung cancer mortality, especially in women. Several Italian initiatives are currently offering LDCT screening and smoking cessation to high-risk individuals, with the aim of implementing a population-based screening program. This position paper provides recommendations for LDCT scan protocol, nodule classification, and management based on international guidelines.
Article
Biology
Yu Gu, Jingqian Chi, Jiaqi Liu, Lidong Yang, Baohua Zhang, Dahua Yu, Ying Zhao, Xiaoqi Lu
Summary: This paper summarizes the CAD approaches using deep learning for lung nodule detection on CT scan data. The technologies show promising results in improving the survival rate of lung cancer patients, but there are still challenges and limitations to be addressed.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sung Hyun Yoon, Yong Ju Kim, Kibbeum Doh, Junghoon Kim, Kyung Hee Lee, Kyung Won Lee, Jihang Kim
Summary: This study assessed interobserver agreement in Lung-RADS categorisation of subsolid nodules in low-dose screening CTs, showing higher concordance among experienced thoracic radiologists. Overall, the interobserver agreement was moderate.
EUROPEAN RADIOLOGY
(2021)
Article
Computer Science, Interdisciplinary Applications
S. P. Morozov, V. A. Gombolevskiy, A. B. Elizarov, M. A. Gusev, V. P. Novik, S. B. Prokudaylo, A. S. Bardin, E. Popov, N. Ledikhova, V. Y. Chernina, I. A. Blokhin, A. E. Nikolaev, R. Reshetnikov, A. V. Vladzymyrskyy, N. S. Kulberg
Summary: This study proposed a practical approach and tool for creating medical image datasets for early detection of lung nodules. Results showed that the maximum transverse diameter approach outperformed alternative methods in terms of speed and accuracy of nodule shape approximation. The dataset markup and annotation revealed the potential presence of lung nodules in the CT scans.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Oncology
Jiabao Liu, Liqin Zhao, Xianjun Han, Hong Ji, Liheng Liu, Wen He
Summary: The study developed a CAD system to assist radiologists in diagnosing pulmonary nodules on CT scans, and found that the CAD system significantly improved the diagnostic performance of radiologists at different experience levels, whether they were senior, secondary, or junior readers. The CAD system achieved sensitivity, specificity, and diagnostic accuracy values of 93.8%, 83.9%, and 90.5%, respectively, and the mean area under the ROC curve values were higher with the CAD system compared to without it.
ASIA-PACIFIC JOURNAL OF CLINICAL ONCOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Andrea Borghesi, Felice Leopoldo Coviello, Alessandra Scrimieri, Pietro Ciolli, Marco Ravanelli, Davide Farina
Summary: The study aimed to evaluate the performance of the open-source software (ImageJ) in predicting the future growth of nonsolid nodules (NSNs) detected in a Caucasian (Italian) population. The results showed that skewness and linear mass density (LMD) were significantly associated with NSN growth, with skewness being the strongest predictor. According to the findings, NSNs with skewness value > 0.90, especially those with LMD > 19.16 mg/mm, should be closely monitored due to their higher growth potential and risk of becoming an active cancer.
Article
Radiology, Nuclear Medicine & Medical Imaging
Vitali Koch, Ibrahim Yel, Leon D. Gruenewald, Sebastian Beckers, Iris Burck, Lukas Lenga, Simon S. Martin, Christoph Mader, Julian L. Wichmann, Moritz H. Albrecht, Katrin Eichler, Tatjana Gruber-Rouh, Tommaso D'Angelo, Silvio Mazziotti, Giorgio Ascenti, Thomas J. Vogl, Christian Booz
Summary: The study found that dual-energy CT (DECT) virtual noncalcium (VNCa) reconstructions demonstrated higher diagnostic accuracy and confidence in assessing thoracic disk herniation compared to standard CT.
EUROPEAN RADIOLOGY
(2021)
Article
Engineering, Biomedical
Himanshu Rikhari, Esha Baidya Kayal, Shuvadeep Ganguly, Archana Sasi, Swetambri Sharma, D. S. Dheeksha, Manish Saini, Krithika Rangarajan, Sameer Bakhshi, Devasenathipathy Kandasamy, Amit Mehndiratta
Summary: The purpose of this work is to develop an algorithm for accurately segmenting the lung parenchyma in thoracic CT scans. The proposed method combines deep learning and traditional image processing algorithms. A trained CNN is used to generate preliminary lung masks, followed by a post-processing algorithm for lung boundary correction.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Libao Hu, Jian Gao, Nan Hong, Huixin Liu, Xin Zhi, Jian Zhou
Summary: CT-guided microcoil localization of pulmonary nodules before VATS is effective and safe, with a technical success rate of 98.4%. Most complications during the procedure are minor adverse events, with pneumothorax and pulmonary hemorrhage being the most common.
EUROPEAN RADIOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Khaled Alawneh, Hiam Alquran, Mohammed Alsalatie, Wan Azani Mustafa, Yazan Al-Issa, Amin Alqudah, Alaa Badarneh
Summary: This study presents a computer-aided diagnosis system for classifying hepatic tumors as benign or malignant using computed tomography scans. By utilizing deep learning classification and a Support Vector Machine classifier, this system achieves high accuracy and provides a lightweight, fast, reliable, and accurate diagnostic approach.
APPLIED SCIENCES-BASEL
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ya-Wen Wang, Jian-Wei Wang, Shou-Xin Yang, Lin-Lin Qi, Hao-Liang Lin, Zhen Zhou, Yi-Zhou Yu
Summary: The study compared the performance of a deep learning method with radiologists' diagnostic approach for diagnosing pulmonary nodules in CT scans. The results showed a significant difference in diagnosis results between the two methods, but no significant difference in diagnostic accuracy.
EUROPEAN RADIOLOGY
(2021)
Article
Chemistry, Analytical
Mudasir Khan, Pir Masoom Shah, Izaz Ahmad Khan, Saif ul Islam, Zahoor Ahmad, Faheem Khan, Youngmoon Lee
Summary: The Internet of Medical Things (IoMT) has transformed Ambient Assisted Living (AAL) by connecting smart medical devices. Deep Neural Network (DNN) has proven effective in extracting meaningful information from the massive data generated by these devices. In this study, a deep learning framework based on DenseNet201 was proposed for the automatic classification of Pulmonary Embolism (PE) in CT scans, achieving promising accuracy, sensitivity, specificity, and AUC.
Article
Oncology
Tianle Shen, Runping Hou, Xiaodan Ye, Xiaoyang Li, Junfeng Xiong, Qin Zhang, Chenchen Zhang, Xuwei Cai, Wen Yu, Jun Zhao, Xiaolong Fu
Summary: The study successfully developed and validated a deep learning-based model on CT images for predicting the malignancy and invasiveness of pulmonary subsolid nodules. Compared to observer readers, the model outperformed in accuracy and has the potential to assist surgeons in making treatment decisions.
FRONTIERS IN ONCOLOGY
(2021)
Article
Public, Environmental & Occupational Health
Hao Wang, Na Tang, Chao Zhang, Ye Hao, Xiangfeng Meng, Jiage Li
Summary: This study aimed to implement a standardized protocol for testing the performance of computer-aided detection (CAD) algorithms for pulmonary nodules. The study established a test dataset and applied three specific rules to match algorithm output with a reference standard. The results showed that algorithms performed differently on different types of pulmonary nodules. This centralized testing protocol supports algorithm comparison and performance evaluation.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Computer Science, Artificial Intelligence
Shiwen Shen, Simon X. Han, Denise R. Aberle, Alex A. Bui, William Hsu
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Respiratory System
Audrey Winter, Denise R. Aberle, William Hsu
Article
Oncology
Kostyantyn Krysan, Linh M. Tran, Brandon S. Grimes, Gregory A. Fishbein, Atsuko Seki, Brian K. Gardner, Tonya C. Walser, Ramin Salehi-Rad, Jane Yanagawa, Jay M. Lee, Sherven Sharma, Denise R. Aberle, Arum E. Spira, David A. Elashoff, William D. Wallace, Michael C. Fishbein, Steven M. Dubinett
Editorial Material
Oncology
Matthew B. Schabath, Denise R. Aberle
NATURE REVIEWS CLINICAL ONCOLOGY
(2019)
Article
Oncology
Reginald F. Munden, Caroline Chiles, Phillip M. Boiselle, JoRean D. Sicks, Denise R. Aberle, Constantine A. Gatsonis
JOURNAL OF THORACIC ONCOLOGY
(2019)
Correction
Radiology, Nuclear Medicine & Medical Imaging
Matthew S. Brown, Pechin Lo, Jonathan G. Goldin, Eran Barnoy, Grace Hyun J. Kim, Michael F. McNitt-Gray, Denise R. Aberle
EUROPEAN RADIOLOGY
(2020)
Article
Oncology
Kosuke Inoue, William Hsu, Onyebuchi A. Arah, Ashley E. Prosper, Denise R. Aberle, Alex A. T. Bui
Summary: This study demonstrates how generalizability and transportability methods can be used to extrapolate treatment effects from different subsets of the population and apply them to target populations. Results show that LDCT screening can significantly reduce lung cancer mortality, with greater effects seen in populations with higher proportions of females and current smokers.
CANCER EPIDEMIOLOGY BIOMARKERS & PREVENTION
(2021)
Review
Oncology
Yannan Lin, Mingzhou Fu, Ruiwen Ding, Kosuke Inoue, Christie Y. Jeon, William Hsu, Denise R. Aberle, Ashley Elizabeth Prosper
Summary: This study conducted a systematic review and meta-analysis on patient adherence to Lung-RADS-recommended screening intervals, finding significant heterogeneity in adherence rates between studies, especially among patients with Lung-RADS categories 1 to 2. To improve adherence rates, future research may focus on implementing tailored interventions after identifying barriers to LCS. Additionally, a minimum standardized set of data elements for future pooled analyses of LCS adherence is proposed based on the findings.
JOURNAL OF THORACIC ONCOLOGY
(2022)
Article
Multidisciplinary Sciences
Mary L. Stackpole, Weihua Zeng, Shuo Li, Chun-Chi Liu, Yonggang Zhou, Shanshan He, Angela Yeh, Ziye Wang, Fengzhu Sun, Qingjiao Li, Zuyang Yuan, Asli Yildirim, Pin-Jung Chen, Paul Winograd, Benjamin Tran, Yi-Te Lee, Paul Shize Li, Zorawar Noor, Megumi Yokomizo, Preeti Ahuja, Yazhen Zhu, Hsian-Rong Tseng, James S. Tomlinson, Edward Garon, Samuel French, Clara E. Magyar, Sarah Dry, Clara Lajonchere, Daniel Geschwind, Gina Choi, Sammy Saab, Frank Alber, Wing Hung Wong, Steven M. Dubinett, Denise R. Aberle, Vatche Agopian, Steven-Huy B. Han, Xiaohui Ni, Wenyuan Li, Xianghong Jasmine Zhou
Summary: Early cancer detection using cell-free DNA faces challenges of low tumor DNA fraction, molecular heterogeneity, and limited sample sizes. In this study, the authors developed a cost-effective method called cfMethyl-Seq to profile the methylome of cell-free DNA and detect and locate cancer. The approach achieved high sensitivity and accuracy for detecting and identifying the tissue-of-origin of various cancer types.
NATURE COMMUNICATIONS
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Nova F. Smedley, Denise R. Aberle, William Hsu
Summary: Neural networks were trained to predict radiomic features and histology in NSCLC patients, outperforming other classifiers with AUC values ranging from 0.71 to 0.91. Gene masking analysis revealed associations between genes and radiomic features or histology types, demonstrating the ability of neural networks to interpret the models and identify predictive genes.
JOURNAL OF MEDICAL IMAGING
(2021)
Proceedings Paper
Engineering, Biomedical
Yannan Lin, Leihao Wei, Simon X. Han, Denise R. Aberle, William Hsu
MEDICAL IMAGING 2020: COMPUTER-AIDED DIAGNOSIS
(2020)
Meeting Abstract
Oncology
B. Liu, A. Lisberg, R. Salehi-Rad, J. M. Lee, L. M. Tran, K. Krysan, R. Li, R. J. Lim, C. Dumitras, Z. Jing, F. Abtin, R. D. Suh, S. J. Genshaft, S. Oh, D. R. Aberle, L. E. Winter, S. Sharma, D. Elashoff, E. B. Garon, S. M. Dubinett
JOURNAL OF THORACIC ONCOLOGY
(2020)
Meeting Abstract
Oncology
Brendon Villegas, Eva Koziolek, Jie Liu, W. Dean Wallace, David Elashoff, Denise R. Aberle, David B. Shackelford, Jorge R. Barrio, Jane Yanagawa, Steven M. Dubinett, Claudio Scafoglio
Meeting Abstract
Oncology
Bin Liu, Edward B. Garon, Aaron E. Lisberg, Ramin Salehi-Rad, Jay M. Lee, Linh M. Tran, Kostyantyn Krysan, Rui Li, Raymond J. Lim, Manash Paul, Ying Lin, Zhe Jing, Fereidoun Abtin, Robert D. Suh, Scott Oh, Denise R. Aberle, Lauren E. Winter, William Dean Wallace, David Elashoff, Sherven Sharma, Steven M. Dubinett
Article
Oncology
Denise R. Aberle, William C. Black, Caroline Chiles, Timothy R. Church, Ilana F. Gareen, David S. Gierada, Irene Mahon, Eric A. Miller, Paul F. Pinsky, JoRean D. Sicks
JOURNAL OF THORACIC ONCOLOGY
(2019)