Review
Immunology
Jie Huang, Xueqin Chen, Bing Xia, Shenglin Ma
Summary: Checkpoint inhibitor-related pneumonitis (CIP) is a complication of immunotherapy for malignant tumors that limits treatment cycles and endangers patients' health. The application of radiomics and the analysis of chest CT imaging features can contribute to the precise prevention, early diagnosis, and instant treatment of CIP. This article reviews the advances in CT features and radiomics in CIP.
FRONTIERS IN IMMUNOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Zuhua Song, Dajing Guo, Zhuoyue Tang, Huan Liu, Xin Li, Sha Luo, Xueying Yao, Wenlong Song, Junjie Song, Zhiming Zhou
Summary: This study aimed to determine whether noncontrast computed tomography (NCCT) models could improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH). NCCT models based on multivariable, radiomics features, and machine learning algorithm could enhance the discriminative power for early HE, with the combined model showing the best performance in identifying sICH patients at risk of early HE.
KOREAN JOURNAL OF RADIOLOGY
(2021)
Article
Oncology
Francois Cousin, Thomas Louis, Sophie Dheur, Frank Aboubakar, Benoit Ghaye, Mariaelena Occhipinti, Wim Vos, Fabio Bottari, Astrid Paulus, Anne Sibille, Frederique Vaillant, Bernard Duysinx, Julien Guiot, Roland Hustinx
Summary: The aim of this retrospective multi-centric study was to determine the potential role of CT-based radiomics machine learning models in predicting treatment response and survival in patients with advanced NSCLC treated with immune checkpoint inhibitors. The results showed that the CT-based delta-radiomics signature could early identify patients who presented a clinical benefit at 6 months, with an AUC of 0.8 (95% CI: 0.65-0.95) on an external test dataset.
Article
Oncology
Matthew R. McFarlane, Kimberly A. Hochstedler, Anna M. Laucis, Yilun Sun, Aulina Chowdhury, Martha M. Matuszak, James Hayman, Derek Bergsma, Thomas Boike, Larry Kestin, Benjamin Movsas, Inga Grills, Michael Dominello, Robert T. Dess, Caitlin Schonewolf, Daniel E. Spratt, Lori Pierce, Peter Paximadis, Shruti Jolly, Matthew Schipper
Summary: This study analyzed pneumonitis risk after radiation therapy for lung cancer using a large, prospective dataset. Comorbidity burden, smoking status, and dosimetric parameters were incorporated in an integrated risk model to guide clinicians in assessing pneumonitis risk in individual patients.
INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS
(2021)
Article
Biology
Sepideh Amiri, Mina Akbarabadi, Fatemeh Abdolali, Alireza Nikoofar, Azam Janati Esfahani, Susan Cheraghi
Summary: The study successfully predicted chronic kidney disease by combining radiomic features from CT scans with clinical features. Among the classifiers used, Random Forest performed the best with an accuracy and AUC of 94% and 0.99, respectively.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Oncology
Peizhe Wang, Jingrui Yan, Hui Qiu, Jingying Huang, Zhe Yang, Qiang Shi, Chengxin Yan
Summary: The purpose of this study was to discriminate the risk stratification in gastrointestinal stromal tumors (GISTs) by preoperatively constructing a model of nonenhanced computed tomography (NECT). A total of 111 GISTs patients were collected retrospectively, and radiomics features were extracted to establish radiomics models. The combined model outperformed the clinical models in predicting the pathological risk of GISTs, demonstrating the clinical usefulness of the combined model nomogram.
JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
(2023)
Review
Medicine, General & Internal
Francesca Grassi, Vincenza Granata, Roberta Fusco, Federica De Muzio, Carmen Cutolo, Michela Gabelloni, Alessandra Borgheresi, Ginevra Danti, Carmine Picone, Andrea Giovagnoni, Vittorio Miele, Nicoletta Gandolfo, Antonio Barile, Valerio Nardone, Roberta Grassi
Summary: The role of radiotherapy in the treatment of lung neoplasms, along with surgery and systemic therapies, has become essential. The focus has shifted towards improving survival outcomes, quality of life, treatment compliance, and management of side effects. Imaging plays a crucial role in evaluating treatment efficacy and identifying rare effects, especially when multiple treatments are involved. Radiation recall pneumonitis, a rare complication, needs to be recognized and characterized accurately, requiring prompt identification and the best therapeutic strategy for minimal disruption of ongoing cancer treatment. Artificial intelligence could play a critical role in this regard, provided a larger patient dataset is available.
JOURNAL OF CLINICAL MEDICINE
(2023)
Review
Medicine, General & Internal
Hala Khasawneh, Hanna Rafaela Ferreira Dalla Pria, Joao Miranda, Rachel Nevin, Shalini Chhabra, Dina Hamdan, Jayasree Chakraborty, Tiago Biachi de Castria, Natally Horvat
Summary: Pancreatic adenocarcinoma is a common and aggressive form of pancreatic cancer with a poor prognosis. Surgical resection is the primary treatment option, but only a small percentage of patients are eligible for this procedure. Neoadjuvant therapy has the potential to increase the number of patients eligible for surgery. Computed tomography (CT) is the main imaging tool for evaluating treatment response, but interpretation can be challenging.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Multidisciplinary Sciences
Kuan-Heng Lin, Chen-Xiong Hsu, Shan-Ying Wang, Greta S. P. Mok, Chiu-Han Chang, Hui-Ju Tien, Pei-Wei Shueng, Tung-Hsin Wu
Summary: This study developed a volume-based algorithm (VBA) to predict lung V-5 and optimize lung dose in treatment planning. The predicted lung V-5 was positively correlated with actual lung V-5, while a decrease in arc angle led to a decrease in lung dose and an increase in heart dose.
SCIENTIFIC REPORTS
(2021)
Article
Oncology
Bin Hu, Wei Xia, Sirong Piao, Ji Xiong, Ying Tang, Hong Yu, Guangyu Tao, Linlin Sun, Minhui Shen, Ajay Wagh, Timothy J. Jaykel, Ding Zhang, Yuxin Li, Li Zhu
Summary: An integrated model combining radiomic, demographic, and radiological features was developed to differentiate pulmonary cryptococcosis nodules from lung adenocarcinomas on noncontrast CT. The integrated model showed better performance compared to a junior radiologist and comparable performance to a senior radiologist.
TRANSLATIONAL LUNG CANCER RESEARCH
(2023)
Article
Oncology
Ying Zhu, Wang Yao, Bing-Chen Xu, Yi-Yan Lei, Qi-Kun Guo, Li-Zhi Liu, Hao-Jiang Li, Min Xu, Jing Yan, Dan-Dan Chang, Shi-Ting Feng, Zhi-Hua Zhu
Summary: The study aimed to develop and validate a radiomics model for evaluating treatment response to immune checkpoint inhibitor plus chemotherapy in patients with advanced esophageal squamous cell carcinoma. The 2D corrected radiomics model showed better performance in the training cohort and significantly outperformed in the validation cohort.
Article
Gastroenterology & Hepatology
Valentina Brancato, Nunzia Garbino, Lorenzo Mannelli, Marco Aiello, Marco Salvatore, Monica Franzese, Carlo Cavaliere
Summary: This study explored the combination of CT radiomic features and molecular targets associated with clinical outcomes for characterization of ESCA patients. The findings revealed interesting relationships between the expression of N6-methyladenosine RNA regulators and up-regulated miRNAs, with CT radiomic features associated with clinical outcomes of ESCA patients.
WORLD JOURNAL OF GASTROENTEROLOGY
(2021)
Article
Oncology
Zhonghua Chen, Linyi Xu, Chuanmin Zhang, Chencui Huang, Minhong Wang, Zhan Feng, Yue Xiong
Summary: A CT-based multi-class prediction model for GISTs risk stratification was established and validated using data from 381 patients. The model showed stable performance with an average AUC of 0.84 in the training cohort and 0.83 in the external validation cohort, indicating its potential for assisting accurate treatment of GISTs.
FRONTIERS IN ONCOLOGY
(2021)
Article
Medicine, General & Internal
Dongxiao Meng, Yingnan Wei, Xiao Feng, Bing Kang, Ximing Wang, Jianni Qi, Xinya Zhao, Qiang Zhu
Summary: The study developed a radiomics score extracted from liver and spleen CT images to predict esophageal variceal rebleeding risk in cirrhotic patients. The Rad-score demonstrated good discriminative performance and risk stratification ability, showing promising usefulness in clinical practice. Additionally, the Rad-score performed better in stratifying patients in the hepatitis B virus cohort than in the non-HBV cohort.
FRONTIERS IN MEDICINE
(2021)
Article
Oncology
Feng Du, Hong Liu, Wei Wang, Yingjie Zhang, Jianbin Li
Summary: The study assessed the relationship between radiation dose and lung density changes in esophageal cancer patients undergoing radiotherapy to identify radiation pneumonitis development. Results showed a positive correlation between radiation dose and Delta HU, with Delta HU increasing as radiation dose increased. Additionally, the occurrence time of radiation pneumonitis was negatively correlated with the degree of Delta HU, indicating an earlier onset with more obvious Delta HU.
FRONTIERS IN ONCOLOGY
(2021)