scholarly journals Radiomics in Differentiated Thyroid Cancer and Nodules: Explorations, Application, and Limitations

Cancers ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 2436
Author(s):  
Yuan Cao ◽  
Xiao Zhong ◽  
Wei Diao ◽  
Jingshi Mu ◽  
Yue Cheng ◽  
...  
Keyword(s):  
Clinical Decision Making ◽  
Prediction Models ◽  
Imaging Techniques ◽  
Disease Free Survival ◽  
Clinical Decision ◽  
Benign Tumors ◽  
Learning Approaches ◽  
Serine Threonine Kinase ◽  
Quantitative Extraction ◽  
Benign Nodules

Radiomics is an emerging technique that allows the quantitative extraction of high-throughput features from single or multiple medical images, which cannot be observed directly with the naked eye, and then applies to machine learning approaches to construct classification or prediction models. This method makes it possible to evaluate tumor status and to differentiate malignant from benign tumors or nodules in a more objective manner. To date, the classification and prediction value of radiomics in DTC patients have been inconsistent. Herein, we summarize the available literature on the classification and prediction performance of radiomics-based DTC in various imaging techniques. More specifically, we reviewed the recent literature to discuss the capacity of radiomics to predict lymph node (LN) metastasis, distant metastasis, tumor extrathyroidal extension, disease-free survival, and B-Raf proto-oncogene serine/threonine kinase (BRAF) mutation and differentiate malignant from benign nodules. This review discusses the application and limitations of the radiomics process, and explores its ability to improve clinical decision-making with the hope of emphasizing its utility for DTC patients.

scholarly journals Clinical decision making and research in hepatocellular carcinoma: Pivotal role of imaging techniques

Hepatology ◽  
2011 ◽  
Vol 54 (6) ◽  
pp. 2238-2244 ◽  
Author(s):  
Jordi Bruix ◽  
Maria Reig ◽  
Jordi Rimola ◽  
Alejandro Forner ◽  
Marta Burrel ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Imaging Techniques ◽  
Clinical Decision ◽  
Pivotal Role

scholarly journals Development of Antibody Immuno-PET/SPECT Radiopharmaceuticals for Imaging of Oncological Disorders—An Update

Cancers ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1868
Author(s):  
Jonatan Dewulf ◽  
Karuna Adhikari ◽  
Christel Vangestel ◽  
Tim Van Den Wyngaert ◽  
Filipe Elvas
Keyword(s):  
Clinical Decision Making ◽  
Single Photon ◽  
Imaging Techniques ◽  
Photon Emission ◽  
Therapy Response ◽  
High Specificity ◽  
Clinical Decision ◽  
Disease Diagnosis ◽  
Emission Computed Tomography ◽  
Wide Range

Positron emission tomography (PET) and single-photon emission computed tomography (SPECT) are molecular imaging strategies that typically use radioactively labeled ligands to selectively visualize molecular targets. The nanomolar sensitivity of PET and SPECT combined with the high specificity and affinity of monoclonal antibodies have shown great potential in oncology imaging. Over the past decades a wide range of radio-isotopes have been developed into immuno-SPECT/PET imaging agents, made possible by novel conjugation strategies (e.g., site-specific labeling, click chemistry) and optimization and development of novel radiochemistry procedures. In addition, new strategies such as pretargeting and the use of antibody fragments have entered the field of immuno-PET/SPECT expanding the range of imaging applications. Non-invasive imaging techniques revealing tumor antigen biodistribution, expression and heterogeneity have the potential to contribute to disease diagnosis, therapy selection, patient stratification and therapy response prediction achieving personalized treatments for each patient and therefore assisting in clinical decision making.

scholarly journals MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care

2020 ◽  
Vol 27 (12) ◽  
pp. 2011-2015 ◽  
Author(s):  
Tina Hernandez-Boussard ◽  
Selen Bozkurt ◽  
John P A Ioannidis ◽  
Nigam H Shah
Keyword(s):  
Artificial Intelligence ◽  
Health Care ◽  
Clinical Decision Making ◽  
Prediction Models ◽  
Clinical Decision ◽  
Digital Data ◽  
Reporting Standards ◽  
Minimum Information ◽  
Support Tools ◽  
Hidden Biases

Abstract The rise of digital data and computing power have contributed to significant advancements in artificial intelligence (AI), leading to the use of classification and prediction models in health care to enhance clinical decision-making for diagnosis, treatment and prognosis. However, such advances are limited by the lack of reporting standards for the data used to develop those models, the model architecture, and the model evaluation and validation processes. Here, we present MINIMAR (MINimum Information for Medical AI Reporting), a proposal describing the minimum information necessary to understand intended predictions, target populations, and hidden biases, and the ability to generalize these emerging technologies. We call for a standard to accurately and responsibly report on AI in health care. This will facilitate the design and implementation of these models and promote the development and use of associated clinical decision support tools, as well as manage concerns regarding accuracy and bias.

An emerging epidemic: cancer and heart failure

2016 ◽  
Vol 131 (2) ◽  
pp. 113-121 ◽  
Author(s):  
Paaladinesh Thavendiranathan ◽  
Mark T. Nolan
Keyword(s):  
Heart Failure ◽  
Cancer Therapy ◽  
Clinical Decision Making ◽  
Prediction Models ◽  
Clinical Decision ◽  
Prevention Strategies ◽  
Patients With Cancer ◽  
Increased Risk ◽  
Adult Cancer Survivors ◽  
Shared Risk

Heart disease and cancer are the two leading causes of mortality globally. Cardiovascular complications of cancer therapy significantly contribute to the global burden of cardiovascular disease. Heart failure (HF) in particular is a relatively common and life-threatening complication. The increased risk is driven by the shared risk factors for cancer and HF, the direct impact of cancer therapy on the heart, an existing care gap in the cardiac care of patients with cancer and the increasing population of adult cancer survivors. The clear relationship between cancer treatment initiation and the potential for myocardial injury makes this population attractive for prevention strategies, targeted cardiovascular monitoring and treatment. However, there is currently no consensus on the optimal strategy for managing this at-risk population. Uniform treatment using cardioprotective medications may reduce the incidence of HF, but would impose frequently unnecessary and burdensome side effects. Ideally we could use validated risk-prediction models to target HF-preventive strategies, but currently no such models exist. In the present review, we focus on evidence and rationales for contemporary clinical decision-making in this novel field and discuss issues, including the burden of HF in patients with cancer, the reasons for the elevated risk and potential prevention strategies.

Artificial Intelligence in Lung Cancer: Bridging the Gap Between Computational Power and Clinical Decision-Making

2020 ◽  
pp. 084653712094143
Author(s):  
Jaryd R. Christie ◽  
Pencilla Lang ◽  
Lauren M. Zelko ◽  
David A. Palma ◽  
Mohamed Abdelrazek ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Lung Cancer ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Prediction Models ◽  
Biomarker Discovery ◽  
Surgical Techniques ◽  
Clinical Decision ◽  
Clinical Implementation ◽  
Cancer Management

Lung cancer remains the most common cause of cancer death worldwide. Recent advances in lung cancer screening, radiotherapy, surgical techniques, and systemic therapy have led to increasing complexity in diagnosis, treatment decision-making, and assessment of recurrence. Artificial intelligence (AI)–based prediction models are being developed to address these issues and may have a future role in screening, diagnosis, treatment selection, and decision-making around salvage therapy. Imaging plays an essential role in all components of lung cancer management and has the potential to play a key role in AI applications. Artificial intelligence has demonstrated value in prognostic biomarker discovery in lung cancer diagnosis, treatment, and response assessment, putting it at the forefront of the next phase of personalized medicine. However, although exploratory studies demonstrate potential utility, there is a need for rigorous validation and standardization before AI can be utilized in clinical decision-making. In this review, we will provide a summary of the current literature implementing AI for outcome prediction in lung cancer. We will describe the anticipated impact of AI on the management of patients with lung cancer and discuss the challenges of clinical implementation of these techniques.

scholarly journals Autologous Versus Unrelated Donor Allogeneic Marrow Transplantation for Acute Lymphoblastic Leukemia

Blood ◽  
1997 ◽  
Vol 90 (8) ◽  
pp. 2962-2968 ◽  
Author(s):  
Daniel J. Weisdorf ◽  
Amy L. Billett ◽  
Peter Hannan ◽  
Jerome Ritz ◽  
Stephen E. Sallan ◽  
...  
Keyword(s):  
Acute Lymphoblastic Leukemia ◽  
Marrow Transplantation ◽  
Clinical Decision Making ◽  
Lymphoblastic Leukemia ◽  
Disease Free Survival ◽  
Clinical Decision ◽  
Unrelated Donor ◽  
University Of Minnesota ◽  
Allogeneic Marrow Transplantation ◽  
Related Donor

Abstract Bone marrow transplantation (BMT) can cure patients with high-risk or recurrent acute lymphoblastic leukemia (ALL). Those lacking a related donor can receive either autologous or histocompatible unrelated donor (URD) marrow. Autotransplantation may result in higher risk of relapse, whereas URD allografts, although associated with serious posttransplant toxicities, may reduce relapse risk. Six years (1987 to 1993) of consecutive autologous BMT (University of Minnesota, Dana Farber Cancer Institute; n = 214) were compared with URD transplants (National Marrow Donor Program; n = 337). Most transplants (70% autologous, 48% URD) were in early remission (first or second complete remission [CR1 or CR2]); 376 patients (75% autologous, 64% URD) were less than 18 years old. Autologous BMT led to significantly lower transplant-related mortality (TRM; relative risk [RR] 0.35; P = .001). URD transplantation offered greater protection against relapse (autologous RR 3.1; P = .001). Patients greater than 18 years old, women, and BMT recipients beyond CR2 had higher TRM, whereas adults, BMT recipients in CR2+, or BMT recipients during 1991 through 1993 had significantly more relapse. After 25 months median follow-up, 100 URD and 56 autologous recipients survive leukemia free. URD BMT in CR2 resulted in superior disease-free survival (DFS), especially for adult patients. Multivariate analysis showed superior DFS for children, men, and BMT during CR1 or 2. Autologous and URD BMT can extend survival for a minority of patients unlikely to be cured by chemotherapy, and the results with either technique are comparable. Greater toxicity and TRM after URD BMT are counterbalanced by better protection against relapse. Prospective studies addressing additional clinical variables are needed to guide clinical decision making about transplant choices for patients with ALL.

scholarly journals Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling

BJR|Open ◽  
2019 ◽  
Vol 1 (1) ◽  
pp. 20190021 ◽  
Author(s):  
Yi Luo ◽  
Huan-Hsin Tseng ◽  
Sunan Cui ◽  
Lise Wei ◽  
Randall K. Ten Haken ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Decision Making ◽  
Radiation Treatment ◽  
Clinical Decision ◽  
Black Box ◽  
Prediction Performance ◽  
Learning Approaches ◽  
Treatment Plans ◽  
The Relationship ◽  
Review Current

Radiation outcomes prediction (ROP) plays an important role in personalized prescription and adaptive radiotherapy. A clinical decision may not only depend on an accurate radiation outcomes’ prediction, but also needs to be made based on an informed understanding of the relationship among patients’ characteristics, radiation response and treatment plans. As more patients’ biophysical information become available, machine learning (ML) techniques will have a great potential for improving ROP. Creating explainable ML methods is an ultimate task for clinical practice but remains a challenging one. Towards complete explainability, the interpretability of ML approaches needs to be first explored. Hence, this review focuses on the application of ML techniques for clinical adoption in radiation oncology by balancing accuracy with interpretability of the predictive model of interest. An ML algorithm can be generally classified into an interpretable (IP) or non-interpretable (NIP) (“black box”) technique. While the former may provide a clearer explanation to aid clinical decision-making, its prediction performance is generally outperformed by the latter. Therefore, great efforts and resources have been dedicated towards balancing the accuracy and the interpretability of ML approaches in ROP, but more still needs to be done. In this review, current progress to increase the accuracy for IP ML approaches is introduced, and major trends to improve the interpretability and alleviate the “black box” stigma of ML in radiation outcomes modeling are summarized. Efforts to integrate IP and NIP ML approaches to produce predictive models with higher accuracy and interpretability for ROP are also discussed.

Sign in / Sign up

Export Citation Format

Share Document