A Systematic Review of the Applications of Deep Learning for the Interpretation of Positron Emission Tomography Images of Patients with Lymphoma DOI Open Access
Theofilos Kanavos, Effrosyni Birbas, Theodoros P. Zanos

et al.

Cancers, Journal Year: 2024, Volume and Issue: 17(1), P. 69 - 69

Published: Dec. 29, 2024

Background: Positron emission tomography (PET) is a valuable tool for the assessment of lymphoma, while artificial intelligence (AI) holds promise as reliable resource analysis medical images. In this context, we systematically reviewed applications deep learning (DL) interpretation lymphoma PET Methods: We searched PubMed until 11 September 2024 studies developing DL models evaluation images patients with lymphoma. The risk bias and applicability concerns were assessed using prediction model (PROBAST). articles included categorized presented based on task performed by proposed models. Our study was registered international prospective register systematic reviews, PROSPERO, CRD42024600026. Results: From 71 papers initially retrieved, 21 total 9402 participants ultimately in our review. achieved promising performance diverse tasks, namely, detection histological classification lesions, differential diagnosis from other conditions, quantification metabolic tumor volume, treatment response survival areas under curve, F1-scores, R2 values up to 0.963, 87.49%, 0.94, respectively. Discussion: primary limitations several small number absence external validation. conclusion, can reliably be aided models, which are not designed replace physicians but assist them managing large volumes scans through rapid accurate calculations, alleviate their workload, provide decision support tools precise care improved outcomes.

Language: Английский

Mapping the landscape and research trend of imaging diagnosis in lymphoma: a bibliometric analysis from 1976 to 2024 DOI Creative Commons
Ma Yi

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 29, 2025

Background Over the past five decades, extensive research has been conducted on lymphoma imaging diagnostics; however, no bibliometric analysis performed in this area. Therefore, we undertook a to clarify progress and current state of field. Methods We search Web Science Core Collection database for articles related diagnosis lymphoma, focusing exclusively English-language publications up June 20, 2024. analyzed visualized various aspects, including publication trends, journals, co-authorship networks, countries, institutions, keywords. To examine trends field, utilized tools such as VOSviewer, CiteSpace, R4.3.3. Results From 1976 2024, total 10,410 were produced topic, with 2021 marking peak numbers. The most significant contributions area found fields Radiology , Nuclear Medicine & Medical Imaging Oncology Hematology . United States, China, Japan leading contributors. Zucca Emanuele ranked first among authors, followed closely by Meignan Michel. In terms Assistance Publique Hôpitaux de Paris was prominent. frequently used keywords included positron emission tomography, computed non-Hodgkin’s lymphoma. Conclusion This study presented diagnosis, highlight showcasing influential studies, collaborative networks. identified key field provide insights future directions.

Language: Английский

Citations

0
Utilizing Nanomaterials in Microfluidic Devices for Disease Detection and Treatment DOI Creative Commons
Zhenyu Tian, Yatian Fu, Zhaolong Dang

et al.

Nanomaterials, Journal Year: 2025, Volume and Issue: 15(6), P. 434 - 434

Published: March 12, 2025

Microfluidic technology has gained widespread application in the field of biomedical research due to its exceptional sensitivity and high specificity. Particularly when combined with nanomaterials, synergy between two significantly advanced fields such as precision medicine, drug delivery, disease detection, treatment. This article aims provide an overview latest achievements microfluidic nanomaterials detection It delves into applications detecting blood parameters, cardiovascular markers, neurological tumor markers. Special emphasis is placed on their roles treatment, including models vessels, blood–brain barrier, lung chips, tumors. The development emerging medical technologies, particularly skin interactive devices imaging, also introduced. Additionally, challenges future prospects current clinical are discussed. In summary, play indispensable role With continuous advancement technology, will become even more profound extensive.

Language: Английский

Citations

0
Integrating AI Into PET/CT and PET/MRI DOI

R. T. Subhalakshmi,

M. Nivaashini,

Gowrishankar Ganesh

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 311 - 332

Published: Feb. 28, 2025

Positron emission tomography combined with artificial intelligence is becoming a powerful tool for drug discovery. By analyzing PET imaging data AI algorithms, researchers can find new targets, improve treatment plans, and better understand diseases. PET/CT leading cancer method used in clinical practice, while combining MRI's anatomical PET's functional offers exciting research opportunities. PET/MRI applications cardiology, neurology, oncology, inflammation are also expanding. Advances like Total-Body could revolutionize therapeutic imaging, providing deeper insights into human physiology Integrating AI, machine learning, deep learning imaging—from image capture to interpretation—has further improved hybrid techniques PET/MRI, enhancing their diagnostic capabilities.

Language: Английский

Citations

0
A Systematic Review of the Applications of Deep Learning for the Interpretation of Positron Emission Tomography Images of Patients with Lymphoma DOI Open Access
Theofilos Kanavos, Effrosyni Birbas, Theodoros P. Zanos

et al.

Cancers, Journal Year: 2024, Volume and Issue: 17(1), P. 69 - 69

Published: Dec. 29, 2024

Background: Positron emission tomography (PET) is a valuable tool for the assessment of lymphoma, while artificial intelligence (AI) holds promise as reliable resource analysis medical images. In this context, we systematically reviewed applications deep learning (DL) interpretation lymphoma PET Methods: We searched PubMed until 11 September 2024 studies developing DL models evaluation images patients with lymphoma. The risk bias and applicability concerns were assessed using prediction model (PROBAST). articles included categorized presented based on task performed by proposed models. Our study was registered international prospective register systematic reviews, PROSPERO, CRD42024600026. Results: From 71 papers initially retrieved, 21 total 9402 participants ultimately in our review. achieved promising performance diverse tasks, namely, detection histological classification lesions, differential diagnosis from other conditions, quantification metabolic tumor volume, treatment response survival areas under curve, F1-scores, R2 values up to 0.963, 87.49%, 0.94, respectively. Discussion: primary limitations several small number absence external validation. conclusion, can reliably be aided models, which are not designed replace physicians but assist them managing large volumes scans through rapid accurate calculations, alleviate their workload, provide decision support tools precise care improved outcomes.

Language: Английский

Citations

0