Molecular imaging in lymphoma beyond 18F-FDG-PET: understanding the biology and its implications for diagnostics and therapy

Kahle, X U; Jesus, Filipe Montes de; Glaudemans, Andor W.J.M.; Hooge, Marjolijn N. Lub-de; Jorritsma-Smit, Annelies; Plattel, Wouter J.; Meerten, Tom van; Diepstra, Arjan; Berg, Anke van den; Kwee, Thomas C.; Noordzij, Walter; Vries, Elisabeth G.E. de; Nijland, Marcel

doi:10.1016/s2352-3026(20)30065-x

Cited by 14 publications

(8 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is used to extract the particular feature from the images. The accuracy is measured as, 𝑎𝑐𝑐 = 𝑇 𝑝 +𝑇 𝑛 𝑡𝑜𝑡𝑎𝑙 𝑛𝑜.𝑜𝑓 𝑠𝑎𝑚𝑝𝑙𝑒𝑠 (11) where 𝑇 𝑝 and 𝑇 𝑛 represents true positives and negatives of the samples , 𝐹 𝑝 and 𝐹 𝑛 represents false positives and negatives of the samples. The performance analysis is shown below table . There is some limitations in the classification process SVM classifies NSCLC and SCLC from normal but it didn't classifies the mixed combination of lung cancer i.e., the both NSCLC and SCLC found in some rare cases and NSCLC has several types of cancer such as squamous cell carcinoma, adenocarcinoma and large cell carcinoma they cannot be identified.…”

Section: Performance Analysismentioning

confidence: 99%

“…Molecular imaging (MI) is a sort of medical imaging that captures the precise images about the changes occurring at the molecular and cellular levels within the body. It is normally used to progress the prognosis and cure of lung cancer [11]. The importance of molecular imaging (MI) is initial evaluation to confirm the prognosis of lung cancer is quickly growing due to its higher detection performance relative to anatomic imaging.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Lung Cancer with Deep Learning Res-U-Net and Molecular Imaging

Malligeswari

Kavya²

2023

Preprint

View full text Add to dashboard Cite

Lung cancer is the prevalent malignancy, despite the great breakthroughs in detection and prevention and it remains the important cause of death. In recent days, artificial intelligence has exploded in all fields of science. The use of artificial intelligence in medical science has improved in accuracy and precision of predicting this infestation in the initial stages. In the proposed study a deep learning and molecular imaging is used for classifying two different types of lung cancer. The PET/CT (positron emission tomography/computed tomography) employing an injection 18F-FDG has developed as a useful tool in therapeutic oncologic imaging for both metabolic and anatomic analysis. The proposed model uses Res-U-Net to classify small cell lung cancer (SCLC) and non-small cell lung cancer (NSCLC) from normal by using 18F-FDG PET/CT images from the radiogenmics dataset. This datasets are pre-processed by Gaussian smoothing to reduce the noise from the PET/CT images. Finally, the classification result is obtained through the support vector machine (SVM) classifier which proves the efficiency of the proposed technique. The outcome of the proposed technique yields best and accurate results and it yields the classification accuracy rate of 96.45%for lung cancer into NSCLC and SCLC.

show abstract

Section: Performance Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of Lung Cancer with Deep Learning Res-U-Net and Molecular Imaging

Malligeswari

Kavya²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The radiometals are loaded to the vector using either a random or site-specific conjugation [113]. Long half-life isotopes, such as cuprum-64 ( 64 Cu, half-life 12 h) or zirconium-89 ( 89 Zr, half-life 78 h), belong among the most commonly used radionuclides for this purpose [114]. In the context of NHL, immuno-PET was studied using antibodies targeting CD20 (e.g., rituximab, obinutuzumab), CD38 (daratumumab), CD30 (SGN-30), and others.…”

Section: Immuno-petmentioning

confidence: 99%

Targeted Drug Delivery and Theranostic Strategies in Malignant Lymphomas

Etrych

Braunová

Zogala

et al. 2022

Cancers

View full text Add to dashboard Cite

Malignant lymphomas represent the most common type of hematologic malignancies. The first clinically approved TDD modalities in lymphoma patients were anti-CD20 radioimmunoconjugates (RIT) 131I-tositumomab and 90Y-ibritumomab-tiuxetan. The later clinical success of the first approved antibody–drug conjugate (ADC) for the treatment of lymphomas, anti-CD30 brentuximab vedotin, paved the path for the preclinical development and clinical testing of several other ADCs, including polatuzumab vedotin and loncastuximab tesirine. Other modalities of TDD are based on new formulations of “old” cytostatic agents and their passive trapping in the lymphoma tissue by means of the enhanced permeability and retention (EPR) effect. Currently, the diagnostic and restaging procedures in aggressive lymphomas are based on nuclear imaging, namely PET. A theranostic approach that combines diagnostic or restaging lymphoma imaging with targeted treatment represents an appealing innovative strategy in personalized medicine. The future of theranostics will require not only the capability to provide suitable disease-specific molecular probes but also expertise on big data processing and evaluation. Here, we review the concept of targeted drug delivery in malignant lymphomas from RIT and ADC to a wide array of passively and actively targeted nano-sized investigational agents. We also discuss the future of molecular imaging with special focus on monoclonal antibody-based and monoclonal antibody-derived theranostic strategies.

show abstract

“…Kahle et al [60] published a review on the contribution of molecular imaging to the understanding of the biology of lymphoma. Adding immunohistochemistry, proteomics, or imaging mass spectrometry to NGS and GEP data enables a multi-dimensional analysis of tumors related to the TME.…”

Section: Clinical Impact and Future Perspectives Of Gene-expression P...mentioning

confidence: 99%

Biological and Clinical Implications of Gene-Expression Profiling in Diffuse Large B-Cell Lymphoma: A Proposal for a Targeted BLYM-777 Consortium Panel as Part of a Multilayered Analytical Approach

Groot

Groen

Berg

et al. 2022

Cancers

Self Cite

View full text Add to dashboard Cite

Gene-expression profiling (GEP) is used to study the molecular biology of lymphomas. Here, advancing insights from GEP studies in diffuse large B-cell lymphoma (DLBCL) lymphomagenesis are discussed. GEP studies elucidated subtypes based on cell-of-origin principles and profoundly changed the biological understanding of DLBCL with clinical relevance. Studies integrating GEP and next-generation DNA sequencing defined different molecular subtypes of DLBCL entities originating at specific anatomical localizations. With the emergence of high-throughput technologies, the tumor microenvironment (TME) has been recognized as a critical component in DLBCL pathogenesis. TME studies have characterized so-called “lymphoma microenvironments” and “ecotypes”. Despite gained insights, unexplained chemo-refractoriness in DLBCL remains. To further elucidate the complex biology of DLBCL, we propose a novel targeted GEP consortium panel, called BLYM-777. This knowledge-based biology-driven panel includes probes for 777 genes, covering many aspects regarding B-cell lymphomagenesis (f.e., MYC signature, TME, immune surveillance and resistance to CAR T-cell therapy). Regarding lymphomagenesis, upcoming DLBCL studies need to incorporate genomic and transcriptomic approaches with proteomic methods and correlate these multi-omics data with patient characteristics of well-defined and homogeneous cohorts. This multilayered methodology potentially enhances diagnostic classification of DLBCL subtypes, prognostication, and the development of novel targeted therapeutic strategies.

show abstract

Molecular imaging in lymphoma beyond 18F-FDG-PET: understanding the biology and its implications for diagnostics and therapy

Cited by 14 publications

References 71 publications

Classification of Lung Cancer with Deep Learning Res-U-Net and Molecular Imaging

Classification of Lung Cancer with Deep Learning Res-U-Net and Molecular Imaging

Targeted Drug Delivery and Theranostic Strategies in Malignant Lymphomas

Biological and Clinical Implications of Gene-Expression Profiling in Diffuse Large B-Cell Lymphoma: A Proposal for a Targeted BLYM-777 Consortium Panel as Part of a Multilayered Analytical Approach

Contact Info

Product

Resources

About