Theranostics and artificial intelligence: new frontiers in personalized medicine

Theranostics, Journal Year: 2024, Volume and Issue: 14(6), P. 2367 - 2378

Published: Jan. 1, 2024

The field of theranostics is rapidly advancing, driven by the goals enhancing patient care. Recent breakthroughs in artificial intelligence (AI) and its innovative theranostic applications have marked a critical step forward nuclear medicine, leading to significant paradigm shift precision oncology. For instance, AI-assisted tumor characterization, including automated image interpretation, segmentation, feature identification, prediction high-risk lesions, improves diagnostic processes, offering precise detailed evaluation. With comprehensive assessment tailored an individual's unique clinical profile, AI algorithms promise enhance risk classification, thereby benefiting alignment needs with most appropriate treatment plans. By uncovering potential factors unseeable human eye, such as intrinsic variations radiosensitivity or molecular software has revolutionize response heterogeneity. accurate efficient dosimetry calculations, technology offers advantages providing customized phantoms streamlining complex mathematical algorithms, making personalized feasible accessible busy settings. tools be leveraged predict mitigate treatment-related adverse events, allowing early interventions. Additionally, generative can utilized find new targets for developing novel radiopharmaceuticals facilitate drug discovery. However, while there immense notable interest role theranostics, these technologies do not lack limitations challenges. There remains still much explored understood. In this study, we investigate current seek broaden horizons future research innovation.

Language: Английский

---

Development and validation of fully automated robust deep learning models for multi-organ segmentation from whole-body CT images

Physica Medica, Journal Year: 2025, Volume and Issue: 130, P. 104911 - 104911

Published: Feb. 1, 2025

This study aimed to develop a deep-learning framework generate multi-organ masks from CT images in adult and pediatric patients. A dataset consisting of 4082 ground-truth manual segmentation various databases, including 300 cases, were collected. In strategy#1, the provided by public databases split into training (90%) testing (10% each database named subset #1) cohort. The set was used train multiple nnU-Net networks five-fold cross-validation (CV) for 26 separate organs. next step, trained models strategy #1 missing organs entire dataset. generated data then model CV (strategy#2). Models' performance evaluated terms Dice coefficient (DSC) other well-established image metrics. lowest DSC strategy#1 0.804 ± 0.094 adrenal glands while average > 0.90 achieved 17/26 strategy#2 (0.833 0.177) obtained pancreas, whereas 13/19 For all mutual included #2, our outperformed TotalSegmentator both strategies. addition, on #3. Our with significant variability different producing acceptable results making it well-suited implementation clinical setting.

Language: Английский

---

Optimizing Cancer Treatment: Exploring the Role of AI in Radioimmunotherapy

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 397 - 397

Published: Feb. 6, 2025

Radioimmunotherapy (RIT) is a novel cancer treatment that combines radiotherapy and immunotherapy to precisely target tumor antigens using monoclonal antibodies conjugated with radioactive isotopes. This approach offers personalized, systemic, durable treatment, making it effective in cancers resistant conventional therapies. Advances artificial intelligence (AI) present opportunities enhance RIT by improving precision, efficiency, personalization. AI plays critical role patient selection, planning, dosimetry, response assessment, while also contributing drug design classification. review explores the integration of into RIT, emphasizing its potential optimize entire process advance personalized care.

Language: Английский

---

Deep learning-based segmentation of ultra-low-dose CT images using an optimized nnU-Net model

La radiologia medica, Journal Year: 2025, Volume and Issue: unknown

Published: March 18, 2025

Abstract Purpose Low-dose CT protocols are widely used for emergency imaging, follow-ups, and attenuation correction in hybrid PET/CT SPECT/CT imaging. However, low-dose images often suffer from reduced quality depending on acquisition patient parameters. Deep learning (DL)-based organ segmentation models typically trained high-quality images, with limited dedicated noisy images. This study aimed to develop a DL pipeline ultra-low-dose Materials methods 274 raw datasets were reconstructed using Siemens ReconCT software ADMIRE iterative algorithm, generating full-dose (FD-CT) simulated (LD-CT) at 1%, 2%, 5%, 10% of the original tube current. Existing FD-nnU-Net segmented 22 organs FD-CT serving as reference masks training new LD-nnU-Net LD-CT Three bony tissue (6 organs), soft-tissue (15 body contour segmentation. The compared standard reference. External actual also compared. Results performance declined radiation dose, especially below (5 mAs). achieved average Dice scores 0.937 ± 0.049 (bony tissues), 0.905 0.117 (soft-tissues), 0.984 0.023 (body contour). LD outperformed FD external datasets. Conclusion Conventional performed poorly Dedicated demonstrated superior across cross-validation evaluations, enabling accurate available our GitHub page.

Language: Английский

---

AI in SPECT Imaging: Opportunities and Challenges

Seminars in Nuclear Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

---

The role of biomarkers and dosimetry parameters in overall and progression free survival prediction for patients treated with personalized 90Y glass microspheres SIRT: a preliminary machine learning study

European Journal of Nuclear Medicine and Molecular Imaging, Journal Year: 2024, Volume and Issue: 51(13), P. 4111 - 4126

Published: July 9, 2024

Overall Survival (OS) and Progression-Free (PFS) analyses are crucial metrics for evaluating the efficacy impact of treatment. This study evaluated role clinical biomarkers dosimetry parameters on survival outcomes patients undergoing

Language: Английский

---

Future Perspectives of Artificial Intelligence in Bone Marrow Dosimetry and Individualized Radioligand Therapy

Seminars in Nuclear Medicine, Journal Year: 2024, Volume and Issue: 54(4), P. 460 - 469

Published: July 1, 2024

Radioligand therapy is an emerging and effective treatment option for various types of malignancies, but may be intricately linked to hematological side effects such as anemia, lymphopenia or thrombocytopenia. The safety efficacy novel theranostic agents, targeting increasingly complex targets, can well served by comprehensive dosimetry. However, optimization in patient management selection based on risk-factors predicting adverse events built upon reliable dose-response relations still open demand. In this context, artificial intelligence methods, especially machine learning deep algorithms, play a crucial role. This review provides overview upcoming opportunities integrating methods into the field dosimetry nuclear medicine improving bone marrow blood accuracy, enabling early identification potential risk-factors, allowing adaptive planning. It will further exemplify inspirational success stories from neighboring disciplines that translated practices, provide conceptual suggestions future directions. future, we expect intelligence-assisted (predictive) combined with clinical parameters pave way towards truly personalized theranostics radioligand therapy.

Language: Английский

---

Potential of Radiomics, Dosiomics, and Dose Volume Histograms for Tumor Response Prediction in Hepatocellular Carcinoma following 90Y-SIRT

Molecular Imaging and Biology, Journal Year: 2025, Volume and Issue: unknown

Published: March 10, 2025

Abstract Purpose We evaluate the role of radiomics, dosiomics, and dose-volume constraints (DVCs) in predicting response hepatocellular carcinoma to selective internal radiation therapy with 90 Y glass microspheres. Methods 99m Tc-macroagregated albumin ( Tc-MAA) SPECT/CT images 17 patients were included. Tumor responses at three months evaluated using modified evaluation criteria solid tumors categorized as responders or non-responders. Dosimetry was conducted local deposition method (Dose) biologically effective dosimetry. A total 264 DVCs, 321 radiomic features, dosiomic features extracted from tumor, normal perfused liver (NPL), whole (WNL). Five different feature selection methods combination eight machine learning algorithms employed. Model performance area under AUC, accuracy, sensitivity, specificity. Results No statistically significant differences observed between neither dose metrics nor radiomicas dosiomics non-responder groups. Y-dosiomics models any given set inputs outperformed other models. This also true for Y-radiomics SPECT SPECT-clinical achieving an specificity 1. Among MAA-dosiomic models, two showed AUC ≥ 0.91. While MAA-dose volume histogram (DVH)-based less promising, Y-DVH-based strong (AUC 0.91) when considered independently clinical features. Conclusion study demonstrated potential Tc-MAA SPECT-derived dosimetry establishing predictive tumor response.

Language: Английский

---

Dosimetry Methods for Radiopharmaceuticals

Royal Society of Chemistry eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 159 - 201

Published: June 4, 2025

Radiopharmaceutical therapy (RPT) is the application of radionuclides tagged with certain linker molecules and ligands to target specific cancer cells for their selective killing. The targeted nature RPT has brought a paradigm shift treatment approaches various cancers. systemic route harmful effects associated ionizing necessitate estimation absorbed dose per gram tissue radiopharmaceutical science this called radiation dosimetry. standard practice includes using an empirical all patients particular type. However, mode cannot be equally beneficial patients, given individual genetic variability each patient. This need precision medicine along development novel therapeutic potential resulted in evolution dosimetry methods, make even more efficient safe.

Language: Английский

---

Tracer-Separator

Clinical Nuclear Medicine, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

Introduction Multiplexed PET imaging revolutionized clinical decision-making by simultaneously capturing various radiotracer data in a single scan, enhancing diagnostic accuracy and patient comfort. Through transformer-based deep learning, this study underscores the potential of advanced techniques to streamline diagnosis improve outcomes. Patients Methods The research cohort consisted 120 patients spanning from cognitively unimpaired individuals those with mild cognitive impairment, dementia, other mental disorders. underwent assessments, including 3D T1-weighted MRI, amyloid scans using either 18 F-florbetapir (FBP) or F-flutemetamol (FMM), F-FDG PET. Summed images FMM/FBP FDG were used as proxy for simultaneous scanning 2 different tracers. A SwinUNETR model, convolution-free transformer architecture, was trained image translation. model mean square error loss function 5-fold cross-validation. Visual evaluation involved assessing similarity status, comparing synthesized actual ones. Statistical analysis conducted determine significance differences. Results inspection revealed remarkable reference across statuses. centiloid bias healthy control subjects FBP tracers is 15.70 ± 29.78, 0.35 33.68, 6.52 25.19, respectively, whereas FMM, it −6.85 25.02, 4.23 23.78, 5.71 21.72, respectively. Clinical readers further confirmed model's efficiency, 97 FBP/FMM 63 (from subjects) found similar ground truth diagnoses (rank 3), 3 15 considered nonsimilar 1). Promising sensitivity, specificity, achieved status assessment based on images, an average sensitivity 95 2.5, specificity 72.5 12.5, 87.5 2.5. Error distribution analyses provided valuable insights into levels brain regions, most falling between −0.1 +0.2 SUV ratio. Correlation demonstrated strong associations particularly FMM (FBP: Y = 0.72X + 20.95, R 0.54; FMM: 0.65X 22.77, 0.77). Conclusions This novel SwinUNETR, synthesizing realistic summation mimicking dual-tracer imaging.

Language: Английский

---