PET-Derived Radiomics and Artificial Intelligence in Breast Cancer: A Systematic Review

FAP-Targeted SPECT/CT and PET/CT Imaging for Breast Cancer Patients

ABSTRACT

Breast cancer presents a significant global health challenge, necessitating continued innovation in diagnostic and therapeutic approaches. Recent advances have led to the identification of cancer-associated fibroblasts, which are highly prevalent in breast cancers and express fibroblast activation proteins (FAPs), as critical targets. FAP-specific radiotracers, when used with PET/CT and SPECT/CT, have significant potential for improving early breast cancer detection, staging, treatment response monitoring, and therapeutic intervention. This review provides insight into FAP-targeted molecular imaging, exploring advanced techniques for protein status assessment, development of early-phase targeted therapies, and other emerging applications. The advent of FAP-targeted imaging stands to significantly enhance personalized oncologic care, leading to improved breast cancer management and overall patient outcomes.

Breast density prediction model in digital versus synthetic mammograms from a radiomic point of view: A retrospective study

PURPOSE

In this retrospective study, we develop radiomics prediction models from synthetic mammograms(SM) and digital mammograms(DM) images to identify which imaging modality has the most predictive power when employed for prediction of breast density.

METHODS

Patients aged between 45 and 74 years, were included in the study. For each, a SM in standard resolution (ST) and High Resolution (HR) were obtained, and a 150 x 150 pixels square area was defined on the images to be used for texture analysis of the breast parenchyma. A semi-automated placing strategy was used to reduce user reliance on the segmentation location. S-IBEX software was employed to extract radiomics features. Feature robustness analysis was also done to ensure model reproducibility. The Least Absolute Shrinkage and Selection Operator(LASSO) logistic regression model was trained to predict dichotomized breast density according to BIRADS classification model performance was assessed through receiver operating curves (ROC) for DM, HR, and ST.

RESULTS

We extracted 123 features from the 10 ROIs of 96 patient. After robustness analysis, the most predictive features were employed to build logistic regression-based models. The average performance of the models were 0.74, 0.67, and 0.64 on DM, HR, and ST, respectively, suggesting that DM maintains the highest informative content on breast density.

CONCLUSIONS

This study investigated how well radiomics models trained on various imaging modalities predicted breast density. Our results may be pertinent to the debate over screening mammography technique optimization using quantitative measures based on radiomics features.

18F-FDG PET/CT radiomic analysis and artificial intelligence to predict pathological complete response after neoadjuvant chemotherapy in breast cancer patients

PURPOSE

Build machine learning (ML) models able to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients based on conventional and radiomic signatures extracted from baseline [18F]FDG PET/CT.

MATERIAL AND METHODS

Primary tumor and the most significant lymph node metastasis were manually segmented in baseline [18F]FDG PET/CT of 52 newly diagnosed BC patients. Clinical parameters, NAC and conventional semiquantitative PET parameters were collected. The standard of reference considered was surgical pCR after NAC (ypT0;ypN0). Eight-hundred-fifty-four radiomic features (RFts) were extracted from both PET and CT datasets, according to IBSI; robust RFTs were selected. The cohort was split in training (70%) and validation (30%) sets. Four ML Models (Clinical Model, CT Model, PET Model_T and PET Model_T + N) each one with 3 learners (Random Forest (RF), Neural Network and Stochastic Gradient Descendent) were trained and tested using RFts and clinical signatures. PET Models were built considering robust RFTs extracted from either primary tumor alone (PET Model_T) or also including the reference lymph node (PET Model_T + N).

RESULTS

72 pathological uptakes (52 primary BC and 20 lymph node metastasis) at [18F]FDG PET/CT were segmented. pCR occurred in 44.2% cases. Twelve, 46 and 141 robust RFts were selected from CT Model, PET Model_T and PET Model_T + N, respectively. PET Models showed better performance than CT and Clinical Models. The best performances were obtained by the RF algorithm of the PET Model_T + N (AUC = 0.83;CA = 0.74;TP = 78%;TN = 72%).

CONCLUSION

ML models trained on PET/CT radiomic features extracted from primary BC and lymph node metastasis could concur in the prediction of pCR after NAC and improve BC management.

A systematic review of the role of artificial intelligence in automating computed tomography-based adaptive radiotherapy for head and neck cancer

Purpose

Adaptive radiotherapy (ART) may improve treatment quality by monitoring variations in patient anatomy and incorporating them into the treatment plan. This systematic review investigated the role of artificial intelligence (AI) in computed tomography (CT)-based ART for head and neck (H&N) cancer.

Methods

A comprehensive search of main electronic databases was conducted until April 2024. Titles and abstracts were reviewed to evaluate the compliance with inclusion criteria: CT-based imaging for photon ART of H&N patients and AI applications. 17 original retrospective studies with samples sizes ranging from 37 to 239 patients were included. The quality of the studies was evaluated with the Quality Assessment of Diagnostic Accuracy Studies-2 and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) tools. Key metrics were examined to evaluate the performances of the proposed AI-methods.

Results

Overall, the risk of bias was low. The average CLAIM score was 70%. A major finding was that generated synthetic CTs improved similarity metrics with planning CT compared to original cone-beam CTs, with average mean absolute error up to 39 HU and maximum improvement of 80%. Auto-segmentation provided an efficient and accurate option for organ-at-risk delineation, with average Dice similarity coefficient ranging from 80 to 87%. Finally, AI models could be trained using clinical and radiomic features to predict the effectiveness of ART with accuracy above 80%.

Conclusions

Automation of processes in ART for H&N cancer is very promising throughout the entire chain, from the generation of synthetic CTs and auto-segmentation to predict the effectiveness of ART.

Advancing precision and personalized breast cancer treatment through multi-omics technologies

Breast cancer is the most common malignant tumour in women, with more than 685,000 women dying of breast cancer each year. The heterogeneity of breast cancer complicates both treatment and diagnosis. Traditional methods based on histopathology and hormone receptor status are now no longer sufficient. Recently, advances in multi-omics techniques, including genomic, proteomic, and transcriptomic analyses, have deepened our understanding of breast cancer. Combining these approaches allows for precise molecular subtyping, which is essential for the detection of key mutations, protein interactions and gene expression patterns that are highly relevant to different therapeutic strategies. Genomic analyses have been effectively identifying key mutations in cancer. Meanwhile, proteomics and transcriptomics complement by identifying new therapeutic targets and elucidating gene expression dynamics. Integrating multi-omics and conventional diagnostics improves tumour characterisation and enables prognostic accuracy comparable to established standards and treatment response. Existing and emerging technologies enable real-time enhanced tumour follow-up and data analysis through liquid biopsy and artificial intelligence, respectively. Despite these clinical implementation challenges, multi-omics including clinical phenotyping offers significant potential for precision breast cancer treatment. This article describes recent advances in molecular subtyping and multi-omics technologies that are driving key innovations to optimise patient outcomes and further develop personalised medicine in the context of breast cancer care.

The impact of PET imaging on triple negative breast cancer: an updated evidence-based perspective

INTRODUCTION

Triple-negative breast cancer (TNBC) is a subtype of breast cancer characterized by the absence of estrogen, progesterone, and HER2 receptors. It predominantly affects younger women and is associated with a poor prognosis. This systematic review aims to evaluate the current role of positron emission tomography (PET) in the management of TNBC patients and to identify future research directions.

METHODS

We systematically searched the PubMed, Scopus, and Web of Science databases up to February 2024. A team of five researchers conducted data extraction and analysis. The quality of the selected studies was assessed using a specific evaluation form.

RESULTS

Twenty-eight studies involving 2870 TNBC patients were included in the review. Key clinical applications of PET in TNBC included predicting pathological complete response (pCR) in patients undergoing neoadjuvant chemotherapy (NAC), assessing the prognostic value of baseline PET, and initial disease staging. Two studies utilized PSMA-ligand agents, while the majority used [18F]FDG-based PET. Significant associations were found between baseline [18F]FDG uptake and molecular biomarkers such as PDL-1, androgen receptor, and Ki67. Baseline [18F]FDG PET led to the upstaging of patients from stage IIB to stage IV, influencing treatment decisions and survival outcomes. In the NAC setting, serial PET scans measuring changes in [18F]FDG uptake, indicated by maximum standardized uptake value (SUVmax), predicted pCR with varying cut-off values correlated with different response rates. Semiquantitative parameters such as metabolic tumor volume (MTV) and PET lung index were prognostic for metastatic disease.

CONCLUSIONS

In TNBC patients, [18F]FDG PET is essential for initial disease staging in both localized and metastatic settings. It is also useful for assessing treatment response to NAC. The ability of PET to correlate metabolic activity with molecular markers and predict treatment outcomes highlights its potential in TNBC management. Further prospective studies are needed to refine these clinical indications and establish its definitive role.

Unveiling the biological side of PET-derived biomarkers: a simulation-based approach applied to PDAC assessment

PURPOSE

Radiomics has revolutionized clinical research by enabling objective measurements of imaging-derived biomarkers. However, the true potential of radiomics necessitates a comprehensive understanding of the biological basis of extracted features to serve as a clinical decision support. In this work, we propose an end-to-end framework for the in silico simulation of [18F]FLT PET imaging process in Pancreatic Ductal Adenocarcinoma, accounting for the biological characterization of tissues (including perfusion and fibrosis) on tracer delivery. We thus establish a direct association between radiomics features and the underlying biological properties of tissues.

METHODS

We considered 4 immunohistochemically stained Whole Slide Images of pancreatic tissue of one healthy control and three patients with PDAC and/or precursor lesions. From marker-specific images, tissue-depending diffusivity properties were estimated and computational domains were built to simulate the [18F]FLT spatial-temporal uptake exploiting Partial Differential Equations and Finite Elements Method. Consequently, we simulated the imaging process obtaining surrogated PET images for the considered patients, and we performed image-derived features extraction from PET images to be mapped with biological properties via correlation estimation.

RESULTS

The framework captured the phenotypic differences and generated Time Activity Curves reflecting the underlying tissue composition. Image-derived biomarkers were ranked in view of their association with biological characteristics of the tissue, unveiling their molecular correlative. Moreover, we showed that the proposed pipeline could serve as a digital phantom to optimize the image acquisition for lesion detection.

CONCLUSIONS

This innovative framework holds the potential to enhance interpretability and reliability of radiomics, fostering the adoption in personalized nuclear medicine and patient care.

Using artificial intelligence based imaging to predict lymph node metastasis in non-small cell lung cancer: a systematic review and meta-analysis

Background

Lung cancer, especially non-small cell lung cancer (NSCLC), is one of the most-deadly malignancies worldwide. Lung cancer has a worse 5-year survival rate than many primary malignancies. Thus, the early detection and prognosis prediction of lung cancer are crucial. The early detection and prognosis prediction of lung cancer have improved with the widespread use of artificial intelligence (AI) technologies. This meta-analysis examined the accuracy and efficacy of AI-based models in predicting lymph node metastasis (LNM) in NSCLC patients using imaging data. Our findings could help clinicians predict patient prognosis and select alternative therapies.

Methods

We searched the PubMed, Web of Science, Cochrane Library, and Embase databases for relevant articles published up to January 31, 2024. Two reviewers individually evaluated all the retrieved articles to assess their eligibility for inclusion in the meta-analysis. The systematic assessment and meta-analysis comprised articles that satisfied the inclusion criteria (e.g., randomized or non-randomized trials, and observational studies) and exclusion criteria (e.g., articles not published in English), and provided data for the quantitative synthesis. The quality of the included articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The pooled sensitivity, specificity, and area under the curve (AUC) were used to evaluate the ability of AI-based imaging models to predict LNM in NSCLC patients. Sources of heterogeneity were investigated using meta-regression. Covariates, including country, sample size, imaging modality, model validation technique, and model algorithm, were examined in the subgroup analysis.

Results

The final meta-analysis comprised 11 retrospective studies of 6,088 NSCLC patients, of whom 1,483 had LNM. The pooled sensitivity, specificity, and AUC of the AI-based imaging model for predicting LNM in NSCLC patients were 0.87 [95% confidence interval (CI): 0.80-0.91], 0.85 (95% CI: 0.78-0.89), and 0.92 (95% CI: 0.90-0.94). Based on the QUADAS-2 results, a risk of bias was detected in the patient selection and diagnostic tests of the included articles. However, the quality of the included articles was generally acceptable. The pooled sensitivity and specificity were heterogeneous (I2>75%). The meta-regression and subgroup analyses showed that imaging modality [computed tomography (CT) or positron emission tomography (PET)/CT], and the neural network method model design significantly affected heterogeneity of this study. Models employing sample size data from a single center and the least absolute shrinkage and selection operator (LASSO) method had greater sensitivity than other techniques. Using the Deek' s funnel plot, no publishing bias was found. The results of the sensitivity analysis showed that deleting each article one by one did not change the findings.

Conclusions

Imaging data models based on AI algorithms have good diagnostic accuracy in predicting LNM in patients with NSCLC and could be applied in clinical settings.

Radiomics in breast cancer: Current advances and future directions

Breast cancer is a common disease that causes great health concerns to women worldwide. During the diagnosis and treatment of breast cancer, medical imaging plays an essential role, but its interpretation relies on radiologists or clinical doctors. Radiomics can extract high-throughput quantitative imaging features from images of various modalities via traditional machine learning or deep learning methods following a series of standard processes. Hopefully, radiomic models may aid various processes in clinical practice. In this review, we summarize the current utilization of radiomics for predicting clinicopathological indices and clinical outcomes. We also focus on radio-multi-omics studies that bridge the gap between phenotypic and microscopic scale information. Acknowledging the deficiencies that currently hinder the clinical adoption of radiomic models, we discuss the underlying causes of this situation and propose future directions for advancing radiomics in breast cancer research.

Performance evaluation of ML models for preoperative prediction of HER2-low BC based on CE-CBBCT radiomic features: A prospective study

To explore the value of machine learning (ML) models based on contrast-enhanced cone-beam breast computed tomography (CE-CBBCT) radiomics features for the preoperative prediction of human epidermal growth factor receptor 2 (HER2)-low expression breast cancer (BC). Fifty-six patients with HER2-negative invasive BC who underwent preoperative CE-CBBCT were prospectively analyzed. Patients were randomly divided into training and validation cohorts at approximately 7:3. A total of 1046 quantitative radiomic features were extracted from CE-CBBCT images and normalized using z-scores. The Pearson correlation coefficient and recursive feature elimination were used to identify the optimal features. Six ML models were constructed based on the selected features: linear discriminant analysis (LDA), random forest (RF), support vector machine (SVM), logistic regression (LR), AdaBoost (AB), and decision tree (DT). To evaluate the performance of these models, receiver operating characteristic curves and area under the curve (AUC) were used. Seven features were selected as the optimal features for constructing the ML models. In the training cohort, the AUC values for SVM, LDA, RF, LR, AB, and DT were 0.984, 0.981, 1.000, 0.970, 1.000, and 1.000, respectively. In the validation cohort, the AUC values for the SVM, LDA, RF, LR, AB, and DT were 0.859, 0.880, 0.781, 0.880, 0.750, and 0.713, respectively. Among all ML models, the LDA and LR models demonstrated the best performance. The DeLong test showed that there were no significant differences among the receiver operating characteristic curves in all ML models in the training cohort (P > .05); however, in the validation cohort, the DeLong test showed that the differences between the AUCs of LDA and RF, AB, and DT were statistically significant (P = .037, .003, .046). The AUCs of LR and RF, AB, and DT were statistically significant (P = .023, .005, .030). Nevertheless, no statistically significant differences were observed when compared to the other ML models. ML models based on CE-CBBCT radiomics features achieved excellent performance in the preoperative prediction of HER2-low BC and could potentially serve as an effective tool to assist in precise and personalized targeted therapy.

Prediction of the axillary lymph-node metastatic burden of breast cancer by 18F-FDG PET/CT-based radiomics

BACKGROUND

The axillary lymph-node metastatic burden is closely associated with treatment decisions and prognosis in breast cancer patients. This study aimed to explore the value of 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT)-based radiomics in combination with ultrasound and clinical pathological features for predicting axillary lymph-node metastatic burden in breast cancer.

METHODS

A retrospective analysis was conducted and involved 124 patients with pathologically confirmed early-stage breast cancer who had undergone 18F-FDG PET/CT examination. The ultrasound, PET/CT, and clinical pathological features of all patients were analysed, and radiomic features from PET images were extracted to establish a multi-parameter predictive model.

RESULTS

The ultrasound lymph-node positivity rate and PET lymph-node positivity rate in the high nodal burden group were significantly higher than those in the low nodal burden group (χ2 = 19.867, p < 0.001; χ2 = 33.025, p < 0.001). There was a statistically significant difference in the PET-based radiomics score (RS) for predicting axillary lymph-node burden between the high and low lymph-node burden groups. (-1.04 ± 0.41 vs. -1.47 ± 0.41, t = -4.775, p < 0.001). The ultrasound lymph-node positivity (US_LNM) (odds ratio [OR] = 3.264, 95% confidence interval [CI] = 1.022-10.423), PET lymph-node positivity (PET_LNM) (OR = 14.242, 95% CI = 2.960-68.524), and RS (OR = 5.244, 95% CI = 3.16-20.896) are all independent factors associated with high lymph-node burden (p < 0.05). The area under the curve (AUC) of the multi-parameter (MultiP) model was 0.895, which was superior to those of US_LNM, PET_LNM, and RS models (AUC = 0.703, 0.814, 0.773, respectively), with statistically significant differences (Z = 2.888, 3.208, 3.804, respectively; p = 0.004, 0.002, < 0.001, respectively). Decision curve analysis indicated that the MultiP model provided a higher net benefit for all patients.

CONCLUSION

A MultiP model based on PET-based radiomics was able to effectively predict axillary lymph-node metastatic burden in breast cancer.

TRIAL REGISTRATION

This study was registered with ClinicalTrials.gov (registration number: NCT05826197) on May 7, 2023.

A real-time augmented reality system integrated with artificial intelligence for skin tumor surgery: experimental study and case series

BACKGROUND

Skin tumors affect many people worldwide, and surgery is the first treatment choice. Achieving precise preoperative planning and navigation of intraoperative sampling remains a problem and is excessively reliant on the experience of surgeons, especially for Mohs surgery for malignant tumors.

MATERIALS AND METHODS

To achieve precise preoperative planning and navigation of intraoperative sampling, we developed a real-time augmented reality (AR) surgical system integrated with artificial intelligence (AI) to enhance three functions: AI-assisted tumor boundary segmentation, surgical margin design, and navigation in intraoperative tissue sampling. Non-randomized controlled trials were conducted on manikin, tumor-simulated rabbits, and human volunteers in Hunan Engineering Research Center of Skin Health and Disease Laboratory to evaluate the surgical system.

RESULTS

The results showed that the accuracy of the benign and malignant tumor segmentation was 0.9556 and 0.9548, respectively, and the average AR navigation mapping error was 0.644 mm. The proposed surgical system was applied in 106 skin tumor surgeries, including intraoperative navigation of sampling in 16 Mohs surgery cases. Surgeons who have used this system highly recognize it.

CONCLUSIONS

The surgical system highlighted the potential to achieve accurate treatment of skin tumors and to fill the gap in global research on skin tumor surgery systems.

Artificial Intelligence in Senology - Where Do We Stand and What Are the Future Horizons?

Artificial Intelligence (AI) is defined as the simulation of human intelligence by a digital computer or robotic system and has become a hype in current conversations. A subcategory of AI is deep learning, which is based on complex artificial neural networks that mimic the principles of human synaptic plasticity and layered brain architectures, and uses large-scale data processing. AI-based image analysis in breast screening programmes has shown non-inferior sensitivity, reduces workload by up to 70% by pre-selecting normal cases, and reduces recall by 25% compared to human double reading. Natural language programs such as ChatGPT (OpenAI) achieve 80% and higher accuracy in advising and decision making compared to the gold standard: human judgement. This does not yet meet the necessary requirements for medical products in terms of patient safety. The main advantage of AI is that it can perform routine but complex tasks much faster and with fewer errors than humans. The main concerns in healthcare are the stability of AI systems, cybersecurity, liability and transparency. More widespread use of AI could affect human jobs in healthcare and increase technological dependency. AI in senology is just beginning to evolve towards better forms with improved properties. Responsible training of AI systems with meaningful raw data and scientific studies to analyse their performance in the real world are necessary to keep AI on track. To mitigate significant risks, it will be necessary to balance active promotion and development of quality-assured AI systems with careful regulation. AI regulation has only recently included in transnational legal frameworks, as the European Union's AI Act was the first comprehensive legal framework to be published, in December 2023. Unacceptable AI systems will be banned if they are deemed to pose a clear threat to people's fundamental rights. Using AI and combining it with human wisdom, empathy and affection will be the method of choice for further, fruitful development of tomorrow's senology.

The Future Direction of Women in Nuclear Medicine and Nuclear Medicine in Women's Health

This work discusses the role of Nuclear Medicine for women's health, the role of women in the development of this emerging field and the various issues which arise from both. It emphasizes the importance of young women and their competing needs due to factors like pregnancy and work-related challenges. The objectives of this overview include improving imaging techniques, preserving fertility during cancer treatment, diagnosing pelvic and uterine conditions, developing radiopharmaceuticals for women's health, protecting female employees in Nuclear Medicine, and considering the role of artificial intelligence.

Current Role and Future Prospects of Positron Emission Tomography (PET)/Computed Tomography (CT) in the Management of Breast Cancer

Breast cancer has become the most diagnosed cancer in women globally, with 2.3 million new diagnoses each year. Accurate early staging is essential for improving survival rates with metastatic spread from loco regional to distant metastasis, decreasing mortality rates by 50%. Current guidelines do not advice the routine use of positron emission tomography (PET)-computed tomography (CT) in the staging of early breast cancer in the absence of symptoms. However, there is a growing body of evidence to suggest that the use of PET-CT in this early stage can benefit the patient by improving staging and as a result treatment and outcomes, as well as psychological burden, without increasing costs to the health service. Ongoing research in PET radiomics and artificial intelligence is showing promising future prospects in its use in diagnosis, staging, prognostication, and assessment of responses to the treatment of breast cancer. Furthermore, ongoing research to address current limitations of PET-CT by improving techniques and tracers is encouraging. In this narrative review, we aim to evaluate the current evidence of the usefulness of PET-CT in the management of breast cancer in different settings along with its future prospects, including the use of artificial intelligence (AI), radiomics, and novel tracers.

Advances in Breast PET Instrumentation

Dedicated breast PET scanners currently have a spatial resolution in the 1.5 to 2 mm range, and the ability to provide tomographic images and quantitative data. They are also commercially available from a few vendors. A review of past and recent advances in the development and performance of dedicated breast PET scanners is summarized.

Positron Emission Tomography-Derived Radiomics and Artificial Intelligence in Multiple Myeloma: State-of-the-Art

Multiple myeloma (MM) is a heterogeneous neoplasm accounting for the second most prevalent hematologic disorder. The identification of noninvasive, valuable biomarkers is of utmost importance for the best patient treatment selection, especially in heterogeneous diseases like MM. Despite molecular imaging with positron emission tomography (PET) has achieved a primary role in the characterization of MM, it is not free from shortcomings. In recent years, radiomics and artificial intelligence (AI), which includes machine learning (ML) and deep learning (DL) algorithms, have played an important role in mining additional information from medical images beyond human eyes' resolving power. Our review provides a summary of the current status of radiomics and AI in different clinical contexts of MM. A systematic search of PubMed, Web of Science, and Scopus was conducted, including all the articles published in English that explored radiomics and AI analyses of PET/CT images in MM. The initial results have highlighted the potential role of such new features in order to improve the clinical stratification of MM patients, as well as to increase their clinical benefits. However, more studies are warranted before these approaches can be implemented in clinical routines.

Artificial intelligence in breast imaging: potentials and challenges

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Application of CT and MRI images based on an artificial intelligence algorithm for predicting lymph node metastasis in breast cancer patients: a meta-analysis

BACKGROUND

This study aimed to comprehensively evaluate the accuracy and effect of computed tomography (CT) and magnetic resonance imaging (MRI) based on artificial intelligence (AI) algorithms for predicting lymph node metastasis in breast cancer patients.

METHODS

We systematically searched the PubMed, Embase and Cochrane Library databases for literature from inception to June 2023 using keywords that included 'artificial intelligence', 'CT,' 'MRI', 'breast cancer' and 'lymph nodes'. Studies that met the inclusion criteria were screened and their data were extracted for analysis. The main outcome measures included sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and area under the curve (AUC).

RESULTS

A total of 16 studies were included in the final meta-analysis, covering 4,764 breast cancer patients. Among them, 11 studies used the manual algorithm MRI to calculate breast cancer risk, which had a sensitivity of 0.85 (95% confidence interval [CI] 0.79-0.90; p < 0.001; I2 = 75.3%), specificity of 0.81 (95% CI 0.66-0.83; p < 0.001; I2 = 0%), a positive likelihood ratio of 4.6 (95% CI 4.0-4.8), a negative likelihood ratio of 0.18 (95% CI 0.13-0.26) and a diagnostic odds ratio of 25 (95% CI 17-38). Five studies used manual algorithm CT to calculate breast cancer risk, which had a sensitivity of 0.88 (95% CI 0.79-0.94; p < 0.001; I2 = 87.0%), specificity of 0.80 (95% CI 0.69-0.88; p < 0.001; I2 = 91.8%), a positive likelihood ratio of 4.4 (95% CI 2.7-7.0), a negative likelihood ratio of 0.15 (95% CI 0.08-0.27) and a diagnostic odds ratio of 30 (95% CI 12-72). For MRI and CT, the AUC after study pooling was 0.85 (95% CI 0.82-0.88) and 0.91 (95% CI 0.88-0.93), respectively.

CONCLUSION

Computed tomography and MRI images based on an AI algorithm have good diagnostic accuracy in predicting lymph node metastasis in breast cancer patients and have the potential for clinical application.

Construction of a comprehensive predictive model for axillary lymph node metastasis in breast cancer: a retrospective study

PURPOSE

The accurate assessment of axillary lymph node metastasis (LNM) in early-stage breast cancer (BC) is of great importance. This study aimed to construct an integrated model based on clinicopathology, ultrasound, PET/CT, and PET radiomics for predicting axillary LNM in early stage of BC.

MATERIALS AND METHODS

124 BC patients who underwent 18 F-fluorodeoxyglucose (18 F-FDG) PET/CT and whose diagnosis were confirmed by surgical pathology were retrospectively analyzed and included in this study. Ultrasound, PET and clinicopathological features of all patients were analyzed, and PET radiomics features were extracted to establish an ultrasound model (clinicopathology and ultrasound; model 1), a PET model (clinicopathology, ultrasound, and PET; model 2), and a comprehensive model (clinicopathology, ultrasound, PET, and radiomics; model 3), and the diagnostic efficacy of each model was evaluated and compared.

RESULTS

The T stage, US_BIRADS, US_LNM, and PET_LNM in the positive axillary LNM group was significantly higher than that of in the negative LNM group (P = 0.013, P = 0.049, P < 0.001, P < 0.001, respectively). Radiomics score for predicting LNM (RS_LNM) for the negative LNM and positive LNM were statistically significant difference (-1.090 ± 0.448 vs. -0.693 ± 0.344, t = -4.720, P < 0.001), and the AUC was 0.767 (95% CI: 0.674-0.861). The ROC curves showed that model 3 outperformed model 1 for the sensitivity (model 3 vs. model 1, 82.86% vs. 48.57%), and outperformed model 2 for the specificity (model 3 vs. model 2, 82.02% vs. 68.54%) in the prediction of LNM. The AUC of mode 1, model 2 and model 3 was 0.687, 0.826 and 0.874, and the Delong test showed the AUC of model 3 was significantly higher than that of model 1 and model 2 (P < 0.05). Decision curve analysis showed that model 3 resulted in a higher degree of net benefit for all the patients than model 1 and model 2.

CONCLUSION

The use of a comprehensive model based on clinicopathology, ultrasound, PET/CT, and PET radiomics can effectively improve the diagnostic efficacy of axillary LNM in BC.

TRIAL REGISTRATION

This study was registered at ClinicalTrials Gov (number NCT05826197) on 7th, May 2023.

Deep learning model with collage images for the segmentation of dedicated breast positron emission tomography images

BACKGROUND

Dedicated breast positron emission tomography (dbPET) has high contrast and resolution optimized for detecting small breast cancers, leading to its noisy characteristics. This study evaluated the application of deep learning to the automatic segmentation of abnormal uptakes on dbPET to facilitate the assessment of lesions. To address data scarcity in model training, we used collage images composed of cropped abnormal uptakes and normal breasts for data augmentation.

METHODS

This retrospective study included 1598 examinations between April 2015 and August 2020. A U-Net-based model with an uptake shape classification head was trained using either the original or augmented dataset comprising collage images. The Dice score, which measures the pixel-wise agreement between a prediction and its ground truth, of the models was compared using the Wilcoxon signed-rank test. Moreover, the classification accuracies were evaluated.

RESULTS

After applying the exclusion criteria, 662 breasts were included; among these, 217 breasts had abnormal uptakes (mean age: 58 ± 14 years). Abnormal uptakes on the cranio-caudal and mediolateral maximum intensity projection images of 217 breasts were annotated and labeled as focus, mass, or non-mass. The inclusion of collage images into the original dataset yielded a Dice score of 0.884 and classification accuracy of 91.5%. Improvement in the Dice score was observed across all subgroups, and the score of images without breast cancer improved significantly from 0.750 to 0.834 (effect size: 0.76, P = 0.02).

CONCLUSIONS

Deep learning can be applied for the automatic segmentation of dbPET, and collage images can improve model performance.

Spatial assessments in texture analysis: what the radiologist needs to know

To date, studies investigating radiomics-based predictive models have tended to err on the side of data-driven or exploratory analysis of many thousands of extracted features. In particular, spatial assessments of texture have proven to be especially adept at assessing for features of intratumoral heterogeneity in oncologic imaging, which likewise may correspond with tumor biology and behavior. These spatial assessments can be generally classified as spatial filters, which detect areas of rapid change within the grayscale in order to enhance edges and/or textures within an image, or neighborhood-based methods, which quantify gray-level differences of neighboring pixels/voxels within a set distance. Given the high dimensionality of radiomics datasets, data dimensionality reduction methods have been proposed in an attempt to optimize model performance in machine learning studies; however, it should be noted that these approaches should only be applied to training data in order to avoid information leakage and model overfitting. While area under the curve of the receiver operating characteristic is perhaps the most commonly reported assessment of model performance, it is prone to overestimation when output classifications are unbalanced. In such cases, confusion matrices may be additionally reported, whereby diagnostic cut points for model predicted probability may hold more clinical significance to clinical colleagues with respect to related forms of diagnostic testing.

Comparison of MRI vs. [18F]FDG PET/CT for Treatment Response Evaluation of Primary Breast Cancer after Neoadjuvant Chemotherapy: Literature Review and Future Perspectives

The purpose of this systematic review was to investigate the diagnostic accuracy of [18F]FDG PET/CT and breast MRI for primary breast cancer (BC) response assessment after neoadjuvant chemotherapy (NAC) and to evaluate future perspectives in this setting. We performed a critical review using three bibliographic databases (i.e., PubMed, Scopus, and Web of Science) for articles published up to the 6 June 2023, starting from 2012. The Quality Assessment of Diagnosis Accuracy Study (QUADAS-2) tool was adopted to evaluate the risk of bias. A total of 76 studies were identified and screened, while 14 articles were included in our systematic review after a full-text assessment. The total number of patients included was 842. Eight out of fourteen studies (57.1%) were prospective, while all except one study were conducted in a single center. In the majority of the included studies (71.4%), 3.0 Tesla (T) MRI scans were adopted. Three out of fourteen studies (21.4%) used both 1.5 and 3.0 T MRI and only two used 1.5 T. [18F]FDG was the radiotracer used in every study included. All patients accepted surgical treatment after NAC and each study used pathological complete response (pCR) as the reference standard. Some of the studies have demonstrated the superiority of [18F]FDG PET/CT, while others proved that MRI was superior to PET/CT. Recent studies indicate that PET/CT has a better specificity, while MRI has a superior sensitivity for assessing pCR in BC patients after NAC. The complementary value of the combined use of these modalities represents probably the most important tool to improve diagnostic performance in this setting. Overall, larger prospective studies, possibly randomized, are needed, hopefully evaluating PET/MR and allowing for new tools, such as radiomic parameters, to find a proper place in the setting of BC patients undergoing NAC.

PET/CT and SPECT/CT Imaging of HER2-Positive Breast Cancer

HER2 (Human Epidermal Growth Factor Receptor 2)-positive breast cancer is characterized by amplification of the HER2 gene and is associated with more aggressive tumor growth, increased risk of metastasis, and poorer prognosis when compared to other subtypes of breast cancer. HER2 expression is therefore a critical tumor feature that can be used to diagnose and treat breast cancer. Moving forward, advances in HER2 in vivo imaging, involving the use of techniques such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT), may allow for a greater role for HER2 status in guiding the management of breast cancer patients. This will apply both to patients who are HER2-positive and those who have limited-to-minimal immunohistochemical HER2 expression (HER2-low), with imaging ultimately helping clinicians determine the size and location of tumors. Additionally, PET and SPECT could help evaluate effectiveness of HER2-targeted therapies, such as trastuzumab or pertuzumab for HER2-positive cancers, and specially modified antibody drug conjugates (ADC), such as trastuzumab-deruxtecan, for HER2-low variants. This review will explore the current and future role of HER2 imaging in personalizing the care of patients diagnosed with breast cancer.

[18F]FDG PET-TC radiomics and machine learning in the evaluation of prostate incidental uptake

AIM

To evaluate the relevance of incidental prostate [18F]FDG uptake (IPU) and to explore the potential of radiomics and machine learning (ML) to predict prostate cancer (PCa).

METHODS

We retrieved [18F]FDG PET/CT scans with evidence of IPU performed in two institutions between 2015 and 2021. Patients were divided into PCa and non-PCa, according to the biopsy. Clinical and PET/CT-derived information (comprehensive of radiomic analysis) were acquired. Five ML models were developed and their performance in discriminating PCa vs non-PCa IPU was evaluated. Radiomic analysis was investigated to predict ISUP Grade.

RESULTS

Overall, 56 IPU were identified and 31 patients performed prostate biopsy. Eighteen of those were diagnosed as PCa. Only PSA and radiomic features (eight from CT and nine from PET images, respectively) showed statistically significant difference between PCa and non-PCa patients. Eight features were found to be robust between the two institutions. CT-based ML models showed good performance, especially in terms of negative predictive value (NPV 0.733-0.867). PET-derived ML models results were less accurate except the Random Forest model (NPV = 0.933). Radiomics could not accurately predict ISUP grade.

CONCLUSIONS

Paired with PSA, radiomic analysis seems to be promising to discriminate PCa/non-PCa IPU. ML could be a useful tool to identify non-PCa IPU, avoiding further investigations.

Dynomics: A Novel and Promising Approach for Improved Breast Cancer Prognosis Prediction

Traditional imaging techniques for breast cancer (BC) diagnosis and prediction, such as X-rays and magnetic resonance imaging (MRI), demonstrate varying sensitivity and specificity due to clinical and technological factors. Consequently, positron emission tomography (PET), capable of detecting abnormal metabolic activity, has emerged as a more effective tool, providing critical quantitative and qualitative tumor-related metabolic information. This study leverages a public clinical dataset of dynamic 18F-Fluorothymidine (FLT) PET scans from BC patients, extending conventional static radiomics methods to the time domain-termed as 'Dynomics'. Radiomic features were extracted from both static and dynamic PET images on lesion and reference tissue masks. The extracted features were used to train an XGBoost model for classifying tumor versus reference tissue and complete versus partial responders to neoadjuvant chemotherapy. The results underscored the superiority of dynamic and static radiomics over standard PET imaging, achieving accuracy of 94% in tumor tissue classification. Notably, in predicting BC prognosis, dynomics delivered the highest performance, achieving accuracy of 86%, thereby outperforming both static radiomics and standard PET data. This study illustrates the enhanced clinical utility of dynomics in yielding more precise and reliable information for BC diagnosis and prognosis, paving the way for improved treatment strategies.

18F-FDG PET-Derived Volume-Based Parameters to Predict Disease-Free Survival in Patients with Grade III Breast Cancer of Different Molecular Subtypes Candidates to Neoadjuvant Chemotherapy

We investigated whether baseline [¹⁸F] Fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET)-derived semiquantitative parameters could predict disease-free survival (DFS) in patients with grade III breast cancer (BC) of different molecular subtypes candidate to neoadjuvant chemotherapy (NAC). For each ¹⁸F-FDG-PET/CT scan, the following parameters were calculated in the primary tumor (SUVmax, SUVmean, MTV, TLG) and whole-body (WB_SUVmax, WB_MTV, and WB_TLG). Receiver operating characteristic (ROC) analysis was used to determine the capability to predict DFS and find the optimal threshold for each parameter. Ninety-five grade III breast cancer patients with different molecular types were retrieved from the databases of the University Hospital of Padua and the University Hospital of Ferrara (luminal A: 5; luminal B: 34; luminal B-HER2: 22; HER2-enriched: 7; triple-negative: 27). In luminal B patients, WB_MTV (AUC: 0.75; best cut-off: WB_MTV > 195.33; SS: 55.56%, SP: 100%; p = 0.002) and WB_TLG (AUC: 0.73; best cut-off: WB_TLG > 1066.21; SS: 55.56%, SP: 100%; p = 0.05) were the best predictors of DFS. In luminal B-HER2 patients, WB_SUVmax was the only predictor of DFS (AUC: 0.857; best cut-off: WB_SUVmax > 13.12; SS: 100%; SP: 71.43%; p < 0.001). No parameter significantly affected the prediction of DFS in patients with grade III triple-negative BC. Volume-based parameters, extracted from baseline ¹⁸F-FDG PET, seem promising in predicting recurrence in patients with grade III luminal B and luminal B- HER2 breast cancer undergoing NAC.

PET/CT in Patients with Breast Cancer Treated with Immunotherapy

Significant advances in breast cancer (BC) treatment have been made in the last decade, including the use of immunotherapy and, in particular, immune checkpoint inhibitors that have been shown to improve the survival of patients with triple negative BC. This narrative review summarizes the studies supporting the use of immunotherapy in BC. Furthermore, the usefulness of 2-deoxy-2-[¹⁸F]fluoro-D-glucose (2-[¹⁸F]FDG) positron emission/computerized tomography (PET/CT) to image the tumor heterogeneity and to assess treatment response is explored, including the different criteria to interpret 2-[¹⁸F]FDG PET/CT imaging. The concept of immuno-PET is also described, by explaining the advantages of mapping treatment targets with a non-invasive and whole-body tool. Several radiopharmaceuticals in the preclinical phase are referred too, and, considering their promising results, translation to human studies is needed to support their use in clinical practice. Overall, this is an evolving field in BC treatment, despite PET imaging developments, the future trends also include expanding immunotherapy to early-stage BC and using other biomarkers.

The Role of Molecular Imaging in Patients with Brain Metastases: A Literature Review

Over the last several years, molecular imaging has gained a primary role in the evaluation of patients with brain metastases (BM). Therefore, the "Response Assessment in Neuro-Oncology" (RANO) group recommends amino acid radiotracers for the assessment of BM. Our review summarizes the current use of positron emission tomography (PET) radiotracers in patients with BM, ranging from present to future perspectives with new PET radiotracers, including the role of radiomics and potential theranostics approaches. A comprehensive search of PubMed results was conducted. All studies published in English up to and including December 2022 were reviewed. Current evidence confirms the important role of amino acid PET radiotracers for the delineation of BM extension, for the assessment of response to therapy, and particularly for the differentiation between tumor progression and radionecrosis. The newer radiotracers explore non-invasively different biological tumor processes, although more consistent findings in larger clinical trials are necessary to confirm preliminary results. Our review illustrates the role of molecular imaging in patients with BM. Along with magnetic resonance imaging (MRI), the gold standard for diagnosis of BM, PET is a useful complementary technique for processes that otherwise cannot be obtained from anatomical MRI alone.

The influence of receptor expression and clinical subtypes on baseline [18F]FDG uptake in breast cancer: systematic review and meta-analysis

BACKGROUND

To quantify the relationship between [18F]FDG uptake of the primary tumour measured by PET-imaging with immunohistochemical (IHC) expression of ER, PR, HER2, Ki-67, and clinical subtypes based on these markers in breast cancer patients.

METHODS

PubMed and Embase were searched for studies that compared SUVmax between breast cancer patients negative and positive for IHC expression of ER, PR, HER2, Ki-67, and clinical subtypes based on these markers. Two reviewers independently screened the studies and extracted the data. Standardized mean differences (SMD) and 95% confidence intervals (CIs) were estimated by using DerSimonian-Laird random-effects models. P values less than or equal to 5% indicated statistically significant results.

RESULTS

Fifty studies were included in the final analysis. SUVmax is significantly higher in ER-negative (31 studies, SMD 0.66, 0.56-0.77, P < 0.0001), PR-negative (30 studies, SMD 0.56; 0.40-0.71, P < 0.0001), HER2-positive (32 studies, SMD - 0.29, - 0.49 to - 0.10, P = 0.0043) or Ki-67-positive (19 studies, SMD - 0.77; - 0.93 to - 0.61, P < 0.0001) primary tumours compared to their counterparts. The majority of clinical subtypes were either luminal A (LA), luminal B (LB), HER2-positive or triple negative breast cancer (TNBC). LA is associated with significantly lower SUVmax compared to LB (11 studies, SMD - 0.49, - 0.68 to - 0.31, P = 0.0001), HER2-positive (15 studies, SMD - 0.91, - 1.21 to - 0.61, P < 0.0001) and TNBC (17 studies, SMD - 1.21, - 1.57 to - 0.85, P < 0.0001); and LB showed significantly lower uptake compared to TNBC (10 studies, SMD - 0.77, - 1.05 to - 0.49, P = 0.0002). Differences in SUVmax between LB and HER2-positive (9 studies, SMD - 0.32, - 0.88 to 0.24, P = 0.2244), and HER2-positive and TNBC (17 studies, SMD - 0.29, - 0.61 to 0.02, P = 0.0667) are not significant.

CONCLUSION

Primary tumour SUVmax is significantly higher in ER-negative, PR-negative, HER2-positive and Ki-67-positive breast cancer patients. Luminal tumours have the lowest and TNBC tumours the highest SUVmax. HER2 overexpression has an intermediate effect.

The Value of Semiquantitative Parameters Derived from 18F-FDG PET/CT for Predicting Response to Neoadjuvant Chemotherapy in a Cohort of Patients with Different Molecular Subtypes of Breast Cancer

Pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) is a strong prognostic factor in breast cancer (BC). The aim of this study was to investigate whether semiquantitative parameters derived from baseline [¹⁸F]Fluorodeoxyglucose ([¹⁸F]FDG) positron emission computed tomography/computed tomography (PET/CT) could predict pCR after NAC and survival outcomes in patients affected by different molecular subtypes of BC. We retrospectively retrieved patients from the databases of two Italian hospitals (Centre A: University Hospital of Ferrara; Centre B: University of Padua) meeting the following inclusion criteria: (1) diagnosis of BC; (2) history of NAC; (3) baseline [¹⁸F]FDG PET/CT performed before the first cycle of NAC; (4) available follow-up data (response after NAC and survival information). For each [¹⁸F]FDG PET/CT scan, semiquantitative parameters (SUVmax, SUVmean, MTV and TLG) related to the primary tumor (B), to the reference lesion for both axillary (N) and distant lymph node (DN), and to the whole-body burden of disease (WB) were evaluated. Patients enrolled were 133: 34 from centre A and 99 from centre B. Patients' molecular subtypes were: 9 luminal A, 49 luminal B, 33 luminal B + HER-2, 10 HER-2 enriched, and 32 triple negative (TNBC). Luminal A and HER-2 enriched BC patients were excluded from the analysis due to the small sample size. pCR after NAC was achieved in 47 patients (41.2%). [¹⁸F]FDG PET/CT detected the primary tumor in 98.3% of patients and lymph node metastases were more frequently detected in Luminal B subgroup. Among Luminal B patients, median SUVmean_B values were significantly higher (p = 0.027) in responders (7.06 ± 5.9) vs. non-responders (4.4 ± 2.1) to NAC. Luminal B + HER-2 non-responders showed a statistically significantly higher median MTV_B (7.3 ± 4.2 cm³ vs. 3.5 ± 2.5 cm³; p = 0.003) and TLG_B (36.5 ± 24.9 vs. 18.9 ± 17.7; p = 0.025) than responders at baseline [¹⁸F]FDG PET/CT. None of the semiquantitative parameters predicted pCR after NAC in TNBC patients. However, among TNBC patients who achieved pCR after NAC, 4 volumetric parameters (MTV_B, TLG_B, MTV_WB and TLG_WB) were significantly higher in patients dead at follow-up. If confirmed in further studies, these results could open up a widespread use of [¹⁸F]FDG PET/CT as a baseline predictor of response to NAC in luminal B and luminal B + HER-2 patients and as a prognostic tool in TNBC.