Automatic dual-modality breast tumor segmentation in PET/CT images using CT-guided transformer.

Purpose Neck ultrasonography (US), computed tomography (CT), and 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) are all known to be useful imaging modalities for detecting supraclavicular lymph node (SCN) metastasis in breast cancer. The authors compared the diagnostic values of neck US, CT, and PET/CT in the detection of SCN metastasis in breast cancer. Methods SCN metastases identified in neck US, CT, or PET/CT during follow-up visits of patients with breast cancer were pathologically confirmed with the use of US-guided fine-needle aspiration cytology. The clinicopathological factors of the patients were analyzed, and the statistical parameters including sensitivity, specificity, positive and negative predictive values, false-positive and false-negative rates, and accuracy of neck US, CT, and PET/CT were compared. Results Among 32 cases of suspicious SCNs, 24 were pathologically confirmed as metastasis of breast cancer. The sensitivity of US + CT was 91.7%, which was the same as that of PET/CT, while the sensitivity rates of US alone and CT alone were 87.5% and 83.3%, respectively. Accuracy was 99.8% in PET/CT alone and 98.1% in US + CT. The false-negative rate was 0.1% in US + PET/CT, while it was 0.2% in PET/CT and US + CT, 0.3% in US alone and 0.4% in CT alone. Conclusion PET/CT can be the first choice for detecting SCN metastases in breast cancer. However, if PET/CT is unavailable for any reason, US + CT could be a good second option to avoid false-negative results.

Aim:Our aim of this study was to evaluate the diagnostic accuracy of staging positron emission tomography/computed tomography (PET/CT) in early breast cancers (EBCs) and to assess its impact on disease management.Patients and Methods:We retrospectively reviewed preoperative PET/CT scans of patients from January 2015 to December 2018 with Stage I/II, clinically T1–T2 N0–N1 breast cancers. The diagnostic performance of PET/CT for nodal (N) and distant metastases (M), its correlation with patient/tumor-specific factors, and its impact on disease management were analyzed using histopathology/clinical follow-up as standards of reference.Results:Of 158 patients evaluated, 14% of patients were Stage I (T1N0), 60% were Stage IIA (T1N1, T2N0), and 26% were Stage IIB (T2N1). Sensitivity, specificity, and the diagnostic accuracy of PET/CT for axillary staging were 76%, 97%, and 84% and for distant metastasis evaluation were 100%, 98%, and 99%, respectively. The diagnostic accuracy of PET/CT for axillary staging was lower for low-grade, T1 tumors, postmenopausal group, and luminal A pathological subtype (77%, 84%, 81%, and 73%, respectively) compared to high-grade, T2 tumors, premenopausal group, and nonluminal A subtype (88%, 88%, 94%, and 87%, respectively). Distant metastases were detected on PET/CT in overall 16% (n = 25) of the patients (9% in Stage IIA and 27% in Stage IIB). PET/CT also incidentally identified clinically occult internal mammary nodes in 5% (n = 8) and organ-confined synchronous second malignancies in 5% (n = 8) of the patients.Conclusion:Preoperative PET/CT should be considered in all EBCs> 2 cm as it upstages the disease and alters management in about 24% of these patients. Given its high specificity for axillary staging PET/CT, patients with PET-positive axilla can be subjected to axillary dissection and those with PET-negative axilla to sentinel lymph node biopsy. The yield and diagnostic accuracy of PET/CT is less for low-grade tumors <2 cm and with luminal A subtype.

BackgroundTo compare the diagnostic sensitivity of [18F]fluoroestradiol ([18F]FES) and [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography/computed tomography (PET/CT) for breast cancer recurrence in patients with estrogen receptor (ER)-positive primary breast cancer.MethodsOur database of consecutive patients enrolled in a previous prospective cohort study to assess [18F]FES PET/CT was reviewed to identify eligible patients who had ER-positive primary breast cancer with suspected first recurrence at presentation and who underwent [18F]FDG PET/CT. The sensitivity of qualitative [18F]FES and [18F]FDG PET/CT interpretations was assessed, comparing them with histological diagnoses.ResultsOf the 46 enrolled patients, 45 were confirmed as having recurrent breast cancer, while one was diagnosed with chronic granulomatous inflammation. Forty (89%) patients were ER-positive, four (9%) were ER-negative, and one (2%) patient did not undergo an ER assay. The sensitivity of [18F]FES PET/CT was 71.1% (32/45, 95% CI, 55.7–83.6), while that of [18F]FDG PET/CT was 80.0% (36/45, 95% CI, 65.4–90.4) with a threshold of positive interpretation, and 93.3% (42/45, 95% CI, 81.7–98.6) when a threshold of equivocal was used. There was no significant difference in sensitivity between [18F]FES and [18F]FDG PET/CT (P = 0.48) with a threshold of positive [18F]FDG uptake, but the sensitivity of [18F]FDG was significantly higher than [18F]FES (P = 0.013) with a threshold of equivocal [18F]FDG uptake. One patient with a benign lesion showed negative [18F]FES but positive [18F]FDG uptake.ConclusionsThe restaging of patients who had ER-positive primary breast cancer and present with recurrent disease may include [18F]FES PET/CT as an initial test when standard imaging studies are equivocal or suspicious.

BackgroundSentinel lymph node biopsy (SLNB) is the standard of care for axillary staging in early breast cancer patients with low-burden axillary metastasis (≤ 2 positive nodes). This study aimed to determine the diagnostic performances of 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) and breast magnetic resonance imaging in detecting axillary lymph node (ALN) metastases and the reliability to predict ALN burden.MethodsA total of 275 patients with primary operable breast cancer receiving preoperative PET/CT and upfront surgery from January 2001 to December 2022 in a single institution were enrolled. A total of 244 (88.7%) of them also received breast MRI. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of PET/CT and breast MRI were assessed. The predictive values to determine ALN burden were evaluated using radio-histopathological concordance.ResultsPET/CT demonstrated a sensitivity of 53.4%, specificity of 82.1%, PPV of 65.5%, NPV of 73.5%, and accuracy of 70.9% for detecting ALN metastasis, and the corresponding values for MRI were 71.8%, 67.8%, 56%, 80.8%, and 69.2%, respectively. Combining PET/CT and MRI showed a significantly higher PPV than MRI (72.7% vs 56% for MRI alone, p = 0.037) and a significantly higher NPV than PET/CT (84% vs 73.5% for PET/CT alone, p = 0.041). For predicting low-burden axillary metastasis (1–2 positive nodes), the PPVs were 35.9% for PET/CT, 36.7% for MRI, and 55% for combined PET/CT and MRI. Regarding patients with 0–2 positive ALNs in imaging, who were indicated for SLNB, the predictive correctness was 96.1% for combined PET/CT and MRI, 95.7% for MRI alone, and 88.6% for PET/CT alone.ConclusionsPET/CT and breast MRI exhibit high predictive values for identifying low-burden axillary metastasis in patients with operable breast cancer with ≦ 2 positive ALNs on imaging.

Recent research has proposed using positron emission tomography/computed tomography (PET/CT) along with the administration of prostate-specific membrane antigen (PSMA)-targeting radiopharmaceuticals to identify breast cancer (BC) lesions. An extensive literature review to investigate the possible diagnostic utility of PET/CT with PSMA-targeting radiopharmaceuticals in BC patients was performed. The research comprised different clinical scenarios, including both newly diagnosed BC patients and those who had experienced disease relapse. This updated systematic review encompassed six studies investigating the diagnostic efficacy of PSMA-targeted PET/CT in BC. Throughout all clinical settings investigated, the papers presented data demonstrating a modest diagnostic performance of PSMA-targeted PET/CT in different subtypes of BC. In this setting, PSMA-guided PET/CT showed slightly higher accuracy in patients diagnosed with triple-negative BC. Based on the current literature, PSMA-targeted PET/CT cannot be suggested as a diagnostic tool to assess BC extent in any clinical scenario. However, based on the PSMA expression observed in triple-negative patients, it can be proposed as a tool to evaluate whether BC patients could benefit from PSMA-targeting radioligand therapy.

Background & objectives:Locally advanced breast cancer (LABC) is associated with substantial risk of occult metastases. The patients with LABC have high rate of systemic relapse, suggesting inadequacy of the current conventional staging in detecting the occult metastatic spread. 18F-fluorodeoxyglucose (FDG) positron emission tomography-computed tomography (PET/CT) is a new modality in the staging of breast cancer patients. Hence, this study was conducted to evaluate the role of 18F-FDG PET/CT in initial staging of LABC and to compare it with conventional methods.Methods:This prospective study included biopsy-confirmed female patients diagnosed with LABC meeting the selection criteria and attending surgical, medical and radiation oncology departments of a tertiary care centre in south India, from April 2013 to December 2014. Conventional workup included serum chemistry, mammogram, bone scan, contrast-enhanced CT (CECT) chest and upper abdomen and ultrasound abdomen and pelvis. All patients following conventional workup underwent 18F-FDG PET/CT.Results:In this study, 61 women with LABC underwent both conventional workup and 18F-FGD PET/CT. The 18F-FDG PET/CT, in comparison to conventional workup, revealed unsuspected N3 nodal disease in 11 more patients, revealed distant metastasis in seven more patients and also detected extra sites of metastasis in five patients. The sensitivity, specificity, positive predictive value, negative predictive value and accuracy of PET/CT to detect distant metastasis were 95, 98, 95, 98 and 97 per cent, respectively, whereas the sensitivity, specificity, positive predictive value, negative predictive value and accuracy of conventional imaging to detect distant metastasis were 65, 93, 81, 84 and 84 per cent, respectively.Interpretation & conclusions:The 18F-FDG PET/CT was found to be more accurate than conventional imaging for staging and modified stage and treatment in 30 and 38 per cent of patients, respectively. It was particularly useful in detecting occult distant metastasis and N3 nodal disease with an added advantage of examining whole body in single session. However, CECT chest was superior over 18F-FDG PET/CT for detecting pulmonary metastasis.

The purpose of this retrospective study was to evaluate the diagnostic performance of positron emission tomography/computed tomography (PET/CT) with fluorine-18-labeled 2-fluoro-2-deoxy-D-glucose (FDG) in comparison with that of ultrasonography and contrast-enhanced computed tomography (CT) in detecting axillary lymph node metastasis in patients with breast cancer. Fifty patients with invasive breast cancer were recruited. They had received no neoadjuvant chemotherapy and underwent PET/CT, ultrasonography and contrast-enhanced CT before mastectomy. The clinical stage was I in 34 patients, II in 15 patients, and III in one patient. The images of these modalities were interpreted in usual practice before surgery and the diagnostic reports were reviewed for analysis. Sensitivity, specificity, positive predictive value, and negative predictive value of each modality were obtained taking histopathological results of axillary lymph node dissection or sentinel lymph node biopsy as the reference standard. Axillary lymph node metastasis was confirmed in 15 of 50 patients by histopathological studies. PET/CT identified lymph node metastasis in three of these 15 patients. The overall sensitivity and specificity, positive predictive value, and negative predictive value of PET/CT in the diagnosis of axillary lymph node metastasis were 20, 97, 75, and 74%, and those of ultrasonography were 33, 94, 71, and 77% and those of contrast-enhanced CT were 27, 97, 80, and 76%, respectively. PET/CT showed poor sensitivity and high specificity in the detection of axillary lymph node metastasis of breast cancer. Diagnostic performance of PET/CT was not superior to that of ultrasonography and contrast-enhanced CT.

Quantitative standardized uptake values (SUVs) from fluorine-18 (18F) fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) are commonly used to evaluate the extent of disease and response to treatment in breast cancer patients. Recently, PET/magnetic resonance imaging (MRI) has been shown to qualitatively detect metastases from various primary cancers with similar sensitivity to PET/CT. However, quantitative validation of PET/MRI requires assessing the reliability of SUVs from MR attenuation correction (MRAC) relative to CT attenuation correction (CTAC). The purpose of this retrospective study was to assess the utility of PET/MRI-derived SUVs in breast cancer patients by testing the hypothesis that SUVs derived from MRAC correlate well with those from CTAC. Between August 2012 and May 2013, 35 breast cancer patients (age 37-78 years, 1 man) underwent clinical 18F-FDG PET/CT followed by PET/MRI. One hundred seventy metastases were seen in 21 of 35 patients; metastases to bone in 16 patients, to liver in seven patients, and to nonaxillary lymph nodes in eight patients were sufficient for statistical analysis on an organ-specific per patient basis. SUVs in the most FDG-avid metastasis per organ per patient from PET/CT and PET/MRI were measured and compared using Pearson's correlations. Correlations between CTAC- and MRAC-derived SUVmax and SUVmean in 31 metastases to bone, liver, and nonaxillary lymph nodes were strong overall (ρ = 0.80, 0.81). SUVmax and SUVmean correlations were also strong on an organ-specific basis in 16 bone metastases (ρ = 0.76, 0.74), seven liver metastases (ρ = 0.85, 0.83), and eight nonaxillary lymph node metastases (ρ = 0.95, 0.91). These strong organ-specific correlations between SUVs from PET/CT and PET/MRI in breast cancer metastases support the use of SUVs from PET/MRI for quantitation of 18F-FDG activity.

Discordant Findings of Skeletal Metastasis Between Tc 99m MDP Bone Scans and F 18 FDG PET/CT Imaging for Advanced Breast and Lung Cancers—Two Case Reports and Literature Review

BackgroundBreast cancer is the most common cancer type in women and the most common cause of deaths in women worldwide.FDG-PET/CT was used in the early stage, estimation of the therapeutic response, revelation of recurrent disease, and distal metastasis. However, with the increasing use of FDG PET/CT, sites of accelerated activity have been occasionally found out in unexpected locations which may not correlate with the patient’s clinical history or the expected propagation of the primary malignancy.The aim of this study is to detect the diagnostic value of PET/CT in breast cancer patients; comparing PET/CT performance with that of contrast-enhanced CT in diagnosis of breast cancer and distant metastasis.ResultsThe study included 30 female patients with breast cancer, mean age 53.56 years ± 10.64 (SD), age range 33–73 years. PET/CT detect contralateral breast affection in 2 patients (6.7%), and distant metastasis was seen on PET/CT. Sites of distant metastasis included the bone (n = 12), axillary lymph nodes (n = 11), cervical lymph nodes (n = 6), mediastinal lymph nodes (n = 12), abdominal lymph nodes (n = 8), liver (n = 5), lung (n = 11), and other visceral sites metastasis (n = 9). PET/CT detected breast lesions with a sensitivity of 100% and specificity of 95.4%. In contrast, the sensitivity and specificity of CT alone were 81.2% and 90.4%, respectively.ConclusionPET/CT has superiority over CT alone in revelation of breast lesions and distant metastases.

ObjectiveTo evaluate positron emission tomography/computed tomography (PET/CT) andconventional imaging tests for the detection of distant metastases inpatients with locally advanced breast cancer.Materials and methodsWe included 81 patients with breast cancer who had undergone18F-fluorodeoxyglucose (FDG) PET/CT before treatment.Conventional imaging included the following: bone scintigraphy; chest X-ray(in 14.5%) or CT (in 85.5%); and abdominal ultrasound (in 10.8%), CT (in87.8%), or magnetic resonance imaging (in 1.4%). Histopathology andclinical/imaging follow-up served as reference.ResultsDistant metastases were observed in nine patients (11.1%). On patient-basedanalysis, conventional imaging identified distant metastases in all 9patients. In one patient, the initial 18F-FDG PET/CT failed todemonstrate bone metastases that was evident on bone scintigraphy. In twopatients, the CT scan failed to show extra-axillary lymph node metastasesthat were identified on 18F-FDG PET/CT. There was no significantdifference between 18F-FDG PET/CT and conventional imaging interms of their sensitivity for the detection of distant metastases inpatients with locally advanced breast cancer.ConclusionThis study showed that 18F-FDG PET/CT and conventional imagingwith CT scans had similar sensitivity for the diagnosis of distantmetastases in patients with locally advanced breast cancer.18F-FDG PET/CT can add information about extra-axillary lymphnode involvements.

estrogen receptor (ER)+/human epithelial growth factor receptor 2 (HER2)- breast cancers have less aggressive traits and a favorable prognosis when treated early. Prediction of prognosis for treatment outcome or survival in ER+/HER2- cancer is important. Ultrasound (US) is an effective and easy technique for breast cancer diagnosis and tumor characterization. Positron emission tomography/computed tomography (PET/CT) is widely used for diagnosis, staging, and therapeutic response in cancer evaluation, and a high maximum standardized uptake value (SUVmax) is associated with poor prognosis. The study aim was to compare the prognostic value of US features with that of the SUVmax assessed by PET/CT in ER+/HER- breast cancer patients. We retrospectively identified breast cancer patients in our institutional database who had undergone preoperative US and PET/CT, and 96 patients with invasive ductal carcinoma and ductal carcinoma in situ were included in this study. The US features of mass shape, margin, echo pattern, orientation, posterior features, boundary, and calcification in the mass were analyzed. We then analyzed the US features to look for correlations with SUVmax and associations with margins, boundaries, posterior features, histological grade, and ki-67 expression. High SUVmax was correlated with irregular shape, not-circumscribed margin, posterior acoustic enhancement, echogenic halo, and calcification in the mass (P < 0.05, all). Posterior acoustic enhancement was correlated with high ki-67 expression. Many US features of ER+/HER- breast cancer showed associations with SUVmax. Some US features of ER+/HER- breast cancer were useful for predicting prognosis.

Breast cancer has become the most prevalent and lethal disease among women worldwide. Over the past years, Positron Emission Tomography/Computed Tomography (PET/CT) has emerged as an indispensable modality in breast cancer diagnosis. However, image data from a single modality often fails to comprehensively reflect the characteristics of lesions, which significantly restricts the accuracy and reliability of diagnosis. To find a solution for this complex challenge, this paper proposes a Multi-modality Medical Vision Transformer (MM-ViT). The primary objective of MM-ViT is to conduct an integrated analysis of PET/CT dual-modal data, aiming to achieve more precise breast cancer subtyping solely using medical imaging. The effectiveness of MM-ViT was validated using 3,797 pairs of PET/CT images from 271 patients with four breast cancer subtypes. The influence of different baseline networks and feature fusion methods on classification performance was analyzed through extensive ablation and comparative experiments. The experimental results indicate that the proposed MM-ViT outperforms baseline models and existing methods. A four-class classification accuracy of 94.52% was achieved. This work provides new insights for personalized breast cancer treatment and demonstrates significant clinical potential.

Role of 18F-PET/CT in Predicting Prognosis of Patients With Breast Cancer After Neoadjuvant Chemotherapy

This prospective study aims to evaluate the value of [18F]AlF-NOTA-fibroblast activation protein inhibitor (FAPI)-04 positron emission tomography-computed tomography (PET/CT) in predicting molecular subtypes of breast cancer. The study consecutively recruited patients suspected of having breast cancer from a single center who were prospectively enrolled from July 2023 to May 2024 and underwent [18F]AlF-NOTA-FAPI-04 PET/CT. This study compared the differences in tracer uptake among breast cancers with different adverse prognostic factors and molecular subtypes. The classification performance for each molecular subtype of breast cancer was assessed using a receiver operating characteristic (ROC) curve. Fifty-three participants (mean age, 51 ± 11 years; 52 females) were evaluated. Breast cancer lesions with adverse prognostic factors showed higher tracer uptake. The five different molecular subtypes exhibited varying levels of uptake. The luminal A and luminal B (HER2-negative) subtypes had relatively low uptake, while the luminal B (HER2-positive), HER2-positive, and triple-negative subtypes had relatively high uptake. ROC analysis identified the max standardized uptake value (SUVmax) as a significant classifier (AUC = 0.912, P = 0.0005) for the luminal A subtype, with 100% sensitivity and 83% specificity. For predicting the luminal B (HER2-negative) subtype, SUVmax had an AUC of 0.770 (P = 0.0015). SUVmax, with an AUC of 0.781 (P = 0.003), was used to identify the triple-negative subtype tumors, resulting in a sensitivity of 100% and specificity of 51%. Lastly, the ROC curve showed the cut-off 15.40 (AUC = 0.921, P < 0.0001) could classify luminal A & luminal B (HER2-negative), and luminal B (HER2-positive) & HER2-positive & triple-negative, yielding a sensitivity of 94% and specificity of 79%. The uptake of [18F]AlF-NOTA-FAPI-04 is significantly correlated with the molecular subtypes of breast cancer, and [18F]AlF-NOTA-FAPI-04 PET/CT is a potential tool for noninvasive identification of luminal A subtypes and guidance of FAP-targeted therapies.