Detection Of Metastases Research Articles

Combining machine and deep transfer learning for mediastinal lymph node evaluation in patients with lung cancer

BackgroundThe prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis. Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of the likelihood of such metastasis, thereby providing clinicians with crucial information to enhance diagnostic precision and ultimately improve patient survival and prognosis MethodsIn total, 623 eligible patients were recruited from two medical institutions. Seven deep learning models, namely Alex, GoogLeNet, Resnet18, Resnet101, Vgg16, Vgg19, and MobileNetv3 (small), were utilized to extract deep image histological features. The dimensionality of the extracted features was then reduced using the Spearman correlation coefficient (r ≥ 0.9) and Least Absolute Shrinkage and Selection Operator. Eleven machine learning methods, namely Support Vector Machine, K-nearest neighbor, Random Forest, Extra Trees, XGBoost, LightGBM, Naive Bayes, AdaBoost, Gradient Boosting Decision Tree, Linear Regression, and Multilayer Perceptron, were employed to construct classification prediction models for the filtered final features. The diagnostic performances of the models were assessed using various metrics, including accuracy, area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value. Calibration and decision-curve analyses were also performed. ResultsThe present study demonstrated that using deep radiomic features extracted from Vgg16, in conjunction with a prediction model constructed via a linear regression algorithm, effectively distinguished the status of mediastinal lymph nodes in patients with lung cancer. The performance of the model was evaluated based on various metrics, including accuracy, area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value, which yielded values of 0.808, 0.834, 0.851, 0.745, 0.829, and 0.776, respectively. The validation set of the model was assessed using clinical decision curves, calibration curves, and confusion matrices, which collectively demonstrated the model's stability and accuracy ConclusionIn this study, information on the deep radiomics of Vgg16 was obtained from computed tomography images, and the linear regression method was able to accurately diagnose mediastinal lymph node metastases in patients with lung cancer.

The 31-GEP to identify patients with localized cutaneous melanoma at the highest risk of metastasis to the central nervous system.

9530 Background: Cutaneous melanoma (CM) metastasis to the central nervous system (CNS) has a poor prognosis; however, treatment of CNS metastasis while asymptomatic is associated with better outcomes. CNS imaging is not routinely recommended for patients with early-stage CM (i.e., AJCC stage I–II), yet ˜14% of patients with stage II melanoma will develop CNS metastases. The 31-gene expression profile test (31-GEP) identifies patients at a low (Class 1A), intermediate (Class 1B/2A), or high risk (Class 2B) of tumor recurrence and metastasis. We evaluated the association of CNS metastasis with the 31-GEP test result for the purpose of directing CNS-directed imaging to detect metastasis earlier and, thus, improve outcomes. Methods: A retrospective analysis of patients clinically tested with the 31-GEP from 2013-2017. Patients were included in the study if they had clinical or pathological AJCC stage I-II CM (n=1,662). Kaplan-Meier analysis was used to estimate 5-year recurrence-free survival (RFS), and the log-rank test was used to compare survival between groups. Patients with non-CNS metastasis were censored at the time of recurrence. Univariate analysis to identify predictors of CNS metastasis was performed for tumor location, mitotic rate, Breslow thickness, ulceration status, tumor-infiltrating lymphocytes, age, sex, regression, lymphovascular invasion, tumor subtype, and 31-GEP results. Only significant (p<0.01) factors in univariate analysis were included in Cox multivariable analysis. Results: Median follow-up time was 4.6 years (range: 0.02-14.5 years). Patients with a CNS metastasis tended to have thicker tumors (median 1.1 vs. 0.8, p=0.003), higher mitotic rate/mm2 (median 2.5 vs. 1.0, p<0.001) and a higher proportion of males (73% vs. 55%, p=0.03) than patients that did not develop CNS metastasis. Patients with a Class 2B result were significantly more likely to develop CNS metastasis (7.4% [15/202]) relative to patients with a Class 1B/2A (1.7% [5/291]) or Class 1A (0.9% [10/1,169], p<0.001) 31-GEP result. Patients with a Class 2B result had significantly lower 5-year RFS than patients with a Class 1B/2A or Class 1A result (91.6% vs. 98.2% vs. 99.1%, p<0.001) and had shorter times to CNS metastases (1.5 yrs. vs. 4.2 yrs. vs. 3.4 yrs. p<0.001). In multivariable analysis, only the 31-GEP Class 2B (HR=9.42, p<0.001) result was a significant predictor of CNS metastasis; mitotic rate, Breslow thickness, and ulceration were not significantly predictive. Conclusions: Under multivariable analysis, the 31-GEP was the only significant predictor of CNS metastasis, and CNS metastasis occurred early (1.5 yrs). Patients with early-stage I-II CM and a Class 2B result should be considered for CNS imaging to enable asymptomatic detection of CNS metastasis and, thus, improve survival relative to symptomatic CNS metastasis.

Papillary thyroid carcinoma: ≤ 10mm does not always mean pN0. A multicentric real-world study.

The incidence of papillary thyroid carcinoma (PTC) is increasing and PTC ≤ 10mm (PTMC) accounts for most new diagnoses. PTMCs are not always low risk, as detection of lymph nodes metastasis (LNM) may occur. The purpose of the study was to analyze the clinical pattern, frequency, and independent risk factors of patients with PTMC and LNM. From January 2022 to June 2023, PTCs managed at CTO Hospital, Rome; Policlinico Vanvitelli, Naples; and Garibaldi Nesima Hospital, Catania were included. PTC management followed the same diagnostic-therapeutic procedures according to the ATA guidelines. Variables such as age, sex, maximum diameter, histologic evidence of LNM (HELNM +), Hashimoto's thyroiditis (HT), multifocality, capsule invasion, and histological subtype were considered. PTCs were divided according to HELNM and size. Two hundred ninety-eight PTCs were included. PTMCs were 136 (45.6%) and LNM occurred in 27.2% of them. In the HELNM + group, analysis of PTMC vs 'MacroPTC' (PTC > 10mm) did not show any statistical difference. Multivariate regression revealed that young age (OR 0.93; CI 95% 0.90-0.96; p < 0.01) and male sex (male OR 3.44; CI 95% 1.16-10.20; p = 0.03) were the only independent risk factors for HELNM + in PTMC. The risk of LNM in PTMC is not negligible; therefore, a careful evaluation by an expert thyroidologist is mandatory for patients with small thyroid nodule, especially in younger and male patients before excluding surgery. In the future, new tools are needed to detect early PTMC with LNM before surgery.

Detection and surveillance of circulating tumor cells in sarcoma for predicting therapy response and prognosis.

e23573 Background: Generally sarcomas are categorized as soft tissue and bone sarcomas and represent heterogenous group of malignancies with more than 70 distinct histologic subtypes. Due to their rarity and heterogeneity, sarcomas present particular challenges for accurate diagnosis, prognosis, and treatment. The presence and persistence of circulating tumor cells (CTCs) in the peripheral blood are believed to be associated with poor prognosis and distant metastases. A blood-based CTCs test is thus greatly needed for monitoring disease progression and predicting clinical outcomes. Methods: In this study, we developed a CTCs test for the detection and surveillance of sarcoma patients’ CTCs, and subsequently explored its clinical value. 123 patients with sarcomas were enrolled as the cohort for serial CTCs tests. Dynamic CTCs counting, in combination with therapy evaluation and post-treatment follow-up, was used to explore predicting pre- and post-chemotherapy evaluation and prognosis. Results: Quantification of CTCs demonstrated a significant increase in sarcoma patients compared to healthy individuals. Furthermore, patients in stage III-IV had a higher CTC count than those in stage I-II (p&lt;0.01), suggesting a correlation between CTCs and disease development. Remarkably, there was variation in the quantity of CTCs among different types of sarcomas. The highest number of CTCs was observed in undifferentiated small round cell sarcoma, followed by soft tissue tumor, while bone tumors had the lowest number. In addition, the number of CTCs in patients with positive PD-L1 expression was considerably greater than in those with negative expression (p&lt;0.01). The count of CTCs shown a substantial decrease following neoadjuvant chemotherapy treatment. There was a decline in the number of CTCs both before and after postoperative adjuvant chemotherapy treatment, however, there was no significant statistical discrepancy. The number of CTCs at the baseline was shown to be considerably larger in the group of patients with progressive disease or stable disease (PD+SD) compared to the group with partial response or complete response (PR+CR) (p&lt;0.05). This difference was particularly pronounced for interstitial-type CTCs (p&lt;0.01). Conclusions: The rate of presence of CTCs in the peripheral blood of sarcoma patients is high, and patients with an increased percentage of CTCs after treatment have a poor treatment effect. The dynamic monitoring of changes in CTCs counts after treatment has clinical significance for the timely detection of recurrence or metastasis. CTCs also showed a clinical value in prediction of therapy efficiency or prognosis, and may be clinically valuable for the whole course management of patients.

Temporal fiber-optic fluorescence study of FAD-NADH interactions in phantoms for potential applications in rapid liquid optical biopsy procedures

Body fluids carry several biomarkers and genetic material that enable the detection of carcinogenesis and tumor metastasis. Owing to this, liquid biopsy is gaining importance and entering clinical practice as an adjunct modality to the current standard of practice in cancer detection. Liquid biopsy involving specimens such as urine is non-invasive and has biomarkers reflecting the tumor microenvironment. We investigate the normal and altered levels of cellular metabolic by-products in liquid phantoms and demonstrate their photon-induced excited-state interaction behaviour for potential diagnostic applications. Short-span temporal analysis of metabolic by-products FAD and NADH in liquid phantoms with fiber optic fluorescence spectroscopy is carried out. The mixed liquid phantom of FAD and NADH, showed excited state interactions that manifested as simultaneous inverse variation in the fluorescence emission from FAD and NADH in varying pH environments. Linear discriminant analysis of the time-varying integrated fluorescence intensity resulted in a 100% accuracy in classifying liquid samples between high and low metabolite concentrations. An extension of application of the experiment model for analysis of body fluids such as urine is also discussed.

A Nomogram Based on Clinicopathological Characteristics for Estimating the Risk of Brain Metastasis from Advanced Gastric Cancer: A Multi-Center Retrospective Clinical Study.

Although brain metastasis (BM) from gastric cancer (GC) is relatively uncommon, its incidence has been increasing owing to advancements in treatment modalities. Unfortunately, patients diagnosed with BM from gastric cancer have poor life expectancy. Our study aims to establish a predictive model for brain metastasis in advanced gastric cancer patients, thus enabling the timely diagnosis of brain metastasis. The clinicopathological features of a cohort which included 40 GC patients with brain metastasis, 32 of whom from the First Affiliated Hospital of Nanchang University, 2 from Gaoxin Branch of the First Affiliated Hospital of Nanchang University, remaining 6 from Anyang District Hospital, and 80 non-metastatic advanced GC patients from the First Affiliated Hospital of Nanchang University between 2018 and 2022. Data were retrospectively analyzed. Age, tumor size, differentiation, lymph node grade, tumor location, Lauren classification, liver metastasis, carbohydrate antigen 199 (CA199), lactate dehydrogenase (LDH), and human epidermal growth factor receptor 2 (Her-2) were associated with BM. A nomogram integrated with nine risk factors (tumor size, differentiation, lymph node grade, tumor location, Lauren classification, liver metastasis, CA-199, LDH, and Her-2) showed good performance (Area Under Curve 0.95, 95% CI: 0.91-0.98). We developed and validated a nomogram that achieved individualized prediction of the possibility of BM from GC. This model enables personalized imaging review schedules for timely brain metastasis detection in advanced gastric cancer patients.

MoS2/MXene Van der Waals heterojunction-based electrochemiluminescence sensor for triple negative breast cancer detection

The van der Waals heterojunction is able to combine the advantages of different materials and has potential to be used in biosensing researches. In this study, we developed a novel van der Waals heterojunction by combining MXene and MoS2 nanosheets for the electrochemiluminescence (ECL) sensing applications. This van der Waals heterojunction material not only possessed the superior conductivity of MXene, but also regulated the electron transport. Additionally, the incorporation of MoS2 nanosheets into the MXene interlayers significantly enhances the material stability. Meanwhile, nitrogen-rich quantum dots (N dots) were synthesized as ECL tags with an impressive nitrogen content of up to 75 %. By integrating the ECL response of N dots within the van der Waals heterojunction, we established a highly efficient sensing system for miRNA-373, which overexpressed in triple negative breast cancer tissues. The van der Waals heterojunction-based biosensor can enhance the ECL signal of N dots effectively to detect miRNA-373 from 1 fM to 1 μM. Consequently, the developed sensing system holds promise for the early detection of metastasis of the triple-negative breast cancer, paving the way for the effective clinical interventions.

Dual-energy CT applications on liver imaging: what radiologists and radiographers should know? A systematic review.

This review aims to provide a comprehensive summary of DECT techniques, acquisition workflows, and post-processing methods. By doing so, we aim to elucidate the advantages and disadvantages of DECT compared to conventional single-energy CT imaging. A systematic search was conducted on MEDLINE/EMBASE for DECT studies in liver imaging published between 1980 and 2024. Information regarding study design and endpoints, patient characteristics, DECT technical parameters, radiation dose, iodinated contrast agent (ICA) administration and postprocessing methods were extracted. Technical parameters, including DECT phase, field of view, pitch, collimation, rotation time, arterial phase timing (from injection), and venous timing (from injection) from the included studies were reported, along with formal narrative synthesis of main DECT applications for liver imaging. Out of the initially identified 234 articles, 153 met the inclusion criteria. Extensive variability in acquisition parameters was observed, except for tube voltage (80/140 kVp combination reported in 50% of articles) and ICA administration (1.5mL/kg at 3-4mL/s, reported in 91% of articles). Radiation dose information was provided in only 40% of articles (range: 6-80mGy), and virtual non-contrast imaging (VNC) emerged as a common strategy to reduce the radiation dose. The primary application of DECT post-processed images was in detecting focal liver lesions (47% of articles), with predominance of study focusing on hepatocellular carcinoma (HCC) (27%). Furthermore, a significant proportion of the articles (16%) focused on enhancing DECT protocols, while 15% explored metastasis detection. Our review recommends using 80/140 kVp tube voltage with 1.5mL/kg ICA at 3-4mL/s flow rate. Post-processing should include low keV-VMI for enhanced lesion detection, IMs for tumor iodine content evaluation, and VNC for dose reduction. However, heterogeneous literature hinders protocol standardization.

When to Consider Invasive Lymph Node Staging in Non–Small-Cell Lung Cancer? A Novel Scoring System Utilising Metabolic Parameters in 18F-FDG PET/CT

ObjectiveThe maximum standardised uptake value (SUVmax) is a widely utilised metric in positron emission tomography/computed tomography for clinically staging non–small-cell lung cancer (NSCLC), yet the reliability of SUVmax remains controversial. We herein aimed to assess the effectiveness of semi-quantitative parameters, encompassing size, SUVmax, metabolic tumour volume (MTV), total lesion glycolysis (TLG) and heterogeneity factor (HF), in evaluating both primary tumours and lymph nodes (LNs) on positron emission tomography/computed tomography. A novel scoring system was devised to appraise the role of semi-quantitative parameters and visually evaluate LNs for nodal staging. Materials and MethodsPatients with pathological NSCLC, diagnosed between 2014 and 2019 and clinically staged I-III, were enrolled in the study. Patient demographics, including age, sex, tumour location, diameter, tumour-node-metastasis stage, as well as SUVmax, MTV, TLG and HF parameters of primary tumours and LNs, were documented. ResultsThe analysis comprised 319 patients and 963 LNs. Patients had a mean age of 61.62 years, with 91.5% being male. Adenocarcinoma exhibited a histological association with LN metastasis (P=0.043). The study findings revealed that tumour size, SUVmax, MTV, TLG and HF did not significantly affect the detection of LN metastasis. Conversely, non-squamous cell carcinoma, LNs exhibiting higher FDG levels than the liver, LN size, SUVmax, MTV and TLG were identified as risk factors (P<0.0001). The identified cut-off values were 1.05cm for LN size, 4.055 for SUVmax, 1.805cm3 for MTV and 5.485 for TLG. The scoring system incorporated these parameters, and visual assessment indicated that a score of ≥3 increased the risk of metastasis by 14.33 times. ConclusionWe devised a novel scoring system and demonstrated that LNs with a score of ≥3 in patients with NSCLC have a high likelihood of metastasis. This innovative scoring system can serve as a valuable tool to mitigate excessive and extreme measures in the assessment of invasive pathological staging.

Comparison of diagnostic value of quantitative parameters from FAPI and FDG PET/CT in the detection of mediastinal lymph node metastasis in non-small cell lung cancer

Comparison of diagnostic value of quantitative parameters from FAPI and FDG PET/CT in the detection of mediastinal lymph node metastasis in non-small cell lung cancer

Surgical treatment for pulmonary metastasis from ovarian cancer: a retrospective case series

BackgroundDistant metastases of ovarian cancer are rarely detected alone. The effectiveness of surgical intervention for pulmonary metastases from ovarian cancer remains uncertain. This study aimed to investigate the clinicopathologic characteristics and outcomes of patients undergoing resection for pulmonary metastasis from ovarian cancer.Case presentationThe clinicopathologic characteristics and outcomes of radical surgery for pulmonary metastasis from ovarian cancer were investigated. Out of 537 patients who underwent pulmonary metastasis resection at two affiliated hospitals between 2010 and 2021, four (0.74%) patients who underwent radical surgery for pulmonary metastasis from ovarian cancer were included. The patients were aged 67, 47, 21, and 59 years; the intervals from primary surgery to detection of pulmonary metastasis from ovarian cancer were 94, 21, 36, and 50 months; and the overall survival times after pulmonary metastasectomy were 53, 50, 94, and 34 months, respectively. Three of the four patients experienced recurrence after pulmonary metastasectomy. Further, preoperative carbohydrate antigen (CA) 125 levels were normal in two surviving patients and elevated in the two deceased patients.ConclusionIn this study, three of the four patients experienced recurrence after pulmonary metastasectomy, but all patients survived for > 30 months after surgery. Patients with ovarian cancer and elevated CA125 levels may not be optimal candidates for pulmonary metastasectomy. To establish appropriate criteria for pulmonary metastasectomy in patients with ovarian cancer, further research on a larger patient cohort is warranted.

Artificial Intelligence Helps Pathologists Increase Diagnostic Accuracy and Efficiency in the Detection of Breast Cancer Lymph Node Metastases.

The detection of lymph node metastases is essential for breast cancer staging, although it is a tedious and time-consuming task where the sensitivity of pathologists is suboptimal. Artificial intelligence (AI) can help pathologists detect lymph node metastases, which could help alleviate workload issues. We studied how pathologists' performance varied when aided by AI. An AI algorithm was trained using more than 32 000 breast sentinel lymph node whole slide images (WSIs) matched with their corresponding pathology reports from more than 8000 patients. The algorithm highlighted areas suspicious of harboring metastasis. Three pathologists were asked to review a dataset comprising 167 breast sentinel lymph node WSIs, of which 69 harbored cancer metastases of different sizes, enriched for challenging cases. Ninety-eight slides were benign. The pathologists read the dataset twice, both digitally, with and without AI assistance, randomized for slide and reading orders to reduce bias, separated by a 3-week washout period. Their slide-level diagnosis was recorded, and they were timed during their reads. The average reading time per slide was 129 seconds during the unassisted phase versus 58 seconds during the AI-assisted phase, resulting in an overall efficiency gain of 55% ( P <0.001). These efficiency gains are applied to both benign and malignant WSIs. Two of the 3 reading pathologists experienced significant sensitivity improvements, from 74.5% to 93.5% ( P ≤0.006). This study highlights that AI can help pathologists shorten their reading times by more than half and also improve their metastasis detection rate.

Clinical characteristics and prognosis analysis of gastric cancer patients with bone metastasis

Objectives: To investigate the clinical characteristics and prognosis of bone metastasis of gastric cancer, analyze the influencing factors of bone metastasis and the effects of different treatment methods, and provide a basis for early detection and treatment optimization of bone metastasis of gastric cancer. Methods: A total of 142 gastric cancer patients with bone metastasis admitted to the First Hospital of Lanzhou University from January 2011 to December 2021 were enrolled, including 60 cases of simple bone metastasis and 82 cases of bone metastasis combined with extraosseous metastasis. 142 patients with stage Ⅲgastric cancer without distant metastasis and 142 gastric cancer patients with visceral metastasis admitted to this hospital during the same period were also enrolled for comparison. Logistic regression analysis was used to determine the influencing factors of bone metastasis, and the Cox proportional hazards regression model was used to evaluate the influencing factors of overall survival (OS) of patients with bone metastasis. Results: Among the 142 patients with bone metastasis, poorly differentiated adenocarcinoma was the main type (123 cases), and 45 patients had simultaneous bone metastasis. Rib metastasis (100 cases), spine metastasis (88 cases), and pelvis metastasis (84 cases) were more common. A total of 110 patients had multiple bone metastasis, and 82 patients had extraosseous metastasis. Results of the stage Ⅲ gastric cancer group, the visceral metastasis group, the bone metastasis group, and the bone metastasis with extraosseous metastasis group were compared. There were significant differences in age, degree of differentiation, Borrmann type, alkaline phosphatase, lactate dehydrogenase, serum calcium, alanine aminotransferase, aspartate aminotransferase, creatine kinase isoenzyme, lymphocyte, hemoglobin, platelet, CEA, CA19-9, and CA724 (all P<0.05). Multivariate logistic regression analysis showed that Borrmann type was an independent protective factor of bone metastasis of gastric cancer (type 3: OR=0.07, 95%CI: 0.01-0.64, P=0.018). Alkaline phosphatase (OR=2.54, 95% CI: 1.07-6.01, P=0.034), serum calcium (OR=2.71, 95% CI: 1.15-6.41, P=0.023), creatine kinase isoenzyme (OR=16.33, 95% CI: 1.83-145.58, P=0.012), platelet (OR=10.08, 95% CI:1.89-53.85, P=0.007), and CA19-9 (OR=2.40, 95% CI: 1.14-5.05, P=0.021) were independent risk factors of bone metastasis of gastric cancer. The median OS of the stage Ⅲ gastric cancer group, the visceral metastasis group, the bone metastasis group, and the bone metastasis with extrabony group were 47, 13, 18, and 6 months, respectively, and the difference was statistically significant (P<0.001). The median OS of patients with bone metastasis only who underwent primary tumor surgery was 33 months, better than 6 months of patients without surgery (P=0.048). Multivariate Cox regression analysis showed that extraosseous metastasis (HR=2.45, 95% CI: 1.56-3.85, P<0.001) and decreased hemoglobin (HR=1.54, 95%CI: 1.02-2.34, P=0.042) were independent risk factors of OS of gastric cancer patients with bone metastasis. Conclusions: The prognosis of gastric cancer patients with bone metastasis alone is significantly better than that of other stage Ⅳ patients. For such patients, surgery on the primary site combined with chemotherapy after full evaluation may prolong the survival time.

Cholangiocarcinoma: The Current Status of Surgical Options including Liver Transplantation.

Cholangiocarcinoma (CCA) poses a substantial threat as it ranks as the second most prevalent primary liver tumor. The documented annual rise in intrahepatic CCA (iCCA) incidence in the United States is concerning, indicating its growing impact. Moreover, the five-year survival rate after tumor resection is only 25%, given that tumor recurrence is the leading cause of death in 53-79% of patients. Pre-operative assessments for iCCA focus on pinpointing tumor location, biliary tract involvement, vascular encasements, and metastasis detection. Numerous studies have revealed that portal vein embolization (PVE) is linked to enhanced survival rates, improved liver synthetic functions, and decreased overall mortality. The challenge in achieving clear resection margins contributes to the notable recurrence rate of iCCA, affecting approximately two-thirds of cases within one year, and results in a median survival of less than 12 months for recurrent cases. Nearly 50% of patients initially considered eligible for surgical resection in iCCA cases are ultimately deemed ineligible during surgical exploration. Therefore, staging laparoscopy has been proposed to reduce unnecessary laparotomy. Eligibility for orthotopic liver transplantation (OLT) requires certain criteria to be granted. OLT offers survival advantages for early-detected unresectable iCCA; it can be combined with other treatments, such as radiofrequency ablation and transarterial chemoembolization, in specific cases. We aim to comprehensively describe the surgical strategies available for treating CCA, including the preoperative measures and interventions, alongside the current options regarding liver resection and OLT.

68Ga]Ga-FAPI-46 PET/CT for penile cancer - a feasibility study.

Penile cancer is a rare entity and has a good prognosis in localized stage. Delayed surgical treatment of lymphatic disease is associated with poor overall survival but conventional imaging cannot detect occult lymph node metastasis sufficiently. Imaging cancer related fibroblasts has shown promising results as non-invasive staging tool in various tumor entities but has not yet been evaluated in penile cancer. In this single-center pilot study, patients planned for surgical treatment for penile cancer underwent preoperatively [68Ga]Ga-FAPI-46 PET/CT. Post-operative histopathology was compared to [68Ga]Ga-FAPI-46 PET/CT results. From January 2022 to June 2022, a total number 11 patients with histopathologically proven penile cancer underwent surgery and received [68Ga]Ga-FAPI-46 PET/CT prior therapy. 8 primary tumor sites and 4 lymph node regions were analyzed. FAPI uptake was increased on primary tumor site (SUVmax 16.2 (9.1 - 25.8)). Histopathological proven lymph node regions showed highly increased FAPI uptakes (SUVmax 17.9 (16.4 - 23.5) on [68Ga]Ga-FAPI-46 PET/CT. In this first pilot cohort, there were no false-positive FAPI uptake which might allow the detection of occult lymph node metastasis by [68Ga]Ga-FAPI-46 PET/CT and might consequently lead to omitting lymph node regions during surgery that had no increased FAPI uptake pre-operatively.

Active Targeting Hyaluronan Conjugated Nanoprobe for Magnetic Particle Imaging and Near-Infrared Fluorescence Imaging of Breast Cancer and Lung Metastasis.

A major contributing cause to breast cancer related death is metastasis. Moreover, breast cancer metastasis often shows little symptoms until a large area of the organs is occupied by metastatic cancer cells. Breast cancer multimodal imaging is attractive since it integrates advantages from several modalities, enabling more accurate cancer detection. Glycoprotein CD44 is overexpressed on most breast cancer cells and is the primary cell surface receptor for hyaluronan (HA). To facilitate breast cancer diagnosis, we report an indocyanine green (ICG) and HA conjugated iron oxide nanoparticle (NP-ICG-HA), which enabled active targeting to breast cancer by HA-CD44 interaction and detected metastasis with magnetic particle imaging (MPI) and near-infrared fluorescence imaging (NIR-FI). When evaluated in a transgenic breast cancer mouse model, NP-ICG-HA enabled the detection of multiple breast tumors in MPI and NIR-FI, providing more comprehensive images and a diagnosis of breast cancer. Furthermore, NP-ICG-HAs were evaluated in a lung metastasis model. Upon NP-ICG-HA administration, MPI showed clear signals in the lungs, indicating the tumor sites. This is the first time that HA-based NPs have enabled MPI of cancer. NP-ICG-HAs are an attractive platform for noninvasive detection of primary breast cancer and lung metastasis.

Abstract IA022: AI in bladder cancer pathology and research: What can we expect and what not?

Abstract Artificial intelligence (AI) applications are rapidly evolving, disruptive technologies that recently attracted tremendous public awareness including euphoria, bull runs at stock exchanges but also criticism and skepticism. Pathology, a crucial clinical diagnostic discipline, faces significant challenges despite its critical role and broad scope. A notable issue is the declining interest among medical graduates in pursuing further training in Surgical Pathology and Molecular Pathology. This disinterest is compounded by a trend towards part-time work and the aging demographic in Western industrial nations, which increases the demand for precise cancer diagnoses, molecular pathology and advanced oncological treatments. As the need for skilled pathologists grows, the availability of these professionals is steadily decreasing. Furthermore, political policies in heavily regulated healthcare systems (e.g., Germany) are exacerbating the shortage by limiting residency and specialist training positions despite the growing need. Adding to the reluctance among medical graduates to consider pathology as discipline is the looming “threat”” of replacing the field with Artificial Intelligence (AI) technologies. However, historical precedents suggest that necessity often spurs significant innovation. AI's role in pathology is expanding, reshaping the field with new technological advancements. AI, broadly encompassing various computational algorithms designed to perform tasks typically requiring human intelligence such as learning, reasoning, and pattern recognition, is now being applied extensively across different domains including medical diagnostics. Recent implementations in pathology include AI-driven algorithms that automate processes such as the Gleason grading of prostate biopsies, lymph node metastasis detection, detection of molecular bladder cancer subtypes or grading of kidney cancer showing high accuracy levels, speed and reproducibility in delivering results. These tools, while they do not replace pathologists, significantly reduce their workload by automating routine tasks, thus freeing up time for more complex diagnostic activities or simply dealing with the increasing workload. Despite the exciting possibilities, the use of AI in predicting molecular alterations, such as FGFR3 mutations in bladder cancer, faces limitations due to insufficient sensitivity and specificity, indicating that such technologies are not yet suitable for screening purposes. In conclusion, AI is increasingly vital in addressing the challenges of modern pathology, particularly in compensating for the shortage of pathologists. As technology advances, its integration into clinical practice offers promising solutions to enhance diagnostic accuracy and efficiency in uropathology, paving the way for more personalized and effective patient care. Citation Format: Markus Eckstein. AI in bladder cancer pathology and research: What can we expect and what not? [abstract]. In: Proceedings of the AACR Special Conference on Bladder Cancer: Transforming the Field; 2024 May 17-20; Charlotte, NC. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(10_Suppl):Abstract nr IA022.

THE APEX TALKS…CARDIAC METASTASIS MIMICKING ST SEGMENT ELEVATION MYOCARDIAL INFARCTION

Abstract A 78–year–old man with a recent diagnosis of lung squamous cell carcinoma was referred to our cardiology department for marked ECG abnormalities (ST segment elevation in V2–V4 and T waves inversion in the antero–lateral leads, Fig.1) in the absence of ischemic symptoms and for the detection of an intramyocardial mass at the apical segments on the CT scan. He had no significant previous cardiovascular history. A transthoracic echocardiogram (TTE) was performed and showed an isoechoic mass at the LV apical segments measuring 3 x 4 cm apparently incorporating the myocardial wall without a clear cleavage plane (Fig.2a). The EF was normal. No pericardial effusion present. The contrast echocardiography with Sonovue revealed a late uptake of the contrast (Fig.2b). Cardiac magnetic resonance (CMR) showed an ovular image in the para–apical area of 40 x 23 cm consistent with a secondary lesion (Fig.3). Unfortunately, the exam was interrupted early due to a patient’s claustrophobic crisis, without having acquired the post–contrast images. Due to infiltrative appearance of the mass and the oncology history, this formation was highly suspicious for metastasis. No complicated ventricular arrhythmias were detected on ECG monitoring. No symptoms of heart failure were reported. Due to the marked EKG repolarization abnormalities the patient underwent coronary angiography which excluded significant stenosis. FDG PET/CT showed areas of increased metabolism also at liver and adrenal left gland. Finally, the patient was transferred to the oncology department for specific management. Cardiac metastases are more common than primary cardiac malignancy and are more frequently related to primary lung cancer, followed by breast cancer and hematologic malignancies. Typical presentation includes arrhythmias or conduction disturbances. The imaging findings of cardiac metastases are non–specific but mostly infiltrative, heterogeneous, and multiple masses may be present. Echocardiography is the initial imaging test for the detection of cardiac metastasis, although CMR, CT and PET/CT may be helpful. Herein we described a case of cardiac metastasis with EKG mimicking acute coronary syndrome. This finding is not uncommon among these patients. EKG findings of myocardial ischemia or injury, particularly localized and prolonged ST elevation, in the absence of ischemic symptoms have been reported in previous studies as high specificity for cardiac metastasis in patients with malignancy.

Oropharyngeal Cancer Staging Health Record Extraction Using Artificial Intelligence

Accurate, timely, and cost-effective methods for staging oropharyngeal cancers are crucial for patient prognosis and treatment decisions, but staging documentation is often inaccurate or incomplete. With the emergence of artificial intelligence in medicine, data abstraction may be associated with reduced costs but increased efficiency and accuracy of cancer staging. To evaluate an algorithm using an artificial intelligence engine capable of extracting essential information from medical records of patients with oropharyngeal cancer and assigning tumor, nodal, and metastatic stages according to American Joint Committee on Cancer eighth edition guidelines. This retrospective diagnostic study was conducted among a convenience sample of 806 patients with oropharyngeal squamous cell carcinoma. Medical records of patients with staged oropharyngeal squamous cell carcinomas who presented to a single tertiary care center between January 1, 2010, and August 1, 2020, were reviewed. A ground truth cancer stage dataset and comprehensive staging rule book consisting of 135 rules encompassing p16 status, tumor, and nodal and metastatic stage were developed. Subsequently, 4 distinct models were trained: model T (entity relationship extraction) for anatomical location and invasion state, model S (numerical extraction) for lesion size, model M (sequential classification) for metastasis detection, and a p16 model for p16 status. For validation, results were compared against ground truth established by expert reviewers, and accuracy was reported. Data were analyzed from March to November 2023. The accuracy of algorithm cancer stages was compared with ground truth. Among 806 patients with oropharyngeal cancer (mean [SD] age, 63.6 [10.6] years; 651 males [80.8%]), 421 patients (52.2%) were positive for human papillomavirus. The artificial intelligence engine achieved accuracies of 55.9% (95% CI, 52.5%-59.3%) for tumor, 56.0% (95% CI, 52.5%-59.4%) for nodal, and 87.6% (95% CI, 85.1%-89.7%) for metastatic stages and 92.1% (95% CI, 88.5%-94.6%) for p16 status. Differentiation between localized (stages 1-2) and advanced (stages 3-4) cancers achieved 80.7% (95% CI, 77.8%-83.2%) accuracy. This study found that tumor and nodal staging accuracies were fair to good and excellent for metastatic stage and p16 status, with clinical relevance in assigning optimal treatment and reducing toxic effect exposures. Further model refinement and external validation with electronic health records at different institutions are necessary to improve algorithm accuracy and clinical applicability.

A growing number of AIs cleared for clinical use is finally available: The AI-assisted Pathologist

As more pathology laboratories are transitioning to a digital workflow, the availability of commercial Artificial Intelligence assistance systems is also increasing. Today nearly 40 such products approved for diagnostic use are available. This article provides an overview of the most widely addressed use cases, including Immunohistochemistry scoring for breast cancer and non-small-cell lung cancer, Gleason grading for prostate cancer, or metastasis detection in lymph nodes. While automation alone already promises an increase in efficiency that may help to bridge the growing gap between supply (pathology work force) and demand (histological testing), this article introduces another category of Artificial Intelligence products that go beyond just mimicking today’s established score. Various Artificial Intelligence are being introduced that detect genetic alterations or stratify risk, directly from the standard hematoxylin &amp; eosin staining. Finally, a brief outlook explains how basic AI models are currently finding their way into computational pathology and promise to further accelerate product developments by decreasing the time-to-model.