Detection Of Metastases Research Articles

Machine learning and deep learning models for preoperative detection of lymph node metastasis in colorectal cancer: a systematic review and meta-analysis

Machine learning and deep learning models for preoperative detection of lymph node metastasis in colorectal cancer: a systematic review and meta-analysis

In Vivo Detection of Lymph Nodes Metastasis of ESCC Using CXCR4-Targeted Tracer [64Cu]Cu-NOTA-CP01.

Esophageal squamous cell carcinoma (ESCC) frequently exhibits skip metastasis to lymph nodes; however, non-invasive imaging techniques capable of directly visualizing metastatic lymph nodes (MLN) are still lacking. Although biopsy is the clinical standard method, it is invasive and poses risks to patient health. This study aims to detect MLN in an intralymphatic tumor metastasis model of ESCC using the CXCR4-targeted tracer [64Cu]Cu-NOTA-CP01. The CXCR4 expression in ESCC cell lines was assessed using Western blot and immunofluorescence. An intralymphatic tumor metastasis model was established and monitored using bioluminescence imaging (BLI). Small animal PET studies and biodistribution studies were performed to evaluate the specificity of [64Cu]Cu-NOTA-CP01 for MLN. Histopathology evaluation was employed to check for the presence of metastatic tumor cells and to assess CXCR4 expression levels in the metastatic lymph nodes. The intralymphatic tumor metastasis model was successfully established using the EC109/Luc cell line, which exhibited high CXCR4 expression, as verified by BLI. PET/CT imaging showed that the MLN uptakes in the baseline group were significantly inhibited in the blocking group. The ratios of MLN/muscle and MLN/blood werealso significantly higher in the baseline group than in the blocking group. Ex vivo PET/CT imaging of MLN corroborated the in vivo data. Biodistribution studies further supported the PET imaging studies, showing rapid clearance of the tracer from the blood and major organs, with significantly higher MLN/muscle and MLN/blood ratios in the baseline group compared to the blocking group. Histopathological staining verified positive CXCR4 expression in these lymph nodes containing metastatic tumor cells. Targeting CXCR4 with [64Cu]Cu-NOTA-CP01 for PET imaging of lymph nodes metastasis represents a promising approach that warrants further investigation. These findings have the potential to enhance diagnostic and therapeutic strategies for individuals with lymph nodes metastasis of ESCC.

AI-Assisted Detection and Localization of Spinal Metastatic Lesions

Objectives: The integration of machine learning and radiomics in medical imaging has significantly advanced diagnostic and prognostic capabilities in healthcare. This study focuses on developing and validating an artificial intelligence (AI) model using U-Net architectures for the accurate detection and segmentation of spinal metastases from computed tomography (CT) images, addressing both osteolytic and osteoblastic lesions. Methods: Our methodology employs multiple variations of the U-Net architecture and utilizes two distinct datasets: one consisting of 115 polytrauma patients for vertebra segmentation and another comprising 38 patients with documented spinal metastases for lesion detection. Results: The model demonstrated strong performance in vertebra segmentation, achieving Dice Similarity Coefficient (DSC) values between 0.87 and 0.96. For metastasis segmentation, the model achieved a DSC of 0.71 and an F-beta score of 0.68 for lytic lesions but struggled with sclerotic lesions, obtaining a DSC of 0.61 and an F-beta score of 0.57, reflecting challenges in detecting dense, subtle bone alterations. Despite these limitations, the model successfully identified isolated metastatic lesions beyond the spine, such as in the sternum, indicating potential for broader skeletal metastasis detection. Conclusions: The study concludes that AI-based models can augment radiologists’ capabilities by providing reliable second-opinion tools, though further refinements and diverse training data are needed for optimal performance, particularly for sclerotic lesion segmentation. The annotated CT dataset produced and shared in this research serves as a valuable resource for future advancements.

Clinical performance of a simulated abbreviated liver MRI in combination with contrast enhanced CT for the baseline evaluation of the liver in patients with colorectal cancer

ObjectivesTo assess the diagnostic accuracy and inter-reader agreement of a simulated abbreviated gadoxetate liver MRI protocol together with CE-CT against a standard gadoxetate MRI for the detection of colorectal liver metastases at baseline. MethodsThree readers independently evaluated two sets of images per patient, recording number and location of metastases and benign lesions. Set 1 comprised T1w, T2w, DWI, multiphase CE-T1w and HPB images (standard). Set 2 included T2w, HBP, DWI (from Set 1) and CE-CT (simulated abbreviated). Diagnostic performance was compared using McNemar’s test. Level of agreement between sets 1 and 2 was determined with Cohen kappa. For agreement in the number of benign lesions and metastases, we applied ICC. Results75 patients (245 metastases, 122 benign lesions) were evaluated. There was no significant difference in diagnostic accuracy between set 1 and 2 for each reader (mean P=0.74). The total number of metastases and benign lesions showed high agreement between reading set 1 and 2 (κ = 0.81, 0.78). The total number of metastases showed substantial agreement between readers for set 1 and 2 (ICC = 0.99, 0.99). Good agreement was seen for metastatic segmental involvement (κ = 0.84–0.99). ConclusionsAt baseline, using a simulated abbreviated liver MRI together with CE-CT showed excellent agreement with standard MRI protocol for liver metastasis detection.

Fisher discriminant analysis of multimodal ultrasound in diagnosis of cervical metastatic lymph nodes in papillary thyroid cancer.

The purpose of this study was to develop a diagnostic model utilizing multimodal ultrasound parameters to aid in the detection of cervical lymph node metastasis in papillary thyroid cancer (PTC) patients. The study included 84 suspicious lymph nodes from 69 PTC patients, all of whom underwent fine needle aspiration with pathological results. Data from conventional grayscale ultrasound, shear wave elastography (SWE), and superb microvascular imaging were analyzed. Key ultrasound features were compared between benign and metastatic groups to create a diagnostic model using Fisher's stepwise discriminant analysis. The model's effectiveness was assessed with self-testing, cross-validation, and receiver operating characteristic curve analysis. Four features, namely lymphatic hilum (X1), cortical hyperechogenicity (X2), vascular pattern (X4), and SWEmean (X7), were integral to the discriminant analysis, resulting in the equation: Y1 = -3.461 + 2.423X1 + 0.321X2 + 1.620X4 + 0.109X7, Y2 = -8.053 + 0.414X1 + 2.600X2 + 2.504X4 + 0.192X7. If Y1 < Y2, the LN would be diagnosed as metastatic lymph nodes. The model demonstrated an area under the curve of 0.833, with a sensitivity of 83.33% and specificity of 83.33%. The multimodal ultrasound diagnostic model, established through Fisher's stepwise discriminant analysis, proved effective in identifying metastatic lymph nodes in PTC patients.

Diagnostic accuracy of imaging modalities for detection of spinal metastases: a systematic review and meta-analysis.

Detecting spinal metastases is highly relevant in patients with oncological disorders as it can affect the staging and treatment of their disease. We aimed to evaluate the diagnostic performance of computed tomography (CT), magnetic resonance imaging (MRI), FDG positron emission tomography (PET)/CT, bone scintigraphy (BS), and single-photon emission computed tomography (SPECT) for spinal metastases detection. Medline, EMBASE, and Web of Science were systematically searched until March 2024 for diagnostic accuracy studies on spinal metastases detection (PROSPERO-registration: CRD42024540139). Data extraction and quality assessment using the QUADAS-2 tool were performed by two independent reviewers. Using bivariate random effects modeling, pooled sensitivities, specificities, and diagnostic odds ratios (DOR) were calculated, and hierarchical summary operating curves were constructed. Twenty-five studies (49 datasets), encompassing 3102 patients were included. Per-patient pooled sensitivities of CT, MRI, PET/CT, BS and SPECT were 70%, 93%, 82%, 75%, and 84%, respectively. Pooled specificities were 74%, 85%, 75%, 92%, and 81%, respectively. Per-lesion pooled sensitivities of CT, MRI, PET/CT, BS and SPECT were 76%, 91%, 92%, 77%, and 92%, respectively. Pooled specificities were 91%, 94%, 85%, 52%, and 86%, respectively. MRI had the highest DOR in per patient and lesion analyses. MRI had highest diagnostic accuracy for spinal metastases detection on patient and lesion level, suggesting a broader use in addition to the routine staging CT, at least in patients at high risk and where the detection of a spinal metastasis could alter therapy decisions. Herein, results should be considered with the limitations of each modality.

Survey on Breast Cancer analysis

Breast cancer constitutes 12% of all newly diagnosed cases globally, making it the most predominant type of cancer as a whole. Histopathology images, among all the medical image modalities, maintain the cancer's path and provide richer phenotypic relevant information. The patient's immune system is progressively predictable as a critical feature in defining the suitable treatment. Tumor-infiltrating lymphocytes (TILs), immune cells found within tumors, are emerging as key biomarkers in breast cancer. The detection of lymph node metastasis affects the management of patients with primary breast cancer significantly in terms of staging, treatment, and prognosis.Tumoour infiltrating lymphocytes score and lymph node metastasis identification plays a very important role in staging of breast cancer.This review aims to provide a comprehensive overview on how deep learning-based method is used to compute the Tumour-Infiltrating Lymphocytes (TILs) score and lymph node metastasis from breast cancer histopathological images.

Lymph nodal volume in head and neck malignancy: can adding a third dimension improve the detection of nodal metastasis?

BackgroundTo compare the diagnostic utility of computed tomography (CT) and ultrasonography (USG) for preoperative determination of metastatic lymph nodes.MethodsHead and neck squamous cell carcinoma (HNSCC) cases planned for neck dissection were included. All underwent preoperative neck USG and CT followed by histopathological evaluation after surgery. Sensitivity, specificity, positive and negative predictive value along with accuracy was calculated for each outcome variable. Efficacy was calculated by comparing these to postoperative histopathology. Both imaging modalities were compared with lymph nodal volume.ResultsEighty-seven lymph nodes were selected from 30 patients. Median volume on CT was 5412.15 mm3 for metastatic and 237.7 mm3 for benign nodes and on ultrasound, 4168.92 mm3 for metastatic and 233.1 mm3 for benign nodes (p < 0.001). Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for volume on USG were 81.8%, 98.7%, 96.6%, 90%, and 97.4% and on CT were 81.8%, 100%, 97.7%, 100%, and 97.4% respectively.ConclusionsLymph nodal volume had higher sensitivity and specificity for detection of metastatic cervical lymphadenopathy and individually or in combination should be included as one of the criteria in preoperative assessment of HNSCC.

Response to furmonertinib in a patient with non-small cell lung cancer harboring HER2 exon 21 insertion mutation: a case report

BackgroundThis is the first case report describing a patient with non-small cell lung cancer (NSCLC) harboring two rare human epidermal growth factor receptor 2 (HER2) exon 21 insertion mutations, who responded to furmonertinib treatment. Furmonertinib maybe one effective and economical treatment for NSCLC patients harboring HER2 mutations with minor side effects.Case descriptionWe present a case report of a 49-year-old female diagnosed with stage IV lung adenocarcinoma who complained of irritating dry cough symptoms followed by chest tightness. Firstly, we describe the patient’s treatment history, including failed third-line combination treatments of systemic chemotherapy with bevacizumab or carrelizumab or anlotinib, primary lung tumor recurrence, bilateral lung metastases progression, and new brain metastatic lesion detection. Next, we detail the patient’s fourth-line treatment with radiotherapy for brain metastases and two cycles of bevacizumab plus Abraxane and cisplatin, however, the disease progressed and relapsed. After that, comprehensive genomic profiling revealed two HER2 exon 21 insertion mutations. Subsequently, the patient received targeted therapy with furmonertinib and achieved 11 months of progression-free survival. The patient received pyrrotinib therapy for 2 months after disease progression, but the disease continued to progress. In October 2023, the patient received therapy with furmonertinib again, and a month later, the disease went into partial remission. However, the patient died due to hypoproteinemia combined with severe pneumonia in December 2023.ConclusionFurmonertinib may be effective for NSCLC patients with HER2 T8962A and L869R mutations and further studies are needed to confirm these results in prospective clinical trials.

Artificial Intelligence-Based Sentinel Lymph Node Metastasis Detection in Cervical Cancer

Background/objectives: Pathological ultrastaging, an essential part of sentinel lymph node (SLN) mapping, involves serial sectioning and immunohistochemical (IHC) staining in order to reliably detect clinically relevant metastases. However, ultrastaging is labor-intensive, time-consuming, and costly. Deep learning algorithms offer a potential solution by assisting pathologists in efficiently assessing serial sections for metastases, reducing workload and costs while enhancing accuracy. This proof-of-principle study evaluated the effectiveness of a deep learning algorithm for SLN metastasis detection in early-stage cervical cancer. Methods: We retrospectively analyzed whole slide images (WSIs) of hematoxylin and eosin (H&amp;E)-stained SLNs from early-stage cervical cancer patients diagnosed with an SLN metastasis with either H&amp;E or IHC. A CE-IVD certified commercially available deep learning algorithm, initially developed for detection of breast and colon cancer lymph node metastases, was employed off-label to assess its sensitivity in cervical cancer. Results: This study included 21 patients with early-stage cervical cancer, comprising 15 with squamous cell carcinoma, five with adenocarcinoma, and one with clear cell carcinoma. Among these patients, 10 had macrometastases and 11 had micrometastases in at least one SLN. The algorithm was applied to evaluate H&amp;E WSIs of 47 SLN specimens, including 22 that were negative for metastasis, 13 with macrometastases, and 12 with micrometastases in the H&amp;E slides. The algorithm detected all H&amp;E macro- and micrometastases with 100% sensitivity. Conclusions: This proof-of-principle study demonstrated high sensitivity of a deep learning algorithm for detection of clinically relevant SLN metastasis in early-stage cervical cancer, despite being originally developed for adenocarcinomas of the breast and colon. Our findings highlight the potential of leveraging an existing algorithm for use in cervical cancer, warranting further prospective validation in a larger population.

Long-Term Outcomes of Prostate-Specific Membrane Antigen–PET Imaging of Recurrent Prostate Cancer

Although prostate-specific membrane antigen positron emission tomography (PSMA-PET) has shown improved sensitivity and specificity compared with conventional imaging for the detection of biochemical recurrent (BCR) prostate cancer, the long-term outcomes of a widespread shift in imaging are unknown. To estimate long-term outcomes of integrating PSMA-PET into the staging pathway for recurrent prostate cancer. This decision analytic modeling study simulated outcomes for patients with BCR following initial definitive local therapy. Inputs used were from the literature and a retrospective cohort study conducted at 2 institutions. The base case analysis assumed modest benefits of earlier detection and treatment, and scenario analyses considered prostate-specific antigen (PSA) level at imaging and different outcomes of earlier vs delayed treatment. The analysis was performed between April 1, 2023, and May 1, 2024. (1) Immediate PSMA-PET imaging, (2) conventional imaging (computed tomography and bone scan [CTBS]) followed by PSMA-PET if CTBS findings were negative or equivocal, and (3) CTBS alone. The main outcomes were detection of metastases, deaths from prostate cancer, and life-years and quality-adjusted life-years (QALYs) gained. The model estimated that per 1000 simulated patients with BCR (assumed median age, 66 years), PSMA-PET is expected to diagnose 611 (95% uncertainty interval [UI], 565-656) patients with metastasis compared with 630 (95% UI, 586-675) patients diagnosed using CTBS followed by PSMA-PET and 297 (95% UI, 202-410) patients diagnosed using CTBS alone. Moreover, the estimated number of prostate cancer deaths was 512 (95% UI, 472-552 deaths) with PSMA-PET, 520 (95% UI, 480-559 deaths) with CTBS followed by PSMA-PET, and 587 (95% UI, 538-632 deaths) with CTBS alone. Imaging with PSMA-PET yielded the highest number of QALYs, which were 824 (95% UI, 698-885) higher than CTBS. These results differed by PSA level at the time of testing, with the highest incremental life-years and QALYs and lowest number of deaths from prostate cancer among patients with PSA levels of at least 5.0 ng/mL. Finally, the estimates were sensitive to the expected benefit of initiating therapy for recurrent prostate cancer earlier in the disease course. The results of this decision-analytic model suggest that upfront PSMA-PET imaging for the evaluation of BCR is expected to be associated with reduced cancer mortality and gains in life-years and QALYs compared with the conventional imaging strategy, assuming modest benefits of earlier detection and treatment.

MFP-YOLO: a multi-scale feature perception network for CT bone metastasis detection.

Bone metastasis is one of the most common forms of metastasis in the late stages of malignancy. The early detection of bone metastases can help clinicians develop appropriate treatment plans. CT images are essential for diagnosing and assessing bone metastases in clinical practice. However, early bone metastasis lesions occupy a small part of the image and display variable sizes as the condition progresses, which adds complexity to the detection. To improve diagnostic efficiency, this paper proposes a novel algorithm-MFP-YOLO. Building on the YOLOv5 algorithm, this approach introduces a feature extraction module capable of capturing global information and designs a new content-aware feature pyramid structure to improve the network's capability in processing lesions of varying sizes. Moreover, this paper innovatively applies a transformer-structure decoder to bone metastasis detection. A dataset comprising 3921 CT images was created specifically for this task. The proposed method outperforms the baseline model with a 5.5% increase in precision and a 7.7% boost in recall. The experimental results indicate that this method can meet the needs of bone metastasis detection tasks in real scenarios and provide assistance for medical diagnosis.

Early experience with an artificial intelligence-based module for brain metastasis detection and segmentation.

- Accurate detection, segmentation, and volumetric analysis of brain lesions are essential in neuro-oncology. Artificial intelligence (AI)-based models have improved the efficiency of these processes. This study evaluated an AI-based module for detecting and segmenting brain metastases, comparing it with manual detection and segmentation. - MRIs from 51 patients treated with Gamma Knife radiosurgery for brain metastases were analyzed. Manual lesion identification and contouring on Leksell Gamma Plan at the time of treatment served as the gold standard. The same MRIs were processed through an AI-based module (Brainlab Smart Brush), and lesion detection and volumes were compared. Discrepancies were analyzed to identify possible sources of error. - Among 51 patients, 359 brain metastases were identified. The AI module achieved a sensitivity of 79.2% and a positive predictive value of 95.6%, compared to a 93.3% sensitivity for manual detection. However, for lesions > 0.1cc, the AI's sensitivity rose to 97.5%, surpassing manual detection at 93%. Volumetric agreement between AI and manual segmentations was high (Spearman's ρ = 0.997, p < 0.001). Most lesions missed by the AI (53.8%) were near anatomical structures that complicated detection. - The AI module demonstrated higher sensitivity than manual detection for metastases larger than 0.1cc, with robust volumetric accuracy. However, human expertise remains critical for detecting smaller lesions, especially near complex anatomical areas. AI offers significant potential to enhance neuro-oncology practice by improving the efficiency and accuracy of lesion management.

Phase 2 trial of PSMA PET CT versus planar bone scan and CT in prostate cancer patients progressing while on androgen deprivation therapy

For prostate cancer patients who experience biochemical progression during androgen deprivation therapy (ADT), prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) has not been prospectively compared to planar bone scan plus CT. This was a single-arm, head-to-head, prospective phase II trial (NCT04928820) designed to enroll 102 men with prostate cancer who experienced biochemical progression (rising prostate-specific antigen [PSA] ≥ 1 ng/mL) during ADT. All patients received 68Ga-PSMA-11 PET/CT and 99mTc-MDP planar bone scans. Each scan was interpreted by three central independent readers. The primary endpoint was the per-patient bone metastasis detection rate of PSMA PET/CT versus planar bone scan and CT. Secondary endpoints compared the number of bone metastases detected per patient and the inter-reader agreement of each imaging modality. Twenty-two men were enrolled between July 2021 and June 2022. Due to slow accrual following approval of PSMA PET radiotracers in the U.S. and a lack of a statistical signal between the two imaging modalities on interim analysis, this trial was closed early on October 2022. Median PSA was 8.5 ng/mL (interquartile range: 1.6–77.6). There was 100% agreement between the two scans. Six patients (27%) had negative findings and 16 patients (73%) had positive findings on both scans. PSMA PET/CT and bone scan plus CT detected an equal number of bone lesions for 14 patients (64%), PSMA PET/CT detected more bone lesions for six patients (27%), and bone scan plus CT detected more bone lesions for two patients (9.1%) (p = 0.092). The inter-reader agreement rates of PSMA PET/CT and bone scan plus CT were 96% and 82%, respectively (p = 0.25). In men with biochemical progression during ADT, 68Ga-PSMA-11 PET/CT and 99mTc-MDP planar bone scan plus CT had identical bone metastasis detection rates. Bone scan plus CT can continue to serve as a cost-effective and readily accessible restaging modality in patients with biochemical progression. ClinicalTrials.gov NCT04928820. Registered 16/06/2021.

Diagnostic value of [18F]FDG PET/MRI in the detection of lymph node metastasis of cervical cancer: a meta-analysis

Diagnostic value of [18F]FDG PET/MRI in the detection of lymph node metastasis of cervical cancer: a meta-analysis

Effect of Fluorescence Lymph Node Mapping on Improving Diagnostic Values of CT D3 Lymph Node Staging for Right-Sided Colon Cancer

Background/Objectives: This study evaluated the impact of fluorescence lymph node mapping (FLNM) using indocyanine green (ICG) on the diagnostic accuracy of preoperative computed tomography (CT) in right-sided colon cancer. Methods: A total of 218 patients who underwent laparoscopic right hemicolectomy with D3 lymph node dissection (LND) were analyzed: 86 patients in the FLNM group and 132 in the conventional surgery group. The FLNM technique allowed for enhanced intraoperative visualization of lymph node (LN) and more precise dissection, improving the identification of metastatic LNs. The diagnostic value of preoperative CT staging was assessed in both the FLNM and control groups by calculating the apparent prevalence, true prevalence, sensitivity, specificity, positive predictive value (PPV), negative predictive value, positive likelihood ratio (PLR), negative likelihood ratio, false positive and false negative proportions, and accuracy. Results: FLNM increased the accuracy of CT staging for detecting D3 LN metastasis in advanced cancer cases, with a higher PPV, PLR, and accuracy. In the FLNM group, the false-positive rate was significantly reduced, and the specificity was higher compared to the control group. Multivariate analysis identified FLNM as an independent factor associated with improved D3 LN metastasis detection. These findings suggest that incorporating FLNM into surgical procedures enhances the diagnostic value of preoperative CT by improving the precision of LND, particularly in patients with advanced colon cancer. Conclusions: The use of FLNM for D3 LND enhances the diagnostic accuracy of cN staging in right-sided colon cancer by improving surgical precision.

Clinical impact of whole-body MRI in staging and surveillance of patients with myxoid liposarcoma: a 14-year single-centre retrospective study.

To assess the clinical impact of regular whole-body magnetic resonance imaging (WBMRI) surveillance in myxoid liposarcoma patients. This was a retrospective cohort study of myxoid liposarcoma patients who underwent at least one WBMRI at our institution between October 2006 and December 2020. The effect of WBMRI on clinical management, namely treatment modification or additional diagnostic investigations was studied. A standardised WBMRI surveillance protocol was instituted in 2015. We compared patient outcomes for the metastatic patients who had and had not received regular WBMRI surveillance and performed survival analysis for both subgroups. Of the 56 patients (60.7% male, median age: 48.1 years) who underwent 345 WBMRI, 17 (30.3%) had metastases, and 168 WBMRI were performed in this group. The median imaging follow-up for the entire cohort was 35 months; the metastatic group had a median follow-up of 42 months. WBMRI changed the clinical management in 13 (76.5%) metastatic patients, with 33 instances of treatment modification. Thirty-five lesions were labelled 'indeterminate,' 16 (45.7%) had additional investigations/interventions, and 4 (11.4%) were confirmed to be metastatic. Twenty-one metastatic lesions were missed initially on WBMRI and confirmed on subsequent WBMRI, of which 5 (23.8%) were clinically significant. The 5-year survival since the detection of metastasis was better in the regular surveillance subgroup (85.7% vs. 45%), but this was not statistically significant (p = 0.068). Five patients (8.9%) developed their first metastasis more than 5 years after diagnosing the primary lesion. Regular WBMRI surveillance of myxoid liposarcoma patients considerably impacts clinical management by frequently influencing treatment decisions. WBMRI has been recently recommended as an imaging option for the staging and surveillance of myxoid liposarcoma patients. Our study highlights the impact of regular WBMRI surveillance on the clinical management of these patients and how it affects their survival.

Developing Individualized Follow-Up Strategies Based on High-Risk Recurrence Factors and Dynamic Risk Assessment for Locally Advanced Rectal Cancer.

Locally advanced rectal cancer (LARC) is one of the most common malignant tumors worldwide, and its incidence is increasing year by year. Despite multimodal treatment, the recurrence rate of LARC patients remains high, about 20%-50%. However, the follow-up strategy according to tumor stage has certain limitations. There is no consensus on the optimal frequency and duration of follow-up. This study aims to comprehensively analyze the high-risk factors for recurrence in LARC from clinical characteristics, nutritional indicators, and imaging indexes. It intends to utilize conditional survival (CS) evaluation to assess dynamic survival and recurrence risks after comprehensive treatment of LARC and to develop individualized follow-up strategies. Logistic regression was utilized to analyze the independent recurrence factors in LARC patients. Calibration curve, decision curve, and ROC curve were employed to evaluate the model's efficacy. Kaplan-Meier curve was used to calculate CS rate and compare survival differences among different risk groups. A total of 561 patients were analyzed in our study. Our multivariable logistic regression analysis revealed that the prognostic nutritional index (PNI), extramural vascular invasion (EMVI), vascular tumor thrombus, perineural invasion, and tumor size were independent factors for recurrence. Subsequently, a nomogram model was constructed and risk stratification was performed. Calibration curves and decision curves demonstrated that the model exhibited good clinical efficacy. The area under the ROC curve for the model was 0.763, indicating good sensitivity and specificity. Kaplan-Meier curves showed significant differences in survival among different risk groups. Furthermore, we observed that the CS without local recurrence and distant metastasis increased each year, while the cumulative recurrence risk decreased annually with prolonged survival time. Tailored follow-up intensities were developed for different risk groups and clinical stages based on the cumulative recurrence risk. The personalized follow-up strategy based on risk stratification can optimize resource allocation, early detection of recurrence or metastasis, and ultimately enhance the overall care and prognosis of LARC patients.

Mid-level data fusion strategy based on urinary nucleosides SERS spectra and blood CEA levels for enhanced preoperative detection of lymph node metastasis in colorectal cancer

BackgroundPreoperative prediction of lymph node metastasis (LNM) plays a crucial role in the treatment and prognosis of colorectal cancer (CRC). The traditional histopathological examination is invasive and time-consuming, providing pathological features only postoperatively. Preoperative serum carcinoembryonic antigen (CEA) is strongly correlated with postoperative LN status. However, the detection accuracy of LNM based on a single preoperative CEA level is low. Therefore, developing a more powerful and sensitive diagnostic tool would be of great clinical value for improving the accurate preoperative prediction of LNM in CRC patients. ResultsThis study aimed to develop a mid-level fusion approach using urinary nucleosides Raman spectra and blood CEA data to enhance the preoperative discrimination of CRC patients with and without LNM. Surface-enhanced Raman scattering (SERS) spectra of urinary modified nucleosides, isolated by affinity chromatography, were first acquired from 48 patients with LNM and 49 patients without LNM. The principal component analysis (PCA) scores obtained from the SERS spectra were then combined with preoperative blood CEA values to create a fused data array. The discriminant accuracy based on either dataset alone or the fused data was evaluated using three machine learning algorithms: linear discriminant analysis, k-nearest neighbors, and support vector machine. Results showed that the fused data could discriminate between the two groups with an accuracy of up to 91 %, outperforming SERS alone (86 %) and CEA alone (69 %). SignificanceTo our knowledge, this is the first report of mid-level data fusion of urinary nucleosides SERS spectra with blood CEA levels for the preoperative prediction of LNM in CRC. This work demonstrates that the mid-level data fusion strategy aided by SVM algorithm can greatly improve the preoperative prediction accuracy of LNM. This is crucial for therapeutic decision-making and prognostic assessment in CRC.

In vivo self-assembled bispecific fluorescence probe for early detection of bladder cancer and metastasis

In vivo self-assembled bispecific fluorescence probe for early detection of bladder cancer and metastasis