Gland surgery最新文献

{"title":"Development and validation of an intratumoral-peritumoral deep transfer learning fusion model for differentiating BI-RADS 3-4 breast nodules.","authors":"Lin Shi, Xinpeng Liu, Jinyu Lai, Feng Lu, Liping Gu, Lichang Zhong","doi":"10.21037/gs-24-457","DOIUrl":"10.21037/gs-24-457","url":null,"abstract":"<p><strong>Background: </strong>The Breast Imaging Reporting and Data System (BI-RADS) 3-4 breast nodules present a diagnostic challenge, as some benign lesions lead to unnecessary biopsies. Traditional imaging modalities like mammography and ultrasound often yield false positives due to limited specificity. While radiomics and machine learning show potential for improving accuracy, most studies focus on intratumoral features, neglecting the diagnostic value of peritumoral regions (PTRs). This study aimed to develop a non-invasive tool integrating intratumoral and peritumoral deep transfer learning (DTL) features to enhance risk stratification.</p><p><strong>Methods: </strong>Clinical data (age, tumor size), ultrasound images, and parameters [calcification, color Doppler flow imaging (CDFI), BI-RADS] were retrospectively collected from 555 patients with BI-RADS 3-4 nodules confirmed by pathology at two Shanghai medical centers. Patients from Center 1 (Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine) were split into training (n=291) and internal validation sets (n=125) at a 7:3 ratio, while those from Center 2 (Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine) formed an external validation set (n=139). Radiomics features from intratumoral and PTRs (5, 10, 20 voxels) were extracted using PyRadiomics, and DTL features were derived using a pre-trained ResNet-18 network. Combined features from DTL, radiomics, and clinical data were selected via least absolute shrinkage and selection operator (LASSO) regression. Machine learning models, including logistic regression (LR), random forest (RF), naive Bayes, K-nearest neighbors (KNN), and light gradient boosting machine (LightGBM), were constructed and compared using metrics like area under the curve (AUC). Ultrasound physicians independently reviewed images, and their performance was compared with the models.</p><p><strong>Results: </strong>The cohort included 555 female patients (mean age: 48.11±14.83 years), with 72.07% of nodules lacking calcifications and 61.08% without CDFI signals. The naive Bayes model based on intratumoral and 10-voxel peritumoral DTL features performed best. In the training set, it achieved an AUC of 0.911 (accuracy: 0.852, sensitivity: 0.852, specificity: 0.852). In the internal and external validation sets, AUCs were 0.909 and 0.910, respectively, outperforming physicians' AUCs of 0.722 and 0.745. The model also surpassed physicians in accuracy, sensitivity, specificity, and efficiency.</p><p><strong>Conclusions: </strong>The DTL feature model integrating intratumoral and PTRs effectively predicts BI-RADS 3-4 nodule malignancy, outperforming ultrasound physicians. It aids in reducing unnecessary biopsies and improving treatment decisions.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"658-669"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intra-parotid lymph node metastasis in primary parotid gland cancer: a narrative review of its significance, anatomic distribution, and therapeutic implications.","authors":"Jeon Yeob Jang, Han-Sin Jeong","doi":"10.21037/gs-2024-575","DOIUrl":"10.21037/gs-2024-575","url":null,"abstract":"<p><strong>Background and objective: </strong>Intra-parotid lymph node metastasis (LNM) has been proven to be an independent predictor of worse prognosis in patients with primary parotid gland cancer (PGC) as well as cervical LNM. However, the anatomic information or distribution of intra-parotid LNM within the parotid glands and its clinical significance remain largely unexplored. In this narrative review summarizing the relevant literature, we sought to answer the sub-site distribution of intra-parotid LNM in PGC, and suggest therapeutic implications.</p><p><strong>Methods: </strong>A comprehensive review of the literature was conducted by searching the PubMed and Web of Science databases. Manuscripts offering objective data on the incidence, subsite distribution, and prognostic significances of intra-parotid LNM were selected for inclusion in this review.</p><p><strong>Key content and findings: </strong>Overall, the rate of intra-parotid LNM appears to be greater than 40% in high-grade PGC but not in low-grade PGC. As for the lymph node (LN) distribution in the normal parotid gland, the majority (>80%) of LNs in the parotid glands are located in the superficial lobe, while the deep lobe contains just one LN on average. The European Salivary Gland Society (ESGS) classification system of the parotid gland sub-site is straightforward and can be applied to confirm intra-parotid LNM. Taking into consideration the intra-parotid LNM location, most intra-parotid LNMs from PGC are observed in the superficial parotid LNs, while metastasis to the deep parotid LNs seems to compose less than 10% of cases.</p><p><strong>Conclusions: </strong>The rate of intra-parotid LNM in the parotid deep lobe is not high enough to justify total parotidectomy in all PGC cases. In some PGC cases, a more selective approach preserving a portion of the deep parotid gland with a low risk of intra-parotid LNM might be an alternative to total parotidectomy.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"761-770"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093159/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risking arm lymphedema in more than a hundred patients to benefit one patient-is it worth it?","authors":"Geok Hoon Lim, Yoon-Sim Yap, Rui Jun Lim, Lester Chee Hao Leong","doi":"10.21037/gs-2025-34","DOIUrl":"10.21037/gs-2025-34","url":null,"abstract":"","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"781-784"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093178/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fluorescent intraoperative tissue angiography during breast reduction: a single institution, single surgeon study evaluating decrease in complication rates with acquired proficiency.","authors":"Jillian A Smith, Scott Sylvester, Daniel Norez, William D Kelly, Hugues Touze, Kristina M Crawford, Brian G Celso, John D Murray","doi":"10.21037/gs-2024-532","DOIUrl":"10.21037/gs-2024-532","url":null,"abstract":"<p><strong>Background: </strong>Fluorescent intraoperative tissue angiography (FITA) provides real-time perfusion analysis that predicts which tissues will progress to postoperative ischemic necrosis. This technology helps guide the surgeon to resect the at-risk tissues preemptively. The purpose of our study was to evaluate whether clinical outcomes are affected by the level of experience with FITA for superomedial-pedicle breast reduction (SBR).</p><p><strong>Methods: </strong>A retrospective, sequential series of 50 patients who underwent single-surgeon bilateral reduction mammaplasty using FITA (SPY Elite, Stryker, Kalamazoo, MI, USA) between April 2015 and September 2020 were included in the study. Two groups from the series were formed: the first three years with 25 patients (Group A) and the last three years with 25 patients (Group B). Operative data included FITA perfusion indices (medial breast, lateral breast, and nipple-areolar complex) and resection weight. Post-operative complications such as return to operating room (RTOR), and skin or nipple loss were reported.</p><p><strong>Results: </strong>Two statistically significant changes were observed: superomedial perfusion indices increased (right breast P<0.001, left breast P=0.02) and resection weights decreased (right breast P=0.044, left breast P=0.007). While the number of observed complications (nipple sensation, minor skin loss, RTOR), decreased in Group B compared to Group A, the difference was not statistically significant (P=0.62). The rate of minor skin or nipple loss was reduced by 57% in Group B versus Group A).</p><p><strong>Conclusions: </strong>FITA may help guide the preservation of perforators in the breast reduction pedicle. Though doing so did not reveal any statistical reduction in the number of complications in our study. These findings require further investigation for definitive conclusions.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"611-617"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093170/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Oncoplastic breast-conserving surgery: advancing oncological outcomes and aesthetic standards in breast cancer treatment.","authors":"Umar Wazir, Kefah Mokbel","doi":"10.21037/gs-2024-572","DOIUrl":"10.21037/gs-2024-572","url":null,"abstract":"","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"797-799"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Should abemaciclib candidacy be an indication for ALND?-commentary on SENOMAC post-hoc analysis.","authors":"Jasmine C Walker, Amanda L Kong, Chandler S Cortina","doi":"10.21037/gs-2025-38","DOIUrl":"10.21037/gs-2025-38","url":null,"abstract":"","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"776-780"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093160/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Erratum: Lysyl oxidase promotes anaplastic thyroid carcinoma cell proliferation and metastasis mediated via BMP1.","authors":"","doi":"10.21037/gs-2025b-1","DOIUrl":"10.21037/gs-2025b-1","url":null,"abstract":"<p><p>[This corrects the article DOI: 10.21037/gs-21-908.].</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"800-802"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093162/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The development and validation of biomarkers-based scoring systems for predicting early recurrence in patients with borderline resectable pancreatic cancer undergoing resection after neoadjuvant therapy.","authors":"Hang He, Cai-Feng Zou, Yong-Jian Jiang, Feng Yang, Yang Di, Ji Li, Chen Jin, De-Liang Fu","doi":"10.21037/gs-2024-500","DOIUrl":"10.21037/gs-2024-500","url":null,"abstract":"<p><strong>Background: </strong>Neoadjuvant therapy (NAT) is a key component of the treatment strategy for borderline resectable pancreatic cancer (BRPC). However, early recurrence (ER) frequently occurs, leading to a poor prognosis. Effective approaches for ER risk stratification in patients with BRPC undergoing NAT have not been well established currently. This study aimed to develop biomarker-based perioperative scoring systems to predict ER in patients with BRPC who underwent resection after NAT.</p><p><strong>Methods: </strong>Patients with BRPC who underwent radical resection following NAT at our institute between 2018 and 2023 were retrospectively enrolled. Serum biochemical marker tests and imaging examinations were performed to evaluate recurrence. Perioperative biochemical and clinicopathological parameters were analyzed. Univariate and multivariate Cox regression analyses were performed to identify independent risk factors for recurrence and to construct nomograms for ER prediction. Internal validation was conducted using the bootstrapping method. The accuracy in predicting ER was evaluated using receiver operating characteristic curve analysis. Survival analysis was performed using the Kaplan-Meier survival plots and log-rank test.</p><p><strong>Results: </strong>A total of 194 patients were enrolled. Recurrence occurred in 69.0% of all patients, and 61.1% of all recurrences were found within 6 months postoperatively. A preoperative scoring system was developed based on preoperative carbohydrate antigen 19-9 (CA19-9) and CA125 levels to predict ER [area under the curve (AUC), 0.700; 95% confidence interval (95% CI): 0.614-0.786] with 86.4% specificity and 48.7% sensitivity (cut-off value was 0.35886). Patients with a post-NAT prognostic score (PNPS) ≥0.35886 exhibited significantly poorer recurrence-free survival (RFS) (P<0.001) and overall survival (OS) (P<0.001) than those with a PNPS <0.35886. A postoperative scoring system based on the postoperative CA19-9 response was established to predict ER (AUC, 0.785; 95% CI: 0.705-0.866) with 65.4% specificity and 80.8% sensitivity (cut-off value was 0.43949). Patients with a postoperative prognostic score (PPS) ≥0.43949 exhibited poorer RFS (P<0.001) and OS (P<0.001) than those with a PPS <0.43949. For patients with normal CA19-9 levels after NAT, PNPS ≥0.35886 or PPS ≥0.43949 indicated a poor prognosis after surgery. For patients without normal CA19-9 levels after NAT, PNPS <0.35886 or PPS <0.43949 was associated with a favorable prognosis after surgery.</p><p><strong>Conclusions: </strong>The preoperative and postoperative scoring systems provide risk stratification for ER in patients with BRPC undergoing NAT. This may provide references to clinicians in identifying suitable candidates and optimal timing for surgery during NAT, and administering tailored adjuvant therapy (AT) after surgery.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"670-686"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093163/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The role of robot-assisted mastectomy: promise, challenges, and evidence gaps.","authors":"Mariam Rizk, Kefah Mokbel","doi":"10.21037/gs-2025-16","DOIUrl":"10.21037/gs-2025-16","url":null,"abstract":"","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"579-583"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a multivariable risk model based on clinicopathological characteristics, mammography, and MRI imaging features for predicting axillary lymph node metastasis in patients with upgraded ductal carcinoma <i>in situ</i>.","authors":"Min-Yi Cheng, Can-Gui Wu, Ying-Yi Lin, Jia-Chen Zou, Dong-Qing Wang, Bruce G Haffty, Kun Wang","doi":"10.21037/gs-2025-89","DOIUrl":"10.21037/gs-2025-89","url":null,"abstract":"<p><strong>Background: </strong>Axillary surgical staging is required for patients with upgraded ductal carcinoma in situ (DCIS) (DCIS is diagnosed on core biopsy with invasive cancer found on pathology after complete surgical excision), which may lead to complications in axillary surgery. At present, there is no reliable and accurate method for predicting axillary lymph node metastasis (ALNM) in patients with upgraded DCIS; however, such a method could prevent unnecessary axillary surgical interventions from being performed. In this study, we aimed to construct a non-invasive model for predicting ALNM in DCIS patients based on clinicopathological characteristics, mammography (MG) features, and magnetic resonance imaging (MRI) features.</p><p><strong>Methods: </strong>Between February 2018 and June 2020, 326 patients with upgraded DCIS were enrolled in this retrospective analysis. These patients were randomly divided into the training cohort (80%) and validation cohort (20%). Univariate and multivariable regression analyses were conducted to identify the candidate pathological features, which then used to develop a clinicopathological model. The features of the 2-mm, 4-mm, and 6-mm intratumoral and peritumoral regions (T-PTR) were extracted to develop the MRI radiomics model, and two deep learning classification models were developed based on the medial-lateral oblique (MLO) and craniocaudal (CC) views of the MG. A fusion model was then established that combined these sub-models. The receiver operating characteristic (ROC) curve, area under the curve (AUC), and other indicators were used to evaluate the performance of these models.</p><p><strong>Results: </strong>The clinicopathological characteristics of the two cohorts were basically balanced. The AUC values of the clinicopathological model were 0.675 and 0.690 in the training and validation cohorts, respectively. The model based on the T-PTR of MRI showed promising predictive ability. Among the three MRI models, the T-PTR (4 mm) model showed the best predictivity both in the training (AUC =0.885) and validation cohorts (AUC =0.843). The AUC values for the deep learning models of the MG CC and MLO positions all exceeded 0.7, indicating reliable predictive performance. The fusion model that combined the three methods significantly improved the accuracy and robustness of ALNM prediction. In both the training (AUC =0.975) and validation (AUC =0.877) cohorts, the fusion model showed excellent performance.</p><p><strong>Conclusions: </strong>We developed a fusion model that combined clinicopathological characteristics, MRI T-PTR (4 mm) radiomics, and MG-based deep learning. Our combined model showed promising performance in predicting ALNM in patients with upgraded DCIS.</p>","PeriodicalId":12760,"journal":{"name":"Gland surgery","volume":"14 4","pages":"738-753"},"PeriodicalIF":1.5,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12093168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144127305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}