Increasing the accuracy and reproducibility of positron emission tomography radiomics for predicting pelvic lymph node metastasis in patients with cervical cancer using 3D local binary pattern-based texture features

Background The reproducibility of positron emission tomography(PET)radiomics features is affected by several factors,such as scanning equipment,drug metabolism time and reconstruction algorithm.We aimed to explore the role of 3D local binary pattern(LBP)-based texture in increasing the accuracy and reproducibility of PET radiomics for predicting pelvic lymph node metastasis(PLNM)in patients with cervical cancer.Methods We retrospectively analysed data from 177 patients with cervical squamous cell carcinoma.They un-derwent18 F-fluorodeoxyglucose(18 F-FDG)whole-body PET/computed tomography(PET/CT),followed by pelvic 18 F-FDG PET/magnetic resonance imaging(PET/MR).We selected reproducible and informative PET radiomics features using Lin’s concordance correlation coefficient,least absolute shrinkage and selection operator algorithm,and established 4 models,PET/CT,PET/CT-fusion,PET/MR and PET/MR-fusion,using the logistic regression al-gorithm.We performed receiver operating characteristic(ROC)curve analysis to evaluate the models in the training data set(65 patients who underwent radical hysterectomy and pelvic lymph node dissection)and test data set(112 patients who received concurrent chemoradiotherapy or no treatment).The DeLong test was used for pairwise comparison of the ROC curves among the models.Results The distribution of age,squamous cell carcinoma(SCC),International Federation of Gynaecology and Obstetrics stage and PLNM between the training and test data sets were different(P<0.05).The LBP-transformed radiomics features(50/379)had higher reproducibility than the original radiomics features(9/107).Accuracy of each model in predicting PLNM was as follows:training data set:PET/CT=PET/CT-fusion=PET/MR-fusion(0.848)and test data set:PET/CT=PET/CT-fusion(0.985)>PET/MR=PET/MR-fusion(0.954).There was no statistical difference between the ROC curve of PET/CT and PET/MR models in both data sets(P>0.05).Conclusions The LBP-transformed radiomics features based on PET images could increase the accuracy and reproducibility of PET radiomics in predicting pelvic lymph node metastasis in cervical cancer to allow the model to be generalised for clinical use across multiple centres.

The Number of Positive Pelvic Lymph Nodes and Multiple Groups of Pelvic Lymph Node Metastasis Influence Prognosis in Stage ⅠA-ⅡB Cervical Squamous Cell Carcinoma

Background：Pelvic lymph node metastasis （LNM） is an important prognostic factor in cervical cancer.Cervical squamous cell carcinoma accounts for approximately 75-80% of all cervical cancers.Analyses of the effects of the number of positive lymph nodes （LNs）,unilateral vcrsus bilateral pelvic LNM and a single group versus multiple groups of pelvic LNM on survival and recurrence of cervical squamous cell carcinoma are still lacking.The study aimed to analyze the effects of the number of positive pelvic LNs and a single group versus multiple groups of pelvic LNM on survival and recurrence.Methods：We performed a retrospective review of 296 patients diagnosed with Stage ⅠA-ⅡB cervical squamous cell carcinoma who received extensive/sub-extensive hysterectomy with pelvic lymphadenectomy/pelvic LN sampling at Peking University People＇s Hospital from November 2004 to July 2013.Ten clinicopathological variables were evaluated as risk factors for pelvic LNM：Age at diagnosis,gravidity,clinical stage,histological grade,tumor diameter,lymph-vascular space involvement （LVSI）,depth of cervical stromal invasion,uterine invasion,parametrial invasion,and neoadjuvant chemotherapy.Results：The incidence of pelvic LNM was 20.27% （60/296 cases）.Pelvic LNM （P =0.00） was significantly correlated with recurrence.Pelvic LNM （P =0.00）,the number of positive pelvic LNs （P =0.04） and a single group versus multiple groups of pelvic LNM （P =0.03）had a significant influence on survival.Multivariate analysis revealed that LVSI （P =0.00）,depth of cervical stromal invasion （P =0.00）and parametrial invasion （P =0.03） were independently associated with pelvic LNM.Conclusions：Patients with pelvic LNM had a higher recurrence rate and poor survival outcomes.Furthermore,more than 2 positive pelvic LNs and multiple groups of pelvic LNM appeared to identify patients with worse survival outcomes in node-positive ⅠA-ⅡB cervical squamous cell carcinoma.LVSI,parametrial invasion,and depth of cervical stromal invasion were identified as independent clinicopathological risk factors for pelvic LNM.

Lateral pelvic lymph nodes for rectal cancer:A review of diagnosis and management

The current status and future prospects for diagnosis and treatment of lateral pelvic lymph node(LPLN)metastasis of rectal cancer are described in this review.Magnetic resonance imaging(MRI)is recommended for the diagnosis of LPLN metastasis.A LPLN-positive status on MRI is a strong risk factor for metastasis,and evaluation by MRI is important for deciding treatment strategy.LPLN dissection(LPLD)has an advantage of reducing recurrence in the lateral pelvis but also has a disadvantage of complications;therefore,LPLD may not be appropriate for cases that are less likely to have LPLN metastasis.Radiation therapy(RT)and chemoradiation therapy(CRT)have limited effects in cases with suspected LPLN metastasis,but a combination of preoperative CRT and LPLD may improve the treatment outcome.Thus,RT and CRT plus selective LPLD may be a rational strategy to omit unnecessary LPLD and produce a favorable treatment outcome.