MRI pelvimetry-based evaluation of surgical difficulty in laparoscopic total mesorectal excision after neoadjuvant chemoradiation for male rectal cancer

Role of pelvimetry in predicting surgical outcomes and morbidity in rectal cancer surgery: A retrospective analysis

BACKGROUND

Rectal cancer has increased in incidence, and surgery remains the cornerstone of multimodal treatment. Pelvic anatomy, particularly a narrow pelvis, poses challenges in rectal cancer surgery, potentially affecting oncological outcomes and postoperative complications.

AIM

To investigate the relationship between radiologically assessed pelvic anatomy and surgical outcomes as well as the impact on local recurrence following rectal cancer surgery.

METHODS

We retrospectively analyzed 107 patients with rectal adenocarcinoma treated with elective rectal surgery between January 1, 2017, and September 1, 2022. Pelvimetric measurements were performed using computed tomography (CT)-based two-dimensional methods (n = 77) by assessing the pelvic inlet area in mm², and magnetic resonance imaging (MRI)-based three-dimensional techniques (n = 52) using the pelvic cavity index (PCI). Patient demographic, clinical, radiological, surgical, and pathological characteristics were collected and analyzed in relation to their pelvimetric data.

RESULTS

When patients were categorized based on CT measurements into narrow and normal/wide pelvis groups, a significant association was observed with male sex, and a lower BMI was more common in the narrow pelvis group (P = 0.002 for both). A significant association was found between a narrow pelvic structure, indicated by low PCI, and increased surgical morbidity (P = 0.049). Advanced age (P = 0.003) and male sex (P = 0.020) were significantly correlated with higher surgical morbidity. Logistic regression analysis identified four parameters that were significantly correlated with local recurrence: older age, early perioperative readmission, longer operation time, and a lower number of dissected lymph nodes (P < 0.05). However, there were no significant differences between the narrow and normal/wide pelvis groups in terms of the operation time, estimated blood loss, or overall local recurrence rate (P > 0.05).

CONCLUSION

MRI-based pelvimetry may be valuable in predicting surgical difficulty and morbidity in rectal cancer surgery, as indicated by the PCI. The observed correlation between low PCI and increased surgical morbidity suggests the potential importance of a preoperative MRI-based pelvimetric evaluation. In contrast, CT-based pelvimetry did not show significant differences in predicting surgical outcomes or cancer recurrence, indicating that the utility of pelvimetry alone may be limited in these respects.

Predictive model of the surgical difficulty of robot-assisted total mesorectal excision for rectal cancer: a multicenter, retrospective study

Rectal cancer robotic surgery is becoming more and more common, but evidence for predicting surgical difficulty is scarce. Our goal was to look at the elements that influence the complexity of robot-assisted total mesorectal excision (R-TME) in the medical care of middle and low rectal cancer as well as to establish and validate a predictive model on the basis of these factors. Within this multicenter retrospective investigation, 166 consecutive patients receiving R-TME between January 2021 and December 2022 with middle and low rectal cancer were included and categorized according to the median operation time. A nomogram was created to forecast the procedure's complexity after variables that could affect its difficulty were found using logistic regression analysis. Using R software, a total of 166 patients were randomly split into two groups: a test group (48 patients) and a training group (118 patients) at a ratio of 7 to 3. The median operation time of all patients was 207.5 min; patients whose operation time was ≥ 207.5 min were allocated to the difficult surgery group (83 patients), and patients whose operation time was < 207.5 min were allocated to the nondifficult surgery group. Multivariate analysis revealed that body mass index (BMI), the gap between the tumor and the anal verge and the posterior rectal mesenteric thickness were independent predictors of surgical duration. A clinical predictive model was created and assessed employing the above independent predictors. The results of the receiver operating characteristic (ROC) analysis revealed the adequate discriminative ability of the predictive model. Our study revealed that it is feasible to predict surgical difficulty by obtaining clinical and magnetic resonance parameters for imaging (the gap between the anal verge and the tumour, and posterior mesorectal thickness), and these predictions could be useful in making clinical decisions.

Using CT-Based Pelvimetry and Visceral Obesity Measurements to Predict Total Mesorectal Excision Quality for Patients Undergoing Rectal Cancer Surgery

BACKGROUND

A complete total mesorectal excision is the criterion standard in curative rectal cancer surgery. Ensuring quality is challenging in a narrow pelvis, and obesity amplifies technical difficulties. Pelvimetry is the measurement of pelvic dimensions, but its role in gauging preoperatively the difficulty of proctectomy is largely unexplored.

OBJECTIVE

To determine pelvic structural factors associated with incomplete total mesorectal excision after curative proctectomy and build a predictive model for total mesorectal excision quality.

DESIGN

Retrospective cohort study.

SETTING

A quaternary referral center database of patients diagnosed with rectal adenocarcinoma (2009-2017).

PATIENTS

Curative-intent proctectomy for rectal adenocarcinoma.

INTERVENTIONS

All radiological measurements were obtained from preoperative CT images using validated imaging processing software tools. Completeness of total mesorectal excision was obtained from histology reports.

MAIN OUTCOME MEASURES

Ability of radiological pelvimetry and obesity measurements to predict total mesorectal excision quality.

RESULTS

Of the 410 cases meeting inclusion criteria, 362 underwent a complete total mesorectal excision (88%). Multivariable regression identified a deeper sacral curve (per 100 mm 2 [OR: 1.14; 95% CI, 1.06-1.23; p < 0.001]) and a greater transverse distance of the pelvic outlet (per 10 mm [OR:1.41, 95% CI, 1.08-1.84; p = 0.012]) to be independently associated with incomplete total mesorectal excision. An increased area of the pelvic inlet (per 10 cm 2 [OR: 0.85; 95% CI, 0.75-0.97; p = 0.02) was associated with a higher rate of complete mesorectal excision. No difference in visceral obesity ratio and visceral obesity (ratio >0.4 vs <0.4) between BMI (<30 vs ≥30) and sex was identified. A model was built to predict mesorectal quality using the following variables: depth of sacral curve, area of pelvic inlet, and transverse distance of the pelvic outlet.

LIMITATIONS

Retrospective analysis is not controlled for the choice of surgical approach.

CONCLUSIONS

Pelvimetry predicts total mesorectal excision quality in rectal cancer surgery and can alert surgeons preoperatively to cases of unusual difficulty. This predictive model may contribute to treatment strategy and aid in the comparison of outcomes between traditional and novel techniques of total mesorectal excision. See Video Abstract .

USO DE MEDICIONES DE PELVIMETRA Y OBESIDAD VISCERAL BASADAS EN TC PARA PREDECIR LA CALIDAD DE TME EN PACIENTES SOMETIDOS A CIRUGA DE CNCER DE RECTO

ANTECEDENTES:Una escisión mesorrectal total y completa es el estándar de oro en la cirugía curativa del cáncer de recto. Garantizar la calidad es un desafío en una pelvis estrecha y la obesidad amplifica las dificultades técnicas. La pelvimetría es la medición de las dimensiones pélvicas, pero su papel para medir la dificultad preoperatoria de la proctectomía está en gran medida inexplorado.OBJETIVO:Determinar los factores estructurales pélvicos asociados con la escisión mesorrectal total incompleta después de una proctectomía curativa y construir un modelo predictivo para la calidad de la escisión mesorrectal total.DISEÑO:Estudio de cohorte retrospectivo.ÁMBITO:Base de datos de un centro de referencia cuaternario de pacientes diagnosticados con adenocarcinoma de recto (2009-2017).PACIENTES:Proctectomía con intención curativa para adenocarcinoma de recto.INTERVENCIONES:Todas las mediciones radiológicas se obtuvieron a partir de imágenes de TC preoperatorias utilizando herramientas de software de procesamiento de imágenes validadas. La integridad de la escisión mesorrectal total se obtuvo a partir de informes histológicos.PRINCIPALES MEDIDAS DE VALORACIÓN:Capacidad de la pelvimetría radiológica y las mediciones de obesidad para predecir la calidad total de la escisión mesorrectal.RESULTADOS:De los 410 casos que cumplieron los criterios de inclusión, 362 tuvieron una escisión mesorrectal total completa (88%). Una regresión multivariable identificó una curva sacra más profunda (por 100 mm2); OR:1,14,[IC95%:1,06-1,23,p<0,001], y mayor distancia transversal de salida pélvica (por 10mm); OR:1,41, [IC 95%:1,08-1,84,p=0,012] como asociación independiente con escisión mesorrectal total incompleta. Un área aumentada de entrada pélvica (por 10 cm2); OR:0,85, [IC95%:0,75-0,97,p=0,02] se asoció con una mayor tasa de escisión mesorrectal completa. No se identificaron diferencias en la proporción de obesidad visceral y la obesidad visceral (proporción>0,4 vs.<0,4) entre el índice de masa corporal (<30 vs.>=30) o el sexo. Se construyó un modelo para predecir la calidad mesorrectal utilizando variables: profundidad de la curva sacra, área de la entrada pélvica y distancia transversal de la salida pélvica.LIMITACIONES:Análisis retrospectivo no controlado por la elección del abordaje quirúrgico.CONCLUSIONES:La pelvimetría predice la calidad de la escisión mesorrectal total en la cirugía del cáncer de recto y puede alertar a los cirujanos preoperatoriamente sobre casos de dificultad inusual. Este modelo predictivo puede contribuir a la estrategia de tratamiento y ayudar en la comparación de resultados entre técnicas tradicionales y novedosas de escisión mesorrectal total. (Traducción- Dr. Ingrid Melo).

Development and validation of machine learning models and nomograms for predicting the surgical difficulty of laparoscopic resection in rectal cancer

BACKGROUND

The objective of this study is to develop and validate a machine learning (ML) prediction model for the assessment of laparoscopic total mesorectal excision (LaTME) surgery difficulty, as well as to identify independent risk factors that influence surgical difficulty. Establishing a nomogram aims to assist clinical practitioners in formulating more effective surgical plans before the procedure.

METHODS

This study included 186 patients with rectal cancer who underwent LaTME from January 2018 to December 2020. They were divided into a training cohort (n = 131) versus a validation cohort (n = 55). The difficulty of LaTME was defined based on Escal's et al. scoring criteria with modifications. We utilized Lasso regression to screen the preoperative clinical characteristic variables and intraoperative information most relevant to surgical difficulty for the development and validation of four ML models: logistic regression (LR), support vector machine (SVM), random forest (RF), and decision tree (DT). The performance of the model was assessed based on the area under the receiver operating characteristic curve(AUC), sensitivity, specificity, and accuracy. Logistic regression-based column-line plots were created to visualize the predictive model. Consistency statistics (C-statistic) and calibration curves were used to discriminate and calibrate the nomogram, respectively.

RESULTS

In the validation cohort, all four ML models demonstrate good performance: SVM AUC = 0.987, RF AUC = 0.953, LR AUC = 0.950, and DT AUC = 0.904. To enhance visual evaluation, a logistic regression-based nomogram has been established. Predictive factors included in the nomogram are body mass index (BMI), distance between the tumor to the dentate line ≤ 10 cm, radiodensity of visceral adipose tissue (VAT), area of subcutaneous adipose tissue (SAT), tumor diameter >3 cm, and comorbid hypertension.

CONCLUSION

In this study, four ML models based on intraoperative and preoperative risk factors and a nomogram based on logistic regression may be of help to surgeons in evaluating the surgical difficulty before operation and adopting appropriate responses and surgical protocols.

Interpretable machine learning model to predict surgical difficulty in laparoscopic resection for rectal cancer

Background

Laparoscopic total mesorectal excision (LaTME) is standard surgical methods for rectal cancer, and LaTME operation is a challenging procedure. This study is intended to use machine learning to develop and validate prediction models for surgical difficulty of LaTME in patients with rectal cancer and compare these models' performance.

Methods

We retrospectively collected the preoperative clinical and MRI pelvimetry parameter of rectal cancer patients who underwent laparoscopic total mesorectal resection from 2017 to 2022. The difficulty of LaTME was defined according to the scoring criteria reported by Escal. Patients were randomly divided into training group (80%) and test group (20%). We selected independent influencing features using the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression method. Adopt synthetic minority oversampling technique (SMOTE) to alleviate the class imbalance problem. Six machine learning model were developed: light gradient boosting machine (LGBM); categorical boosting (CatBoost); extreme gradient boost (XGBoost), logistic regression (LR); random forests (RF); multilayer perceptron (MLP). The area under receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity and F1 score were used to evaluate the performance of the model. The Shapley Additive Explanations (SHAP) analysis provided interpretation for the best machine learning model. Further decision curve analysis (DCA) was used to evaluate the clinical manifestations of the model.

Results

A total of 626 patients were included. LASSO regression analysis shows that tumor height, prognostic nutrition index (PNI), pelvic inlet, pelvic outlet, sacrococcygeal distance, mesorectal fat area and angle 5 (the angle between the apex of the sacral angle and the lower edge of the pubic bone) are the predictor variables of the machine learning model. In addition, the correlation heatmap shows that there is no significant correlation between these seven variables. When predicting the difficulty of LaTME surgery, the XGBoost model performed best among the six machine learning models (AUROC=0.855). Based on the decision curve analysis (DCA) results, the XGBoost model is also superior, and feature importance analysis shows that tumor height is the most important variable among the seven factors.

Conclusions

This study developed an XGBoost model to predict the difficulty of LaTME surgery. This model can help clinicians quickly and accurately predict the difficulty of surgery and adopt individualized surgical methods.

Value of the newly developed pelvic dimension index/prostate volume ratio in predicting positive surgical margin in prostate cancer

PURPOSE

To evaluate the diagnostic performance of pelvimetric measurements, in particular the pelvic dimension index (PDI)/prostate volume (PV) ratio (PDI/PV), in predicting positive surgical margin (PSM) in prostate cancer (PC).

MATERIALS AND METHODS

127 patients who had pre-operative pelvic imaging were included in this study. Demographic and clinical data were recorded. Apical depth (AD), interspinous distance (ISD), intertuberous distance (ITD), bony femoral width (BFW), soft-tissue width (SW), symphysis angle (SA), anteroposterior diameter of the pelvic inlet (API), anteroposterior diameter of the pelvic mid-plane (APM), anteroposterior diameter of the pelvic outlet (APO), pelvic depth (PD), bony width index (BWI), soft tissue width index (SWI), pelvic cavity index (PCI), PDI and PV were measured on MRI or CT. Using PDI and PV, we developed a new parameter of "PDI to PV ratio" (PDI/PV). Logistic regression analysis was used to determine the predictive potential of variables in detection of PSM.

RESULTS

The AD, PV, SA and total prostate specific antigen (PSA) were significantly higher in PSM( +), while PDI, BWI, SWI, API, PDI/PV and PD were significantly lower in PSM( +) (p < 0.05). In multivariate analysis, PDI/PV ratio and clinical stage were all significant predictor of PSM, where PDI/PV ratio was the strongest predictor, followed by clinical stage.

CONCLUSION

Pelvimetric measurements indicating deep location of the prostatic apex rather than pelvic width are more effective in predicting PSM. Prediction of PSM with pelvimetric measurements, in particular PDI/PV ratio, may be helpful for surgical planning in preoperative period.

Establishment of Surgical Difficulty Grading System and Application of MRI-Based Artificial Intelligence to Stratify Difficulty in Laparoscopic Rectal Surgery

(1) Background: The difficulty of pelvic operation is greatly affected by anatomical constraints. Defining this difficulty and assessing it based on conventional methods has some limitations. Artificial intelligence (AI) has enabled rapid advances in surgery, but its role in assessing the difficulty of laparoscopic rectal surgery is unclear. This study aimed to establish a difficulty grading system to assess the difficulty of laparoscopic rectal surgery, as well as utilize this system to evaluate the reliability of pelvis-induced difficulties described by MRI-based AI. (2) Methods: Patients who underwent laparoscopic rectal surgery from March 2019 to October 2022 were included, and were divided into a non-difficult group and difficult group. This study was divided into two stages. In the first stage, a difficulty grading system was developed and proposed to assess the surgical difficulty caused by the pelvis. In the second stage, AI was used to build a model, and the ability of the model to stratify the difficulty of surgery was evaluated at this stage, based on the results of the first stage; (3) Results: Among the 108 enrolled patients, 53 patients (49.1%) were in the difficult group. Compared to the non-difficult group, there were longer operation times, more blood loss, higher rates of anastomotic leaks, and poorer specimen quality in the difficult group. In the second stage, after training and testing, the average accuracy of the four-fold cross validation models on the test set was 0.830, and the accuracy of the merged AI model was 0.800, the precision was 0.786, the specificity was 0.750, the recall was 0.846, the F1-score was 0.815, the area under the receiver operating curve was 0.78 and the average precision was 0.69; (4) Conclusions: This study successfully proposed a feasible grading system for surgery difficulty and developed a predictive model with reasonable accuracy using AI, which can assist surgeons in determining surgical difficulty and in choosing the optimal surgical approach for rectal cancer patients with a structurally difficult pelvis.

Development of artificial blood loss and duration of excision score to evaluate surgical difficulty of total laparoscopic anterior resection in rectal cancer

PURPOSE

Total laparoscopic anterior resection (tLAR) has been gradually applied in the treatment of rectal cancer (RC). This study aims to develop a scoring system to predict the surgical difficulty of tLAR.

METHODS

RC patients treated with tLAR were collected. The blood loss and duration of excision (BLADE) scoring system was built to assess the surgical difficulty by using restricted cubic spline regression. Multivariate logistic regression was used to evaluate the effect of the BLADE score on postoperative complications. The random forest (RF) algorithm was used to establish a preoperative predictive model for the BLADE score.

RESULTS

A total of 1,994 RC patients were randomly selected for the training set and the test set, and 325 RC patients were identified as the external validation set. The BLADE score, which was built based on the thresholds of blood loss (60 ml) and duration of surgical excision (165 min), was the most important risk factor for postoperative complications. The areas under the curve of the predictive RF model were 0.786 in the training set, 0.640 in the test set, and 0.665 in the external validation set.

CONCLUSION

This preoperative predictive model for the BLADE score presents clinical feasibility and reliability in identifying the candidates to receive tLAR and in making surgical plans for RC patients.

Advances in pelvic imaging parameters predicting surgical difficulty in rectal cancer

Due to the fixed bony structure of the pelvis, the pelvic operation space is limited, complicating the surgical operation of rectal cancer, especially middle and low rectal cancer. The closer the tumor is to the anal verge, the smaller the operative field and operating space, the longer the operative time, and the greater the incidence of intraoperative side injuries and postoperative complications. To date, there is still no clear definition of a difficult pelvis that affects the surgical operation of rectal cancer. Few related research reports exist in the literature, and views on this aspect are not the same between countries. Therefore, it is particularly important to predict the difficulty of rectal cancer surgery in a certain way before surgery and to select the surgical method most suitable for each case during the treatment of rectal cancer.

BMI and pelvimetry help to predict the duration of laparoscopic resection for low and middle rectal cancer

BACKGROUND

In rectal cancer surgery, recent studies have found associations between clinical factors, especially pelvic parameters, and surgical difficulty; however, their findings are inconsistent because the studies use different criteria. This study aimed to evaluate common clinical factors that influence the operative time for the laparoscopic anterior resection of low and middle rectal cancer.

METHODS

Patients who underwent laparoscopic radical resection of low and middle rectal cancer from January 2018 to December 2020 were retrospectively analyzed and classified according to the operative time. Preoperative clinical and magnetic resonance imaging (MRI)-related parameters were collected. Logistic regression analysis was used to identify factors for predicting the operative time.

RESULTS

In total, 214 patients with a mean age of 60.3 ± 8.9 years were divided into two groups: the long operative time group (n = 105) and the short operative time group (n = 109). Univariate analysis revealed that the male sex, a higher body mass index (BMI, ≥ 24.0 kg/m²), preoperative treatment, a smaller pelvic inlet (< 11.0 cm), a deeper pelvic depth (≥ 10.7 cm) and a shorter intertuberous distance (< 10.1 cm) were significantly correlated with a longer operative time (P < 0.05). However, only BMI (OR 1.893, 95% CI 1.064-3.367, P = 0.030) and pelvic inlet (OR 0.439, 95% CI 0.240-0.804, P = 0.008) were independent predictors of operative time. Moreover, the rate of anastomotic leakage was higher in the long operative time group (P < 0.05).

CONCLUSION

Laparoscopic rectal resection is expected to take longer to perform in patients with a higher BMI or smaller pelvic inlet.

Evaluation of Nursing Effects of Pelvic Floor Muscle Rehabilitation Exercise on Gastrointestinal Tract Rectal Cancer Patients Receiving Anus-preserving Operation by Intelligent Algorithm-based Magnetic Resonance Imaging

Based on magnetic resonance imaging (MRI) technology under artificial intelligence algorithm, the postoperative nursing effects of pelvic floor muscle rehabilitation exercise on gastrointestinal tract rectal cancer (RC) patients were investigated. A total of 88 patients receiving RC anus-preserving surgery in hospital were selected. The included patients were divided randomly into the experimental group (44 cases) and the control group (44 cases). Patients in the control group engaged in Kegel motion, while patients in the experimental group underwent self-designed comprehensive pelvic floor training. Anorectum function rating scale and quality of life questionnaire for colorectal cancer (EORTC QLQ-CR29) were utilized to compare and analyze anus functions and living quality of patients in the two groups. Besides, all patients in two groups received MRI examinations, and images were processed by a convolutional neural network (CNN) algorithm. The results showed that in MRI images, there were significant signal differences between lesion tissues and normal tissues. After being processed by an artificial intelligence algorithm, the definition of MRI images was remarkably enhanced with clearer lesion edges. The quality of images was also significantly improved. Besides, the comparison of anus functions of patients in two groups showed that the differences demonstrated statistical meaning after the intervention (P < 0.05). In conclusion, artificial intelligence algorithm-based MRI and comprehensive pelvic floor muscle exercise showed significant application prospects and values in the recovery of patients' intestinal functions after RC anus-preserving surgery.