Development and validation of a multi-modal ultrasomics model to predict response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer

OBJECTIVES

To assess the performance of multi-modal ultrasomics model to predict efficacy to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC) and compare with the clinical model.

MATERIALS AND METHODS

This study retrospectively included 106 patients with LARC who underwent total mesorectal excision after nCRT between April 2018 and April 2023 at our hospital, randomly divided into a training set of 74 and a validation set of 32 in a 7: 3 ratios. Ultrasomics features were extracted from the tumors' region of interest of B-mode ultrasound (BUS) and contrast-enhanced ultrasound (CEUS) images based on PyRadiomics. Mann-Whitney U test, spearman, and least absolute shrinkage and selection operator algorithms were utilized to reduce features dimension. Five models were built with ultrasomics and clinical analysis using multilayer perceptron neural network classifier based on python. Including BUS, CEUS, Combined_1, Combined_2 and Clinical models. The diagnostic performance of models was assessed with the area under the curve (AUC) of the receiver operating characteristic. The DeLong testing algorithm was utilized to compare the models' overall performance.

RESULTS

The AUC (95% confidence interval [CI]) of the five models in the validation cohort were as follows: BUS 0.675 (95%CI: 0.481-0.868), CEUS 0.821 (95%CI: 0.660-0.983), Combined_1 0.829 (95%CI: 0.673-0.985), Combined_2 0.893 (95%CI: 0.780-1.000), and Clinical 0.690 (95%CI: 0.509-0.872). The Combined_2 model was the best in the overall prediction performance, showed significantly better compared to the Clinical model after DeLong testing (P < 0.01). Both univariate and multivariate logistic regression analyses showed that age (P < 0.01) and clinical stage (P < 0.01) could be an independent predictor of efficacy after nCRT in patients with LARC.

CONCLUSION

The ultrasomics model had better diagnostic performance to predict efficacy to nCRT in patients with LARC than the Clinical model.

Effects of neoadjuvant therapy on health-related quality of life for patients with gastroesophageal cancer

BACKGROUND

Neoadjuvant therapy in combination with surgery increases survival in gastroesophageal cancer; however, little is known about its impact on health-related quality of life. This study compared the impact of neoadjuvant therapy with that of surgery alone on the health-related quality of life in patients treated for gastroesophageal cancer.

METHODS

A single-centre cohort study with prospectively collected data from patients undergoing curative intended treatment for gastroesophageal cancer between 2013 and 2020 was performed. Health-related quality of life was assessed prior to surgery and patients stratified according to neoadjuvant therapy or surgery alone. The primary endpoint was self-assessed health-related quality of life, evaluated using validated cancer-specific questionnaires. A pre-specified multivariable model adjusted for age, ASA score, and clinical T- and N-stage was used.

RESULTS

A total of 361 patients were included, of whom 239 (61%) were treated with neoadjuvant therapy. Patients treated with neoadjuvant therapy reported less difficulties with eating restrictions (-11.9, p = 0.005), pain (-10.9, p = 0.004), and insomnia (-12.6, p = 0.004) than patients treated with surgery alone. Patients with oesophageal cancer and neoadjuvant therapy reported less dysphagia (-16.6, p < 0.001), eating restrictions (-23.2, p < 0.001), and odynophagia (-18.0, p = 0.002) than those who underwent surgery alone.

CONCLUSION

Neoadjuvant therapy was associated with a significant reduction in symptoms affecting malnutrition and improved health-related quality of life in patients with gastroesophageal cancer. These results indicates that more patients might be available for neoadjuvant therapy, despite the baseline burden of gastroesophageal cancer.

Multiparametric MRI-based Radiomics approaches on predicting response to neoadjuvant chemoradiotherapy (nCRT) in patients with rectal cancer

PURPOSE

To investigate the value of multiparametric MRI-based radiomics on predicting response to nCRT in patients with rectal cancer.

METHODS

This study enrolled 193 patients with pathologically confirmed LARC who received nCRT treatment between Apr. 2014 and Jun. 2018. All patients underwent baseline T1-weighted (T1W), T2-weighted (T2W) and T2-weighted fat-suppression (T2FS) MRI scans before neoadjuvant chemoradiotherapy. Radiomics features were extracted and selected from the MRI data to establish the radiomics signature. Important clinical predictors were identified by Mann-Whitney U test and Chi-square test. The nomogram integrating the radiomics signature and important clinical predictors was constructed using multivariate logistic regression. Prediction capabilities of each model were assessed with receiver operating characteristic (ROC) curve analysis. Performance of the nomogram was evaluated by its calibration and potential clinical usefulness.

RESULTS

For the prediction of good response (GR) and pathologic complete response (pCR), the developed radiomics signature comprising 10 and 7 features, respectively, were significantly associated with the therapeutic response to nCRT. The nomogram incorporating the radiomics signature and important clinical predictors (CEA and CA19-9 for predicting GR; CEA, posttreatment length and posttreatment thickness for predicting pCR) achieved favorable prediction efficacy, with AUCs of 0.918 (95% confidence interval [CI]: 0.867-0.971, Sen = 0.972, Spe = 0.828) and 0.944 (95% CI: 0.891-0.997, Sen = 0.943, Spe = 0.828) in the training and validation cohort for predicting GR, respectively; with AUCs of 0.959 (95% CI: 0.927-0.991, Sen = 1.000, Spe = 0.833) and 0.912 (95% CI: 0.843-0.982, Sen = 1.000, Spe = 0.815) in the training and validation cohort for predicting pCR, respectively. Decision curve analysis confirmed potential clinical usefulness of our nomogram.

CONCLUSIONS

This study demonstrated that the MRI-based radiomics nomogram is predictive of response to nCRT and can be considered as a promising tool for facilitating treatment decision-making for patients with LARC.

A Pipeline for Predicting the Treatment Response of Neoadjuvant Chemoradiotherapy for Locally Advanced Rectal Cancer Using Single MRI Modality: Combining Deep Segmentation Network and Radiomics Analysis Based on "Suspicious Region"

Patients with locally advanced rectal cancer (LARC) who achieve a pathologic complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) typically have a good prognosis. An early and accurate prediction of the treatment response, i.e., whether a patient achieves pCR, could significantly help doctors make tailored plans for LARC patients. This study proposes a pipeline of pCR prediction using a combination of deep learning and radiomics analysis. Taking into consideration missing pre-nCRT magnetic resonance imaging (MRI), as well as aiming to improve the efficiency for clinical application, the pipeline only included a post-nCRT T2-weighted (T2-w) MRI. Unlike other studies that attempted to carefully find the region of interest (ROI) using a pre-nCRT MRI as a reference, we placed the ROI on a “suspicious region”, which is a continuous area that has a high possibility to contain a tumor or fibrosis as assessed by radiologists. A deep segmentation network, termed the two-stage rectum-aware U-Net (tsraU-Net), is designed to segment the ROI to substitute for a time-consuming manual delineation. This is followed by a radiomics analysis model based on the ROI to extract the hidden information and predict the pCR status. The data from a total of 275 patients were collected from two hospitals and partitioned into four datasets: Seg-T (N = 88) for training the tsraUNet, Rad-T (N = 107) for building the radiomics model, In-V (N = 46) for internal validation, and Ex-V (N = 34) for external validation. The proposed method achieved an area under the curve (AUC) of 0.829 (95% confidence interval [CI]: 0.821, 0.837) on In-V and 0.815 (95% CI, 0.801, 0.830) on Ex-V. The performance of the method was considerable and stable in two validation sets, indicating that the well-designed pipeline has the potential to be used in real clinical procedures.

Clinical response assessment on DW-MRI compared with FDG-PET/CT after neoadjuvant chemoradiotherapy in patients with oesophageal cancer

PURPOSE

In about 30% of patients treated with neoadjuvant chemoradiotherapy (nCRT) followed by surgical resection for locally advanced oesophageal cancer no vital tumour is found in the resection specimen. Accurate clinical response assessment is critical if deferral from surgery is considered in complete responders. Our study aimed to compare the performance of MRI and of FDG-PET/CT for the detection of residual disease after nCRT.

METHODS

Patients with oesophageal cancer eligible for nCRT and oesophagectomy were prospectively included. All patients underwent FDG-PET/CT and MRI before and between 6 and 8 weeks after nCRT. Two radiologists scored the MRI scans, and two nuclear medicine physicians scored the FDG-PET/CT scans using a 5-point score for residual disease. Histopathology after oesophagectomy represented the reference standard. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated for detection of residual tumour (ypT+), residual nodal disease (ypN+), and any residual disease (ypT+Nx/ypT0N+).

RESULTS

Seven out of 33 (21%) patients had a pathological complete response. The AUCs for individual readers to detect ypT+ were 0.71/0.70 on diffusion-weighted (DW)-MRI and 0.54/0.57 on FDG-PET/CT, and to detect ypN+ were 0.89/0.81 on DW-MRI and 0.75/0.71 on FDG-PET/CT. The AUCs/sensitivities/specificities for the individual readers to detect any residual disease were 0.74/92%/57% and 0.70/96%/43% on MRI; these were 0.49/69%/29% and 0.60/69%/43% on FDG-PET/CT, respectively.

CONCLUSION

MRI reached higher diagnostic accuracies than FDG-PET/CT for the detection of residual tumour in oesophageal cancer patients at 6 to 8 weeks after nCRT.

Laparoscopic Ultra Low Anterior Resection: Single Center, 6-Year Study

Background: This study represents a prospective analysis of a series of laparoscopic ultra low anterior resection (ULAR) done at a laparoscopic surgical center to assess the surgical outcome, oncological efficacy, and quality of life after surgery. Methods: Over a period of 6 years (2013-2018), 43 patients aged between 40 and 68 years, with very low rectal cancers (3-6 cm from the anal verge), within T3N1M0 stage, assessed by positron emission tomography-computed tomography and pelvic magnetic resonance imaging, underwent neoadjuvant chemoradiotherapy (nCRT) followed by laparoscopic ULAR and simultaneous diversion ileostomy. Results: The overall complication rate was low and there was an overall leak rate of 9.3% with a radiological leak (Grade A) in 3 of the 43 patients (7%), but only 1 (2.3%) patient required a local lavage and a resuturing for secondary hemorrhage. Recurrence was seen in 2/43 (4.7%), one of whom had a conversion to abdominoperineal resection. The other had distant metastasis and refused further treatment. The functional outcome is assessed in 41 (95.3%) patients by low anterior resection syndrome (LARS) score and a reasonable quality of life with major LARS was seen in only 7.3% of the patients at a follow-up ranging from 1 to 6 years. Conclusion: The nCRT followed by laparoscopic ULAR is a feasible option for operable very low rectal cancers and is associated with minimal postoperative events, a low local recurrence and less incidence of LARS.

Tolerability, Safety, and Outcomes of Neoadjuvant Chemoradiotherapy With Capecitabine for Patients Aged ≥ 70 Years With Locally Advanced Rectal Cancer

INTRODUCTION

In studies of colorectal cancer, the elderly have been frequently underrepresented because comorbid conditions and functional status often lead to study exclusion. For elderly patients with an indication for neoadjuvant chemoradiotherapy (nCRT), physicians usually decide using clinical factors whether nCRT should be offered. The aim of the present retrospective study was to assess the tolerability of nCRT with capecitabine and the surgical outcomes in patients aged ≥ 70 years with locally advanced rectal cancer.

PATIENTS AND METHODS

Data from 1372 rectal cancer patients diagnosed from 2002 to 2012 at 4 Dutch hospitals were used. Patients aged ≥ 70 years were included if they had received nCRT, and their data were analyzed for treatment deviations, postoperative complications, mortality, disease-free survival (DFS), and overall survival (OS). The data were stratified into 3 age groups (ie, 70-74, 75-79, and ≥ 80 years).

RESULTS

We identified 447 patients aged ≥ 70 years. Of these patients, 42 had received nCRT, and 37 (88%) had completed nCRT. Radiation dermatitis, fatigue, and diarrhea were reported in 62%, 57%, and 43% of the 42 patients, respectively. Of the 42 patients, 40 (95%) underwent surgery, 1 patient refused resection, and 1 patient died during nCRT of severe mucositis due to dihydropyrimidine dehydrogenase deficiency. The postoperative complication rate was 30%, and the 30-day mortality rate was 0%. A pathologic complete response was found in 7.5%. The 2- and 5-year DFS and OS rates were 58.5% and 40.7% and 81.0% and 58.2%, respectively.

CONCLUSION

The results of the present multicenter study have shown that if selected on clinical factors, nCRT with capecitabine is safe and well tolerated in elderly patients. No negative effect on surgical outcome was measured, and the beneficial effect (pathologic complete response, DFS, and OS) seemed comparable to that for younger age groups. We believe that elderly patients should not be excluded from nCRT on the basis of age only.

Adjuvant Chemotherapy Is Associated With Improved Overall Survival in Locally Advanced Rectal Cancer After Achievement of a Pathologic Complete Response to Chemoradiation

BACKGROUND

In locally advanced rectal adenocarcinoma, 15% to 20% of patients treated with neoadjuvant chemoradiation (nCRT) achieve a pathologic complete response (pCR). The benefit of adjuvant chemotherapy is controversial in rectal cancer. Our objective was to evaluate the effect of clinical risk factors and adjuvant chemotherapy usage on the outcomes of the pCR patient population.

PATIENTS AND METHODS

We performed a retrospective study using the National Cancer Data Base from 2006 to 2013. The primary outcome was overall survival (OS). The association between OS and patient characteristics (demographics, tumor variables, and treatment) was examined using multivariable Cox regression modelling.

RESULTS

A total of 2891 patients were identified who had achieved a pCR. Of these 2891 patients, 2102 received nCRT and 789 received nCRT followed by adjuvant chemotherapy. The median follow-up duration was 43.2 months. The factors significantly associated with OS included age (P < .001), gender (P = .011), Charlson-Deyo comorbidity score (P < .001), grade (P = .029), clinical T stage (P = .030), carcinoembryonic antigen negativity (P = .002), and receipt of adjuvant chemotherapy (P < .001). Nodal status was not significantly associated with survival. The 5-year OS rate was 94% in the nCRT plus adjuvant group compared with 84% in the nCRT-alone group. Adjuvant chemotherapy was more likely to be given to younger patients (aged < 60 years), higher grade, lower Charlson-Deyo comorbidity score, elevated carcinoembryonic antigen level, higher clinical T stage, and higher clinical N stage.

CONCLUSION

Our findings showed a significant improvement in OS for patients who received nCRT plus adjuvant chemotherapy compared with those who received nCRT alone. The nCRT plus adjuvant patients were more likely to be younger, have a lower comorbidity score, have clinical ≥ T3 disease, and have clinical node-positive disease. Thus, a selection bias could have been present. Nonetheless, even in the setting of already excellent outcomes, for patients with locally advanced rectal adenocarcinoma who achieve a pCR, the additional benefit of adjuvant chemotherapy should be weighed against the potential for toxicity.