Random Forest Modeling of Acute Toxicity in Anal Cancer: Effects of Peritoneal Cavity Contouring Approaches on Model Performance

PURPOSE

Our purpose was to analyze the effect on gastrointestinal (GI) toxicity models when their dose-volume metrics predictors are derived from segmentations of the peritoneal cavity after different contouring approaches.

METHODS AND MATERIALS

A random forest machine learning approach was used to predict acute grade ≥3 GI toxicity from dose-volume metrics and clinicopathologic factors for 246 patients (toxicity incidence = 9.5%) treated with definitive chemoradiation for squamous cell carcinoma of the anus. Three types of random forest models were constructed based on different bowel bag segmentation approaches: (1) physician-delineated after Radiation Therapy Oncology Group (RTOG) guidelines, (2) autosegmented by a deep learning model (nnU-Net) following RTOG guidelines, and (3) autosegmented but spanning the entire bowel space. Each model type was evaluated using repeated cross-validation (100 iterations; 50%/50% training/test split). The performance of the models was assessed using area under the precision-recall curve (AUPRC) and the receiver operating characteristic curve (AUROCC), as well as optimal F1 score.

RESULTS

When following RTOG guidelines, the models based on the nnU-Net auto segmentations (mean values: AUROCC, 0.71 ± 0.07; AUPRC, 0.42 ± 0.09; F1 score, 0.46 ± 0.08) significantly outperformed (P < .001) those based on the physician-delineated contours (mean values: AUROCC, 0.67 ± 0.07; AUPRC, 0.34 ± 0.08; F1 score, 0.36 ± 0.07). When spanning the entire bowel space, the performance of the autosegmentation models improved considerably (mean values: AUROCC, 0.87 ± 0.05; AUPRC, 0.70 ± 0.09; F1 score, 0.68 ± 0.09).

CONCLUSIONS

Random forest models were superior at predicting acute grade ≥3 GI toxicity when based on RTOG-defined bowel bag autosegmentations rather than physician-delineated contours. Models based on autosegmentations spanning the entire bowel space show further considerable improvement in model performance. The results of this study should be further validated using an external data set.

Stability of metabolic tumor volume may enable radiotherapy dose painting in anal cancer

PURPOSE

To evaluate the variability of the 18F-FDG-PET/CT-based metabolic tumor volume (MTV) in anal cancers during fractionated chemoradiotherapy (CRT), and assess the impact of this variability on dosimetric accuracy in MTV-targeted dose painting.

METHODS

Eleven patients with anal squamous cell carcinoma who received fractionated chemoradiotherapy with curative intent were included. 18F-FDG PET/CT images were acquired at pre- and mid-treatment. Target volumes and organs at risk (OARs) were contoured manually on both image series. The MTV was generated from the PET images by thresholding. Treatment plans were retrospectively optimized for both image series using volumetric modulated arc therapy (VMAT). Standard plans prescribed 48.6 Gy, 54 Gy and 57.5 Gy in 27 fractions to elective regions, lymph node metastases and primary tumor, respectively. Dose painting plans included an extra dose level of 65 Gy to the MTV. Pre-treatment plans were transferred and re-calculated at mid-treatment basis.

RESULTS

MTV decreased from pre- to mid-treatment in 10 of the 11 patients. On average, 71 % of MTVmid overlapped with MTVpre. The median and mean doses to the MTV were robust against anatomical changes, but the transferred dose painting plans had lower D98% values than the original and re-optimized plans. No major differences were found between standard and dose painting plans for OARs.

CONCLUSIONS

Despite volumetric changes in the MTV, adequate dose coverage was observed in most dose painting plans. The findings indicate little or no need for adaptive dose painting at mid-treatment. Dose painting appears to be a safe treatment alternative with similar dose sparing of OARs.

Evaluation of dosimetric predictors of toxicity after IMRT with concurrent chemotherapy for anal cancer

BACKGROUND

This study investigates the impact of dosimetric parameters on acute and late toxicity for patients with anal squamous cell carcinoma (SCC) treated with image-guided intensity modulated radiation therapy (IG-IMRT) and concurrent chemotherapy.

MATERIALS AND METHODS

Patients were enrolled in an observational cohort study between 2008 and 2013 (median follow-up 3.4 years). They were treated with standardized target and organ-at-risk (OAR) contouring, planning, and IG-IMRT. Radiotherapy dose, based on clinicopathologic features, ranged from 45 Gy to 63 Gy to gross targets and 27 Gy to 36 Gy to elective targets. Chemotherapy was concurrent 5-fluorouracil and mitomycin C (weeks 1&5). Toxicity was prospectively graded using NCI CTCAE v.3 and RTOG scales. Logistic regression was used to assess the association between dose/volume parameters (e.g small bowel V5) and corresponding grade 2 + and 3+ (G2+/3 + ) toxicities (e.g. diarrhea).

RESULTS

In total, 87 and 79 patients were included in the acute and late toxicity analyses, respectively. The most common acute G2 + toxicities were skin (dermatitis in 87 % [inguino-genital skin], 91 % [perianal skin]) and hematologic in 58 %. G2 + late anal toxicity (sphincter dysfunction), gastrointestinal toxicity, and skin toxicity were respectively experienced by 49 %, 38 %, and 44 % of patients. Statistically significant associations were observed between: G2 + acute diarrhea and small bowel V35; G2 + acute genitourinary toxicity and bladder D_0.5cc; G2 + inguino-genital skin toxicity and anterior skin V35; G2 + perianal skin toxicity and posterior skin V15; G2 + anemia and lower pelvis bone V45. D0.5 cc was significantly predictive of late toxicity (G2 + anal dysfunction, intestinal toxicity, and inguino-genital/perianal dermatitis). Maximum skin toxicity grade was significantly correlated with the requirement for a treatment break.

CONCLUSION

Statistically significant dose-volume parameters were identified and may be used to offer individualized risk prediction and to inform treatment planning. Additional validation of the results is required.

Dosimetric and Clinical Predictors for Acute and Late Gastrointestinal Toxicity Following Chemoradiotherapy of Locally Advanced Anal Cancer

AIMS

To analyse dosimetric and clinical predictors for acute and late gastrointestinal toxicity following chemoradiotherapy of anal cancer.

MATERIALS AND METHODS

Consecutive patients with locally advanced (T2 ≥4 cm - T4 or N+) anal cancer were selected from an institutional database (n = 114). All received intensity-modulated radiotherapy with concomitant 5-fluorouracil and mitomycin C. Gastrointestinal toxicity was retrospectively graded according to Common Terminology Criteria for Adverse Events (CTCAE) version 5.0 and bowel cavity, small bowel and large bowel were contoured. Dosimetric and clinical variables were tested for associations with acute grade ≥3 gastrointestinal toxicity and late grade ≥2 gastrointestinal toxicity using the Mann-Whitney test, area under receiver operating characteristic curve (AUC) and logistic regression.

RESULTS

The median follow-up was 40 months. Acute grade ≥3 gastrointestinal toxicity was seen in 51 (44.7%) of the patients; late grade ≥2 gastrointestinal toxicity was seen in 36 of the patients (39.6% of 91 patients with >1 year recurrence-free follow-up). Bowel cavity V30Gy was the best dosimetric predictor for acute gastrointestinal toxicity (AUC 0.633; P = 0.02). Large bowel V20Gy was the best dosimetric predictor for late gastrointestinal toxicity (AUC 0.698; P = 0.001) but showed no association with acute gastrointestinal toxicity. In multivariate logistic regression, increasing age was significantly associated with acute gastrointestinal toxicity; smoking and large bowel V20Gy were significantly associated with late gastrointestinal toxicity. Patients who experienced acute grade ≥3 gastrointestinal toxicity were not at an increased risk of late grade ≥2 gastrointestinal toxicity (odds ratio 1.3; P = 0.55).

CONCLUSIONS

Factors of importance for acute and late gastrointestinal toxicity were not the same. Bowel cavity V30Gy is a good metric to use for the prediction of acute gastrointestinal toxicity, but the results of our study indicate that individual large and small bowel loops need to be contoured for better prediction of late gastrointestinal toxicity. The role of the large bowel as an important organ at risk for late gastrointestinal toxicity merits further research.

Dosimetric comparison of organs at risk using different contouring guidelines for definition of the clinical target volume in anal cancer

Background

There are different contouring guidelines for definition of the clinical target volume (CTV) for intensity-modulated radiation therapy (IMRT) of anal cancer (AC). We conducted a planning comparison study to evaluate and compare the dose to relevant organs at risk (OARs) while using different CTV definitions.

Methods

Twelve patients with a primary diagnosis of anal cancer, who were treated with primary chemoradiation (CRT), were selected. We generated four guideline-specific CTVs and subsequently planned target volumes (PTVs) on the planning CT scan of each patient. An IMRT plan for volumetric arc therapy (VMAT) was set up for each PTV. Dose parameters of the planned target volume (PTV) and OARs were evaluated and compared, too.

Results

The mean volume of the four PTVs ranged from 2138 cc to 2433 cc. The target volumes contoured by the authors based on the recommendations of each group were similar in the pelvis, while they differed significantly in the inguinal region. There were no significant differences between the four target volumes with regard to the dose parameters of the cranially located OARs. Conversely, some dose parameters concerning the genitals and the skin varied significantly among the different guidelines.

Conclusion

The four contouring guidelines differ significantly concerning the inguinal region. In order to avoid inguinal recurrence and to protect relevant OARs, further investigations are needed to generate uniform standards for definition of the elective clinical target volume in the inguinal region.

Robust dose planning objectives for mesorectal radiotherapy of early stage rectal cancer - A multicentre dose planning study

BACKGROUND AND PURPOSE

Organ preservation strategies are increasingly being explored for early rectal cancer. This requires revision of target volumes according to disease stage, as well as new guidelines for treatment planning. We conducted an international, multicentre dose planning study to develop robust planning objectives for modern radiotherapy of a novel mesorectal-only target volume, as implemented in the STAR-TReC trial (NCT02945566).

MATERIALS AND METHODS

The published literature was used to establish relevant dose levels for organ at risk (OAR) plan optimisation. Ten representative patients with early rectal cancer were identified. Treatment scans had mesorectal target volumes as well as bowel cavity, bladder and femoral heads outlined, and were circulated amongst the three participating institutions. Each institution produced plans for short course (SCRT, 5 × 5 Gy) and long course (LCRT, 25 × 2 Gy) treatment, using volumetric modulated arc therapy on different dose planning systems. Optimisation objectives for OARs were established by determining dose metric objectives achievable for ≥90% of plans.

RESULTS

Sixty plans, all fulfilling target coverage criteria, were produced. The planning results and literature review suggested optimisation objectives for SCRT: V 10Gy < 180 cm3, V 18Gy < 110 cm3, V 23Gy < 85 cm3 for bowel cavity; V 21Gy < 15% and V 25Gy < 5% for bladder; and V 12.5Gy < 11% for femoral heads. Corresponding objectives for LCRT: V 20Gy < 180 cm3, V 30Gy < 130 cm3, V 45Gy < 90 cm3 for bowel cavity; V 35Gy < 22% and V 50Gy < 7% for bladder; and V 25Gy < 15% for femoral heads. Constraints were validated across all three institutions.

CONCLUSION

We utilized a multicentre planning study approach to develop robust planning objectives for mesorectal radiotherapy for early rectal cancer.

Anal adenocarcinoma: Treatment outcomes and trends in a rare disease entity

Importance

Primary Adenocarcinoma of the anus is a rare disease with a poor prognosis and thus tends to have a more aggressive treatment algorithm, typically involving a surgical approach. Prior to 2001, a few retrospective studies outlined improved outcomes with the incorporation of surgery with chemoradiation. However, since the publication of these studies, advancement in radiotherapy modalities and imaging have left the question of improved outcomes while reserving surgery for salvage.

Objective

We conducted this National Cancer Database (NCDB)‐driven retrospective study to analyze treatment trends and outcomes in the current time from 2004 to 2015 with respect to chemoradiation and surgery.

Design

Retrospective NCDB tumor registry data review—using propensity score‐adjusted multivariable analyses for survival.

Setting

Database review.

Participants

We selected for patients listed in the NCDB with AJCC stage 1‐3 anal adenocarcinoma diagnosed between 2004 and 2015 and selected out patients with undocumented/stage 4 disease, those with radiation outside the pelvis, not treated with systemic therapy and patients lost to follow‐up.

Exposure(s)

None.

Main outcomes and measures

Overall survival and use of surgery in the up‐front management of anal adenocarcinoma.

Results

Of the 1729 patients eligible in this study, 1028 were treated with surgery as up‐front management and 701 had definitive chemoradiation. Median overall survival for all patients was 55 months with a 5‐year survival rate of 55%. Patients treated without surgery had worse overall survival, median survival of 45 months compared to 87 months (P < 0.0001) with 5‐year survival rates of 42% and 55% in favor of incorporation of surgery. Analysis across patients treated with surgery alone, surgery followed by adjuvant chemoradiation, neoadjuvant chemoradiation followed by surgery, and chemoradiation alone had median survival rates of 78, 83, 92, and 46 months, respectively. Propensity score‐adjusted multivariable analysis identified older age, grade 3, high comorbidity score, and lack of surgery as predictive of worse outcome.

Conclusions and Relevance

The results of the NCDB analysis indicate improved overall survival with the incorporation of surgery into the initial management of anal adenocarcinoma when compared to chemoradiation alone, despite the omission of surgery in up to 50% of the cases logged. Our results corroborate earlier studies published prior to the year 2000 for surgery to be included in the definitive management of anal adenocarcinoma.

Trends in Radiation Dose and Technique For Anal Canal Squamous Cell Carcinoma

BACKGROUND

Anal canal squamous cell carcinoma (SCC) is managed definitively with chemoradiation, reserving surgery for salvage. The dosage of radiation has varied from 30 Gy to in excess of 60 Gy. RTOG 0529 established intensity modulated radiation therapy (IMRT) as standard of care for anal canal SCC with doses of 50.4 to 54 Gy. We sought to use the National Cancer Database to examine trends in dose selection and radiation technique over time.

METHODS

We queried the National Cancer Database from 2004 to 2015 for cases of anal cancer stage groups 1 to 3, treated with definitive doses of radiation with chemotherapy. Dose escalation was defined as >54 Gy. Univariable and multivariable analyses were performed to identify factors predictive of dose, IMRT, and overall survival. Propensity-adjusted Cox proportional hazard ratios for survival were used to account for indication bias.

RESULTS

We identified 7792 patients meeting the eligibility criteria, with 4269 treated to doses of 45 to 54 Gy and 3163 treated to doses >54 Gy. Patients who were older, had government or private insurance, IMRT treatment, treatment at an academic center, or more recent years were less likely to get dose escalation. The use of dose escalation decreased over time, from 50% in 2005 to 30% in 2015. IMRT use increased over time from 2% to 63%. On multivariable analysis with propensity score included it was found that increased age, higher comorbidity score, lower income, shorter distance to facility, and male sex were predictive of decreased overall survival. In addition, escalated dose was associated with a lower survival (hazard ratio: 1.10, 95% confidence interval: 1.01-1.20, P=0.03).

CONCLUSIONS

The results of this analysis show a steady increase in the use of IMRT, with corresponding decrease in dose escalation. These findings correlate with the results of RTOG 0529 establishing IMRT as standard of care for anal SCC, using doses of 50.4 to 54 Gy.

Dosimetric comparison of helical tomotherapy and VMAT for anal cancer: A single institutional experience

To compare the dosimetric results of helical tomotherapy (HT) and volumetric arc therapy (VMAT) in the treatment of anal cancer. Plans were created for 20 (n = 20) patients treated for anal cancer using HT and 2 arc VMAT. Dosimetric comparison was assessed for doses to targets and organs at risk (small bowel, bladder, external genitalia, and femoral heads). Delivery time and dosimetric verification results were also compared. HT showed a higher V95% for both primary and nodal targets (V95% increase by 0.5% to 1.3%; p = ≤0.05). No differences were seen in V105%, V107%, or V110 % between techniques. HT provided better sparing of the small bowel for dose levels V30, V35, and V40 (p = 0.005, 0.001, and 0.030), but was similar at higher doses. Similarly HT provided better bladder dose at V35 only (p = 0.020). Doses to femoral heads and genitalia were similar. Delivery time was higher for the HT plans (4.58 ± 1.1 min) than VMAT (3.13 ± 0.2 minutes) (p = 0.011). Dose verification results were 99.5 ± 0.9% and 100 ± 0% (HT, n = 6) vs 95.0 ± 3.1% and 99.2 ± 0.8% (VMAT, n = 20) for global gamma criteria 3%/3 mm and 4%/4 mm, respectively. Both HT and VMAT produced high quality plans that frequently met most of the dose objectives apart from genitalia V20, V40, bladder V35, and V50. Although absolute dose differences were small, the PTV V95%, small bowel V30, V35, and V40 and bladder V35 were statistically better in the HT plans. VMAT provided a shorter delivery time by 1.45 minutes; however, our HT plans were more likely to pass tighter plan dose verification criteria than VMAT.

Feasibility of preference-driven radiotherapy dose treatment planning to support shared decision making in anal cancer

PURPOSE/OBJECTIVE

Chemo-radiotherapy is an established primary curative treatment for anal cancer, but clinically equal rationale for different target doses exists. If joint preferences (physician and patient) are used to determine acceptable tradeoffs in radiotherapy treatment planning, multiple dose plans must be simultaneously explored. We quantified the degree to which different toxicity priorities might be incorporated into treatment plan selection, to elucidate the feasible decision space for shared decision making in anal cancer radiotherapy.

MATERIAL AND METHODS

Retrospective plans were generated for 22 anal cancer patients. Multi-criteria optimization handles dynamically changing priorities between clinical objectives while meeting fixed clinical constraints. Four unique dose distributions were designed to represent a wide span of clinically relevant objectives: high-dose preference (60.2 Gy tumor boost and 50.4 Gy to elective nodes with physician-defined order of priorities), low-dose preference (53.75 Gy tumor boost, 45 Gy to elective nodes, physician-defined priorities), bowel sparing preference (lower dose levels and priority for bowel avoidance) and bladder sparing preference (lower dose levels and priority for bladder avoidance).

RESULTS

Plans satisfied constraints for target coverage. A senior oncologist approved a random subset of plans for quality assurance. Compared to a high-dose preference, bowel sparing was clinically meaningful at the lower prescribed dose [median change in V_45Gy: 234 cm³; inter-quartile range (66; 247); p < .01] and for a bowel sparing preference [median change in V_45Gy: 281 cm³; (73; 488); p < .01]. Compared to a high-dose preference, bladder sparing was clinically meaningful at the lower prescribed dose [median change in V_35Gy: 13.7%-points; (0.3; 30.6); p < .01] and for a bladder sparing preference [median change in V_35Gy: 30.3%-points; (12.4; 43.1); p < .01].

CONCLUSIONS

There is decision space available in anal cancer radiotherapy to incorporate preferences, although tradeoffs are highly patient-dependent. This study demonstrates that preference-informed dose planning is feasible for clinical studies utilizing shared decision making.

Predictors of Radiation Therapy-Related Gastrointestinal Toxicity From Anal Cancer Dose-Painted Intensity Modulated Radiation Therapy: Secondary Analysis of NRG Oncology RTOG 0529

PURPOSE

NRG Oncology RTOG 0529 assessed the feasibility of dose-painted intensity modulated radiation therapy (DP-IMRT) to reduce the acute morbidity of chemoradiation with 5-fluorouracil (5FU) and mitomycin-C (MMC) for T2-4N0-3M0 anal cancer. This secondary analysis was performed to identify patient and treatment factors associated with acute and late gastrointestinal (GI) adverse events (AEs).

METHODS AND MATERIALS

NRG Oncology RTOG 0529 treatment plans were reviewed to extract dose-volume data for tightly contoured small bowel, loosely contoured anterior pelvic contents (APC), and uninvolved colon outside the target volume (UC). Univariate logistic regression was performed to evaluate association between volumes of each structure receiving doses ≥5 to 60 Gy (V5-V60) in 5-Gy increments between patients with and without grade ≥2 acute and late GI AEs, and grade ≥3 acute GI AEs. Additional patient and treatment factors were evaluated in multivariate logistic regression (acute AEs) or Cox proportional hazards models (late AEs).

RESULTS

Among 52 evaluable patients, grade ≥2 acute, grade ≥2 late, and grade ≥3 acute GI AEs were observed in 35, 17, and 10 patients, respectively. Trends (P<.05) toward statistically significant associations were observed between grade ≥2 acute GI AEs and small bowel dose (V20-V40), grade ≥2 late GI AEs and APC dose (V60), grade ≥3 acute GI AEs and APC dose (V5-V25), increasing age, tumor size >4 cm, and worse Zubrod performance status. Small bowel volumes of 186.0 cc, 155.0 cc, 41.0 cc, and 30.4 cc receiving doses greater than 25, 30, 35, and 40 Gy, respectively, correlated with increased risk of acute grade ≥2 GI AEs.

CONCLUSIONS

Acute and late GI AEs from 5FU/MMC chemoradiation using DP-IMRT correlate with radiation dose to the small bowel and APC. Such associations will be incorporated in the dose-volume normal tissue constraint design for future NRG oncology anal cancer studies.

[Recommendations for the management of cancers of the anal canal]

Anal canal carcinomas remain rare, but their management has improved recently. The PET-CT is now used as a standard at the first diagnosis and after relapses. The introduction of intensity-modulated irradiation techniques makes it possible to better conform the pelviperineal and inguinal volumes, improving the homogeneity of the irradiation while sparing some pelvic structures, thus reducing acute and late effects. Nevertheless, the conversion from 3D to intensity-modulated radiotherapy needs a specific and careful approach, mainly for the management of the perineal region, where relapses and complications occur. Last but not least, new chemotherapy associations are studied for metastatic disease.

Prospective evaluation of acute toxicity and quality of life after IMRT and concurrent chemotherapy for anal canal and perianal cancer

PURPOSE

A prospective cohort study was conducted to evaluate toxicity, quality of life (QOL), and clinical outcomes in patients treated with intensity modulated radiation therapy (IMRT) and concurrent chemotherapy for anal and perianal cancer.

METHODS AND MATERIALS

From June 2008 to November 2010, patients with anal or perianal cancer treated with IMRT were eligible. Radiation dose was 27 Gy in 15 fractions to 36 Gy in 20 fractions for elective targets and 45 Gy in 25 fractions to 63 Gy in 35 fractions for gross targets using standardized, institutional guidelines, with no planned treatment breaks. The chemotherapy regimen was 5-fluorouracil and mitomycin C. Toxicity was graded with the National Cancer Institute Common Terminology Criteria for Adverse Events, version 3. QOL was assessed with the European Organization for Research and Treatment of Cancer (EORTC) QLQ-C30 and CR29 questionnaires. Correlations between dosimetric parameters and both physician-graded toxicities and patient-reported outcomes were evaluated by polyserial correlation.

RESULTS

Fifty-eight patients were enrolled. The median follow-up time was 34 months; the median age was 56 years; 52% of patients were female; and 19% were human immunodeficiency virus-positive. Stage I, II, III, and IV disease was found in 9%, 57%, 26%, and 9% of patients, respectively. Twenty-six patients (45%) required a treatment break because of acute toxicity, mainly dermatitis (23/26). Acute grade 3 + toxicities included skin 46%, hematologic 38%, gastrointestinal 9%, and genitourinary 0. The 2-year overall survival (OS), disease-free survival (DFS), colostomy-free survival (CFS), and cumulative locoregional failure (LRF) rates were 90%, 77%, 84%, and 16%, respectively. The global QOL/health status, skin, defecation, and pain scores were significantly worse at the end of treatment than at baseline, but they returned to baseline 3 months after treatment. Social functioning and appetite scores were significantly better at 12 months than at baseline. Multiple dose-volume parameters correlated moderately with diarrhea, skin, and hematologic toxicity scores.

CONCLUSION

IMRT reduces acute grade 3 + hematologic and gastrointestinal toxicities compared with reports from non-IMRT series, without compromising locoregional control. The reported QOL scores most relevant to acute toxicities returned to baseline by 3 months after treatment.

Technical aspects of radiation therapy for anal cancer

Historically treated with surgery, current practice recommends anal carcinoma to be treated with a combination of chemotherapy and radiation. This review will examine the anatomy, modes of disease spread and recurrence, and evaluate the existing evidence for treatment options for these tumors. An in-depth examination of specific radiation therapy (RT) techniques-such as conventional 3D-conformal RT and intensity-modulated RT-will be discussed along with modern dose constraints. RT field arrangement, patient setup, and recommended gross and clinical target volume (CTV) contours will be considered. Areas in need of further investigation, such as the role in treatment for positron emission tomography (PET) will be explored.