Predicting Hematologic Toxicity of Anal Cancer Patients before Chemoradiation Using Deep Residual Network with Transfer Learning

775 Background: Hematologic toxicities (HT) induced during chemoradiotherapy (CRT) for anal cancer can lead to increased infection rates, bleeding, asthenia, and unplanned breaks compromising treatment efficacy. We hypothesize that HT in anal cancer patients treated with CRT correlate with change in active bone marrow (ABM) characterized by pre- and post-CRT 18F-FDG PET/CT (PET). Methods: Twenty-eight locally advanced anal cancer patients treated with definitive CRT from 2011-2016 were identified. PET scans were obtained 0-2 weeks pre- and 6-8 weeks post-CRT. HT was evaluated by weekly white blood cell count, absolute neutrophil count (ANC), hemoglobin (Hg) and platelet nadirs. Total bone marrow (TBM) was defined on CT images, and segmented into three subregions: lumbosacral (LS), left and right iliac pelvis. PET images were normalized to bone outside of the TBM uptakes. ABM was characterized in all PET images as the volume having standard uptake value SUV > 40% of SUVmax in the TBM. Image variables (global, subregional SUVmean, SUVmax, ABMs) of pre- and post-CRT and their differential changes were evaluated as predictors of HT. Locoregional radiomics features were calculated using a 3D kernel-based approach. HT prediction was modeled by logistic regression with the Lasso algorithm with 10-fold cross-validation. HT endpoints were defined as change between baseline blood nadir and the lowest nadir values during and up to 2 weeks after CRT. Results: The lasso regression identified 5 predictors of HT (pre-SUVmax, post-LS-ABM, LS-ABM change, homogeneity texture change, and variance). Ratios of LS-ABMs to TBM were reduced from 18.9% (pre-CRT) to 16.3% (post-CRT). This reduction of LS-ABM significantly correlated with acute HT measured by ANC (p < 0.001) and Hg (p < 0.001) nadirs. Conclusions: PET-derived active BM changes between pre- and post-CRT significantly associated with HT in anal cancer patients undergoing definitive CRT. LS-ABM is a robust surrogate for evaluation of HT and can be used to develop BM-sparing radiotherapy for reduction of potential HT.

Download Full-text

Concurrent Chemoradiation in Anal Cancer Patients Delivered with Bone Marrow-Sparing IMRT: Final Results of a Prospective Phase II Trial

Journal of Personalized Medicine ◽

10.3390/jpm11050427 ◽

2021 ◽

Vol 11 (5) ◽

pp. 427

Author(s):

Francesca Arcadipane ◽

Patrick Silvetti ◽

Francesco Olivero ◽

Alessio Gastino ◽

Roberta Carlevato ◽

...

Keyword(s):

Bone Marrow ◽

Cancer Patients ◽

Anal Cancer ◽

Intensity Modulated Radiotherapy ◽

Pelvic Bone ◽

Hematologic Toxicity ◽

18Fdg Pet ◽

Prospective Phase ◽

Bone Marrow Sparing

We investigated the role of the selective avoidance of haematopoietically active pelvic bone marrow (BM), with a targeted intensity-modulated radiotherapy (IMRT) approach, to reduce acute hematologic toxicity (HT) in anal cancer patients undergoing concurrent chemo-radiation. We designed a one-armed two-stage Simon’s design study to test the hypothesis that BM-sparing IMRT would improve by 20% the rate of G0–G2 (vs. G3–G4) HT, from 42% of RTOG 0529 historical data to 62% (α = 0.05; β = 0.20). A minimum of 21/39 (54%) with G0–G2 toxicity represented the threshold for the fulfilment of the criteria to define this approach as ‘promising’. We employed 18FDG-PET to identify active BM within the pelvis. Acute HT was assessed via weekly blood counts and scored as per the Common Toxicity Criteria for Adverse Effects version 4.0. From December 2017 to October 2020, we enrolled 39 patients. Maximum observed acute HT comprised 20% rate of ≥G3 leukopenia and 11% rate of ≥G3 thrombocytopenia. Overall, 11 out of 39 treated patients (28%) experienced ≥G3 acute HT. Conversely, in 28 patients (72%) G0–G2 HT events were observed, above the threshold set. Hence, 18FDG-PET-guided BM-sparing IMRT was able to reduce acute HT in this clinical setting.

Download Full-text

Bone Marrow-Sparing IMRT in Anal Cancer Patients Undergoing Concurrent Chemo-Radiation: Results of the First Phase of a Prospective Phase II Trial

Cancers ◽

10.3390/cancers12113306 ◽

2020 ◽

Vol 12 (11) ◽

pp. 3306

Author(s):

Francesca Arcadipane ◽

Patrick Silvetti ◽

Francesco Olivero ◽

Alessio Gastino ◽

Viola De Luca ◽

...

Keyword(s):

Cancer Patients ◽

Phase Ii ◽

Anal Cancer ◽

Phase Ii Trial ◽

Hematologic Toxicity ◽

18Fdg Pet ◽

Prospective Phase ◽

Bone Marrow Sparing ◽

Toxicity Criteria

Purpose: to investigate the role of selective avoidance of hematopoietically active BM within the pelvis, as defined with 18FDG-PET, employing a targeted IMRT approach, to reduce acute hematologic toxicity (HT) profile in anal cancer patients undergoing concurrent chemo-radiation. Methods: a one-armed two-stage Simon’s design was selected to test the hypothesis that BM-sparing approach would improve by 20% the rate of G0–G2 (vs. G3–G4) HT, from 42% of RTOG 0529 historical data to 62% (α = 0.05 and the β = 0.20). At the first stage, among 21 enrolled patients, at least 9 should report G0–G2 acute HT to further proceed with the trial. We employed 18FDG-PET to identify active BM within the pelvis. Acute HT was assessed via weekly blood counts and scored as per the Common Toxicity Criteria for Adverse Effects version 4.0. Results: from December 2017 to October 2019, 21 patients were enrolled. Maximum observed acute HT comprised 9% rate of ≥G3 leukopenia and 5% rate of ≥G3 neutropenia and anemia. Overall, only 4 out of 21 treated patients (19%) experienced ≥G3 acute HT. Conversely, 17 patients (81%) experienced G0–G2 events, way above the threshold set by the trial design. Conclusion: 18FDG-PET-guided BM-sparing IMRT was able to reduce acute HT in anal cancer patients treated with concomitant chemo-radiation. These results prompted us to conclude the second part of this prospective phase II trial.

Download Full-text