Active bone marrow segmentation based on computed tomography imaging in anal cancer patients: A machine-learning-based proof of concept

PURPOSE

Different methods are available to identify haematopoietically active bone marrow (ActBM). However, their use can be challenging for radiotherapy routine treatments, since they require specific equipment and dedicated time. A machine learning (ML) approach, based on radiomic features as inputs to three different classifiers, was applied to computed tomography (CT) images to identify haematopoietically active bone marrow in anal cancer patients.

METHODS

A total of 40 patients was assigned to the construction set (training set + test set). Fluorine-18-Fluorodeoxyglucose Positron Emission Tomography (18FDG-PET) images were used to detect the active part of the pelvic bone marrow (ActPBM) and stored as ground-truth for three subregions: iliac, lower pelvis and lumbosacral bone marrow (ActIBM, ActLPBM, ActLSBM). Three parameters were used for the correspondence analyses between 18FDG-PET and ML classifiers: DICE index, Precision and Recall.

RESULTS

For the 40-patient cohort, median values [min; max] of the Dice index were 0.69 [0.20; 0.84], 0.76 [0.25; 0.89], and 0.36 [0.15; 0.67] for ActIBM, ActLSBM, and ActLPBM, respectively. The Precision/Recall (P/R) ratio median value for the ActLPBM structure was 0.59 [0.20; 1.84] (over segmentation), while for the other two subregions the P/R ratio median has values of 1.249 [0.43; 4.15] for ActIBM and 1.093 [0.24; 1.91] for ActLSBM (under segmentation).

CONCLUSION

A satisfactory degree of overlap compared to 18FDG-PET was found for 2 out of the 3 subregions within pelvic bones. Further optimization and generalization of the process is required before clinical implementation.

Dosimetric predictors of acute hematologic toxicity during concurrent intensity-modulated radiotherapy and chemotherapy for anal cancer

PURPOSE

This study aimed at investigating whether the irradiated volume of pelvic bone marrow (PBM) and specific subsites may predict the occurrence of acute hematologic toxicity (HT) in anal cancer patients undergoing concurrent chemo-radiation.

METHODS

50 patients, submitted to IMRT and concurrent chemotherapy, were analyzed. Several bony structures were defined on planning-CT: PBM and lumbar-sacral (LSBM), lower pelvis (LPBM) and iliac (IBM) bone marrow. On dose-volume histograms, dosimetric parameters were taken. Endpoints included white blood-cell-count (WBC), absolute-neutrophil-count (ANC), hemoglobin (Hb) and platelet nadirs and acute hematologic toxicity (HT) according to RTOG scoring scale. Generalized linear modeling was used to find correlations between dosimetric variables and blood cell nadirs, while logistic regression analysis was used to test correlation with ≥G3 HT. Receiver Operating Characteristic (ROC) curve analysis was used to evaluate the optimal cut-off points for predictive dosimetric variables with the Youden method.

RESULTS

Maximum detected acute HT comprised 38 % of ≥G3 leukopenia and 32 % of ≥G3 neutropenia. Grade 2 anemia was observed in 4 % of patients and ≥G3 thrombocytopenia in 10 %. On multivariate analysis a higher PBM-V ₂₀ was associated with lower WBC nadir. Increased LSBM-V ₄₀ was correlated with a higher likelihood to develop ≥G3 HT. A cut-off point at 41 % for LSBM-V ₄₀ was found. Patients with LSBM-V ₄₀ ≥41 % were more likely to develop ≥G3 HT (55.3 vs. 32.4 %; p < 0.01).

CONCLUSIONS

Increased low-dose to pelvic bony structures significantly predicted for WBC decrease. Medium-high dose to specific osseous subsites was associated with a higher probability of HT. LSBM-V ₄₀ was a strong predictor of ≥G3 HT. A threshold at 41 % for LSBM-V ₄₀ could be used to limit HT.