Radiomics classifier to quantify automatic segmentation quality of cardiac sub-structures for radiotherapy treatment planning.

PURPOSE: A radiomics features classifier was implemented to evaluate segmentation quality of heart structures. A robust feature set sensitive to incorrect contouring would provide an ideal quantitative index to drive autocontouring optimization. METHODS: Twenty-five cardiac sub-structures were contoured as regions of interest in 36 CTs. Radiomic features were extracted from manually-contoured (MC) and Hierarchical-Clustering automatic-contouring (AC) structures. A robust feature-set was identified from correctly contoured CT datasets. Features variation was analyzed over a MC/AC dataset. A supervised-learning approach was used to train an Artificial-Intelligence (AI) classifier; incorrect contouring cases were generated from the gold-standard MC datasets with translations, expansions and contractions. ROC curves and confusion matrices were used to evaluate the AI-classifier performance. RESULTS: Twenty radiomics features, were found to be robust across structures, showing a good/excellent intra-class correlation coefficient (ICC) index comparing MC/AC. A significant correlation was obtained with quantitative indexes (Dice-Index, Hausdorff-distance). The trained AI-classifier detected correct contours (CC) and not correct contours (NCC) with an accuracy of 82.6% and AUC of 0.91. True positive rate (TPR) was 85.1% and 81.3% for CC and NCC. Detection of NCC at this point of the development still depended strongly on degree of contouring imperfection. CONCLUSIONS: A set of radiomics features, robust on "gold-standard" contour and sensitive to incorrect contouring was identified and implemented in an AI-workflow to quantify segmentation accuracy. This workflow permits an automatic assessment of segmentation quality and may accelerate expansion of an existing autocontouring atlas database as well as improve dosimetric analyses of large treatment plan databases.

Unexpected tumor response to palliative pelvic radiotherapy in mismatch repair-deficient advanced prostate cancer: a case report.

BACKGROUND: Mismatch-repair-deficiency resulting in microsatellite instability (MSI) may confer increased radiosensitivity in locally advanced/metastatic tumors and thus radiotherapy (RT) potentially might have a changing role in treating this subset of patients, alone or in combination with checkpoint inhibitors. CASE PRESENTATION: We report a 76 year-old Italian male patient presenting with locally advanced undifferentiated prostate cancer (LAPC), infiltrating bladder and rectum. Molecular analysis revealed high-MSI with an altered expression of MSH2 and MSH6 at immunohistochemistry. Two months after 6 chemotherapy cycles with Docetaxel associated to an LHRH analogue, a computed tomography scan showed stable disease. After palliative RT (30 Gy/10 fractions) directed to the tumor mass with a 3D-conformal setup, a follow-up computed tomography scan at 8 weeks revealed an impressive response that remained stable at computed tomography after 9 months, with sustained biochemical response. To our knowledge, this is the first case of such a sustained response to low dose RT alone in high-MSI LAPC. CONCLUSIONS: Routine evaluation of MSI in patients with locally problematic advanced tumors might change treatment strategy and treatment aim in this setting, from a purely palliative approach to a quasi-curative paradigm.

Hierarchical clustering applied to automatic atlas based segmentation of 25 cardiac sub-structures.

PURPOSE: Segmentation of cardiac sub-structures for dosimetric analyses is usually performed manually in time-consuming procedure. Automatic segmentation may facilitate large-scale retrospective analysis and adaptive radiotherapy. Various approaches, among them Hierarchical Clustering, were applied to improve performance of atlas-based segmentation (ABS). METHODS: Training dataset of ABS consisted of 36 manually contoured CT-scans. Twenty-five cardiac sub-structures were contoured as regions of interest (ROIs). Five auto-segmentation methods were compared: simultaneous automatic contouring of all 25 ROIs (Method-1); automatic contouring of all 25 ROIs using lungs as anatomical barriers (Method-2); automatic contouring of a single ROI for each contouring cycle (Method-3); hierarchical cluster-based automatic contouring (Method-4); simultaneous truth and performance level estimation (STAPLE). Results were evaluated on 10 patients. Dice similarity coefficient (DSC), average Hausdorff distance (AHD), volume comparison and physician score were used as validation metrics. RESULTS: Atlas performance improved increasing number of atlases. Among the five ABS methods, Hierarchical Clustering workflow showed a significant improvement maintaining a clinically acceptable time for contouring. Physician scoring was acceptable for 70% of the ROI automatically contoured. Inter-observer evaluation showed that contours obtained by Hierarchical Clustering method are statistically comparable with them obtained by a second, independent, expert contourer considering DSC. Considering AHD, distance from the gold standard is lower for ROIs segmented by ABS. CONCLUSIONS: Hierarchical clustering resulted in best ABS results for the primarily investigated platforms and compared favorably to a second benchmark system. Auto-contouring of smaller structures, being in range of variation between manual contourers, may be ideal for large-scale retrospective dosimetric analysis.