Link-INVENT enables design of PROTACs, fragment linking, and scaffold hopping while satisfying multiple optimization criteria.

Target volume delineation is a vital but time-consuming and challenging part of radiotherapy, where the goal is to deliver sufficient dose to the target while reducing risks of side effects. For head and neck cancer (HNC) this is complicated by the complex anatomy of the head and neck region and the proximity of target volumes to organs at risk. The purpose of this study was to compare and evaluate conventional PET thresholding methods, six classical machine learning algorithms and a 2D U-Net convolutional neural network (CNN) for automatic gross tumor volume (GTV) segmentation of HNC in PET/CT images. For the latter two approaches the impact of single versus multimodality input on segmentation quality was also assessed. 197 patients were included in the study. The cohort was split into training and test sets (157 and 40 patients, respectively). Five-fold cross-validation was used on the training set for model comparison and selection. Manual GTV delineations represented the ground truth. Tresholding, classical machine learning and CNN segmentation models were ranked separately according to the cross-validation Sørensen–Dice similarity coefficient (Dice). PET thresholding gave a maximum mean Dice of 0.62, whereas classical machine learning resulted in maximum mean Dice scores of 0.24 (CT) and 0.66 (PET; PET/CT). CNN models obtained maximum mean Dice scores of 0.66 (CT), 0.68 (PET) and 0.74 (PET/CT). The difference in cross-validation Dice between multimodality PET/CT and single modality CNN models was significant (p ≤ 0.0001). The top-ranked PET/CT-based CNN model outperformed the best-performing thresholding and classical machine learning models, giving significantly better segmentations in terms of cross-validation and test set Dice, true positive rate, positive predictive value and surface distance-based metrics (p ≤ 0.0001). Thus, deep learning based on multimodality PET/CT input resulted in superior target coverage and less inclusion of surrounding normal tissue.

Tumor delineation is time- and labor-intensive and prone to inter- and intraobserver variations. Magnetic resonance imaging (MRI) provides good soft tissue contrast, and functional MRI captures tis...

Tumor delineation is required both for radiotherapy planning and quantitative imaging biomarker purposes. It is a manual, time- and labor-intensive process prone to inter- and intraobserver variations. Semi or fully automatic segmentation could provide better efficiency and consistency. This study aimed to investigate the influence of including and combining functional with anatomical magnetic resonance imaging (MRI) sequences on the quality of automatic segmentations. T2-weighted (T2w), diffusion weighted, multi-echo T2*-weighted, and contrast enhanced dynamic multi-echo (DME) MR images of eighty-one patients with rectal cancer were used in the analysis. Four classical machine learning algorithms; adaptive boosting (ADA), linear and quadratic discriminant analysis and support vector machines, were trained for automatic segmentation of tumor and normal tissue using different combinations of the MR images as input, followed by semi-automatic morphological post-processing. Manual delineations from two experts served as ground truth. The Sørensen-Dice similarity coefficient (DICE) and mean symmetric surface distance (MSD) were used as performance metric in leave-one-out cross validation. Using T2w images alone, ADA outperformed the other algorithms, yielding a median per patient DICE of 0.67 and MSD of 3.6 mm. The performance improved when functional images were added and was highest for models based on either T2w and DME images (DICE: 0.72, MSD: 2.7 mm) or all four MRI sequences (DICE: 0.72, MSD: 2.5 mm). Machine learning models using functional MRI, in particular DME, have the potential to improve automatic segmentation of rectal cancer relative to models using T2w MRI alone.

Objective. Intensity modulated proton therapy (IMPT) is susceptible to uncertainties in patient setup and proton range. Robust optimization is employed in IMPT treatment planning to ensure sufficient coverage of the clinical target volume (CTV) in predefined scenarios, albeit at a price of increased planning times. We investigated a deep learning (DL) strategy for dose predictions in individual error scenarios in head and neck cancer IMPT treatment planning, enabling direct evaluation of plan robustness. The model is able to differentiate between scenarios by using embeddings of the scenario index. Approach. To accommodate resolution disparities in planning CT-scans and accommodate the setup error scenarios, we introduced scenario-specific isocentric distance maps as inputs to the DL models. For 392 H&N cancer patients, high-quality 9-scenario ground truth (GT) robust plans were generated with wish-list driven fully automated multi-criteria optimization. The scenario index is converted to one-hot-vector that is used to derive the scenarios embeddings through the training of the DL model, aiding the model to predict a scenario specific dose distribution. Main results. The model achieved within 1%-point of agreement with the GT the predicted V 95 % of the voxelwise minimum dose for CTV Low and CTV High for 96% and 75% respectively of the test patients. Considering all robustness scenarios, median differences were 0.035%-point for CTV High V 95 % , 0.11%-point for CTV Low V 95 % , 0.29 GyE for parotids D mean , 0.7 GyE for submandibular glands D mean and 0.9 GyE for oral cavity D mean . Prediction of full 3D dose distributions for all scenarios took around 14 s. Significance. Predicting individual scenarios for robust proton therapy using DL dose prediction is feasible, enabling direct robustness evaluation of the predicted scenario doses.