To study radiotherapy-related adverse effects, detailed dose information (3D distribution) is needed for accurate dose-effect modeling. For childhood cancer survivors who underwent radiotherapy in the pre-CT era, only 2D radiographs were acquired, thus 3D dose distributions must be reconstructed from limited information. State-of-the-art methods achieve this by using 3D surrogate anatomies. These can however lack personalization and lead to coarse reconstructions. We present and validate a surrogate-free dose reconstruction method based on Machine Learning (ML). Abdominal planning CTs (n = 142) of recently-treated childhood cancer patients were gathered, their organs at risk were segmented, and 300 artificial Wilms' tumor plans were sampled automatically. Each artificial plan was automatically emulated on the 142 CTs, resulting in 42,600 3D dose distributions from which dose-volume metrics were derived. Anatomical features were extracted from digitally reconstructed radiographs simulated from the CTs to resemble historical radiographs. Further, patient and radiotherapy plan features typically available from historical treatment records were collected. An evolutionary ML algorithm was then used to link features to dose-volume metrics. Besides 5-fold cross validation, a further evaluation was done on an independent dataset of five CTs each associated with two clinical plans. Cross-validation resulted in mean absolute errors ≤ 0.6 Gy for organs completely inside or outside the field. For organs positioned at the edge of the field, mean absolute errors ≤ 1.7 Gy for Dmean, ≤ 2.9 Gy for 2cc,}, and ≤ 13% for V5 Gy10 Gy, were obtained, without systematic bias. Similar results were found for the independent dataset. To conclude, we proposed a novel organ dose reconstruction method that uses ML models to predict dose-volume metric values given patient and plan features. Our approach is not only accurate, but also efficient, as the setup of a surrogate is no longer needed.

Fully or semi-automatic contouring tools are increasingly being used in the tumor contouring task for radiotherapy. While the fully automatic contouring tools have not reached sufficient efficiency, the semi-automatic contouring tools balance more effectively between the human interaction and automation. This study evaluates the influences of a semi-automation contouring tool, called between-slice interpolation, on the resulting contours and the contouring process. The tumor contouring study was conducted on three patient cases with five physicians in a naturalistic setting. The contouring task consisted of initiating the 2D contour manually or with the interpolation tool and correcting that initial contour. The similarity of the resulting contours was pairwise measured within the manual or the interpolated category. Interactions with the software were recorded, and variations in the contouring workflows steps were compared. Results indicated that using the between-slice interpolation tool for creating the initial contour, instead of initiating it manually, influenced both the contouring process and outcomes. First, it was identified that contours initiated by the interpolation tool showed an increased similarity among themselves compared to the manually initiated contours. At the same time, influences to the resulting contours were below clinical relevance, and toward the desired direction—improved consistency of contours. Second, when interpolation was used, in two cases out of three, the average contouring time also decreased significantly. Therefore, the use of such an automation tool can be encouraged.

Sensemaking theories help designers understand the cognitive processes of a user when he/she performs a complicated task. This paper introduces a two-step approach of incorporating sensemaking support within the design of health information systems by: (1) modeling the sensemaking process of physicians while performing a task, and (2) identifying software interaction design requirements that support sensemaking based on this model. The two-step approach is presented based on a case study of the tumor contouring clinical task for radiotherapy planning. In the first step of the approach, a contextualized sensemaking model was developed to describe the sensemaking process based on the goal, the workflow and the context of the task. In the second step, based on a research software prototype, an experiment was conducted where three contouring tasks were performed by eight physicians respectively. Four types of navigation interactions and five types of interaction sequence patterns were identified by analyzing
the gathered interaction log data from those twenty-four cases. Further in-depth study on each of the navigation interactions and interaction sequence patterns in relation to the contextualized sensemaking model revealed five main areas for design improvements to increase sensemaking support. Outcomes of the case study indicate that the proposed two-step approach was beneficial for gaining a deeper understanding of the sensemaking process during the task, as well as for identifying design requirements for
better sensemaking support.