Soft-Tissue Tumor Bed Size Change


Detect and quantify volumetric changes of a soft-tissue tumor








 Jay Patti

Panel Chair

 Jay Patti

Panel Reviewers

 Musculoskeletal Panel


 Creative Commons 4.0

Status  Public Commenting

Clinical Implementation

Value Proposition

Sarcomas and other soft-tissue tumors are sometimes treated with local excision (removal while preserving adjacent anatomy) or radiation/chemotherapy (intravenous medical or high-energy radiation treatment without surgery, in which the intent is to shrink the tumor) or a combination of both of these techniques. In such cases, imaging is used to follow the tumor and assess the response to the chosen therapy. When the tumor decreases in volume, this is usually an indication that the current therapy is effective. When the tumor increases in volume, this is an indication that the current therapy is not effective. Changes are then made to the chosen therapy to hopefully achieve an effective response.


A 63-year-old patient presents to the oncologist after local resection of a low-grade sarcoma. MRI imaging is obtained after the surgery but before the initiation of chemotherapy. The postsurgical area is then imaged every year with MRI for the next 5 years. Each time the patient is imaged, the AI tool, with the help of a radiologist, identifies the postsurgical area and defines it in 3-dimensional space. Each year, the new area is compared with the prior year's imaging, and AI-defined fiduciary markers are compared, which the AI tool uses to determine if the postsurgical area has increased or decreased in volume. Areas where the AI believes there has been an enlargement are highlighted for the radiologist.

Workflow Description

Volumetric DICOM images are obtained from the modality and sent to PACS and the AI engine. The radiologist interacts with the images to identify or verify the center of the postsurgical area. The AI engine identifies the borders of the postsurgical area and calculates the volume of the postsurgical area or mass. The location and size data are sent to PACS to highlight the region that the engine identified.

Considerations for Dataset Development

Procedures(s): {MRI, any body region with soft-tissue mass}

View(s): Volumetric dataset


Sex at Birth: {Male, Female}


Age: [0,90]


Soft Tissue Tumor Types: {Angiosarcoma, Dermatofibrosarcoma, Epithelioid sarcoma, Ewing sarcoma, Fibrosarcoma, Gastrointestinal stromal tumors, Kaposi sarcoma, Leiomyosarcoma, Liposarcoma, Malignant fibrous histiocytoma, Neurofibrosarcoma, Rhabdomyosarcoma, Synovial sarcoma}

Technical Specifications






Volumetric dataset

Data Type




Primary Outputs

Tumor Bed Size Change

RadElement ID



Status of the tumor bed

Data Type


Value Set

0-No change in size

1-Increase in size

2-Decrease in size



Future Development Ideas

Segment the tumor bed and represent the change in size from prior imaging.

Public Commenting

Use cases are meant to be a primary vehicle for distributing clinical information to the developer community. They pinpoint precise scenarios within radiology workflows where potential automation could add noticeable value and establish standards for interpreting and passing corresponding common data elements. Implementing effective standards requires the perspective from all stakeholders. So to that end, we encourage your feedback on use cases.

To submit comments, please email with the use case title(s) and relevant comments by January 1, 2019. If more convenient, you may also download this use case and comment directly on the PDF. Just attach the PDF copy on the email.