Machine-learned target volume delineation of 18F-FDG PET images after one cycle of induction chemotherapy

Artificial intelligence in radiation oncology: A review of its current status and potential application for the radiotherapy workforce

OBJECTIVE

Radiation oncology is a continually evolving speciality. With the development of new imaging modalities and advanced imaging processing techniques, there is an increasing amount of data available to practitioners. In this narrative review, Artificial Intelligence (AI) is used as a reference to machine learning, and its potential, along with current problems in the field of radiation oncology, are considered from a technical position.

KEY FINDINGS

AI has the potential to harness the availability of data for improving patient outcomes, reducing toxicity, and easing clinical burdens. However, problems including the requirement of complexity of data, undefined core outcomes and limited generalisability are apparent.

CONCLUSION

This original review highlights considerations for the radiotherapy workforce, particularly therapeutic radiographers, as there will be an increasing requirement for their familiarity with AI due to their unique position as the interface between imaging technology and patients.

IMPLICATIONS FOR PRACTICE

Collaboration between AI experts and the radiotherapy workforce are required to overcome current issues before clinical adoption. The development of educational resources and standardised reporting of AI studies may help facilitate this.

Applications of artificial intelligence in oncologic 18F-FDG PET/CT imaging: a systematic review

Artificial intelligence (AI) is a growing field of research that is emerging as a promising adjunct to assist physicians in detection and management of patients with cancer. ¹⁸F-FDG PET imaging helps physicians in detection and management of patients with cancer. In this study we discuss the possible applications of AI in ¹⁸F-FDG PET imaging based on the published studies. A systematic literature review was performed in PubMed on early August 2020 to find the relevant studies. A total of 65 studies were available for review against the inclusion criteria which included studies that developed an AI model based on 18F-FDG PET data in cancer to diagnose, differentiate, delineate, stage, assess response to therapy, determine prognosis, or improve image quality. Thirty-two studies met the inclusion criteria and are discussed in this review. The majority of studies are related to lung cancer. Other studied cancers included breast cancer, cervical cancer, head and neck cancer, lymphoma, pancreatic cancer, and sarcoma. All studies were based on human patients except for one which was performed on rats. According to the included studies, machine learning (ML) models can help in detection, differentiation from benign lesions, segmentation, staging, response assessment, and prognosis determination. Despite the potential benefits of AI in cancer imaging and management, the routine implementation of AI-based models and ¹⁸F-FDG PET-derived radiomics in clinical practice is limited at least partially due to lack of standardized, reproducible, generalizable, and precise techniques.

Accuracy of metabolic volume and total glycolysis among six threshold-based target segmentation algorithms

OBJECTIVE

This study aimed to evaluate the accuracy of six threshold-based segmentation methods with different target-to-background ratios (TBR), images with different voxel sizes and image noise, in measuring metabolic volume (MV) and total glycolysis (TG).

METHODS

A standard body phantom consisting of six spheres (inner diameters of 37, 28, 22, 17, 13, and 10 mm) was filled with ¹⁸F-FDG solution. The background radioactivity level was 2.65 kBq/mL, and the TBRs were 4 and 8. PET data were acquired for 30 min with list mode. PET data for 30 and 3 min were reconstructed with a three-dimensional ordered subset expectation maximization algorithm plus time-of-flight information with images with 2 and 4 mm isotropic voxels. The six methods examined were absolute standardized uptake value (SUV) of 2.5 (SUV_2.5), 41%, 50%, adaptive 41%, and adaptive 50% thresholds of maximum SUV (Th₄₁, Th₅₀, ThA₄₁, and ThA₅₀, respectively); and the contrast-oriented algorithm (Th_COA). Segmented MV and TG were compared with the actual inner volume and expressed as percentages (%MV_seg and %TG_seg, respectively). In addition, the segmented MV was converted to the diameter, and the differences of it from the reference diameter were compared among six methods.

RESULTS

The Th_COA method yielded the most accurate measurements of %MV_seg and %TG_seg; the difference between %MV_seg or %TG_seg and its reference were smaller than 10% in 30-min and 15% in 3-min images, but the segmented contour was almost the same as the reference diameter. Measurements with Th₅₀ and Th_COA were highly accurate for both %MV_seg and %TG_seg in the large spheres, and the adaptive threshold methods, including ThA₄₁, ThA₅₀, and Th_COA, were also highly accurate in the small spheres. The voxel sizes affected the accuracy of %MV_seg and %TG_seg with a TBR of 4 in any threshold-based methods.

CONCLUSIONS

Of the six threshold-based segmentation methods studied, Th_COA was the most accurate method for evaluating MV and TG and had only minor dependence on TBRs and sphere size. The small voxel sizes improved the variation of the accuracy in low TBR.