Tagged: PET

Oncotarget

AI for Improved PET/CT Attenuation Correction in Prostate Cancer Imaging

July 11, 2024

In this new study, researchers investigated an artificial intelligence (AI) tool that produces attenuation-corrected PET images while reducing radiation exposure for patients.

—

Positron Emission Tomography (PET) combined with Computed Tomography (CT) is a powerful imaging modality used in oncology for diagnosis, staging, and treatment monitoring. However, one limitation of PET/CT is the need for accurate attenuation correction (AC) to account for tissue density variations. Traditionally, low-dose CT scans are used for AC, but these contribute to patient radiation exposure.

In a new study, researchers Kevin C. Ma, Esther Mena, Liza Lindenberg, Nathan S. Lay, Phillip Eclarinal, Deborah E. Citrin, Peter A. Pinto, Bradford J. Wood, William L. Dahut, James L. Gulley, Ravi A. Madan, Peter L. Choyke, Ismail Baris Turkbey, and Stephanie A. Harmon from the National Cancer Institute proposed an artificial intelligence (AI) tool to generate attenuation-corrected PET (AC-PET) images directly from non-attenuation-corrected PET (NAC-PET) images, reducing the reliance on CT scans. Their research paper was published in Oncotarget’s Volume 15 on May 7, 2024, entitled, “Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.”

“Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans.”

The Study

The researchers developed a deep learning algorithm based on a 2D Pix-2-Pix generative adversarial network (GAN) architecture. They used paired AC-PET and NAC-PET images from 302 prostate cancer patients. The dataset was split into training, validation, and testing cohorts (183, 60, and 59 studies, respectively). Two normalization strategies were employed: Standard Uptake Value (SUV)-based and SUV-Nyul-based. The AI model learned to generate AC-PET images from NAC-PET images, effectively bypassing the need for CT scans during PET/CT studies. The performance of the AI model was evaluated at the scan level using several metrics:

  • Normalized Mean Square Error (NMSE): A measure of the difference between predicted and ground truth AC-PET images. Lower NMSE indicates better performance.
  • Mean Absolute Error (MAE): Similar to NMSE, lower MAE signifies improved accuracy.
  • Structural Similarity Index (SSIM): Measures image similarity. Higher SSIM values indicate better alignment between AC-PET and ground truth images.
  • Peak Signal-to-Noise Ratio (PSNR): Evaluates image quality. Higher PSNR values correspond to better image fidelity.

The AI model demonstrated promising results, achieving competitive performance across all metrics. The choice of normalization strategy (SUV-based or SUV-Nyul-based) did not significantly impact the model’s effectiveness.

The proposed AI tool has several clinical implications. By eliminating the need for low-dose CT scans, patients are exposed to less ionizing radiation during PET/CT studies. Additionally AC-PET images can be generated directly from NAC-PET data, simplifying the imaging process. The AI model also produces accurate AC-PET images, enhancing diagnostic confidence.

Conclusions

Deep learning-based AC-PET image generation using Pix-2-Pix GANs represents a promising approach to improve PET/CT imaging in prostate cancer patients. As AI continues to evolve, its integration into clinical practice may revolutionize how we acquire and interpret medical images, ultimately benefiting patient care. In summary, this research contributes to the ongoing efforts to enhance imaging techniques, reduce patient radiation exposure, and streamline clinical workflows.

“The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.”

Click here to read the full research paper in Oncotarget.

—

Oncotarget is an open-access, peer-reviewed journal that has published primarily oncology-focused research papers since 2010. These papers are available to readers (at no cost and free of subscription barriers) in a continuous publishing format at Oncotarget.com. 

Oncotarget is indexed and archived by PubMed/Medline, PubMed Central, Scopus, EMBASE, META (Chan Zuckerberg Initiative) (2018-2022), and Dimensions (Digital Science).

Click here to subscribe to Oncotarget publication updates.

For media inquiries, please contact media@impactjournals.com.

Oncotarget

Trending with Impact: New Prognostic Parameters for Breast Cancer

February 16, 2021

Different imaging and assessment tools across multiple clinics can result in varied prognostic values. Researchers from Japan conducted a retrospective study of harmonized pretreatment volume-based quantitative FDG-PET/CT parameters for prognostic values in breast cancer patients.

PET Scan image of whole body Comparision Axial, Coronal plane in patient breast cancer recurrence treatment.

The Trending with Impact series highlights Oncotarget publications attracting higher visibility among readers around the world online, in the news, and on social media—beyond normal readership levels. Look for future science news and articles about the latest trending publications here, and at Oncotarget.com.

—

Listen to an audio version of this article

Breast cancer consists of a wide variety of tumor types, symptoms, disease progression courses, and responses to treatments. In the clinic, researchers decide which disease interventions to use by evaluating the patients’ stage of tumor-node-metastasis (TNM), histologic tumor grade, and the levels of hormone receptors and molecular markers that are present.

Standardized uptake value (SUV), metabolic tumor volume (MTV), and tumor lesion glycolysis (TLG) are derived from 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT). These variables have also been reported to correlate with clinicopathological prognostic factors and are considered predictive factors of prognosis.

Breast Cancer Prognostic Parameters

“Recently, noninvasive diagnostic tools have been gaining popularity for prediction of tumor behavior, with magnetic resonance spectroscopy (MRS) and diffusion-weighted imaging (DWI) with magnetic resonance imaging (MRI) reported to provide surrogate imaging biomarkers showing correlations with clinicopathological prognostic factors [2, 3].”

In a multi-institutional retrospective study in Japan, researchers—from the Hyogo College of Medicine, Nippon Medical School Hospital, National Cancer Center Hospital, Kinki University Faculty of Medicine, and Gunma Prefectural College of Health Sciences—explain that the factors and algorithms used by different assessment tools across multiple clinics can result in varied standardized uptake values. These inconsistencies have provided an opportunity for the researchers to standardize parameters of prognostic values when imaging breast cancer patients to improve patient outcomes.

“Thus, a harmonization strategy is necessary for comparing semi-quantitative PET parameters among available imaging methods, which is a notably relevant issue for multicenter trials employing different PET systems.”

The Study

Researchers gathered records of 546 patients treated from 2010 to 2016 with stage I–III invasive breast cancer. Of those patients, 344 were estrogen receptor (ER)-positive/human epidermal growth factor receptor two (HER2)-negative, 110 were HER2-positive, and 92 were triple-negative. The patients were treated at four separate institutions using different PET/CT scanner systems. In addition to surgeries, chemotherapy, and radiotherapy, patients were assessed during their follow-up appointments.

“Mammography, ultrasound, CT, bone scanning, and FDG-PET/CT were used for determining disease recurrence, metastasis, and progression during follow-up.”

Researchers in this study retrospectively performed histological and statistical analyses of overall survival and recurrence-free survival in patients of each breast cancer subtype group.

“An experienced reader (12 years of experience with oncologic FDG-PET/CT) who had no knowledge of other imaging results or clinical and histopathologic data retrospectively reviewed all of the FDG-PET/CT images.”

They found that the average maximum standardized uptake values (SUVmax) for HER2-positive and triple-negative tumor patients were higher than in patients with ER-positive/HER2-negative tumors.

“Harmonized primary tumor and nodal maximum SUVmax, metabolic tumor volume (MTV), and TLG indicated in pretreatment FDG-PET/CT results were analyzed.”

Conclusion

Results from this study suggest that harmonized PET classifications with final clinical response assessments demonstrate a better ability to predict disease-free survival compared to non-harmonized PET classification.

“We concluded that harmonized quantitative volume-based values, especially those for the primary tumor and nodal SUVmax and TLG, obtained with FDG-PET/CT can provide useful information regarding prognosis for both recurrence and death in patients with operable invasive breast cancer, including all three main subtypes. The findings presented here are considered useful for improving care of individual patients.”

Click here to read the full retrospective study, published in Oncotarget.

—

Oncotarget is a unique platform designed to house scientific studies in a journal format that is available for anyone to read—without a paywall making access more difficult. This means information that has the potential to benefit our societies from the inside out can be shared with friends, neighbors, colleagues and other researchers, far and wide.

For media inquiries, please contact media@impactjournals.com.