Machine Learning Facilitates Hotspot Classification in PSMA-PET/CT with Nuclear Medicine Specialist Accuracy

Sobhan Moazemi; Zain Khurshid; Annette Erle; Susanne Lütje; Markus Essler; Thomas Schultz; Ralph A Bundschuh

doi:10.3390/diagnostics10090622

Machine Learning Facilitates Hotspot Classification in PSMA-PET/CT with Nuclear Medicine Specialist Accuracy

Diagnostics (Basel). 2020 Aug 22;10(9):622. doi: 10.3390/diagnostics10090622.

Authors

Sobhan Moazemi^{1

2}, Zain Khurshid³, Annette Erle¹, Susanne Lütje¹, Markus Essler¹, Thomas Schultz^{2

4}, Ralph A Bundschuh¹

Affiliations

¹ Department of Nuclear Medicine, University Hospital Bonn, 53127 Bonn, Germany.
² Department of Computer Science, University of Bonn, 53115 Bonn, Germany.
³ Department of Nuclear Medicine, Nuclear Medicine, Oncology and Radiotherapy Institute, 21061 Islamabad, Pakistan.
⁴ Bonn-Aachen International Center for Information Technology (B-IT), University of Bonn, 53115 Bonn, Germany.

Abstract

Gallium-68 prostate-specific membrane antigen positron emission tomography (⁶⁸Ga-PSMA-PET) is a highly sensitive method to detect prostate cancer (PC) metastases. Visual discrimination between malignant and physiologic/unspecific tracer accumulation by a nuclear medicine (NM) specialist is essential for image interpretation. In the future, automated machine learning (ML)-based tools will assist physicians in image analysis. The aim of this work was to develop a tool for analysis of ⁶⁸Ga-PSMA-PET images and to compare its efficacy to that of human readers. Five different ML methods were compared and tested on multiple positron emission tomography/computed tomography (PET/CT) data-sets. Forty textural features extracted from both PET- and low-dose CT data were analyzed. In total, 2419 hotspots from 72 patients were included. Comparing results from human readers to those of ML-based analyses, up to 98% area under the curve (AUC), 94% sensitivity (SE), and 89% specificity (SP) were achieved. Interestingly, textural features assessed in native low-dose CT increased the accuracy significantly. Thus, ML based on ⁶⁸Ga-PSMA-PET/CT radiomics features can classify hotspots with high precision, comparable to that of experienced NM physicians. Additionally, the superiority of multimodal ML-based analysis considering all PET and low-dose CT features was shown. Morphological features seemed to be of special additional importance even though they were extracted from native low-dose CTs.

Keywords: computed tomography (CT); machine learning (ML); positron emission tomography (PET); prostate cancer (PC); prostate-specific membrane antigen (PSMA).