Incidental detection of prostate cancer with computed tomography scans

Abstract

Prostate cancer (PCa) is the second most frequent type of cancer found in men worldwide, with around one in nine men being diagnosed with PCa within their lifetime. PCa often shows no symptoms in its early stages and its diagnosis techniques are either invasive, resource intensive, or has low efficacy, making widespread early detection onerous. Inspired by the recent success of deep convolutional neural networks (CNN) in computer aided detection (CADe), we propose a new CNN based framework for incidental detection of clinically significant prostate cancer (csPCa) in patients who had a CT scan of the abdomen/pelvis for other reasons. While CT is generally considered insufficient to diagnose PCa due to its inferior soft tissue characterisation, our evaluations on a relatively large dataset consisting of 139 clinically significant PCa patients and 432 controls show that the proposed deep neural network pipeline can detect csPCa patients at a level that is suitable for incidental detection. The proposed pipeline achieved an area under the receiver operating characteristic curve (ROC-AUC) of 0.88 (95% Confidence Interval: 0.86–0.90) at patient level csPCa detection on CT, significantly higher than the AUCs achieved by two radiologists (0.61 and 0.70) on the same task.

Artificial Intelligence for Clinical Diagnosis and Treatment of Prostate Cancer

“…The study was performed at RMIT University and by St Vincent’s Hospital Melbourne researchers. The AI system was developed by examining asymptomatic individuals with and without prostate cancer CT scans to identify the disease’s characteristics [ 99 ]. As per the early studies, CT scans are highly acceptable data points for diagnosing bone and joint disorders, but the radiologists had difficulties recognising prostate cancer in the CT scan images.…”

“…Dr Mark Page from St. Vincent’s hospital in Melbourne mentioned that this technology could allow healthcare workers to detect prostate cancer early. The patients with critical conditions that had CT scans might be tested for prostate cancer simultaneously, and its early identification by this technology could significantly improve their prognosis [ 99 ]. Here, the early diagnosis of prostate cancer is an essential factor for the patients.…”

Künstliche Intelligenz in der Urologie – Chancen und Möglichkeiten

“…Während die Computertomographie (CT) aufgrund ihrer eingeschränkten Weichteilcharakterisierung i. Allg. als unzureichend angesehen wird, haben Koreevaar et al [14] [17]. Präoperative MRT-Bilder der Prostata werden während der roboterassistierten Prostatektomie fusioniert und die vom Tumor betroffene Zone der Prostata in einem dreidimensionalen (3D-)Bild dem Operateur aktiv demonstriert.…”

“…als unzureichend angesehen wird, haben Koreevaar et al. [ 14 ] gezeigt, dass eine neue KI-basierte Software für die CT-grafische Diagnostik eines klinisch-signifikanten Prostatakarzinoms geeignet ist. Mit einer 88 %igen Genauigkeit des neuronalen Netzwerks belegt diese Studie, dass CT-Bilder genügend Informationen beinhalten, um klinisch signifikante Prostatakarzinome detektieren zu können [ 14 ].…”

Recent Advances in Prostate Cancer (PCa) Diagnostics

“…However, CT is sometimes used for nodal staging of PCa [48]. A recent study showed that CT, in conjunction with deep learning, has the potential to perform comparably to diagnostic pipelines based on MRI [49], suggesting enhancements in the diagnostic capability of CT are potentially forthcoming.…”