Artificial Intelligence–Assisted Prostate Cancer Diagnosis on Transrectal Microultrasound—A Pilot Study for the DeepTRUS Model
Haney-Aubert, Caelán Max Kovacs, Balint Aubert, Ophelia Elise Marie Fattal, Wahid Mangold, Maurin Helen Thiele, Antonia Winter, Nektarios Kämpfert, Karina Wessendorf, Maximilian Philip Brochhausen, Christoph
Haney-Aubert, Caelán Max
Kovacs, Balint
Aubert, Ophelia Elise Marie
Fattal, Wahid
Mangold, Maurin Helen
Thiele, Antonia
Winter, Nektarios
Kämpfert, Karina
Wessendorf, Maximilian Philip
Brochhausen, Christoph
Author
Haney-Aubert, Caelán Max
Kovacs, Balint
Aubert, Ophelia Elise Marie
Fattal, Wahid
Mangold, Maurin Helen
Thiele, Antonia
Winter, Nektarios
Kämpfert, Karina
Wessendorf, Maximilian Philip
Brochhausen, Christoph
Reible, Bruno
Carlsson, Sigrid V
Michel, Maurice Stephan
Maier-Hein, Klaus
Kowalewski, Karl-Friedrich
Kovacs, Balint
Aubert, Ophelia Elise Marie
Fattal, Wahid
Mangold, Maurin Helen
Thiele, Antonia
Winter, Nektarios
Kämpfert, Karina
Wessendorf, Maximilian Philip
Brochhausen, Christoph
Reible, Bruno
Carlsson, Sigrid V
Michel, Maurice Stephan
Maier-Hein, Klaus
Kowalewski, Karl-Friedrich
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Purpose: Microultrasound might serve as a viable alternative to MRI for initial prostate cancer detection. This study developed a deep learning model to detect clinically significant prostate cancer (csPCa) on microultrasound and evaluated its impact on diagnostic performance among novice readers. Materials and Methods: One hundred microultrasound sweeps (50 csPCa, 50 benign) were used to train a deep learning model. Model performance was assessed using the area under the receiver operating characteristics curve (AUC) and Dice similarity coefficient (DSC). In an independent test set (25 csPCa, 25 benign), 5 novice readers each evaluated 2 unique sets of 10 sweeps before and after a structured microultrasound training. In both sessions, they first reviewed sweeps unaided and then with algorithm-generated heatmaps. Results: On the training set, DeepTRUS achieved an AUC of 0.687 (95% confidence interval 0.583-0.791) and a DSC of 0.30 (0.21-0.39). In the test set, reader AUC improved from 0.459 (0.294-0.624) to 0.556 (0.394-0.718) before training, and from 0.610 (0.452-0.767) to 0.782 (0.656-0.908) after training, with DeepTRUS assistance. Sensitivity increased from 60% to 72% pretraining and from 80% to 88% posttraining. The interaction between training and DeepTRUS assistance was significant ( P = .006). Conclusions: This pilot study demonstrates the feasibility of training deep learning models on microultrasound data and their potential to enhance diagnostic performance when combined with reader training. The findings provide proof of concept for artificial intelligence–assisted microultrasound interpretation and inform the design of larger validation studies.
Citation
C.M. Haney-Aubert, B. Kovacs, O.E.M. Aubert, W. Fattal, M.H. Mangold, A. Thiele , et al., "Artificial Intelligence–Assisted Prostate Cancer Diagnosis on Transrectal Microultrasound—A Pilot Study for the DeepTRUS Model," JU Open Plus, vol. 4, no. 4, https://doi.org/10.1097/ju9.0000000000000441.
Source
JU Open Plus
Conference
Keywords
32 Biomedical and Clinical Sciences, 3211 Oncology and Carcinogenesis
Subjects
Source
Publisher
Wolters Kluwer