Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Oct 29:63:816-821.
doi: 10.2340/1651-226X.2024.40475.

A pilot study of AI-assisted reading of prostate MRI in Organized Prostate Cancer Testing

Erik Thimansson  1 , Sophia Zackrisson  2 , Fredrik Jäderling  3 , Max Alterbeck  4 , Thomas Jiborn  5 , Anders Bjartell  4 , Jonas Wallström  6
Affiliations

A pilot study of AI-assisted reading of prostate MRI in Organized Prostate Cancer Testing

Erik Thimansson et al. Acta Oncol. .

Abstract

Objectives: To evaluate the feasibility of AI-assisted reading of prostate magnetic resonance imaging (MRI) in Organized Prostate cancer Testing (OPT).

Methods: Retrospective cohort study including 57 men with elevated prostate-specific antigen (PSA) levels ≥3 µg/L that performed bi-parametric MRI in OPT. The results of a CE-marked deep learning (DL) algorithm for prostate MRI lesion detection were compared with assessments performed by on-site radiologists and reference radiologists. Per patient PI-RADS (Prostate Imaging-Reporting and Data System)/Likert scores were cross-tabulated and compared with biopsy outcomes, if performed. Positive MRI was defined as PI-RADS/Likert ≥4. Reader variability was assessed with weighted kappa scores.

Results: The number of positive MRIs was 13 (23%), 8 (14%), and 29 (51%) for the local radiologists, expert consensus, and DL, respectively. Kappa scores were moderate for local radiologists versus expert consensus 0.55 (95% confidence interval [CI]: 0.37-0.74), slight for local radiologists versus DL 0.12 (95% CI: -0.07 to 0.32), and slight for expert consensus versus DL 0.17 (95% CI: -0.01 to 0.35). Out of 10 cases with biopsy proven prostate cancer with Gleason ≥3+4 the DL scored 7 as Likert ≥4.

Interpretation: The Dl-algorithm showed low agreement with both local and expert radiologists. Training and validation of DL-algorithms in specific screening cohorts is essential before introduction in organized testing.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Study cohort.
Figure 2
Figure 2
The Region Skåne OPT biopsy algorithm in force during the execution of the study.
Figure 3
Figure 3
56 yo man, PSA 3.1 µg/L, PSAD 0,10 µg/L/cm3. MRI lesion dorsal portion PZ midgland, characterized as PI-RADS 4 by radiologist. (a) DWI b1500, white arrow indicates lesion, grey arrow artefact from rectal gas. (b) ADC, arrow indicates lesion. (c) T2W tra, arrow indicates lesion. (d) heatmap with lesion segmentation from DL algorithm, the lesion was characterized as Likert 5/PI-RADS 5. (e) lesion localization in sector map by DL-algorithm and lesion volume.
See this image and copyright information in PMC

References

    1. Hugosson J, Månsson M, Wallström J, Axcrona U, Carlsson SV, Egevad L, et al. . Prostate cancer screening with PSA and MRI followed by targeted biopsy only. N Engl J Med. 2022;387:2126–37. 10.1056/NEJMoa2209454 - DOI - PMC - PubMed
    1. Winkel DJ, Tong A, Lou B, Kamen A, Comaniciu D, Disselhorst JA, et al. . A novel deep learning based computer-aided diagnosis system improves the accuracy and efficiency of radiologists in reading biparametric magnetic resonance images of the prostate: results of a multireader, multicase study. Invest Radiol. 2021;56:605–13. 10.1097/RLI.0000000000000780 - DOI - PubMed
    1. Turkbey B, Haider MA. Deep learning-based artificial intelligence applications in prostate MRI: brief summary. Br J Radiol. 2022;95:20210563. 10.1259/bjr.20210563 - DOI - PMC - PubMed
    1. Válek, V. Council recommendation of 9 December 2022 on strengthening prevention through early detection: a new EU approach on cancer screening. Off J Eur Union. C, 2022, 473..
    1. Alterbeck M, Järbur E, Thimansson E, Wallström J, Bengtsson J, Björk-Eriksson T, et al. . Designing and implementing a population-based organised prostate cancer testing programme. Eur Urol Focus. 2022;8(6):1568-74. 10.1016/j.euf.2022.06.008 - DOI - PubMed

Substances