Assessing deep learning reconstruction for faster prostate MRI: visual vs. diagnostic performance metrics.

OBJECTIVE: Deep learning (DL) MRI reconstruction enables fast scan acquisition with good visual quality, but the diagnostic impact is often not assessed because of large reader study requirements. This study used existing diagnostic DL to assess the diagnostic quality of reconstructed images. MATERIALS AND METHODS: A retrospective multisite study of 1535 patients assessed biparametric prostate MRI between 2016 and 2020. Likely clinically significant prostate cancer (csPCa) lesions (PI-RADS ≥ 4) were delineated by expert radiologists. T2-weighted scans were retrospectively undersampled, simulating accelerated protocols. DL reconstruction (DLRecon) and diagnostic DL detection (DLDetect) were developed. The effect on the partial area under (pAUC), the Free-Response Operating Characteristic (FROC) curve, and the structural similarity (SSIM) were compared as metrics for diagnostic and visual quality, respectively. DLDetect was validated with a reader concordance analysis. Statistical analysis included Wilcoxon, permutation, and Cohen's kappa tests for visual quality, diagnostic performance, and reader concordance. RESULTS: DLRecon improved visual quality at 4- and 8-fold (R4, R8) subsampling rates, with SSIM (range: -1 to 1) improved to 0.78 ± 0.02 (p < 0.001) and 0.67 ± 0.03 (p < 0.001) from 0.68 ± 0.03 and 0.51 ± 0.03, respectively. However, diagnostic performance at R4 showed a pAUC FROC of 1.33 (CI 1.28-1.39) for DL and 1.29 (CI 1.23-1.35) for naive reconstructions, both significantly lower than fully sampled pAUC of 1.58 (DL: p = 0.024, naïve: p = 0.02). Similar trends were noted for R8. CONCLUSION: DL reconstruction produces visually appealing images but may reduce diagnostic accuracy. Incorporating diagnostic AI into the assessment framework offers a clinically relevant metric essential for adopting reconstruction models into clinical practice. CLINICAL RELEVANCE STATEMENT: In clinical settings, caution is warranted when using DL reconstruction for MRI scans. While it recovered visual quality, it failed to match the prostate cancer detection rates observed in scans not subjected to acceleration and DL reconstruction.

Recent Developments in Speeding up Prostate MRI.

The increasing incidence of prostate cancer cases worldwide has led to a tremendous demand for multiparametric MRI (mpMRI). In order to relieve the pressure on healthcare, reducing mpMRI scan time is necessary. This review focuses on recent techniques proposed for faster mpMRI acquisition, specifically shortening T2W and DWI sequences while adhering to the PI-RADS (Prostate Imaging Reporting and Data System) guidelines. Speeding up techniques in the reviewed studies rely on more efficient sampling of data, ranging from the acquisition of fewer averages or b-values to adjustment of the pulse sequence. Novel acquisition methods based on undersampling techniques are often followed by suitable reconstruction methods typically incorporating synthetic priori information. These reconstruction methods often use artificial intelligence for various tasks such as denoising, artifact correction, improvement of image quality, and in the case of DWI, for the generation of synthetic high b-value images or apparent diffusion coefficient maps. Reduction of mpMRI scan time is possible, but it is crucial to maintain diagnostic quality, confirmed through radiological evaluation, to integrate the proposed methods into the standard mpMRI protocol. Additionally, before clinical integration, prospective studies are recommended to validate undersampling techniques to avoid potentially inaccurate results demonstrated by retrospective analysis. This review provides an overview of recently proposed techniques, discussing their implementation, advantages, disadvantages, and diagnostic performance according to PI-RADS guidelines compared to conventional methods. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 3.

What makes a good scientific presentation on artificial intelligence in medical imaging?

PURPOSE: Adequate communication of scientific findings is crucial to enhance knowledge transfer. This study aimed to determine the key features of a good scientific oral presentation on artificial intelligence (AI) in medical imaging. METHODS: A total of 26 oral presentations dealing with original research on AI studies in medical imaging at the 2023 RSNA annual meeting were included and systematically assessed by three observers. The presentation quality of the research question, inclusion criteria, reference standard, method, results, clinical impact, presentation clarity, presenter engagement, and the presentation's quality of knowledge transfer were assessed using five-point Likert scales. The number of slides, the average number of words per slide, the number of interactive slides, the number of figures, and the number of tables were also determined for each presentation. Mixed-effects ordinal regression was used to assess the association between the above-mentioned variables and the quality of knowledge transfer of the presentation. RESULTS: A significant positive association was found between the quality of the presentation of the research question and the presentation's quality of knowledge transfer (odds ratio [OR]: 2.5, P = 0.005). The average number of words per slide was significantly negatively associated with the presentation's quality of knowledge transfer (OR: 0.9, P < 0.001). No other significant associations were found. CONCLUSION: Researchers who orally present their scientific findings in the field of AI and medical imaging should pay attention to clearly communicating their research question and minimizing the number of words per slide to maximize the value of their presentation.

Using deep learning to optimize the prostate MRI protocol by assessing the diagnostic efficacy of MRI sequences.

PURPOSE: To explore diagnostic deep learning for optimizing the prostate MRI protocol by assessing the diagnostic efficacy of MRI sequences. METHOD: This retrospective study included 840 patients with a biparametric prostate MRI scan. The MRI protocol included a T2-weighted image, three DWI sequences (b50, b400, and b800 s/mm2), a calculated ADC map, and a calculated b1400 sequence. Two accelerated MRI protocols were simulated, using only two acquired b-values to calculate the ADC and b1400. Deep learning models were trained to detect prostate cancer lesions on accelerated and full protocols. The diagnostic performances of the protocols were compared on the patient-level with the area under the receiver operating characteristic (AUROC), using DeLong's test, and on the lesion-level with the partial area under the free response operating characteristic (pAUFROC), using a permutation test. Validation of the results was performed among expert radiologists. RESULTS: No significant differences in diagnostic performance were found between the accelerated protocols and the full bpMRI baseline. Omitting b800 reduced 53% DWI scan time, with a performance difference of + 0.01 AUROC (p = 0.20) and -0.03 pAUFROC (p = 0.45). Omitting b400 reduced 32% DWI scan time, with a performance difference of -0.01 AUROC (p = 0.65) and + 0.01 pAUFROC (p = 0.73). Multiple expert radiologists underlined the findings. CONCLUSIONS: This study shows that deep learning can assess the diagnostic efficacy of MRI sequences by comparing prostate MRI protocols on diagnostic accuracy. Omitting either the b400 or the b800 DWI sequence can optimize the prostate MRI protocol by reducing scan time without compromising diagnostic quality.

K2S Challenge: From Undersampled K-Space to Automatic Segmentation.

Magnetic Resonance Imaging (MRI) offers strong soft tissue contrast but suffers from long acquisition times and requires tedious annotation from radiologists. Traditionally, these challenges have been addressed separately with reconstruction and image analysis algorithms. To see if performance could be improved by treating both as end-to-end, we hosted the K2S challenge, in which challenge participants segmented knee bones and cartilage from 8× undersampled k-space. We curated the 300-patient K2S dataset of multicoil raw k-space and radiologist quality-checked segmentations. 87 teams registered for the challenge and there were 12 submissions, varying in methodologies from serial reconstruction and segmentation to end-to-end networks to another that eschewed a reconstruction algorithm altogether. Four teams produced strong submissions, with the winner having a weighted Dice Similarity Coefficient of 0.910 ± 0.021 across knee bones and cartilage. Interestingly, there was no correlation between reconstruction and segmentation metrics. Further analysis showed the top four submissions were suitable for downstream biomarker analysis, largely preserving cartilage thicknesses and key bone shape features with respect to ground truth. K2S thus showed the value in considering reconstruction and image analysis as end-to-end tasks, as this leaves room for optimization while more realistically reflecting the long-term use case of tools being developed by the MR community.

Comparative Performance of Deep Learning and Radiologists for the Diagnosis and Localization of Clinically Significant Prostate Cancer at MRI: A Systematic Review.

BACKGROUND: Deep learning (DL)-based models have demonstrated an ability to automatically diagnose clinically significant prostate cancer (PCa) on MRI scans and are regularly reported to approach expert performance. The aim of this work was to systematically review the literature comparing deep learning (DL) systems to radiologists in order to evaluate the comparative performance of current state-of-the-art deep learning models and radiologists. METHODS: This systematic review was conducted in accordance with the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Studies investigating DL models for diagnosing clinically significant (cs) PCa on MRI were included. The quality and risk of bias of each study were assessed using the checklist for AI in medical imaging (CLAIM) and QUADAS-2, respectively. Patient level and lesion-based diagnostic performance were separately evaluated by comparing the sensitivity achieved by DL and radiologists at an identical specificity and the false positives per patient, respectively. RESULTS: The final selection consisted of eight studies with a combined 7337 patients. The median study quality with CLAIM was 74.1% (IQR: 70.6-77.6). DL achieved an identical patient-level performance to the radiologists for PI-RADS ≥ 3 (both 97.7%, SD = 2.1%). DL had a lower sensitivity for PI-RADS ≥ 4 (84.2% vs. 88.8%, p = 0.43). The sensitivity of DL for lesion localization was also between 2% and 12.5% lower than that of the radiologists. CONCLUSIONS: DL models for the diagnosis of csPCa on MRI appear to approach the performance of experts but currently have a lower sensitivity compared to experienced radiologists. There is a need for studies with larger datasets and for validation on external data.