The association between clinical, sociodemographic, familial, and environmental factors and treatment resistance in schizophrenia: A machine-learning-based approach.

BACKGROUND: Prediction of treatment resistance in schizophrenia (TRS) would be helpful to reduce the duration of ineffective treatment and avoid delays in clozapine initiation. We applied machine learning to identify clinical, sociodemographic, familial, and environmental variables that are associated with TRS and could potentially predict TRS in the future. STUDY DESIGN: Baseline and follow-up data on trait(-like) variables from the Genetic Risk and Outcome of Psychosis (GROUP) study were used. For the main analysis, we selected patients with non-affective psychotic disorders who met TRS (n = 200) or antipsychotic-responsive criteria (n = 423) throughout the study. For a sensitivity analysis, we only selected patients who met TRS (n = 76) or antipsychotic-responsive criteria (n = 123) at follow-up but not at baseline. Random forest models were trained to predict TRS in both datasets. SHapley Additive exPlanation values were used to examine the variables' contributions to the prediction. STUDY RESULTS: Premorbid functioning, age at onset, and educational degree were most consistently associated with TRS across both analyses. Marital status, current household, intelligence quotient, number of moves, and family loading score for substance abuse also consistently contributed to the prediction of TRS in the main or sensitivity analysis. The diagnostic performance of our models was modest (area under the curve: 0.66-0.69). CONCLUSIONS: We demonstrate that various clinical, sociodemographic, familial, and environmental variables are associated with TRS. Our models only showed modest performance in predicting TRS. Prospective large multi-centre studies are needed to validate our findings and investigate whether the model's performance can be improved by adding data from different modalities.

Sensitivity of an AI method for [18F]FDG PET/CT outcome prediction of diffuse large B-cell lymphoma patients to image reconstruction protocols.

BACKGROUND: Convolutional neural networks (CNNs), applied to baseline [18F]-FDG PET/CT maximum intensity projections (MIPs), show potential for treatment outcome prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study is to investigate the robustness of CNN predictions to different image reconstruction protocols. Baseline [18F]FDG PET/CT scans were collected from 20 DLBCL patients. EARL1, EARL2 and high-resolution (HR) protocols were applied per scan, generating three images with different image qualities. Image-based transformation was applied by blurring EARL2 and HR images to generate EARL1 compliant images using a Gaussian filter of 5 and 7 mm, respectively. MIPs were generated for each of the reconstructions, before and after image transformation. An in-house developed CNN predicted the probability of tumor progression within 2 years for each MIP. The difference in probabilities per patient was then calculated between both EARL2 and HR with respect to EARL1 (delta probabilities or ΔP). We compared these to the probabilities obtained after aligning the data with ComBat using the difference in median and interquartile range (IQR). RESULTS: CNN probabilities were found to be sensitive to different reconstruction protocols (EARL2 ΔP: median = 0.09, interquartile range (IQR) = [0.06, 0.10] and HR ΔP: median = 0.1, IQR = [0.08, 0.16]). Moreover, higher resolution images (EARL2 and HR) led to higher probability values. After image-based and ComBat transformation, an improved agreement of CNN probabilities among reconstructions was found for all patients. This agreement was slightly better after image-based transformation (transformed EARL2 ΔP: median = 0.022, IQR = [0.01, 0.02] and transformed HR ΔP: median = 0.029, IQR = [0.01, 0.03]). CONCLUSION: Our CNN-based outcome predictions are affected by the applied reconstruction protocols, yet in a predictable manner. Image-based harmonization is a suitable approach to harmonize CNN predictions across image reconstruction protocols.

An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients.

Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmaxbulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (< 0.4, generally). These findings suggest that MIP-based CNNs are able to predict treatment outcome in DLBCL.

Explainable artificial intelligence (XAI) in radiology and nuclear medicine: a literature review.

Rational: Deep learning (DL) has demonstrated a remarkable performance in diagnostic imaging for various diseases and modalities and therefore has a high potential to be used as a clinical tool. However, current practice shows low deployment of these algorithms in clinical practice, because DL algorithms lack transparency and trust due to their underlying black-box mechanism. For successful employment, explainable artificial intelligence (XAI) could be introduced to close the gap between the medical professionals and the DL algorithms. In this literature review, XAI methods available for magnetic resonance (MR), computed tomography (CT), and positron emission tomography (PET) imaging are discussed and future suggestions are made. Methods: PubMed, Embase.com and Clarivate Analytics/Web of Science Core Collection were screened. Articles were considered eligible for inclusion if XAI was used (and well described) to describe the behavior of a DL model used in MR, CT and PET imaging. Results: A total of 75 articles were included of which 54 and 17 articles described post and ad hoc XAI methods, respectively, and 4 articles described both XAI methods. Major variations in performance is seen between the methods. Overall, post hoc XAI lacks the ability to provide class-discriminative and target-specific explanation. Ad hoc XAI seems to tackle this because of its intrinsic ability to explain. However, quality control of the XAI methods is rarely applied and therefore systematic comparison between the methods is difficult. Conclusion: There is currently no clear consensus on how XAI should be deployed in order to close the gap between medical professionals and DL algorithms for clinical implementation. We advocate for systematic technical and clinical quality assessment of XAI methods. Also, to ensure end-to-end unbiased and safe integration of XAI in clinical workflow, (anatomical) data minimization and quality control methods should be included.

3D Convolutional Neural Network-Based Denoising of Low-Count Whole-Body 18F-Fluorodeoxyglucose and 89Zr-Rituximab PET Scans.

Acquisition time and injected activity of 18F-fluorodeoxyglucose (18F-FDG) PET should ideally be reduced. However, this decreases the signal-to-noise ratio (SNR), which impairs the diagnostic value of these PET scans. In addition, 89Zr-antibody PET is known to have a low SNR. To improve the diagnostic value of these scans, a Convolutional Neural Network (CNN) denoising method is proposed. The aim of this study was therefore to develop CNNs to increase SNR for low-count 18F-FDG and 89Zr-antibody PET. Super-low-count, low-count and full-count 18F-FDG PET scans from 60 primary lung cancer patients and full-count 89Zr-rituximab PET scans from five patients with non-Hodgkin lymphoma were acquired. CNNs were built to capture the features and to denoise the PET scans. Additionally, Gaussian smoothing (GS) and Bilateral filtering (BF) were evaluated. The performance of the denoising approaches was assessed based on the tumour recovery coefficient (TRC), coefficient of variance (COV; level of noise), and a qualitative assessment by two nuclear medicine physicians. The CNNs had a higher TRC and comparable or lower COV to GS and BF and was also the preferred method of the two observers for both 18F-FDG and 89Zr-rituximab PET. The CNNs improved the SNR of low-count 18F-FDG and 89Zr-rituximab PET, with almost similar or better clinical performance than the full-count PET, respectively. Additionally, the CNNs showed better performance than GS and BF.

Non-invasive Standardised Uptake Value for Verification of the Use of Previously Validated Reference Region for [18F]Flortaucipir and [18F]Florbetapir Brain PET Studies.

PURPOSE: The simplified reference tissue model (SRTM) is commonly applied for the quantification of brain positron emission tomography (PET) studies, particularly because it avoids arterial cannulation. SRTM requires a validated reference region which is obtained by baseline-blocking or displacement studies. Once a reference region is validated, the use should be verified for each new subject. This verification normally requires volume of distribution (VT) of a reference region. However, performing dynamic scanning and arterial sampling is not always possible, specifically in elderly subjects and in advanced disease stages. The aim of this study was to investigate the use of non-invasive standardised uptake value (SUV) approaches, in comparison to VT, as a verification of the previously validated grey matter cerebellum reference region for [18F]flortaucipir and [18F]florbetapir PET imaging in Alzheimer's disease (AD) patients and controls. PROCEDURES: Dynamic 130-min [18F]flortaucipir PET scans obtained from nineteen subjects (10 AD patients) and 90-min [18F]florbetapir dynamic scans obtained from fourteen subjects (8 AD patients) were included. Regional VT's were estimated for both tracers and were considered the standard verification of the previously validated reference region. Non-invasive SUVs corrected for body weight (SUVBW), lean body mass (SUL), and body surface area (SUVBSA) were obtained by using later time intervals of the dynamic scans. Simulations were also performed to assess the effect of flow and specific binding (BPND) on the SUVs. RESULTS: A low SUV corresponded well with a low VT for both [18F]flortaucipir and [18F]florbetapir. Simulation confirmed that SUVs were only slightly affected by flow changes and that increases in SUV were predominantly determined by the presence of specific binding. CONCLUSIONS: In situations where dynamic scanning and arterial sampling is not possible, a low SUV(80-100 min) for [18F]flortaucipir and a low SUV(50-70 min) for [18F]florbetapir may be used as indication for absence of specific binding in the grey matter cerebellum reference region.

Machine learning-based analysis of [18F]DCFPyL PET radiomics for risk stratification in primary prostate cancer.

PURPOSE: Quantitative prostate-specific membrane antigen (PSMA) PET analysis may provide for non-invasive and objective risk stratification of primary prostate cancer (PCa) patients. We determined the ability of machine learning-based analysis of quantitative [18F]DCFPyL PET metrics to predict metastatic disease or high-risk pathological tumor features. METHODS: In a prospective cohort study, 76 patients with intermediate- to high-risk PCa scheduled for robot-assisted radical prostatectomy with extended pelvic lymph node dissection underwent pre-operative [18F]DCFPyL PET-CT. Primary tumors were delineated using 50-70% peak isocontour thresholds on images with and without partial-volume correction (PVC). Four hundred and eighty standardized radiomic features were extracted per tumor. Random forest models were trained to predict lymph node involvement (LNI), presence of any metastasis, Gleason score ≥ 8, and presence of extracapsular extension (ECE). For comparison, models were also trained using standard PET features (SUVs, volume, total PSMA uptake). Model performance was validated using 50 times repeated 5-fold cross-validation yielding the mean receiver-operator characteristic curve AUC. RESULTS: The radiomics-based machine learning models predicted LNI (AUC 0.86 ± 0.15, p < 0.01), nodal or distant metastasis (AUC 0.86 ± 0.14, p < 0.01), Gleason score (0.81 ± 0.16, p < 0.01), and ECE (0.76 ± 0.12, p < 0.01). The highest AUCs reached using standard PET metrics were lower than those of radiomics-based models. For LNI and metastasis prediction, PVC and a higher delineation threshold improved model stability. Machine learning pre-processing methods had a minor impact on model performance. CONCLUSION: Machine learning-based analysis of quantitative [18F]DCFPyL PET metrics can predict LNI and high-risk pathological tumor features in primary PCa patients. These findings indicate that PSMA expression detected on PET is related to both primary tumor histopathology and metastatic tendency. Multicenter external validation is needed to determine the benefits of using radiomics versus standard PET metrics in clinical practice.