Search

Purpose: Hydronephrosis is a common pediatric urological condition, characterized by dilation of the renal collecting system. Accurate identification of the severity of hydronephrosis is crucial in clinical management, as high-grade hydronephrosis can cause significant damage to the kidney. In this pilot study, we demonstrate the feasibility of machine learning in differentiating between high and low-grade hydronephrosis in pediatric patients. Materials and Methods: We retrospectively reviewed 592 images from 90 unique patients ages 0–8 years diagnosed with hydronephrosis at the University of Chicago’s Pediatric Urology Clinic. The study included 74 high-grade hydronephrosis (145 images) and 227 low-grade hydronephrosis (447 images). Patients were excluded if they had less than 2 studies prior to surgical intervention or had structural abnormalities. We developed a radiomic-based artificial intelligence algorithm incorporating computerized texture analysis and machine learning (support-vector machine) to yield a predictor of hydronephrosis grade. Results: Receiver operating characteristic analysis of the classifier output yielded an area under the curve value of 0.86 (95% CI 0.81–0.92) in the task of distinguishing between low and high-grade hydronephrosis using a five-fold cross-validation by kidney. In addition, a Mann–Kendall trend test between computer output and clinical hydronephrosis grade yielded a statistically significant upward trend (p

Abstract In addition to lung cancer, other thoracic abnormalities, such as emphysema, can be visualized within low-dose CT scans that were initially obtained in cancer screening programs, and thus, opportunistic evaluation of these diseases may be highly valuable. However, manual assessment for each scan is tedious and often subjective, thus we have developed an automatic, rapid computer-aided diagnosis system for emphysema using attention-based multiple instance deep learning and 865 LDCTs. In the task of determining if a CT scan presented with emphysema or not, our novel Transfer AMIL approach yielded an area under the ROC curve of 0.94 ± 0.04, which was a statistically significant improvement compared to other methods evaluated in our study following the Delong Test with correction for multiple comparisons. Further, from our novel attention weight curves, we found that the upper lung demonstrated a stronger influence in all scan classes, indicating that the model prioritized upper lobe information. Overall, our novel Transfer AMIL method yielded high performance and provided interpretable information by identifying slices that were most influential to the classification decision, thus demonstrating strong potential for clinical implementation.

In response to the unprecedented global healthcare crisis of the COVID-19 pandemic, the scientific community has joined forces to tackle the challenges and prepare for future pandemics. Multiple modalities of data have been investigated to understand the nature of COVID-19. In this paper, MIDRC investigators present an overview of the state-of-the-art development of multimodal machine learning for COVID-19 and model assessment considerations for future studies. We begin with a discussion of the lessons learned from radiogenomic studies for cancer diagnosis. We then summarize the multi-modality COVID-19 data investigated in the literature including symptoms and other clinical data, laboratory tests, imaging, pathology, physiology, and other omics data. Publicly available multimodal COVID-19 data provided by MIDRC and other sources are summarized. After an overview of machine learning developments using multimodal data for COVID-19, we present our perspectives on the future development of multimodal machine learning models for COVID-19.

Rationale and Objectives: Thyroid nodules are a common occurrence and up to 30% are indeterminate on Fine Needle Aspiration (FNA) biopsy. Use of machine learning (ML) algorithms as computer aids, i.e., computer-aided diagnosis (CADx), may provide accessible, accurate methods of diagnosing thyroid cancer on ultrasound (US) images of thyroid nodules. We conducted a systematic review to synthesize the current knowledge and potential of ML in assisting physicians in diagnosing indeterminate thyroid nodules. Materials and Methods: We searched PubMed for studies without a year constraint. Inclusion criteria were as follows: (1) publication of the study as a full-text manuscript in a peer-reviewed journal, (2) original work (e.g., not a review). Studies were excluded if they (1) did not perform FNA biopsy, (2) excluded all indeterminate lesions, (3) focused on a non-cancer thyroid pathology, (4) described only non-diagnostic uses of their model(s) (e.g. calcification quantification), or (5) did not use grayscale ultrasound. We used the Joanna Briggs Institute Appraisal Checklist for Diagnostic Test Accuracy Studies to synthesize and present quality data and PRISMA guidelines for reporting. Results: Our search yielded only 6 articles published between 2013 and 2022. All studies used either only fine-needle aspiration (FNA) biopsy or a combination of FNA and surgery as the reference standard. Of these, one study included only indeterminate nodules, while 5 studies included other nodules in categories as well. Results varied greatly and studies were inconsistent in which performance metrics they reported. Physician performances yielded areas under the ROC curve (AUC) ranging from 0.68 to 0.83, while ML models gave AUCs from 0.666 to 0.954. One study showed that their model had a greater AUC than physicians, while another study showed no difference in AUCs of their ML model and physicians. Another study demonstrated that their ML-assisted approach had a greater AUC (0.917) than either an American College of Radiology (ACR) Thyroid Imaging Reporting & Data System (TI-RADS)-only approach (AUC 0.68) or a ML only approach (AUC 0.77). One study measured the performance of ML models without physician comparison, with AUCs ranging from 0.85 to 0.90. One study found no difference between their ML model and molecular testing (AUC 0.88 and 0.81, respectively). Conclusion: The growing field of CADx and increasing availability of commercial models suggests an increasing interest toward utilization of ML-assisted diagnosis in the clinical setting. However, there is a significant lack of research on the role of ML the diagnosis of indeterminate thyroid nodules. Funding: The source of funding for this review was institutional funds from the University of Chicago.

BACKGROUND In human lupus nephritis (LN), tubulointerstitial inflammation (TII) on biopsy predicts progression to end-stage renal disease (ESRD). However, only about half of patients with moderate-to-severe TII develop ESRD. We hypothesized that this heterogeneity in outcome reflects different underlying inflammatory states. Therefore, we interrogated renal biopsies from LN longitudinal and cross-sectional cohorts.METHODS Data were acquired using conventional and highly multiplexed confocal microscopy. To accurately segment cells across whole biopsies, and to understand their spatial relationships, we developed computational pipelines by training and implementing several deep-learning models and other computer vision techniques.RESULTS High B cell densities were associated with protection from ESRD. In contrast, high densities of CD8+, γδ, and other CD4–CD8– T cells were associated with both acute renal failure and progression to ESRD. B cells were often organized into large periglomerular neighborhoods with Tfh cells, while CD4– T cells formed small neighborhoods in the tubulointerstitium, with frequency that predicted progression to ESRD.CONCLUSION These data reveal that specific in situ inflammatory states are associated with refractory and progressive renal disease.FUNDING This study was funded by the NIH Autoimmunity Centers of Excellence (AI082724), Department of Defense (LRI180083), Alliance for Lupus Research, and NIH awards (S10-OD025081, S10-RR021039, and P30-CA14599).

Abstract We demonstrate that structured illumination microscopy has the potential to enhance fluorescence lifetime imaging microscopy (FLIM) as an early detection method for oral squamous cell carcinoma. FLIM can be used to monitor or detect changes in the fluorescence lifetime of metabolic cofactors (e.g. NADH and FAD) associated with the onset of carcinogenesis. However, out of focus fluorescence often interferes with this lifetime measurement. Structured illumination fluorescence lifetime imaging (SI-FLIM) addresses this by providing depth-resolved lifetime measurements, and applied to oral mucosa, can localize the collected signal to the epithelium. In this study, the hamster model of oral carcinogenesis was used to evaluate SI-FLIM in premalignant and malignant oral mucosa. Cheek pouches were imaged in vivo and correlated to histopathological diagnoses. The potential of NADH fluorescence signal and lifetime, as measured by widefield FLIM and SI-FLIM, to differentiate dysplasia (pre-malignancy) from normal tissue was evaluated. ROC analysis was carried out with the task of discriminating between normal tissue and mild dysplasia, when changes in fluorescence characteristics are localized to the epithelium only. The results demonstrate that SI-FLIM (AUC = 0.83) is a significantly better (p-value = 0.031) marker for mild dysplasia when compared to widefield FLIM (AUC = 0.63).

Abstract Background As artificial intelligence methods for the diagnosis of disease advance, we aimed to evaluate machine learning in the predictive task of distinguishing between malignant and benign breast lesions on an independent clinical magnetic resonance imaging (MRI) dataset within a single institution for subsequent use as a computer aid for radiologists. Methods Computer analysis was conducted on consecutive dynamic contrast-enhanced MRI (DCE-MRI) studies from 1483 breast cancer and 496 benign patients who underwent MRI examinations between February 2015 and October 2017; with the age ranges of the cancer and benign patients being 19 to 77 and 16 to 76 years old, respectively. Cases were separated into a training dataset (years 2015 & 2016; 1444 cases) and an independent testing dataset (year 2017; 535 cases) based solely on MRI examination date. After radiologist indication of the lesion, the computer automatically segmented and extracted radiomic features, which were subsequently merged with a support-vector machine (SVM) to yield a lesion signature. Area under the receiving operating characteristic (ROC) curve (AUC) with 95% confidence intervals (CI) served as the primary figure of merit in the statistical evaluation for this clinical classification task. Results In the task of distinguishing malignant and benign breast lesions DCE-MRI, the trained predictive model yielded an AUC value of 0.89 (95% CI: 0.858, 0.922) on the independent image set. AUC values of 0.88 (95% CI: 0.845, 0.926) and 0.90 (95% CI: 0.837, 0.940) were obtained for mass lesions only and non-mass lesions only, respectively. Compared with actual clinical management decisions, the predictive model achieved 99.5% sensitivity with 9.6% fewer recommended biopsies. Conclusion On an independent, consecutive clinical dataset within a single institution, a trained machine learning system yielded promising performance in distinguishing between malignant and benign breast lesions.

Abstract Background Imaging techniques can provide information about the tumor non-invasively and have been shown to provide information about the underlying genetic makeup. Correlating image-based phenotypes (radiomics) with genomic analyses is an emerging area of research commonly referred to as “radiogenomics” or “imaging-genomics”. The purpose of this study was to assess the potential for using an automated, quantitative radiomics platform on magnetic resonance (MR) breast imaging for inferring underlying activity of clinically relevant gene pathways derived from RNA sequencing of invasive breast cancers prior to therapy. Methods We performed quantitative radiomic analysis on 47 invasive breast cancers based on dynamic contrast enhanced 3 Tesla MR images acquired before surgery and obtained gene expression data by performing total RNA sequencing on corresponding fresh frozen tissue samples. We used gene set enrichment analysis to identify significant associations between the 186 gene pathways and the 38 image-based features that have previously been validated. Results All radiomic size features were positively associated with multiple replication and proliferation pathways and were negatively associated with the apoptosis pathway. Gene pathways related to immune system regulation and extracellular signaling had the highest number of significant radiomic feature associations, with an average of 18.9 and 16 features per pathway, respectively. Tumors with upregulation of immune signaling pathways such as T-cell receptor signaling and chemokine signaling as well as extracellular signaling pathways such as cell adhesion molecule and cytokine-cytokine interactions were smaller, more spherical, and had a more heterogeneous texture upon contrast enhancement. Tumors with higher expression levels of JAK/STAT and VEGF pathways had more intratumor heterogeneity in image enhancement texture. Other pathways with robust associations to image-based features include metabolic and catabolic pathways. Conclusions We provide further evidence that MR imaging of breast tumors can infer underlying gene expression by using RNA sequencing. Size and shape features were appropriately correlated with proliferative and apoptotic pathways. Given the high number of radiomic feature associations with immune pathways, our results raise the possibility of using MR imaging to distinguish tumors that are more immunologically active, although further studies are necessary to confirm this observation.

Abstract Background The hypothesis of this study was that MRI-based radiomics has the ability to predict recurrence-free survival “early on” in breast cancer neoadjuvant chemotherapy. Methods A subset, based on availability, of the ACRIN 6657 dynamic contrast-enhanced MR images was used in which we analyzed images of all women imaged at pre-treatment baseline (141 women: 40 with a recurrence, 101 without) and all those imaged after completion of the first cycle of chemotherapy, i.e., at early treatment (143 women: 37 with a recurrence vs. 105 without). Our method was completely automated apart from manual localization of the approximate tumor center. The most enhancing tumor volume (METV) was automatically calculated for the pre-treatment and early treatment exams. Performance of METV in the task of predicting a recurrence was evaluated using ROC analysis. The association of recurrence-free survival with METV was assessed using a Cox regression model controlling for patient age, race, and hormone receptor status and evaluated by C-statistics. Kaplan-Meier analysis was used to estimate survival functions. Results The C-statistics for the association of METV with recurrence-free survival were 0.69 with 95% confidence interval of [0.58; 0.80] at pre-treatment and 0.72 [0.60; 0.84] at early treatment. The hazard ratios calculated from Kaplan-Meier curves were 2.28 [1.08; 4.61], 3.43 [1.83; 6.75], and 4.81 [2.16; 10.72] for the lowest quartile, median quartile, and upper quartile cut-points for METV at early treatment, respectively. Conclusion The performance of the automatically-calculated METV rivaled that of a semi-manual model described for the ACRIN 6657 study (published C-statistic 0.72 [0.60; 0.84]), which involved the same dataset but required semi-manual delineation of the functional tumor volume (FTV) and knowledge of the pre-surgical residual cancer burden.