Lung nodule malignancy classification with associated pulmonary fibrosis using 3D attention-gated convolutional network with CT scans.

BACKGROUND: Chest Computed tomography (CT) scans detect lung nodules and assess pulmonary fibrosis. While pulmonary fibrosis indicates increased lung cancer risk, current clinical practice characterizes nodule risk of malignancy based on nodule size and smoking history; little consideration is given to the fibrotic microenvironment. PURPOSE: To evaluate the effect of incorporating fibrotic microenvironment into classifying malignancy of lung nodules in chest CT images using deep learning techniques. MATERIALS AND METHODS: We developed a visualizable 3D classification model trained with in-house CT dataset for the nodule malignancy classification task. Three slightly-modified datasets were created: (1) nodule alone (microenvironment removed); (2) nodule with surrounding lung microenvironment; and (3) nodule in microenvironment with semantic fibrosis metadata. For each of the models, tenfold cross-validation was performed. Results were evaluated using quantitative measures, such as accuracy, sensitivity, specificity, and area-under-curve (AUC), as well as qualitative assessments, such as attention maps and class activation maps (CAM). RESULTS: The classification model trained with nodule alone achieved 75.61% accuracy, 50.00% sensitivity, 88.46% specificity, and 0.78 AUC; the model trained with nodule and microenvironment achieved 79.03% accuracy, 65.46% sensitivity, 85.86% specificity, and 0.84 AUC. The model trained with additional semantic fibrosis metadata achieved 80.84% accuracy, 74.67% sensitivity, 84.95% specificity, and 0.89 AUC. Our visual evaluation of attention maps and CAM suggested that both the nodules and the microenvironment contributed to the task. CONCLUSION: The nodule malignancy classification performance was found to be improving with microenvironment data. Further improvement was found when incorporating semantic fibrosis information.

Comparison of lung cancer occurring in fibrotic versus non-fibrotic lung on chest CT.

PURPOSE: Evaluate the behavior of lung nodules occurring in areas of pulmonary fibrosis and compare them to pulmonary nodules occurring in the non-fibrotic lung parenchyma. METHODS: This retrospective review of chest CT scans and electronic medical records received expedited IRB approval and a waiver of informed consent. 4500 consecutive patients with a chest CT scan report containing the word fibrosis or a specific type of fibrosis were identified using the system M*Model Catalyst (Maplewood, Minnesota, U.S.). The largest nodule was measured in the longest dimension and re-evaluated, in the same way, on the follow-up exam if multiple time points were available. The nodule doubling time was calculated. If the patient developed cancer, the histologic diagnosis was documented. RESULTS: Six hundred and nine patients were found to have at least one pulmonary nodule on either the first or the second CT scan. 274 of the largest pulmonary nodules were in the fibrotic tissue and 335 were in the non-fibrotic lung parenchyma. Pathology proven cancer was more common in nodules occurring in areas of pulmonary fibrosis compared to nodules occurring in areas of non-fibrotic lung (34% vs 15%, p < 0.01). Adenocarcinoma was the most common cell type in both groups but more frequent in cancers occurring in non-fibrotic tissue. In the non-fibrotic lung, 1 of 126 (0.8%) of nodules measuring 1 to 6 mm were cancer. In contrast, 5 of 49 (10.2%) of nodules in fibrosis measuring 1 to 6 mm represented biopsy-proven cancer (p < 0.01). The doubling time for squamous cell cancer was shorter in the fibrotic lung compared to non-fibrotic lung, however, the difference was not statistically significant (p = 0.24). 15 incident lung nodules on second CT obtained ≤ 18 months after first CT scan was found in fibrotic lung and eight (53%) were diagnosed as cancer. CONCLUSIONS: Nodules occurring in fibrotic lung tissue are more likely to be cancer than nodules in the nonfibrotic lung. Incident pulmonary nodules in pulmonary fibrosis have a high likelihood of being cancer.

Generalizing Diffusion Tensor Imaging of the Physis and Metaphysis.

BACKGROUND: Current methods to predict height potential are inaccurate. Predicting height by using MRI of the physeal cartilage has shown promise but the applicability of this technique in different imaging setups has not been well-evaluated. PURPOSE: To assess variability in diffusion tensor imaging of the physis and metaphysis (DTI-P/M) of the distal femur between different scanners, imaging parameters, tractography software, and resolution. STUDY TYPE: Prospective. POPULATION/SUBJECTS: Eleven healthy subjects (five males and six females ages 10-16.94). FIELD STRENGTH/SEQUENCE: 3 T; DTI single shot echo planar sequences. ASSESSMENT: Physeal DTI tract measurements of the distal femur were compared between different scanners, imaging parameters, tractography settings, interpolation correction, and tractography software. STATISTICAL TESTS: Bland-Altman, Spearman correlation, linear regression, and Shapiro-Wilk tests. Threshold for statistical significance was set at P = 0.05. RESULTS: DTI tract values consistently showed low variability with different imaging and analysis settings. Vendor to vendor comparison exhibited strong correlation (ρ = 0.93) and small but significant bias (bias -5.76, limits of agreement [LOA] -24.31 to 12.78). Strong correlation and no significant difference were seen between technical replicates of the General Electric MRI scanner (ρ = 1, bias 0.17 [LOA -1.5 to 1.2], P = 0.42) and the Siemens MRI scanner (ρ = 0.89, bias = 0.56, P = 0.71). Different voxel sizes (1 × 1 × 2 mm3 vs. 2 × 2 × 3 mm3) did not significantly affect DTI values (bias = 1.4 [LOA -5.7 to 8.4], P = 0.35) but maintained a strong correlation (ρ = 0.82). Gap size (0 mm vs. 0.6 mm) significantly affects tract volume (bias = 1.8 [LOA -5.4 to 1.8]) but maintains a strong correlation (ρ = 0.93). Comparison of tractography algorithms generated significant differences in tract number, length, and volume while maintaining correlation (ρ = 0.86, 0.99, 0.93, respectively). Comparison of interobserver variability between different tractography software also revealed significant differences while maintaining high correlation (ρ = 0.85-0.98). DATA CONCLUSION: DTI of the pediatric physis cartilage shows high reproducibility between different imaging and analytic parameters. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 1.

Diagnostic Utility of Restriction Spectrum Imaging in Head and Neck Tumors: A Pilot Study.

OBJECTIVE: Imaging is crucial in the assessment of head and neck cancers for site, extension, and enlarged lymph nodes. Restriction spectrum imaging (RSI) is a new diffusion-weighted magnetic resonance imaging (MRI) technique that enhances the ability to differentiate aggressive cancer from low-grade or benign tumors and helps guide treatment and biopsy. Its contribution to imaging of brain and prostate tumors has been previously published. However, there are no prior studies using RSI sequence in head and neck tumors. The purpose of this study was to evaluate the feasibility of performing RSI in head and neck cancer. METHODS: An additional RSI sequence was added in the routine MRI neck protocol for 13 patients diagnosed with head and neck cancer between November 2018 and April 2019. Restriction spectrum imaging sequence was performed with b values of 0, 500, 1500, and 3000 s/mm 2 and 29 directions on 1.5T magnetic resonance scanners.Diffusion-weighted imaging (DWI) images and RSI images were compared according to their ability to detect the primary malignancy and possible metastatic lymph nodes. RESULTS: In 71% of the patients, RSI outperformed DWI in detecting the primary malignancy and possible metastatic lymph nodes, whereas in the remaining cases, the 2 were comparable. In 66% of the patients, RSI detected malignant lymph nodes that DWI/apparent diffusion coefficient failed to detect. CONCLUSIONS: This is the first study of RSI in head and neck imaging and showed its superiority over the conventional DWI sequence. Because of its ability to differentiate benign and malignant lymph nodes in some cases, the addition of RSI to routine head and neck MRI should be considered.

UTE T2* cartilage mapping in the hip: a pilot study assessing cartilage in patients with femoroacetabular impingement.

BACKGROUND: UTE T2* cartilage mapping use in patients undergoing femoroacetabular impingement (FAI) has been lacking but may allow the detection of early cartilage damage. PURPOSE: To assess the reproducibility of UTE T2* cartilage mapping and determine the difference in UTE T2* values between FAI and asymptomatic patients and to evaluate the correlation between UTE T2* values and patient-reported symptoms. MATERIAL AND METHODS: Prospective evaluation of both hips (7 FAI and 7 asymptomatic patients). Bilateral hip 3-T MRI scans with UTE T2* cartilage maps were acquired. A second MRI scan was acquired 1-9 months later. Cartilage was segmented into anterosuperior, superior, and posterosuperior regions. Assessment was made of UTE T2* reproducibility (ICC). Mean UTE T2* values in patients were compared (t-tests) and correlation was made with patient-reported outcomes (Spearman's). RESULTS: ICCs of mean UTE T2* were as follows: acetabular, 0.82 (95% CI=0.50-0.95); femoral, 0.76 (95% CI=0.35-0.92). Significant strong correlation was found between mean acetabular UTE T2* values and iHOT12 (ρ = -0.63) and moderate correlation with mHHS (ρ = -0.57). There was no difference in mean UTE T2* values between affected vs. non-affected FAI hips. FAI-affected hips had significantly higher values in acetabulum vs. asymptomatic patients (13.47 vs. 12.55 ms). There was no difference in mean femoral cartilage values between the FAI-affected hips vs. asymptomatic patients. The posterosuperior femoral region had a higher mean value in non-affected FAI hips vs. asymptomatic patients (12.60 vs. 11.53 ms). CONCLUSION: UTE T2* cartilage mapping had excellent reproducibility. Affected FAI hips had higher mean acetabular UTE T2* values than asymptomatic patients. Severity of patient-reported symptoms correlates with UTE T2* acetabular cartilage values.

Diffusion tensor imaging of the physis: the ABC's.

The physis, or growth plate, is the primary structure responsible for longitudinal growth of the long bones. Diffusion tensor imaging (DTI) is a technique that depicts the anisotropic motion of water molecules, or diffusion. When diffusion is limited by cellular membranes, information on tissue microstructure can be acquired. Tractography, the visual display of the direction and magnitude of water diffusion, provides qualitative visualization of complex cellular architecture as well as quantitative diffusion metrics that appear to indirectly reflect physeal activity. In the growing bones, DTI depicts the columns of cartilage and new bone in the physeal-metaphyseal complex. In this "How I do It", we will highlight the value of DTI as a clinical tool by presenting DTI tractography of the physeal-metaphyseal complex of children and adolescents during normal growth, illustrating variation in qualitative and quantitative tractography metrics with age and skeletal location. In addition, we will present tractography from patients with physeal dysfunction caused by growth hormone deficiency and physeal injury due to trauma, chemotherapy, and radiation therapy. Furthermore, we will delineate our process, or "DTI pipeline," from image acquisition to data interpretation.

Chronic convection-enhanced delivery of topotecan for patients with recurrent glioblastoma: a first-in-patient, single-centre, single-arm, phase 1b trial.

BACKGROUND: Topotecan is cytotoxic to glioma cells but is clinically ineffective because of drug delivery limitations. Systemic delivery is limited by toxicity and insufficient brain penetrance, and, to date, convection-enhanced delivery (CED) has been restricted to a single treatment of restricted duration. To address this problem, we engineered a subcutaneously implanted catheter-pump system capable of repeated, chronic (prolonged, pulsatile) CED of topotecan into the brain and tested its safety and biological effects in patients with recurrent glioblastoma. METHODS: We did a single-centre, open-label, single-arm, phase 1b clinical trial at Columbia University Irving Medical Center (New York, NY, USA). Eligible patients were at least 18 years of age with solitary, histologically confirmed recurrent glioblastoma showing radiographic progression after surgery, radiotherapy, and chemotherapy, and a Karnofsky Performance Status of at least 70. Five patients had catheters stereotactically implanted into the glioma-infiltrated peritumoural brain and connected to subcutaneously implanted pumps that infused 146 µM topotecan 200 µL/h for 48 h, followed by a 5-7-day washout period before the next infusion, with four total infusions. After the fourth infusion, the pump was removed and the tumour was resected. The primary endpoint of the study was safety of the treatment regimen as defined by presence of serious adverse events. Analyses were done in all treated patients. The trial is closed, and is registered with ClinicalTrials.gov, NCT03154996. FINDINGS: Between Jan 22, 2018, and July 8, 2019, chronic CED of topotecan was successfully completed safely in all five patients, and was well tolerated without substantial complications. The only grade 3 adverse event related to treatment was intraoperative supplemental motor area syndrome (one [20%] of five patients in the treatment group), and there were no grade 4 adverse events. Other serious adverse events were related to surgical resection and not the study treatment. Median follow-up was 12 months (IQR 10-17) from pump explant. Post-treatment tissue analysis showed that topotecan significantly reduced proliferating tumour cells in all five patients. INTERPRETATION: In this small patient cohort, we showed that chronic CED of topotecan is a potentially safe and active therapy for recurrent glioblastoma. Our analysis provided a unique tissue-based assessment of treatment response without the need for large patient numbers. This novel delivery of topotecan overcomes limitations in delivery and treatment response assessment for patients with glioblastoma and could be applicable for other anti-glioma drugs or other CNS diseases. Further studies are warranted to determine the effect of this drug delivery approach on clinical outcomes. FUNDING: US National Institutes of Health, The William Rhodes and Louise Tilzer Rhodes Center for Glioblastoma, the Michael Weiner Glioblastoma Research Into Treatment Fund, the Gary and Yael Fegel Foundation, and The Khatib Foundation.

High-resolution simulation of B0 field conditions in the human heart from segmented computed tomography images.

B0 inhomogeneity leads to imaging artifacts in cardiac magnetic resonance imaging (MRI), in particular dark band artifacts with steady-state free precession pulse sequences. The limited spatial resolution of MR-derived in vivo B0 maps and the lack of population data prevent systematic analysis of the problem at hand and the development of optimized B0 shim strategies. We used readily available clinical computed tomography (CT) images to simulate the B0 conditions in the human heart at high spatial resolution. Calculated B0 fields showed consistency with MRI-based B0 measurements. The B0 maps for both the simulations and in vivo measurements showed local field inhomogeneities in the vicinity of lung tips with dominant Z3 spherical harmonic terms in the field distribution. The presented simulation approach allows for the derivation of B0 field conditions at high spatial resolution from CT images and enables the development of subject- and population-specific B0 shim strategies for the human heart.

COVID-19 neuropathology at Columbia University Irving Medical Center/New York Presbyterian Hospital.

Many patients with SARS-CoV-2 infection develop neurological signs and symptoms; although, to date, little evidence exists that primary infection of the brain is a significant contributing factor. We present the clinical, neuropathological and molecular findings of 41 consecutive patients with SARS-CoV-2 infections who died and underwent autopsy in our medical centre. The mean age was 74 years (38-97 years), 27 patients (66%) were male and 34 (83%) were of Hispanic/Latinx ethnicity. Twenty-four patients (59%) were admitted to the intensive care unit. Hospital-associated complications were common, including eight patients (20%) with deep vein thrombosis/pulmonary embolism, seven (17%) with acute kidney injury requiring dialysis and 10 (24%) with positive blood cultures during admission. Eight (20%) patients died within 24 h of hospital admission, while 11 (27%) died more than 4 weeks after hospital admission. Neuropathological examination of 20-30 areas from each brain revealed hypoxic/ischaemic changes in all brains, both global and focal; large and small infarcts, many of which appeared haemorrhagic; and microglial activation with microglial nodules accompanied by neuronophagia, most prominently in the brainstem. We observed sparse T lymphocyte accumulation in either perivascular regions or in the brain parenchyma. Many brains contained atherosclerosis of large arteries and arteriolosclerosis, although none showed evidence of vasculitis. Eighteen patients (44%) exhibited pathologies of neurodegenerative diseases, which was not unexpected given the age range of our patients. We examined multiple fresh frozen and fixed tissues from 28 brains for the presence of viral RNA and protein, using quantitative reverse-transcriptase PCR, RNAscope® and immunocytochemistry with primers, probes and antibodies directed against the spike and nucleocapsid regions. The PCR analysis revealed low to very low, but detectable, viral RNA levels in the majority of brains, although they were far lower than those in the nasal epithelia. RNAscope® and immunocytochemistry failed to detect viral RNA or protein in brains. Our findings indicate that the levels of detectable virus in coronavirus disease 2019 brains are very low and do not correlate with the histopathological alterations. These findings suggest that microglial activation, microglial nodules and neuronophagia, observed in the majority of brains, do not result from direct viral infection of brain parenchyma, but more likely from systemic inflammation, perhaps with synergistic contribution from hypoxia/ischaemia. Further studies are needed to define whether these pathologies, if present in patients who survive coronavirus disease 2019, might contribute to chronic neurological problems.

An Analytic Method for Calculating Scanner-, Kilovoltage Peak-, and Patient Size-Specific Hounsfield Unit Scale Thresholds for Agatston Score.

OBJECTIVE: This study aimed to calculate scanner-, kilovoltage peak (kVp)-, and patient size-specific computed tomography (CT) number thresholds for determining Agatston score (AgSc). METHODS: The proposed method was validated using calcium measurements in an anthropomorphic phantom for 4 CT scanners made by 4 vendors. The derived mass concentration (γ) thresholds were used to calculate kVp- and patient size-specific CT number thresholds. Two models were applied to reduce intrascanner and interscanner AgSc variation, respectively. RESULTS: The mean error of the modeled CT numbers is 1.8% (0.1%-4.4%). Model 1 has comparable results to the published phantom calibration method for an average-size patient (error, 1.5%; 0.1%-5.1%). The size- and the kVp-dependent fitting of modeled results have R2 greater than 0.965. CONCLUSIONS: Our results show a potential to enable accurate determination of AgSc under diverse conditions (eg, reduced tube potential) and are more easily applicable to different patient sizes than the phantom calibration method.

Feasibility of ultrashort echo time (UTE) T2* cartilage mapping in the hip: a pilot study.

BACKGROUND: Ultrashort echo time (UTE) T2* is sensitive to molecular changes within the deep calcified layer of cartilage. Feasibility of its use in the hip needs to be established to determine suitability for clinical use. PURPOSE: To establish feasibility of UTE T2* cartilage mapping in the hip and determine if differences in regional values exist. MATERIAL AND METHODS: MRI scans with UTE T2* cartilage maps were prospectively acquired on eight hips. Hip cartilage was segmented into whole and deep layers in anterosuperior, superior, and posterosuperior regions. Quantitative UTE T2* maps were analyzed (independent one-way ANOVA) and reliability was calculated (ICC). RESULTS: UTE T2* mean values (anterosuperior, superior, posterosuperior): full femoral layer (19.55, 18.43, 16.84 ms) (P=0.004), full acetabular layer (19.37, 17.50, 16.73 ms) (P=0.013), deep femoral layer (18.68, 17.90, 15.74 ms) (P=0.010), and deep acetabular layer (17.81, 16.18, 15.31 ms) (P=0.007). Values were higher in anterosuperior compared to posterosuperior regions (mean difference; 95% confidence interval [CI]): full femur layer (2.71 ms; 95% CI 0.91-4.51: P=0.003), deep femur layer (2.94 ms; 95% CI 0.69-5.19; P=0.009), full acetabular layer (2.63 ms 95% CI 0.55-4.72; P=0.012), and deep acetabular layer (2.50 ms; 95% CI 0.69-4.30; P=0.006). Intra-reader (ICC 0.89-0.99) and inter-reader reliability (ICC 0.63-0.96) were good to excellent for the majority of cartilage layers. CONCLUSION: UTE T2* cartilage mapping was feasible in the hip with mean values in the range of 16.84-19.55 ms in the femur and 16.73-19.37 ms in the acetabulum. Significantly higher values were present in the anterosuperior region compared to the posterosuperior region.

Dosimetric assessment of patient dose calculation on a deep learning-based synthesized computed tomography image for adaptive radiotherapy.

PURPOSE: Dose computation using cone beam computed tomography (CBCT) images is inaccurate for the purpose of adaptive treatment planning. The main goal of this study is to assess the dosimetric accuracy of synthetic computed tomography (CT)-based calculation for adaptive planning in the upper abdominal region. We hypothesized that deep learning-based synthetically generated CT images will produce comparable results to a deformed CT (CTdef) in terms of dose calculation, while displaying a more accurate representation of the daily anatomy and therefore superior dosimetric accuracy. METHODS: We have implemented a cycle-consistent generative adversarial networks (CycleGANs) architecture to synthesize CT images from the daily acquired CBCT image with minimal error. CBCT and CT images from 17 liver stereotactic body radiation therapy (SBRT) patients were used to train, test, and validate the algorithm. RESULTS: The synthetically generated images showed increased signal-to-noise ratio, contrast resolution, and reduced root mean square error, mean absolute error, noise, and artifact severity. Superior edge matching, sharpness, and preservation of anatomical structures from the CBCT images were observed for the synthetic images when compared to the CTdef registration method. Three verification plans (CBCT, CTdef, and synthetic) were created from the original treatment plan and dose volume histogram (DVH) statistics were calculated. The synthetic-based calculation shows comparatively similar results to the CTdef-based calculation with a maximum mean deviation of 1.5%. CONCLUSIONS: Our findings show that CycleGANs can produce reliable synthetic images for the adaptive delivery framework. Dose calculations can be performed on synthetic images with minimal error. Additionally, enhanced image quality should translate into better daily alignment, increasing treatment delivery accuracy.

A Pilot Study on Feasibility of Ultrashort Echo Time T2* Cartilage Mapping in the Sacroiliac Joints.

PURPOSE: Assess feasibility of ultrashort echo time (UTE) T2* cartilage mapping in sacroiliac (SI) joints. METHODS: Prospective magnetic resonance imagings with UTE T2* cartilage maps obtained on 20 SI joints in 10 subjects. Each joint was segmented into thirds by 2 radiologists. The UTE T2* maps were analyzed; reliability and differences in UTE T2* values between radiologists were assessed. RESULTS: Mean UTE T2* value was 10.44 ± 0.60 ms. No difference between right/left SI joints (median, 10.52 vs 10.45 ms; P = 0.940), men/women (median, 10.34 vs. 10.57 ms; P = 0.174), or different anatomic regions (median range 10.55-10.69 ms; P = 0.805). Intraclass correlation coefficients were 0.94 to 0.99 (intraobserver) and 0.91 to 0.96 (interobserver). Mean bias ± standard deviation on Bland-Altman was -0.137 ± 0.196 ms (limits of agreement -0.521 and 0.247) without proportional bias (ß = 0.148, P = 0.534). CONCLUSIONS: The UTE T2* cartilage mapping in the SI joints is feasible with high reader reliability.

3D Isotropic Super-resolution Prostate MRI Using Generative Adversarial Networks and Unpaired Multiplane Slices.

We developed a deep learning-based super-resolution model for prostate MRI. 2D T2-weighted turbo spin echo (T2w-TSE) images are the core anatomical sequences in a multiparametric MRI (mpMRI) protocol. These images have coarse through-plane resolution, are non-isotropic, and have long acquisition times (approximately 10-15 min). The model we developed aims to preserve high-frequency details that are normally lost after 3D reconstruction. We propose a novel framework for generating isotropic volumes using generative adversarial networks (GAN) from anisotropic 2D T2w-TSE and single-shot fast spin echo (ssFSE) images. The CycleGAN model used in this study allows the unpaired dataset mapping to reconstruct super-resolution (SR) volumes. Fivefold cross-validation was performed. The improvements from patch-to-volume reconstruction (PVR) to SR are 80.17%, 63.77%, and 186% for perceptual index (PI), RMSE, and SSIM, respectively; the improvements from slice-to-volume reconstruction (SVR) to SR are 72.41%, 17.44%, and 7.5% for PI, RMSE, and SSIM, respectively. Five ssFSE cases were used to test for generalizability; the perceptual quality of SR images surpasses the in-plane ssFSE images by 37.5%, with 3.26% improvement in SSIM and a higher RMSE by 7.92%. SR images were quantitatively assessed with radiologist Likert scores. Our isotropic SR volumes are able to reproduce high-frequency detail, maintaining comparable image quality to in-plane TSE images in all planes without sacrificing perceptual accuracy. The SR reconstruction networks were also successfully applied to the ssFSE images, demonstrating that high-quality isotropic volume achieved from ultra-fast acquisition is feasible.

Deep semantic lung segmentation for tracking potential pulmonary perfusion biomarkers in chronic obstructive pulmonary disease (COPD): The multi-ethnic study of atherosclerosis COPD study.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is associated with high morbidity and mortality. Identification of imaging biomarkers for phenotyping is necessary for future treatment and therapy monitoring. However, translation of visual analytic pipelines into clinics or their use in large-scale studies is significantly slowed by time-consuming postprocessing steps. PURPOSE: To implement an automated tool chain for regional quantification of pulmonary microvascular blood flow in order to reduce analysis time and user variability. STUDY TYPE: Prospective. POPULATION: In all, 90 MRI scans of 63 patients, of which 31 had a COPD with a mean Global Initiative for Chronic Obstructive Lung Disease status of 1.9 ± 0.64 (µ ± σ). FIELD STRENGTH/SEQUENCE: 1.5T dynamic gadolinium-enhanced MRI measurement using 4D dynamic contrast material-enhanced (DCE) time-resolved angiography acquired in a single breath-hold in inspiration. [Correction added on August 20, 2019, after first online publication: The field strength in the preceding sentence was corrected.] ASSESSMENT: We built a 3D convolutional neural network for semantic segmentation using 29 manually segmented perfusion maps. All five lobes of the lung are denoted, including the middle lobe. Evaluation was performed on 61 independent cases from two sites of the Multi-Ethnic Study of Arteriosclerosis (MESA)-COPD study. We publish our implementation of a model-free deconvolution filter according to Sourbron et al for 4D DCE MRI scans as open source. STATISTICAL TEST: Cross-validation 29/61 (# training / # testing), intraclass correlation coefficient (ICC), Spearman ρ, Pearson r, Sørensen-Dice coefficient, and overlap. RESULTS: Segmentations and derived clinical parameters were processed in ~90 seconds per case on a Xeon E5-2637v4 workstation with Tesla P40 GPUs. Clinical parameters and predicted segmentations exhibit high concordance with the ground truth regarding median perfusion for all lobes with an ICC of 0.99 and a Sørensen-Dice coefficient of 93.4 ± 2.8 (µ ± σ). DATA CONCLUSION: We present a robust end-to-end pipeline that allows for the extraction of perfusion-based biomarkers for all lung lobes in 4D DCE MRI scans by combining model-free deconvolution with deep learning. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:571-579.

Radiomics of MRI for pretreatment prediction of pathologic complete response, tumor regression grade, and neoadjuvant rectal score in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiation: an international multicenter study.

OBJECTIVE: To investigate whether pretreatment MRI-based radiomics of locally advanced rectal cancer (LARC) and/or the surrounding mesorectal compartment (MC) can predict pathologic complete response (pCR), neoadjuvant rectal (NAR) score, and tumor regression grade (TRG). METHODS: One hundred thirty-two consecutive patients with LARC who underwent neoadjuvant chemoradiation and total mesorectal excision (TME) were retrospectively collected from 2 centers in the USA and Italy. The primary tumor and surrounding MC were segmented on the best available T2-weighted sequence (axial, coronal, or sagittal). Three thousand one hundred ninety radiomic features were extracted using a python package. The most salient radiomic features as well as MRI parameter and clinical-based features were selected using recursive feature elimination. A logistic regression classifier was built to distinguish between any 2 binned categories in the considered endpoints: pCR, NAR, and TRG. Repeated k-fold validation was performed and AUCs calculated. RESULTS: There were 24, 87, and 21 T4, T3, and T2 LARCs, respectively (median age 63 years, 32 to 86). For NAR and TRG, the best classification performance was obtained using both the tumor and MC segmentations. The AUCs for classifying NAR 0 versus 2, pCR, and TRG 0/1 versus 2/3 were 0.66 (95% CI, 0.60-0.71), 0.80 (95% CI, 0.74-0.85), and 0.80 (95% CI, 0.77-0.82), respectively. CONCLUSION: Radiomics of pretreatment MRIs can predict pCR, TRG, and NAR score in patients with LARC undergoing neoadjuvant treatment and TME with moderate accuracy despite extremely heterogenous image data. Both the tumor and MC contain important prognostic information. KEY POINTS: • Machine learning of rectal cancer on images from the pretreatment MRI can predict important patient outcomes with moderate accuracy. • The tumor and the tissue around it both contain important prognostic information.

The role of initial chest X-ray in triaging patients with suspected COVID-19 during the pandemic.

PURPOSE: The purpose of our research is to evaluate the usefulness of chest X-ray for triaging patients with suspected COVID-19 infection. METHODS: IRB approval was obtained to allow a retrospective review of adult patients who presented to the Emergency Department with a complaint of fever, cough, dyspnea or hypoxia and had a chest X-ray between 12 March 2020 and 26 March 2020. The initial chest X-ray was graded on a scale of 0-3 with grade 0 representing no alveolar opacities, grade 1: < 1/3 alveolar opacities of the lung, Grade 2: 1/3 to 2/3 lung with alveolar opacities and grade 3: > 2/3 alveolar opacities of the lung. Past medical history of diabetes and hypertension, initial oxygen saturation, COVID-19 testing results, intubation, and outcome were also collected. RESULTS: Four hundred ten patient chest X-rays were reviewed. Oxygen saturation and X-ray grade were both significantly associated with the length of stay in hospital, the hazard ratio (HR) of discharge was 1.05 (95% CI [1.01, 1.09], p = 0.017) and 0.61 (95% CI [0.51, 0.73], p < 0.001), respectively. In addition, oxygen saturation and X-ray grade were significant predictors of intubation (odds ratio (OR) of intubation is 0.88 (95% CI [0.81, 0.96], p = 0.004) and 3.69 (95% CI [2.25, 6.07], p < 0.001). CONCLUSIONS: Initial chest X-ray is a useful tool for triaging those subjects who might have poor outcomes with suspected COVID-19 infection and benefit most from hospitalization.

Convolutional Neural Network Using a Breast MRI Tumor Dataset Can Predict Oncotype Dx Recurrence Score.

BACKGROUND: Oncotype Dx is a validated genetic analysis that provides a recurrence score (RS) to quantitatively predict outcomes in patients who meet the criteria of estrogen receptor positive / human epidermal growth factor receptor-2 negative (ER+/HER2-)/node negative invasive breast carcinoma. Although effective, the test is invasive and expensive, which has motivated this investigation to determine the potential role of radiomics. HYPOTHESIS: We hypothesized that convolutional neural network (CNN) can be used to predict Oncotype Dx RS using an MRI dataset. STUDY TYPE: Institutional Review Board (IRB)-approved retrospective study from January 2010 to June 2016. POPULATION: In all, 134 patients with ER+/HER2- invasive ductal carcinoma who underwent both breast MRI and Oncotype Dx RS evaluation. Patients were classified into three groups: low risk (group 1, RS <18), intermediate risk (group 2, RS 18-30), and high risk (group 3, RS >30). FIELD STRENGTH/SEQUENCE: 1.5T and 3.0T. Breast MRI, T1 postcontrast. ASSESSMENT: Each breast tumor underwent 3D segmentation. In all, 1649 volumetric slices in 134 tumors (mean 12.3 slices/tumor) were evaluated. A CNN consisted of four convolutional layers and max-pooling layers. Dropout at 50% was applied to the second to last fully connected layer to prevent overfitting. Three-class prediction (group 1 vs. group 2 vs. group 3) and two-class prediction (group 1 vs. group 2/3) models were performed. STATISTICAL TESTS: A 5-fold crossvalidation test was performed using 80% training and 20% testing. Diagnostic accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) area under the curve (AUC) were evaluated. RESULTS: The CNN achieved an overall accuracy of 81% (95% confidence interval [CI] ± 4%) in three-class prediction with specificity 90% (95% CI ± 5%), sensitivity 60% (95% CI ± 6%), and the area under the ROC curve was 0.92 (SD, 0.01). The CNN achieved an overall accuracy of 84% (95% CI ± 5%) in two-class prediction with specificity 81% (95% CI ± 4%), sensitivity 87% (95% CI ± 5%), and the area under the ROC curve was 0.92 (SD, 0.01). DATA CONCLUSION: It is feasible for current deep CNN architecture to be trained to predict Oncotype DX RS. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:518-524.

Quantitative imaging biomarkers alliance (QIBA) recommendations for improved precision of DWI and DCE-MRI derived biomarkers in multicenter oncology trials.

Physiological properties of tumors can be measured both in vivo and noninvasively by diffusion-weighted imaging and dynamic contrast-enhanced magnetic resonance imaging. Although these techniques have been used for more than two decades to study tumor diffusion, perfusion, and/or permeability, the methods and studies on how to reduce measurement error and bias in the derived imaging metrics is still lacking in the literature. This is of paramount importance because the objective is to translate these quantitative imaging biomarkers (QIBs) into clinical trials, and ultimately in clinical practice. Standardization of the image acquisition using appropriate phantoms is the first step from a technical performance standpoint. The next step is to assess whether the imaging metrics have clinical value and meet the requirements for being a QIB as defined by the Radiological Society of North America's Quantitative Imaging Biomarkers Alliance (QIBA). The goal and mission of QIBA and the National Cancer Institute Quantitative Imaging Network (QIN) initiatives are to provide technical performance standards (QIBA profiles) and QIN tools for producing reliable QIBs for use in the clinical imaging community. Some of QIBA's development of quantitative diffusion-weighted imaging and dynamic contrast-enhanced QIB profiles has been hampered by the lack of literature for repeatability and reproducibility of the derived QIBs. The available research on this topic is scant and is not in sync with improvements or upgrades in MRI technology over the years. This review focuses on the need for QIBs in oncology applications and emphasizes the importance of the assessment of their reproducibility and repeatability. Level of Evidence: 5 Technical Efficacy Stage: 1 J. Magn. Reson. Imaging 2019;49:e101-e121.

Accuracy of Distinguishing Atypical Ductal Hyperplasia From Ductal Carcinoma In Situ With Convolutional Neural Network-Based Machine Learning Approach Using Mammographic Image Data.

OBJECTIVE. The purpose of this study was to test the hypothesis that convolutional neural networks can be used to predict which patients with pure atypical ductal hyperplasia (ADH) may be safely monitored rather than undergo surgery. MATERIALS AND METHODS. A total of 298 unique images from 149 patients were used for our convolutional neural network algorithm. A total of 134 images from 67 patients with ADH that had been diagnosed by stereotactic-guided biopsy of calcifications but had not been upgraded to ductal carcinoma in situ or invasive cancer at the time of surgical excision. A total of 164 images from 82 patients with mammographic calcifications indicated that ductal carcinoma in situ was the final diagnosis. Two standard mammographic magnification views of the calcifications (a craniocaudal view and a mediolateral or lateromedial view) were used for analysis. Calcifications were segmented using an open-source software platform and images were resized to fit a bounding box of 128 × 128 pixels. A topology with 15 hidden layers was used to implement the convolutional neural network. The network architecture contained five residual layers and dropout of 0.25 after each convolution. Patients were randomly separated into a training-and-validation set (80% of patients) and a test set (20% of patients). Code was implemented using open-source software on a workstation with an open-source operating system and a graphics card. RESULTS. The AUC value was 0.86 (95% CI, ± 0.03) for the test set. Aggregate sensitivity and specificity were 84.6% (95% CI, ± 4.0%) and 88.2% (95% CI, ± 3.0%), respectively. Diagnostic accuracy was 86.7% (95% CI, ± 2.9). CONCLUSION. It is feasible to apply convolutional neural networks to distinguish pure atypical ductal hyperplasia from ductal carcinoma in situ with the use of mammographic images. A larger dataset will likely result in further improvement of our prediction model.