State of the art: radiomics and radiomics-related artificial intelligence on the road to clinical translation

Radiomics and artificial intelligence carry the promise of increased precision in oncologic imaging assessments due to the ability of harnessing thousands of occult digital imaging features embedded in conventional medical imaging data. While powerful, these technologies suffer from a number of sources of variability that currently impede clinical translation. In order to overcome this impediment, there is a need to control for these sources of variability through harmonization of imaging data acquisition across institutions, construction of standardized imaging protocols that maximize the acquisition of these features, harmonization of post-processing techniques, and big data resources to properly power studies for hypothesis testing. For this to be accomplished, it will be critical to have multidisciplinary and multi-institutional collaboration.

Concurrent IRF4 Rearrangements in a Patient with B Cell and T Cell Disorders

Introduction/Objective

IRF4 is a regulatory protein which required at several stages of B and T cell development and differentiation. Rearrangements of the IRF4 chromosomal region have been detected in various B and T cell neoplasms including a distinct entity in the WHO tumor classification for diffuse large B cell lymphoma (DLBCL) with IRF4 rearrangement and another for an IRF4 rearranged subtype of the CD30-positive T cell lymphoproliferative disorder, lymphomatoid papulosis (LyP).

Methods/Case Report

We present the case of a 52-year-old man with a past medical history of treated Hodgkin disease in remission who now presents with a DLBCL of the tonsil as well a cutaneous LyP, both of which demonstrate the IRF4 gene rearrangement. Immunohistochemical stains support the morphologic diagnoses and the rearrangement is detected in both cases using fluorescence in situ hybridization (FISH).

Results (if a Case Study enter NA)

NA.

Conclusion

The detection of IRF4 translocation in two separate cell lineages may result from one of a handful of possible explanations that we explore. First, a mutation in a multipotent hematopoietic progenitor cell may give rise to common lymphoid progenitors which pass the mutation on to subsequent B and T differentiated lymphocytes. Second, de novo mutations may be occurring in both B and T cell lines leading to the mature lesions. Finally, it may be possible that one of the two lesions is not truly positive for IRF4 rearrangement, but rather the background B cells in the skin or T cells in the tonsil are the cells positive for the aberration. This is a unique case of a B and T cell lesion in the same patient which both possess the same rare genetic rearrangement. The implications on our understanding of the genetic development of such lesions is significant and may subsequently impact diagnosis and therapy going forward.

A single-center retrospective cohort study of perioperative systemic chemotherapy in diffuse malignant peritoneal mesothelioma

Background

Diffuse malignant peritoneal mesothelioma (DMPM) is a rare variant of malignant mesothelioma, representing 10–15% of malignant mesothelioma cases. The preferred therapeutic approach is cytoreductive surgery (CRS) accompanied by hyperthermic intraperitoneal chemotherapy (HIPEC); the role of systemic chemotherapy is not well established. While some limited retrospective studies report worse outcomes with neoadjuvant chemotherapy, our institution has favored the use of neoadjuvant chemotherapy for symptom relief and surgical optimization. The aim of our study was to assess the outcomes of patients receiving neoadjuvant chemotherapy, compared to those receiving adjuvant or no perioperative chemotherapy.

Patients and methods

We conducted a single-center retrospective cohort study of treatment-naïve, non-papillary DMPM patients seen at our institution between 1/1/2009 and 9/1/2019. We explored the effect of type of systemic therapy on clinical outcomes and estimated median overall survival (mOS) using Kaplan-Meier curves. Hazard ratios (HR) calculated by Cox proportional hazard model were used to estimate effect of the exposures on overall survival.

Results

47 patients were identified with DMPM (median age at diagnosis 61.2 years, 76.6% epithelioid histology, 74.5% white race, 55.3% known asbestos exposure). CRS was performed in 53.2% of patients (25/47); 76.0% of surgical patients received HIPEC (19/25). The majority received systemic chemotherapy (37/47, 78.7%); among patients receiving both CRS and chemotherapy, neoadjuvant chemotherapy was more common than adjuvant chemotherapy (12 neoadjuvant, 8 adjuvant). Overall mOS was 84.1 months. Among neoadjuvant patients, 10/12 underwent surgery, and 2 were lost to follow-up; the majority (9/10) had clinically stable or improved disease during the pre-operative period. There were numerical more issues with chemotherapy with the adjuvant patients (4/8: 2 switches in platinum agent, 2 patients stopped therapy) than with the neoadjuvant patients (2/10: 1 switch in platinum agent, 1 delay due to peri-procedural symptoms). Neoadjuvant chemotherapy was not associated with worse mOS compared to adjuvant chemotherapy (mOS NR vs 95.1 mo, HR 0.89, 95% CI 0.18–4.5, p = 0.89).

Conclusions

When used preferentially, the use of neoadjuvant chemotherapy in DMPM patients was not associated with worse outcomes compared to adjuvant chemotherapy. It was well-tolerated and did not prevent surgical intervention.

CT Features of Lymphatic Plastic Bronchitis in Adults: Correlation with Multimodality Lymphatic Imaging

Purpose

To distinguish CT patterns of lymphatic and nonlymphatic causes of plastic bronchitis (PB) through comparison with lymphatic imaging.

Materials and Methods

In this retrospective study, chest CT images acquired prior to lymphatic workup were assessed in 44 patients with PB from January 2014 to August 2020. The location and extent of ground-glass opacity (GGO) was compared with symptoms and lymphatic imaging. Statistical analysis was performed using descriptive statistics, logistic regression, Pearson correlation coefficient, and unweighted κ coefficient for interobserver agreement. Sensitivity and specificity of GGO for lymphatic PB were calculated.

Results

Lymphatic imaging was performed in 44 patients (median age, 52 years ± 21 [IQR]; 23 women): 35 with lymphatic PB and nine with nonlymphatic PB. GGO was more frequently observed in patients with lymphatic PB than in those with nonlymphatic PB (91% [32 of 35] vs 33% [three of nine]; P < .001). Univariate logistic regression confirmed this result by showing that GGO was a significant predictor of lymphatic PB (odds ratio, 21 (95% CI: 3.8, 159.7). The model areas under the receiver operating characteristic curve (AUCs) of GGO unadjusted and adjusted for demographics were 0.79 and 0.86, respectively. The location of GGO correlated with lymphatic imaging and bronchoscopic findings. Overall sensitivity and specificity of GGO for lymphatic PB were 91% (32 of 35; 95% CI: 76, 98) and 67% (six of nine; 95% CI: 30, 93), respectively.

Conclusion

Patients with lymphatic PB predominantly had multifocal GGO with or without a "crazy paving" pattern; identification of GGO should prompt lymphatic workup in this frequently misdiagnosed condition.Keywords: Lymphography, Lymphatic, CT, Tracheobronchial Tree, Thorax© RSNA, 2022See also commentary by Kligerman and White in this issue.

InterCarb: A Community Effort to Improve Interlaboratory Standardization of the Carbonate Clumped Isotope Thermometer Using Carbonate Standards

Increased use and improved methodology of carbonate clumped isotope thermometry has greatly enhanced our ability to interrogate a suite of Earth-system processes. However, interlaboratory discrepancies in quantifying carbonate clumped isotope (Δ47) measurements persist, and their specific sources remain unclear. To address interlaboratory differences, we first provide consensus values from the clumped isotope community for four carbonate standards relative to heated and equilibrated gases with 1,819 individual analyses from 10 laboratories. Then we analyzed the four carbonate standards along with three additional standards, spanning a broad range of δ47 and Δ47 values, for a total of 5,329 analyses on 25 individual mass spectrometers from 22 different laboratories. Treating three of the materials as known standards and the other four as unknowns, we find that the use of carbonate reference materials is a robust method for standardization that yields interlaboratory discrepancies entirely consistent with intralaboratory analytical uncertainties. Carbonate reference materials, along with measurement and data processing practices described herein, provide the carbonate clumped isotope community with a robust approach to achieve interlaboratory agreement as we continue to use and improve this powerful geochemical tool. We propose that carbonate clumped isotope data normalized to the carbonate reference materials described in this publication should be reported as Δ47 (I-CDES) values for Intercarb-Carbon Dioxide Equilibrium Scale.

Abstract PO-035: Development of a robust radiomic biomarker of PDL1 expression and patient survival after first-line immunotherapy for non-small cell lung cancer

Pembrolizumab (PEMBRO), a PD1antagonist, is 1st-line therapy for non-small cell lung cancer (NSCLC) without actionable mutations. While up to 70% of PDL1 enriched NSCLC respond to PEMBRO, those that will fail therapy, with resulting worse overall survival, cannot be reliably predicted. We propose a novel radiomic biomarker which integrates with PDL1 expression data to enhance precision in therapy response prediction. NSCLC patients (n=98) treated with PEMBRO at our institution, either alone or in combination with chemotherapy, with available staging computed tomography (CT) imaging were retrospectively identified. 3D tumor CT volumes were labeled by thoracic radiologists using ITK-SNAP software and radiomic features were extracted from segmented tumor volumes using PyRadiomics (Py) (107 features) and the Cancer Imaging Phenomics Toolkit (CaPTk)(102 features). The impact of imaging acquisition heterogeneity was mitigated using a nested ComBat approach, sequentially parsing parameters as batch covariates to harmonize differences in radiomic features. Harmonization reduced the number of features (KS test p &lt; 0.05; Py: 41.67%, CaPTk: 22.4% feature reduction) significantly different by kernel resolution. Six principal components (PCs) capturing 85% of the variance from the retained robust radiomic features of each software package were extracted and combined into a prognostic model (number of predictors capped at six (deaths = 59) to avoid overfitting). The concordance index for overall survival prediction was computed using a 5-fold cross-validated (CV) Cox proportional hazards model (200 iterations). Results for the ComBat feature PCs model are (C-statistic, 95% CI): CaPTk (0.58, [0.52, 0.62]), Py (0.59, [0.53,0.63]) For patients with available PDL1 expression data (n=67, deaths= 40), we used three radiomic PCs to predict survival for tumors with ≥ 50% PDL1 expression. Results for ComBat feature PCs are (5-fold CV AUC results): CaPTk (0.68), Py (0.71). We also combined the three radiomic PCs with a binary variable indicating the presence of &gt;50% PDL1 expression into a model. The complete dataset was used to evaluate the models’ ability to separate patients above versus below the median prognostic score in a Kaplan Meier curve (for all cases, log-rank test p values &lt; 0.05). The five-fold cross-validated ComBat PCs model had the highest accuracy in the prediction of overall survival among all the tested models. The ComBat PCs model performance is ((5-fold cross-validated C-statistic, 95% CI): Captk (0.60, [0.51, 0.64]), Py model (0.61, [0.52,0.65])). We demonstrated that both toolkits capture similar information from the tumor imaging volume with comparable prediction modeling results. ComBat harmonizes differences in image acquisition parameters and allows the generation of a radiomic model leveraging heterogeneous imaging data typical of the standard of care CT. Combining radiomic feature analysis with tumor PDL1 expression improves NSCLC survival prediction for therapy with PEMBRO.

Citation Format: Apurva Singh, Hannah Horng, Joanna Weeks, Michelle Hershman, Leonid Roshkovan, Sharyn Katz, Despina Kontos. Development of a robust radiomic biomarker of PDL1 expression and patient survival after first-line immunotherapy for non-small cell lung cancer [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-035.

WITHDRAWN: Radiology Extenders: Impact on Throughput and Accuracy for Routine Chest Radiographs

This article has been withdrawn at the request of the author(s) and/or editor. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at https://www.elsevier.com/about/our-business/policies/article-withdrawal.

Preliminary Assessment of an Optical Flow Method (OFM) for Nonrigid Registration and Temporal Subtraction (TS) of Serial CT Examinations to Facilitate Evaluation of Interval Change in Metastatic Lung Nodules

RATIONALE AND OBJECTIVES

Accurate assessment of size change of lung nodules on chest computed tomography (CT) is important for diagnosis and response assessment. However, manual methods are time-consuming and error-prone. We therefore assessed whether an optical flow method (OFM) with temporal subtraction (TS) can facilitate detection and quantification of lung nodule change on serial CT datasets.

MATERIALS AND METHODS

Serial chest CT examinations were selected from 12 patients with multiple pulmonary metastases. Lung nodules were evaluated for change in size using: (1) OFM with TS and (2) reference standard visual and manual assessment. Average time required to assess interval change using both methods was recorded and compared. Concordance of agreement between OFM with TS and reference standard assessment for nodule change was examined.

RESULTS

285 solid pulmonary nodules were evaluated. The average time per nodule to assess interval change in nodule size by OFM with TS (mean 1.15 + 0.5 minutes) was significantly less (P = 0.02) than that the reference standard approach (mean 1.56 + 0.5 minutes). Agreement between OFM with TS and reference standard occurred for 63.2% of nodules overall (kappa = 0.50, standard error 0.35, P< 0.00001), and significantly increased with larger nodule size (kappa = 0.48 for nodules <5 mm; kappa = 0.94 for nodules >20 mm, P < 0.0001).

CONCLUSIONS

This preliminary study demonstrates the feasibility of an OFM with TS to assess for interval change in metastatic lung nodules on serial CT examinations with significantly improved reading speed and moderate agreement relative to reference standard assessment. Agreement improved with larger nodule size.

Posterior Intercostal Lymph Nodes Double Recurrence and Death Risk in Malignant Pleural Mesothelioma

BACKGROUND

Posterior intercostal lymph nodes, previously undescribed for cancer staging, are part of the lymphatic drainage of the pleural space. This study assessed the impact of posterior intercostal lymph nodes on survival in patients undergoing extended pleurectomy/decortication for malignant pleural mesothelioma.

METHODS

As part of the thoracic lymphadenectomy, posterior intercostal lymph nodes were accessed by incising the endothoracic fascia at the level of the rib heads. These nodes were systematically harvested in 56 consecutive patients undergoing extended pleurectomy decortication in a clinical trial. The impact of these nodes on progression-free (PFS) and overall survival (OS) was analyzed by multiple statistical methods.

RESULTS

Median PFS and OS were 11.6 and 25.5 months, respectively. In 6 of 56 patients (11%), posterior intercostal lymph nodes were the only positive nodes, and overall, 48.2% had posterior intercostal lymph node metastases. Patients with N2 disease had significantly poorer prognosis if the posterior intercostal lymph nodes were involved: PFS (7.3 vs 14.9 months, P = .002) and OS (14.4 vs 26.1 months, P = .028). In the multivariable models, after adjustment for nodal stage and other prognostic factors, intercostal nodes remained associated with a 2.5-fold elevated risk of progression (P < .001) and a 2.3-fold elevated risk of death (P < .001).

CONCLUSIONS

Metastases to posterior intercostal lymph nodes independently more than doubled the risk of progression and death and were the only site of nodal metastases in 11% of patients. These nodes warrant further investigation, including nonoperative techniques to identify and factor them into treatment decision making.