Requisite role of dorsal raphé in contextual cocaine-memory reconsolidation

Memory reconsolidation is a process by which labile drug memories are restabilized in long-term memory stores, permitting their enduring control over drug-seeking behaviors. In the present study, we investigated the involvement of the dorsal raphé nuclei (DRN) in cocaine-memory reconsolidation. Sprague-Dawley rats (male, female) were trained to self-administer cocaine in a distinct environmental context to establish contextual drug memories. They then received extinction training in a different context. Next, the rats were re-exposed to the cocaine-predictive context for 15 min to reactivate their cocaine memories or remained in their home cages (no-reactivation control). Memory reactivation was sufficient to increase c-Fos expression, an index of neuronal activation, in the DRN, but not in the median raphé nuclei, during reconsolidation, compared to no reactivation. To determine whether DRN neuronal activity was necessary for cocaine-memory reconsolidation, rats received intra-DRN baclofen plus muscimol (BM; GABAB/A agonists) or vehicle microinfusions immediately after or 6 h after a memory reactivation session conducted with or without lever access. The effects of DRN functional inactivation on long-term memory strength, as indicated by the magnitude of context-induced cocaine seeking, were assessed 72 h later. Intra-DRN BM treatment immediately after memory reactivation with or without lever access attenuated subsequent context-induced cocaine-seeking behavior, independent of sex. Conversely, BM treatment in the adjacent periaqueductal gray (PAG) immediately after memory reactivation, or BM treatment in the DRN 6 h after memory reactivation, did not alter responding. Together, these findings indicate that the DRN plays a requisite role in maintaining cocaine-memory strength during reconsolidation.

Cortical surface analysis for focal cortical dysplasia diagnosis by using PET images

Focal cortical dysplasia (FCD) is a neurological disorder distinguished by faulty brain cell structure and development. Repetitive and uncontrollable seizures may be linked to FCD's aberrant cortical thickness, gyrification, and sulcal depth. Quantitative cortical surface analysis is a crucial alternative to ineffective visual inspection. This study recruited 42 subjects including 22 FCD patients who underwent surgery and 20 healthy controls (HC). For the FCD patients, T1-weighted and PET images were obtained by a PET-MRI scanner, and the confirmed epileptogenic zone (EZ) was collected from postsurgical follow-up. For the HCs, CT and PET images were obtained by a PET-CT scanner. Cortical thickness, gyrification index, and sulcal depth were calculated using a computational anatomical toolbox (CAT12). A cluster-based analysis is carried out to determine each FCD patient's aberrant cortical surface. After parcellating the cerebral cortex into 68 regions by the Desikan-Killiany atlas, a region of interest (ROI) analysis was conducted to know whether the feature in the FCD group is significantly different from that in the HC group. Finally, the features of all ROIs were utilised to train a support vector machine classifier (SVM). The classification performance is evaluated by the leave-one-out cross-validation. The cluster-based analysis can localize the EZ cluster with the highest accuracy of 54.5 % (12/22) for cortical thickness, 40.9 % (9/22) and 13.6 % (3/22) for sulcal depth and gyrification, respectively. Moderate concordance (Kappa, 0.6) is observed between the confirmed EZs and identified clusters by using the cortical thickness. Fair concordance (Kappa, 0.3) and no concordance (Kappa, 0.1) is found by using sulcal depth and gyrification. Significant differences are found in 46 of 68 regions (67.7 %) for the three measures. The trained SVM classifier achieved a prediction accuracy of 95.5 % for the cortical thickness, while the sulcal depth and the gyrification obtained 86.0 % and 81.5 %. Cortical thickness, as determined by quantitative cortical surface analysis of PET data, has a greater ability than sulcal depth and gyrification to locate aberrant EZ clusters in FCD. Surface measures might be different in many regions for FCD and HC. By integrating machine learning and cortical morphologies features, individual prediction of FCD seems to be feasible.

A hybrid few-shot multiple-instance learning model predicting the aggressiveness of lymphoma in PET/CT images

BACKGROUND AND OBJECTIVE

Patients with aggressive non-Hodgkin lymphoma (NHL) undergo distinct therapy strategies compared with indolent NHL patients. However, it is challenging to estimate NHL aggressiveness based on visual inspection of positron emission tomography (PET) or computed tomography (CT) images. Since diffuse large B-cell lymphoma (DLBCL) and Follicular lymphoma (FL) are the most typical and dominant aggressive and indolent NHL, respectively, this study aims to develop an artificial-intelligence-enabled model to distinguish DLBCL from FL in PET/CT images as the first step to tackle this challenge.

METHODS

We propose a hybrid few-shot multiple-instance learning model to predict the aggressiveness of the NHL. First, rotation-based self-supervision learning (SSL) has been employed to train the encoder on a large-scale, publicly available CT image dataset. Second, hybrid instance-level features are obtained for each NHL lesion by combining deep features with the radiomics features from both PET and CT modalities. Third, instance-level features are transformed into bag-level (or patient-level) representations. Finally, bag-level representations are fed into a distance-based classifier through few-shot learning to predict NHL aggressiveness.

RESULTS

Our model achieves an accuracy of 0.751 ± 0.008, a sensitivity of 0.787 ± 0.012, a specificity of 0.715 ± 0.013, an F1-score of 0.753 ± 0.009, and an area under the curve (AUC) of 0.795 ± 0.009 at the bag level. It outperforms the typical counterparts that use the radiomic features, random forest for feature selection, and support vector machines (SVMs) as classifiers. The three counterparts yield accuracies of 0.714 ± 0.023, 0.705 ± 0.008, and 0.698 ± 0.008, respectively. Moreover, settings of the SSL training dataset (Deep lesion) and task (rotation), hybrid CT and radiomic PET features, the pool-layer strategy of maximum, and distance-based classifier generate the best model.

CONCLUSIONS

A hybrid few-shot multiple-instance learning model can predict lymphoma aggressiveness in PET/CT images and could be a potential tool for determining therapy strategies. Hybrid features and the combination of SSL, few-shot learning, and weakly supervised learning are the two powerful pillars of the model, and these can be expanded to other medical applications with limited samples and incomplete annotations.

New insight in massive cerebral infarction predictions after anterior circulation occlusion

To predict massive cerebral infarction (MCI) occurrence after anterior circulation occlusion (ACO) by cASPECTS-CTA-CS (combined ASPECTS and CTA-CS). Of 185 cerebral infarction patients with the ACO, their collateral circulation scores from CT angiography (CTA) images in two groups (MCI and non-MCI) were evaluated using Alberta Stroke Program Early CT Score (ASPECTS) and CT angiography collateral score (CTA-CS) approaches. The cASPECTS-CTA-CS was validated internally using the bootstrap sampling method with 1000 bootstrap repetitions and compared to CTA-CS. Receiver-operating characteristic curve (ROC), clinical impact curve (CIC), and decision curve analysis (DCA) strategies were used to assess the clinical practicality and predictability of both approaches (cASPECTS-CTA-CS and CTA-CS). Using net reclassification improvement (NRI) and integrated discrimination improvement (IDI) analyses, discrimination levels of the cASPECTS-CTA-CS were compared with CTA-CS. Classification and regression tree (CART) analyses was conducted to identify the best predictive values and identify subgroup of MCI. The discrimination ability of collateral circulation evaluation score using the cASPECTS-CTA-CS [AUC: 0.918, 95% confidence interval (CI): 0.869-0.967, P < 0.01; NRI: 0.200, 95% CI: -0.104 to 0.505, P = 0.197; and IDI: 0.107, 95% CI: 0.035-0.178, P = 0.004] was better than CTA-CS alone (AUC: 0.885, 95% CI: 0.833-0.937, P < 0.01). DCA indicated the net benefits of the cASPECTS-CTA-CS approach was higher than CTA-CS alone when the threshold probability range over 20%. CIC analyses showed that the number of high risks and true positives were in agreement when the threshold probability > 80%. Less than 23 of cASPECTS-CTA-CS by CART was important factor in determining MCI occurrence, and ASPECTS < 7 was followed factor. The cASPECTS-CTA-CS approach cumulatively predicted MCI after ACO.

A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest

BACKGROUND

Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa, leading to more precise diagnosis and treatment. The purpose of this study is to present a radiomics-based method for determining the Gleason score (GS) for PCa using tumour heterogeneity on multiparametric MRI (mp-MRI).

METHODS

Twenty-six patients with biopsy-proven PCa were included in this study. The quantitative T2 values, apparent diffusion coefficient (ADC) and signal enhancement rates (α) were calculated using multi-echo T2 images, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), for the annotated region of interests (ROI). After texture feature analysis, ROI range expansion and feature filtering was performed. Then obtained data were put into support vector machine (SVM), K-Nearest Neighbor (KNN) and other classifiers for binary classification.

RESULTS

The highest classification accuracy was 73.96% for distinguishing between clinically significant (Gleason 3 + 4 and above) and non-significant cancers (Gleason 3 + 3) and 83.72% for distinguishing between Gleason 3 + 4 from Gleason 4 + 3 and above, which was achieved using initial ROIs drawn by the radiologists. The accuracy improved when using expanded ROIs to 80.67% using SVM and 88.42% using Bayesian classification for distinguishing between clinically significant and non-significant cancers and Gleason 3 + 4 from Gleason 4 + 3 and above, respectively.

CONCLUSIONS

Our results indicate the research significance and value of this study for determining the GS for prostate cancer using the expansion of the ROI region.

Depicting and predicting changes of lung after lobectomy for cancer by using CT images

Lobectomy is an effective and well-established therapy for localized lung cancer. This study aimed to assess the lung and lobe change after lobectomy and predict the postoperative lung volume. The study included 135 lung cancer patients from two hospitals who underwent lobectomy (32, right upper lobectomy (RUL); 31, right middle lobectomy (RML); 24, right lower lobectomy (RLL); 26, left upper lobectomy (LUL); 22, left lower lobectomy (LLL)). We initially employ a convolutional neural network model (nnU-Net) for automatically segmenting pulmonary lobes. Subsequently, we assess the volume, effective lung volume (ELV), and attenuation distribution for each lobe as well as the entire lung, before and after lobectomy. Ultimately, we formulate a machine learning model, incorporating linear regression (LR) and multi-layer perceptron (MLP) methods, to predict the postoperative lung volume. Due to the physiological compensation, the decreased TLV is about 10.73%, 8.12%, 13.46%, 11.47%, and 12.03% for the RUL, RML, RLL, LUL, and LLL, respectively. The attenuation distribution in each lobe changed little for all types of lobectomy. LR and MLP models achieved a mean absolute percentage error of 9.8% and 14.2%, respectively. Radiological findings and a predictive model of postoperative lung volume might help plan the lobectomy and improve the prognosis.

[Efficacy and safety of endovascular therapy after 24 h from ischemic stroke onset in patients with acute anterior circulation ischemic stroke]

Objective: To explore the effectiveness and safety of endovascular treatment (EVT) for patients with acute anterior circulation ischemic stroke with symptom onset exceeding 24 h. Methods: In this retrospective cohort study, data were extracted from patients who underwent endovascular treatment for acute anterior circulation ischemic stroke at the First Hospital of Jilin University from February 2019 to April 2022. A total of 569 patients were included, with a mean age of 63 (54-70) years. Among them, 398 (69.9%) were male. The patients were divided into two groups based on symptom onset time:>24 h group and≤24 h group. Propensity score matching (PSM) was used to match the patients in a 1︰1 ratio between the>24 h group and the≤24 h group. Logistic regression was used to evaluate the impact of symptom onset time on outcome events. Results: Before PSM, compared with≤24 h group, the>24 h group had a younger age [56 (48, 64) vs. 64 (55, 70), Z=-3. 60, P<0.001]; lower proportion of prior atrial fibrillation [1.8% (1/57) vs. 21.1% (108/512), χ2=12.39, P<0.001]; lower proportion of wake-up stroke [7.0% (4/57) vs. 27.7% (142/512), χ2=11.54, P<0.001]; lower baseline NIHSS score [11.0 (7.5, 14.0) vs. 13.0 (10.0, 16.0), Z=-3.22, P<0.001]; and a higher American Society of Interventional and Therapeutic Neuroradiology/Society of Interventional Radiology(ASITN/SIR) grading (P<0.001). After PSM, there were no significant differences in baseline characteristics between the two groups. There was no significant difference in the proportion of patients with a modified Rankin Scale (mRS) score≤2 at 90 days after surgery between the two groups (before matching: 42.0% vs. 40.4%, OR=0.745, 95%CI 0.407-1.362, P=0.339; after matching: 51.8% vs. 39.3%, OR=0.511, 95%CI 0.212-1.236, P=0.136). No significant differences were observed in the incidence of any safety outcomes between the>24 h group and the≤24 h group. Conclusion: For patients with acute anterior circulation ischemic stroke with symptom onset exceeding 24 h, EVT is feasible after strict radiological screening and has similar safety and effectiveness as for patients with symptom onset under 24 h.

Nomograms integrating CT radiomic and deep learning signatures to predict overall survival and progression-free survival in NSCLC patients treated with chemotherapy

OBJECTIVES

This study aims to establish nomograms to accurately predict the overall survival (OS) and progression-free survival (PFS) in patients with non-small cell lung cancer (NSCLC) who received chemotherapy alone as the first-line treatment.

MATERIALS AND METHODS

In a training cohort of 121 NSCLC patients, radiomic features were extracted, selected from intra- and peri-tumoral regions, and used to build signatures (S1 and S2) using a Cox regression model. Deep learning features were obtained from three convolutional neural networks and utilized to build signatures (S3, S4, and S5) that were stratified into over- and under-expression subgroups for survival risk using X-tile. After univariate and multivariate Cox regression analyses, a nomogram incorporating the tumor, node, and metastasis (TNM) stages, radiomic signature, and deep learning signature was established to predict OS and PFS, respectively. The performance was validated using an independent cohort (61 patients).

RESULTS

TNM stages, S2 and S3 were identified as the significant prognosis factors for both OS and PFS; S2 (OS: (HR (95%), 2.26 (1.40-3.67); PFS: (HR (95%), 2.23 (1.36-3.65)) demonstrated the best ability in discriminating patients with over- and under-expression. For the OS nomogram, the C-index (95% CI) was 0.74 (0.70-0.79) and 0.72 (0.67-0.78) in the training and validation cohorts, respectively; for the PFS nomogram, the C-index (95% CI) was 0.71 (0.68-0.81) and 0.72 (0.66-0.79). The calibration curves for the 3- and 5-year OS and PFS were in acceptable agreement between the predicted and observed survival. The established nomogram presented a higher overall net benefit than the TNM stage for predicting both OS and PFS.

CONCLUSION

By integrating the TNM stage, CT radiomic signature, and deep learning signatures, the established nomograms can predict the individual prognosis of NSCLC patients who received chemotherapy. The integrated nomogram has the potential to improve the individualized treatment and precise management of NSCLC patients.

Development and Validation of Clinical-Metabolic-Radiomics Model Based on Nomogram-Revised Risk Index for Prognosis Prediction in Patients with Extranodal Natural Kill/T Cell Lymphoma

PURPOSE/OBJECTIVE(S)

To identify clinical-metabolic-radiomics model using clinical data and 18F-FDG PET/CT image for predicting progression-free survival (PFS) of nasal-type extranodal natural killer/T cell lymphoma (ENKTCL) on the basis of the nomogram-revised risk index (NRI) model previously established and validated by our research group.

MATERIALS/METHODS

A total of 133 ENKTCL patients were prospectively included and randomly divided into a training cohort (n = 73) and a validation cohort (n = 50). 107 features and 7 commonly used metabolic parameters (SUVmax, MTV, TLG, SD, TLR, TAR and TBR) were extracted from baseline PET images of the patients. Least absolute shrinkage and selection operator (LASSO) following Cox regression were used to select optimal features and parameters. NRI-metabolic-radiomics model was developed and validated in the two cohorts and compared with NRI model and NRI-metabolic model.

RESULTS

TLG and 5 radiomics features were selected after LASSO and Cox regression. NRI-metabolic (NRI-TLG) model and NRI-metabolic-radiomics (NRI-TLG-RAD) model was developed based on NRI, TLG and selected 5 radiomics features. For PFS, NRI-TLG-RAD showed better PFS discrimination than NRI-TLG model and NRI model in both training cohort (C-index = 0.791, 0.743 and 0.690, respectively) and validation cohort (C-index = 0.785, 0.707, and 0.610 respectively). Moreover, NRI-TLG-RAD model and NRI-TLG model divided more patients into low-risk group (No. of patients: 66, 42 vs. 20) and very high-risk group (No. of patients: 25, 25 vs. 9), compared to preexisting NRI model.

CONCLUSION

The addition of metabolic and radiomics information improved the prognostic performance of preexisting NRI model greatly. Better prognostic discrimination and more reasonable patient division of the new NRI-TLG and NRI-TLG-RAD model may provide the basis for more precise treatment modality in the future.

Optimizing the Combination of Cytotoxic Drugs Along with Radiotherapy as Effective Treatment for Extranodal NK/T-Cell Lymphoma

PURPOSE/OBJECTIVE(S)

The optimal combination of cytotoxic drugs along with radiotherapy (RT) is unknown. We undertook multidrug screening process to identify the most efficacious cytotoxic drugs, and appraise the efficacy of various drug combinations.

MATERIALS/METHODS

We reviewed 3105 patients who received 40 chemotherapy regimens with different combinations of nine drug classes and/or RT. Least absolute shrinkage and selection operator (LASSO) and multivariable Cox regression analyses were used to screen efficacious single drugs and identify optimal combinations for overall survival (OS). Inverse probability of treatment weighting (IPTW) and multivariable analyses were used to compare survival between treatment regimens.

RESULTS

Screening and validation revealed RT, asparaginase (ASP), and gemcitabine (GEM) to be the most efficacious single modality/drugs. RT remained an important component of first-line treatment, whereas ASP was a fundamental drug of non-anthracycline (ANT)-based regimens. Addition of RT to non-ANT-based or ASP/GEM-based regimens, or addition of an ASP-drug into ANT-based or GEM/PLA-based regimens, improved 5-year OS significantly. Use of ASP/GEM-based regimens led to significantly higher 5-year OS (79.9%) compared with ASP/ANT-based (69.2%, P = 0.001), ASP/MTX-based (63.5%, P = 0.011), or ASP/NOS-based (63.2%, P<0.001) regimens. The survival benefit of ASP/GEM-based regimens over other ASP-based regimens was substantial across risk-stratified and advanced-stage subgroups. The survival benefits of a combination of RT, ASP, and GEM were consistent after adjustment for confounding factors by IPTW.

CONCLUSION

These results suggest that combining ASP/GEM with RT for ENKTCL is an efficacious and feasible therapeutic option, and provides a rationale and strategy for developing combination therapies.

Transformer-based 3D U-Net for pulmonary vessel segmentation and artery-vein separation from CT images

Transformer-based methods have led to the revolutionizing of multiple computer vision tasks. Inspired by this, we propose a transformer-based network with a channel-enhanced attention module to explore contextual and spatial information in non-contrast (NC) and contrast-enhanced (CE) computed tomography (CT) images for pulmonary vessel segmentation and artery-vein separation. Our proposed network employs a 3D contextual transformer module in the encoder and decoder part and a double attention module in skip connection to effectively finish high-quality vessel and artery-vein segmentation. Extensive experiments are conducted on the in-house dataset and the ISICDM2021 challenge dataset. The in-house dataset includes 56 NC CT scans with vessel annotations and the challenge dataset consists of 14 NC and 14 CE CT scans with vessel and artery-vein annotations. For vessel segmentation, Dice is 0.840 for CE CT and 0.867 for NC CT. For artery-vein separation, the proposed method achieves a Dice of 0.758 of CE images and 0.602 of NC images. Quantitative and qualitative results demonstrated that the proposed method achieved high accuracy for pulmonary vessel segmentation and artery-vein separation. It provides useful support for further research associated with the vascular system in CT images. The code is available at https://github.com/wuyanan513/Pulmonary-Vessel-Segmentation-and-Artery-vein-Separation .

MSA-YOLOv5: Multi-scale attention-based YOLOv5 for automatic detection of acute ischemic stroke from multi-modality MRI images

BACKGROUND AND OBJECTIVE

Acute ischemic stroke (AIS) is a common neurological disorder characterized by the sudden onset of cerebral ischemia, leading to functional impairments. Swift and precise detection of AIS lesions is crucial for stroke diagnosis and treatment but poses a significant challenge. This study aims to leverage multimodal fusion technology to combine complementary information from various modalities, thereby enhancing the detection performance of AIS target detection models.

METHODS

In this retrospective study of AIS, we collected data from 316 AIS patients and created a multi-modality magnetic resonance imaging (MRI) dataset. We propose a Multi-Scale Attention-based YOLOv5 (MSA-YOLOv5), targeting challenges such as small lesion size and blurred borders at low resolutions. Specifically, we augment YOLOv5 with a prediction head to detect objects at various scales. Next, we replace the original prediction head with a Multi-Scale Swin Transformer Prediction Head (MS-STPH), which reduces computational complexity to linear levels and enhances the ability to detect small lesions. We incorporate a Second-Order channel attention (SOCA) module to adaptively rescale channel features by employing second-order feature statistics for more discriminative representations. Finally, we further validate the effectiveness of our method using the ISLES 2022 dataset.

RESULTS

On our in-house AIS dataset, MSA-YOLOv5 achieves a 79.0% mAP0.5, substantially surpassing other single-stage models. Compared to two-stage models, it maintains a comparable performance level while significantly reducing the number of parameters and resolution. On the ISLES 2022 dataset, MSA-YOLOv5 attains an 80.0% mAP0.5, outperforming other network models by a considerable margin. MS-STPH and SOCA modules can significantly increase mAP0.5 by 2.7% and 1.9%, respectively. Visualization interpretability results show that the proposed MSA-YOLOv5 restricts high attention in the small regions of AIS lesions.

CONCLUSIONS

The proposed MSA-YOLOv5 is capable of automatically and effectively detecting acute ischemic stroke lesions in multimodal images, particularly for small lesions and artifacts. Our enhanced model reduces the number of parameters while improving detection accuracy. This model can potentially assist radiologists in providing more accurate diagnosis, and enable clinicians to develop better treatment plans.

Early Cardiotoxicity in Patients Receiving Hypofractionated Radiotherapy after Breast Conserving Surgery: Analysis of a Prospective Study

PURPOSE/OBJECTIVE(S)

To evaluate the early cardiotoxicity of hypofractionated radiotherapy (HFRT) in patients with left-sided breast cancer after breast-conserving surgery, and to investigate the correlation between cardiotoxicity and cardiac dose.

MATERIALS/METHODS

A total of 103 women from 2017 to 2018 who received left-sided whole-breast with or without regional nodal irradiation either using deep inspiration breath-hold (DIBH) or free-breathing (FB) technique were prospectively enrolled. N-terminal pro-B-type natriuretic peptide (NT-proBNP), electrocardiogram, and radionuclide myocardial perfusion imaging were conducted before and after HFRT. Logistic regression analyses were performed to determine the association of cancer treatment, cardiac dose, and cardiovascular risk factors with cardiotoxic effects.

RESULTS

The mean dose (Dmean) of the heart, left anterior descending coronary artery (LAD), left ventricular (LV), and right ventricular (RV) in all patients was 403 cGy, 1685 cGy, 627 cGy, and 444 cGy, respectively. In comparison to FB, DIBH significantly reduced cardiac dose (heart Dmean 250 cGy vs. 570 cGy, LAD Dmean 1250 cGy vs. 2170 cGy, LV Dmean 420 cGy vs. 850 cGy, RV Dmean 260 cGy vs. 650 cGy; all p<0.001). With a median follow-up of 49 months (range, 2-65 months), no patients had clinical cardiac abnormalities or cardiac-related symptoms, but 42 (41%) patients had subclinical cardiac events. Among them, 41 were electrocardiogram changes, and one had LV ejection fraction decreased by 10% compared with the baseline level. Twenty-five (60%) recovered during follow-up, of which 17 (40%) experienced subclinical changes only once. The mean value of NT-proBNP did not change significantly before and after HFRT. In univariate analyses, DIBH technique significantly decreased the risk of subclinical cardiac events compared with FB (OR 0.31, 95% CI 0.14-0.71; p = 0.006); however, higher mean doses of heart and LV, anthracycline-based chemotherapy, obesity, and hypertension were associated with increased risk of subclinical cardiac events (all p<0.05).

CONCLUSION

Early subclinical cardiac damage after HFRT in left-sided breast cancer is dose-related, and mostly manageable and reversible without medical intervention.

Adaptive Ultra-Hypofractionated Whole-Pelvic Radiotherapy in High-Risk and Very High-Risk Prostate Cancer on 1.5-1.5 MR Linac: The Estimated Delivered Dose and Early Toxicity Results

PURPOSE/OBJECTIVE(S)

To study the feasibility and safety for patients with high-risk (HR) and very high-risk (VHR) prostate cancer treated with adaptive ultra-hypofractionated whole-pelvic radiotherapy (UHF-WPRT) on 1.5 magnetic resonance (MR)-Linac.

MATERIALS/METHODS

Sevenpatients with clinical stage T3a-4N0-1M0-1c consecutively treated with UHF-WPRT on a 1.5-T MR-Linac were recruited prospectively in a phase II trial (NCT05183074, ChiCTR2000033382). A 36.25 Gy dose in five fractions was delivered every other day with a boost of 40 Gy to the whole prostate, as well as 25 Gy to whole pelvic nodal area with a concomitant boost of 35 Gy to metastatic regional nodes. To estimate the delivered dose, we collected data by 3D-MR for the following stages: pre-MR, position verification-MR (PV-MR) in the Adapt-To-Shape (ATS) workflow, and 3D-MR during the beam-on phase (Bn-MR) and at the end of RT (post-MR). The target and organ-at-risk contours in the PV-MR, Bn-MR, and post-MR stages were projected from the pre-MR data by deformable image registration and manually adapted by the physician, followed by dose recalculation for the ATS plan. The cumulative acute genitourinary (GU) and gastrointestinal (GI) toxicities were evaluated as per NCI-CTCAE 5.0 criteria. The primary endpoints were acute ≥grade 3 genitourinary (GU) and gastrointestinal (GI) toxicities during the first 3 months.

RESULTS

Overall, 133 MR scans were collected (35 pre-MR, 35 PV-MR, 31 Bn-MR and 32 post-MR scans). With a median on-couch time of 61 minutes, the mean prostate and pelvic planning target volume (PTV)-V95% of all scans was 96.98 ± 3.06% and 96.44 ± 2.85%, respectively. The corresponding mean prostate clinical target volume (CTV)-V100% was 99.89 ± 0.32%, 98.71 ± 1.90%, 97.77 ± 2.89%, and 98.56 ± 1.72%, and the mean pelvic CTV-V100% was 97.57% ± 3.70%, 96.54 ± 3.80%, 95.43 ± 4.31%, and 94.39 ± 4.47% on pre-MR, PV-MR, Bn-MR and post-MR scans, respectively. For the 4 patients with positive nodes, the mean V100% of metastatic regional nodes was 99.89 ± 0.81%. The median V29 Gy change in the rectal wall was -1% (-18%-20%). The V29 Gy of the rectal wall increased by >15% was observed in one scan. A slight increase in the high dose of bladder wall was noted due to gradual bladder growth during the workflow. With median follow-up time of 7.3 (4.6-12.2) months, all patients were followed-up for more than 3 months. No patient was observed with acute CTCAE grade 2 or more severe GU or GI toxicities (0%).

CONCLUSION

UHF-RT to prostate and pelvic with ATS workflow is well tolerated by patients with HR and VHR prostate cancer, with only mild GU and GI toxicities. The 3D-MR-based dosimetry analysis demonstrated clinically acceptable estimated dose coverage of target volumes during the beam-on period.

Engaging Ambulatory Cancer Patients to Develop and Validate a Comprehensive New Patient-Reported Outcomes Measure

PURPOSE/OBJECTIVE(S)

The ambulatory cancer program in Alberta, Canada routinely collects Patient-Reported Outcomes (PROs) using a common symptom rating measure, the Edmonton Symptom Assessment System-Revised (ESAS-r). The purpose of this study was to redesign, test, and validate a modified ESAS-r (the ESAS-r Cancer) for use in the province's new clinical information system and online patient portal.

MATERIALS/METHODS

Patient advisors participated in regular meetings to redesign the measure, creating expanded definitions for the original symptoms and new symptoms, added based on trends identified in our historical PRO data. To test the modified measure, patient advisors first completed the measure online to test the feasibility of remote electronic completion. Next, the advisors participated in cognitive interviews to discuss and finalize the wording of each symptom definition for clarity. To test the validity and reliability of the finalized measure, 1600 randomly sampled patients were mailed paper copies of the ESAS-r Cancer, ESAS-r, and a validated PRO measure called the Memorial System Assessment Scale-Short Form (MSAS-SF), which is often used with cancer patients. Canonical Correlation Analysis and exploratory factor analyses were performed to assess concurrent and construct validity of the ESAS-r Cancer against ESAS-r, using MSAS-SF as the gold standard. Cronbach's α was calculated to assess reliability.

RESULTS

The nine original ESAS-r symptoms were retained and six new symptoms were added to create the ESAS-r Cancer. All but one of the 26 patient advisors (96.2%) who completed the online measure did so without assistance. After two rounds of cognitive interviews all symptom definitions were finalized and deemed clear by almost all advisors. 461 patients (29% response rate) completed all three questionnaires. Using MSAS-SF as the gold standard, ESAS-r Cancer showed stronger canonical correlation than ESAS-r, indicating higher concurrent validity and fitting degree. ESAS-r Cancer also accounted for more information included on MSAS-SF than did ESAS-r, explaining more variance (75.2% vs. 73.5%). As revealed by factor analysis, the three-dimensional factor structure of ESAS-r Cancer outperformed the two-dimensional factor structure of ESAS-r, by allowing for new constructs within measurement. The reliability of ESAS-r Cancer was verified (Cronbach's α = .903, > threshold of 0.8) and slightly higher than ESAS-r (Cronbach's α = .884).

CONCLUSION

ESAS-r Cancer is now in use with patients throughout Alberta's cancer program. The redesign, testing, and validation process involved patient engagement throughout. Patient testing and perspectives were critical as ESAS-r Cancer is intended for use with ambulatory cancer patients. ESAS-r Cancer can help ensure patients are included in care decisions and that their perspectives are involved in guiding care.

Association of Overall Survival Benefit Profile of Radiotherapy with Progression-Free Survival after Chemotherapy for Diffuse Large B-Cell Lymphoma

PURPOSE/OBJECTIVE(S)

Benefit of radiotherapy (RT) after chemotherapy (CT) of diffuse large B-cell lymphoma (DLBCL) remains controversial. It is unknown whether improved progression-free survival (PFS) by RT translate into an overall survival (OS) benefit. To address this question, our research comprehensively evaluated the risk-benefit assessment of RT in DLBCL through an in-depth examination of previously reported data from randomized controlled trials (RCTs) and retrospective comparative studies.

MATERIALS/METHODS

After screening and quality control, this study included 7 randomized controlled trials and 52 retrospective studies of combined-modality therapy (CMT) versus CT alone. The correlation between PFS and OS was evaluated using the Pearson linear correlation coefficient at trial- and study arm-level. A risk-benefit assessment to describe the OS benefit of RT was performed in meta-analyses of pooled HROS with PFS patterns.

RESULTS

In RCTs, strong correlations were found between HRPFS and HROS at trial-level (r = 0.876), and PFS and OS at treatment arm-level, regardless of treatments (r = 0.945-0.964 for all, CMT or CT). In retrospective studies, similar correlations between HRPFS and HROS (r = 0.639-0.650), and PFS and OS rates (r = 0.882-0.910) were observed, independent of treatments or rituximab. Adding RT into rituximab-based CT increased the average PFS rate from 63.6 ± 18.9% to 81.5 ± 10.6% (P<0.001), with differential OS benefits of RT between studies. Patients can be stratified into four PFS patterns (>80%, >60-80%, >40-60%, and ≤40%); absolute gain in OS from RT ranged from ≤5% at PFS >80% to ∼21% at PFS ≤40%, with pooled-HROS from 0.70 (95% CI, 0.51-0.97) to 0.48 (95% CI, 0.36-0.63) after rituximab-based CT. Linear analysis revealed an OS advantage of CMT over CT alone in a PFS-dependent manner.

CONCLUSION

We demonstrate a varied OS benefit profile of RT upon different PFS patterns, and provide valuable evidence for making treatment decisions and designing clinical trials. Future strategies to select the use of RT will need careful tailoring in clinical practice or within RCT to optimize outcome.

Lymphocyte Count Kinetics and the Effect of Different Radiotherapy Techniques on Radiation-Induced Lymphopenia in Patients with Breast Cancer Receiving Hypofractionated Postmastectomy Radiotherapy

PURPOSE/OBJECTIVE(S)

Radiation-induced lymphopenia (RIL) is associated with poor prognosis in solid tumors. This study aimed to describe the lymphocyte kinetics in patients with breast cancer receiving hypofractionated postmastectomy radiotherapy (RT) and to investigate the association of different RT techniques with RIL.

MATERIALS/METHODS

We assessed 607 patients who received hypofractionated postmastectomy RT for breast cancer in our prospective clinical database from 8 hospitals. All patients received irradiation to the chest wall and supraclavicular fossa. RT techniques included integrated RT with the photon-based intensity modulated techniques to irradiate all target volumes (integrated RT) and a hybrid approach combining photon irradiation to supraclavicular nodes and electron irradiation to the chest wall (hybrid RT). Peripheral lymphocyte counts (PLC) were tested prior to RT (baseline), weekly during RT, at 1, 2 weeks, 3, 6 months after RT, and then every 6 months. Grade 3+ RIL was defined as PLC nadir during RT of <0.5 ×103/ml. Mean PLC was compared by the t test. Univariate, multivariate, and propensity score matching (PSM) analyses were used to evaluate the effect of different RT techniques on grade 3+ RIL.

RESULTS

During RT, 121 (19.9%) of patients had grade 3+ RIL. The PLC started to recover at 1 week and reached baseline levels 1 year after RT. A greater proportion of the patients treated with the integrated RT (90/269, 33.5%) developed grade 3+ PLC compared with those receiving hybrid RT (31/338, 9.2%, P < 0.001). After conducting PSM, multivariate analyses showed lower baseline PLC (HR = 0.15, P<0.001) and RT technique (the integrated RT vs. hybrid RT, HR = 4.76, P<0.001) were independent risk factors for grade 3+ RIL. The PLC in patients receiving the integrated RT after RT were higher than that in those receiving hybrid RT (p<0.05).

CONCLUSION

RT technique affect the risk of and recovery from RIL, which may impact survival. Choosing appropriate RT technique to minimize RIL might be considered to benefit their outcomes.

Association of Treatment Disparities and Primary Sites with the Survival of Non-Gastric Early-Stage MALT Lymphoma

PURPOSE/OBJECTIVE(S)

To investigate the association between utilization of radiotherapy and differences in survival among patients with non-gastric early-stage mucosa-associated lymphoid tissue (MALT) lymphoma at different primary sites.

MATERIALS/METHODS

A total of 5,995 patients with non-gastric early-stage MALT lymphoma in the Surveillance, Epidemiology, and End Results (SEER) database treated between 2000-2015 were extracted and analyzed. Mediation analyses were conducted to quantitatively determine the proportion of the relationship between OS and primary sites mediated by radiotherapy. Inverse probability of treatment weighting (IPTW) was conducted to control confounding factors affecting treatment choice.

RESULTS

After controlling for confounding factors, pulmonary MALT lymphoma was found to have the highest rate of omitted radiotherapy compared to other primary sites, including ocular adnexa, salivary gland, skin and other sites. Multivariate Cox analyses showed that lung MALT lymphoma patients had the lowest 10-year OS rate of 58.3%, while skin MALT lymphoma patients had the highest 10-year OS rate of 81.6%. After balancing confounding factors that potentially affected the choice of radiotherapy using IPTW, differences in utilization of radiotherapy explained a significant portion of the poor prognosis of lung MALT lymphoma (35.6%, P = 0.002) and the favorable prognosis of skin MALT lymphoma (6.1%, P <0.001).

CONCLUSION

Differences in survival among patients with non-gastric early-stage MALT lymphoma at different primary sites are associated with disparities in the utilization of radiotherapy.

Radiotherapy Effect on Long-Term Net Survival Benefit for Early-Stage Diffuse Large B-Cell Lymphoma in the Rituximab Era

PURPOSE/OBJECTIVE(S)

It is controversial whether to add consolidative radiotherapy (RT) after chemoimmunotherapy in the first-line treatment for diffuse large B-cell lymphoma (DLBCL). This study aimed to investigate the long-term net survival benefit of RT for early-stage DLBCL in the rituximab era.

MATERIALS/METHODS

The data of 10,841 adult patients with early-stage DLBCL from the Surveillance, Epidemiology, and End Results (SEER) database between 2002 and 2015 were extracted and analyzed. The patients had received combined modality treatment (CMT, chemotherapy plus RT) or chemotherapy alone. Linear regression analysis was performed for RT utilization by year of diagnosis. Competing risk analysis was used to evaluate the cumulative incidence of mortality according to the cause of death. Inverse probability of treatment weighting (IPTW) was used to balance the distribution of covariates between treatment arms. Relative survival (RS), standardized mortality ratio (SMR), and transformed Cox regression were performed to estimate the net survival benefit of RT by controlling for background mortality.

RESULTS

Linear regression revealed that the slope of the best-fit line for RT utilization over time was negative between 2002 and 2015 (m = -0.006, P = 0.003). A total of 4,648 deaths were recorded among 10,841 patients; 55.6% were lymphoma-related death (LRD), and 44.4% were attributed to other causes. Patients initially treated with CMT had a lower cumulative incidence of LRD than chemotherapy alone (HR 0.63, 95% CI: 0.57-0.69; P < 0.001). The 10-year overall survival (OS) rate of 66.1%, RS rate of 85.0%, and SMR of 1.71 achieved with CMT were significantly better than chemotherapy alone (OS, 53.0%; RS, 69.8%; SMR, 2.62; P < 0.001). By IPTW and multivariable analysis, the addition of RT remained associated with better OS (HR 0.67, 95% CI: 0.62-0.71; P < 0.001) and RS (HR 0.69, 95% CI: 0.65-0.74; P < 0.001).

CONCLUSION

RT was associated with better long-term net survival in patients with early-stage DLBCL in the rituximab era.

An Entropy Weighted Nonnegative Matrix Factorization Algorithm for Feature Representation

Nonnegative matrix factorization (NMF) has been widely used to learn low-dimensional representations of data. However, NMF pays the same attention to all attributes of a data point, which inevitably leads to inaccurate representations. For example, in a human-face dataset, if an image contains a hat on a head, the hat should be removed or the importance of its corresponding attributes should be decreased during matrix factorization. This article proposes a new type of NMF called entropy weighted NMF (EWNMF), which uses an optimizable weight for each attribute of each data point to emphasize their importance. This process is achieved by adding an entropy regularizer to the cost function and then using the Lagrange multiplier method to solve the problem. Experimental results with several datasets demonstrate the feasibility and effectiveness of the proposed method. The code developed in this study is available at https://github.com/Poisson-EM/Entropy-weighted-NMF.

Two-stage contextual transformer-based convolutional neural network for airway extraction from CT images

Accurate airway segmentation from computed tomography (CT) images is critical for planning navigation bronchoscopy and realizing a quantitative assessment of airway-related chronic obstructive pulmonary disease (COPD). Existing methods face difficulty in airway segmentation, particularly for the small branches of the airway. These difficulties arise due to the constraints of limited labeling and failure to meet clinical use requirements in COPD. We propose a two-stage framework with a novel 3D contextual transformer for segmenting the overall airway and small airway branches using CT images. The method consists of two training stages sharing the same modified 3D U-Net network. The novel 3D contextual transformer block is integrated into both the encoder and decoder path of the network to effectively capture contextual and long-range information. In the first training stage, the proposed network segments the overall airway with the overall airway mask. To improve the performance of the segmentation result, we generate the intrapulmonary airway branch label, and train the network to focus on producing small airway branches in the second training stage. Extensive experiments were performed on in-house and multiple public datasets. Quantitative and qualitative analyses demonstrate that our proposed method extracts significantly more branches and longer lengths of the airway tree while accomplishing state-of-the-art airway segmentation performance. The code is available at https://github.com/zhaozsq/airway_segmentation.

Disconnectome associated with progressive white matter hyperintensities in aging: a virtual lesion study

Objective

White matter hyperintensities (WMH) are commonly seen on T2-weighted magnetic resonance imaging (MRI) in older adults and are associated with an increased risk of cognitive decline and dementia. This study aims to estimate changes in the structural connectome due to age-related WMH by using a virtual lesion approach.

Methods

High-quality diffusion-weighted imaging data of 30 healthy subjects were obtained from the Human Connectome Project (HCP) database. Diffusion tractography using q-space diffeomorphic reconstruction (QSDR) and whole brain fiber tracking with 107 seed points was conducted using diffusion spectrum imaging studio and the brainnetome atlas was used to parcellate a total of 246 cortical and subcortical nodes. Previously published WMH frequency maps across age ranges (50's, 60's, 70's, and 80's) were used to generate virtual lesion masks for each decade at three lesion frequency thresholds, and these virtual lesion masks were applied as regions of avoidance (ROA) in fiber tracking to estimate connectivity changes. Connections showing significant differences in fiber density with and without ROA were identified using paired tests with False Discovery Rate (FDR) correction.

Results

Disconnections appeared first from the striatum to middle frontal gyrus (MFG) in the 50's, then from the thalamus to MFG in the 60's and extending to the superior frontal gyrus in the 70's, and ultimately including much more widespread cortical and hippocampal nodes in the 80's.

Conclusion

Changes in the structural disconnectome due to age-related WMH can be estimated using the virtual lesion approach. The observed disconnections may contribute to the cognitive and sensorimotor deficits seen in aging.

Abnormal functional connectivity density involvement in freezing of gait and its application for subtyping Parkinson's disease

The pathophysiological mechanisms at work in Parkinson's disease (PD) patients with freezing of gait (FOG) remain poorly understood. Functional connectivity density (FCD) could provide an unbiased way to analyse connectivity across the brain. In this study, a total of 23 PD patients with FOG (PD FOG + patients), 26 PD patients without FOG (PD FOG- patients), and 22 healthy controls (HCs) were recruited, and their resting-state functional magnetic resonance imaging (rs-fMRI) images were collected. FCD mapping was first performed to identify differences between groups. Pearson correlation analysis was used to explore relationships between FCD values and the severity of FOG. Then, a machine learning model was employed to classify each pair of groups. PD FOG + patients showed significantly increased short-range FCD in the precuneus, cingulate gyrus, and fusiform gyrus and decreased long-range FCD in the frontal gyrus, temporal gyrus, and cingulate gyrus. Short-range FCD values in the middle temporal gyrus and inferior temporal gyrus were positively correlated with FOG questionnaire (FOGQ) scores, and long-range FCD values in the middle frontal gyrus were negatively correlated with FOGQ scores. Using FCD in abnormal regions as input, a support vector machine (SVM) classifier can achieve classification with good performance. The mean accuracy values were 0.895 (PD FOG + vs. HC), 0.966 (PD FOG- vs. HC), and 0.897 (PD FOG + vs. PD FOG-). This study demonstrates that PD FOG + patients showed altered short- and long-range FCD in several brain regions involved in action planning and control, motion processing, emotion, cognition, and object recognition.

Deep radiomic model based on the sphere-shell partition for predicting treatment response to chemotherapy in lung cancer

BACKGROUND

The prognosis of chemotherapy is important in clinical decision-making for non-small cell lung cancer (NSCLC) patients.

OBJECTIVES

To develop a model for predicting treatment response to chemotherapy in NSCLC patients from pre-chemotherapy CT images.

MATERIALS AND METHODS

This retrospective multicenter study enrolled 485 patients with NSCLC who received chemotherapy alone as a first-line treatment. Two integrated models were developed using radiomic and deep-learning-based features. First, we partitioned pre-chemotherapy CT images into spheres and shells with different radii around the tumor (0-3, 3-6, 6-9, 9-12, 12-15 mm) containing intratumoral and peritumoral regions. Second, we extracted radiomic and deep-learning-based features from each partition. Third, using radiomic features, five sphere-shell models, one feature fusion model, and one image fusion model were developed. Finally, the model with the best performance was validated in two cohorts.

RESULTS

Among the five partitions, the model of 9-12 mm achieved the highest area under the curve (AUC) of 0.87 (95% confidence interval: 0.77-0.94). The AUC was 0.94 (0.85-0.98) for the feature fusion model and 0.91 (0.82-0.97) for the image fusion model. For the model integrating radiomic and deep-learning-based features, the AUC was 0.96 (0.88-0.99) for the feature fusion method and 0.94 (0.85-0.98) for the image fusion method. The best-performing model had an AUC of 0.91 (0.81-0.97) and 0.89 (0.79-0.93) in two validation sets, respectively.

CONCLUSIONS

This integrated model can predict the response to chemotherapy in NSCLC patients and assist physicians in clinical decision-making.

NCCT-CECT image synthesizers and their application to pulmonary vessel segmentation

BACKGROUND AND OBJECTIVES

Non-contrast CT (NCCT) and contrast-enhanced CT (CECT) are important diagnostic tools with distinct features and applications for chest diseases. We developed two synthesizers for the mutual synthesis of NCCT and CECT and evaluated their applications.

METHODS

Two synthesizers (S₁ and S₂) were proposed based on a generative adversarial network. S₁ generated synthetic CECT (SynCECT) from NCCT and S₂ generated synthetic NCCT (SynNCCT) from CECT. A new training procedure for synthesizers was proposed. Initially, the synthesizers were pretrained using self-supervised learning (SSL) and dual-energy CT (DECT) and then fine-tuned using the registered NCCT and CECT images. Pulmonary vessel segmentation from NCCT was used as an example to demonstrate the effectiveness of the synthesizers. Two strategies (ST₁ and ST₂) were proposed for pulmonary vessel segmentation. In ST₁, CECT images were used to train a segmentation model (Model-CECT), NCCT images were converted to SynCECT through S₁, and SynCECT was input to Model-CECT for testing. In ST₂, CECT data were converted to SynNCCT through S₂. SynNCCT and CECT-based annotations were used to train an additional model (Model-NCCT), and NCCT was input to Model-NCCT for testing. Three datasets, D1 (40 paired CTs), D2 (14 NCCTs and 14 CECTs), and D3 (49 paired DECTs), were used to evaluate the synthesizers and strategies.

RESULTS

For S₁, the mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) were 14.60± 2.19, 1644± 890, 34.34± 1.91, and 0.94± 0.02, respectively. For S₂, they were 12.52± 2.59, 1460± 922, 35.08± 2.35, and 0.95± 0.02, respectively. Our synthesizers outperformed the counterparts of CycleGAN, Pix2Pix, and Pix2PixHD. The results of ablation studies on SSL pretraining, DECT pretraining, and fine-tuning showed that performance worsened (for example, for S₁, MAE increased to 16.53± 3.10, 17.98± 3.10, and 20.57± 3.75, respectively). Model-NCCT and Model-CECT achieved dice similarity coefficients (DSC) of 0.77 and 0.86 on D1 and 0.77 and 0.72 on D2, respectively.

CONCLUSIONS

The proposed synthesizers realized mutual and high-quality synthesis between NCCT and CECT images; the training procedures, including SSL pretraining, DECT pretraining, and fine-tuning, were critical to their effectiveness. The results demonstrated the usefulness of synthesizers for pulmonary vessel segmentation from NCCT images.

[Eriocitrin suppresses proliferation and migration of hepatocellular carcinoma SMMC-7721 cells by promoting ROS production and activating the MAPK pathway]

OBJECTIVE

To investigate the role of the ROS/MAPK signaling axis in mediating the inhibitory effect of eriocitrin on proliferation and migration of hepatocellular carcinoma SMMC-7721 cells.

METHODS

SMMC-7721 cells were treated with different concentrations of eriocitrin for 24 h, and the changes in cell viability were detected with CCK-8 assay. The migration and invasion abilities of the treated cells were evaluated using Transwell and scratch healing assays, the cell proliferation was assessed with colony-forming assay, and changes in nuclear morphology were observed with DAPI staining. Western blotting was performed to examine the changes in the expressions of E-cadherin, N-cadherin, MMP-2, MMP-9, PARP, Pro-caspase 3, pJNK, p-P38, and p-ERK. The effect of eriocitrin on PARP cleavage in SMMC-7721 cells pretreated with ERK, JNK and P38 inhibitors (U0126, SB203580 and SP600125, respectively) was detected using Western blotting. The effect of treatment with Nacetyl-cysteine (NAC, 30 μmol/L) and eriocitrin (100, 200, and 300 μg/mL), alone or in combination, on reactive oxygen species (ROS) levels in the cells was examined using a DCFH-DA fluorescent probe.

RESULTS

Eriocitrin below 50 μg/mL did not produce significant effect on the viability of SMMC-7721 cells (P>0.05). Treatment with eriocitrin significantly inhibited scratch healing, migration, and colony formation of the cells (P < 0.01), reduced the protein expressions of N-cadherin, MMP-2, and MMP-9 (P < 0.01), and up-regulated E-cadherin protein expression (P < 0.05). Eriocitrin-treated SMMC-7721 cells showed obvious apoptotic morphologies with decreased Procaspase 3 expression and increased PARP cleavage (P < 0.01) and phosphorylation levels of JNK, P38, and ERK (P < 0.01); Eriocitrin-induced PAPR cleavage was obviously enhanced by U0126 and SB203580 but attenuated by SP600125. Treatment with 300 μg/mL eriocitrin for 30 min significantly increased ROS level in the cells, and this effect was obviously suppressed by NAC.

CONCLUSION

Eriocitrin can suppress the proliferation and migration and promote apoptosis of hepatocellular carcinoma SMMC-7721 cells by promoting ROS production and activating the MAPKs signaling pathway.

A hybrid P300-SSVEP brain-computer interface speller with a frequency enhanced row and column paradigm

Objective

This study proposes a new hybrid brain-computer interface (BCI) system to improve spelling accuracy and speed by stimulating P300 and steady-state visually evoked potential (SSVEP) in electroencephalography (EEG) signals.

Methods

A frequency enhanced row and column (FERC) paradigm is proposed to incorporate the frequency coding into the row and column (RC) paradigm so that the P300 and SSVEP signals can be evoked simultaneously. A flicker (white-black) with a specific frequency from 6.0 to 11.5 Hz with an interval of 0.5 Hz is assigned to one row or column of a 6 × 6 layout, and the row/column flashes are carried out in a pseudorandom sequence. A wavelet and support vector machine (SVM) combination is adopted for P300 detection, an ensemble task-related component analysis (TRCA) method is used for SSVEP detection, and the two detection possibilities are fused using a weight control approach.

Results

The implemented BCI speller achieved an accuracy of 94.29% and an information transfer rate (ITR) of 28.64 bit/min averaged across 10 subjects during the online tests. An accuracy of 96.86% is obtained during the offline calibration tests, higher than that of only using P300 (75.29%) or SSVEP (89.13%). The SVM in P300 outperformed the previous linear discrimination classifier and its variants (61.90–72.22%), and the ensemble TRCA in SSVEP outperformed the canonical correlation analysis method (73.33%).

Conclusion

The proposed hybrid FERC stimulus paradigm can improve the performance of the speller compared with the classical single stimulus paradigm. The implemented speller can achieve comparable accuracy and ITR to its state-of-the-art counterparts with advanced detection algorithms.

Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans

BACKGROUND

The coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically distinguishing between them is crucial.

METHODS

A deep learning method for distinguishing COVID-19 from CAP is developed using maximum intensity projection (MIP) images from CT scans. LinkNet is employed for lung segmentation of chest CT images. MIP images are produced by superposing the maximum gray of intrapulmonary CT values. The MIP images are input into a capsule network for patient-level pred iction and diagnosis of COVID-19. The network is trained using 333 CT scans (168 COVID-19/165 CAP) and validated on three external datasets containing 3581 CT scans (2110 COVID-19/1471 CAP).

RESULTS

LinkNet achieves the highest Dice coefficient of 0.983 for lung segmentation. For the classification of COVID-19 and CAP, the capsule network with the DenseNet-121 feature extractor outperforms ResNet-50 and Inception-V3, achieving an accuracy of 0.970 on the training dataset. Without MIP or the capsule network, the accuracy decreases to 0.857 and 0.818, respectively. Accuracy scores of 0.961, 0.997, and 0.949 are achieved on the external validation datasets. The proposed method has higher or comparable sensitivity compared with ten state-of-the-art methods.

CONCLUSIONS

The proposed method illustrates the feasibility of applying MIP images from CT scans to distinguish COVID-19 from CAP using capsule networks. MIP images provide conspicuous benefits when exploiting deep learning to detect COVID-19 lesions from CT scans and the capsule network improves COVID-19 diagnosis.

Using CT radiomic features based on machine learning models to subtype adrenal adenoma

BACKGROUND

Functioning and non-functioning adrenocortical adenoma are two subtypes of benign adrenal adenoma, and their differential diagnosis is crucial. Current diagnostic procedures use an invasive method, adrenal venous sampling, for endocrinologic assessment.

METHODS

This study proposes establishing an accurate differential model for subtyping adrenal adenoma using computed tomography (CT) radiomic features and machine learning (ML) methods. Dataset 1 (289 patients with adrenal adenoma) was collected to develop the models, and Dataset 2 (54 patients) was utilized for external validation. Cuboids containing the lesion were cropped from the non-contrast, arterial, and venous phase CT images, and 1,967 features were extracted from each cuboid. Ten discriminative features were selected from each phase or the combined phases. Random forest, support vector machine, logistic regression (LR), Gradient Boosting Machine, and eXtreme Gradient Boosting were used to establish prediction models.

RESULTS

The highest accuracies were 72.7%, 72.7%, and 76.1% in the arterial, venous, and non-contrast phases, respectively, when using radiomic features alone with the ML classifier of LR. When features from the three CT phases were combined, the accuracy of LR reached 83.0%. After adding clinical information, the area under the receiver operating characteristic curve increased for all the machine learning methods except for LR. In Dataset 2, the accuracy of LR was the highest, reaching 77.8%.

CONCLUSION

The radiomic features of the lesion in three-phase CT images can potentially suggest the functioning or non-functioning nature of adrenal adenoma. The resulting radiomic models can be a non-invasive, low-cost, and rapid method of minimizing unnecessary testing in asymptomatic patients with incidentally discovered adrenal adenoma.

EBHI-Seg: A novel enteroscope biopsy histopathological hematoxylin and eosin image dataset for image segmentation tasks

Background and purpose

Colorectal cancer is a common fatal malignancy, the fourth most common cancer in men, and the third most common cancer in women worldwide. Timely detection of cancer in its early stages is essential for treating the disease. Currently, there is a lack of datasets for histopathological image segmentation of colorectal cancer, which often hampers the assessment accuracy when computer technology is used to aid in diagnosis.

Methods

This present study provided a new publicly available Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset for Image Segmentation Tasks (EBHI-Seg). To demonstrate the validity and extensiveness of EBHI-Seg, the experimental results for EBHI-Seg are evaluated using classical machine learning methods and deep learning methods.

Results

The experimental results showed that deep learning methods had a better image segmentation performance when utilizing EBHI-Seg. The maximum accuracy of the Dice evaluation metric for the classical machine learning method is 0.948, while the Dice evaluation metric for the deep learning method is 0.965.

Conclusion

This publicly available dataset contained 4,456 images of six types of tumor differentiation stages and the corresponding ground truth images. The dataset can provide researchers with new segmentation algorithms for medical diagnosis of colorectal cancer, which can be used in the clinical setting to help doctors and patients. EBHI-Seg is publicly available at: https://figshare.com/articles/dataset/EBHI-SEG/21540159/1.

CLSSL-ResNet: Predicting malignancy of solitary pulmonary nodules from CT images by chimeric label with self-supervised learning

BACKGROUND

Pulmonary granulomatous nodules (GN) with spiculation or lobulation have a similar morphological appearance to solid lung adenocarcinoma (SADC) under computed tomography (CT). However, these two kinds of solid pulmonary nodules (SPN) have different malignancies and are sometimes misdiagnosed.

OBJECTIVE

This study aims to predict malignancies of SPNs by a deep learning model automatically.

METHODS

A chimeric label with self-supervised learning (CLSSL) is proposed to pre-train a ResNet-based network (CLSSL-ResNet) for distinguishing isolated atypical GN from SADC in CT images. The malignancy, rotation, and morphology labels are integrated into a chimeric label and utilized to pre-train a ResNet50. The pre-trained ResNet50 is then transferred and fine-tuned to predict the malignancy of SPN. Two image datasets of 428 subjects (Dataset1, 307; Dataset2, 121) from different hospitals are collected. Dataset1 is divided into training, validation, and test data by a ratio of 7:1:2 to develop the model. Dataset2 is utilized as an external validation dataset.

RESULTS

CLSSL-ResNet achieves an area under the ROC curve (AUC) of 0.944 and an accuracy (ACC) of 91.3%, which was much higher than that of the consensus of two experienced chest radiologists (77.3%). CLSSL-ResNet also outperforms other self-supervised learning models and many counterparts of other backbone networks. In Dataset2, AUC and ACC of CLSSL-ResNet are 0.923 and 89.3%, respectively. Additionally, the ablation experiment result indicates higher efficiency of the chimeric label.

CONCLUSION

CLSSL with morphology labels can increase the ability of feature representation by deep networks. As a non-invasive method, CLSSL-ResNet can distinguish GN from SADC via CT images and may support clinical diagnoses after further validation.

Aberrant degree centrality of functional brain networks in subclinical depression and major depressive disorder

BACKGROUND

As one of the most common diseases, major depressive disorder (MDD) has a significant adverse impact on the li of patients. As a mild form of depression, subclinical depression (SD) serves as an indicator of progression to MDD. This study analyzed the degree centrality (DC) for MDD, SD, and healthy control (HC) groups and identified the brain regions with DC alterations.

METHODS

The experimental data were composed of resting-state functional magnetic resonance imaging (rs-fMRI) from 40 HCs, 40 MDD subjects, and 34 SD subjects. After conducting a one-way analysis of variance, two-sample t-tests were used for further analysis to explore the brain regions with changed DC. Receiver operating characteristic (ROC) curve analysis of single index and composite index features was performed to analyze the distinguishable ability of important brain regions.

RESULTS

For the comparison of MDD vs. HC, increased DC was found in the right superior temporal gyrus (STG) and right inferior parietal lobule (IPL) in the MDD group. For SD vs. HC, the SD group showed a higher DC in the right STG and the right middle temporal gyrus (MTG), and a smaller DC in the left IPL. For MDD vs. SD, increased DC in the right middle frontal gyrus (MFG), right IPL, and left IPL, and decreased DC in the right STG and right MTG was found in the MDD group. With an area under the ROC (AUC) of 0.779, the right STG could differentiate MDD patients from HCs and, with an AUC of 0.704, the right MTG could differentiate MDD patients from SD patients. The three composite indexes had good discriminative ability in each pairwise comparison, with AUCs of 0.803, 0.751, and 0.814 for MDD vs. HC, SD vs. HC, and MDD vs. SD, respectively.

CONCLUSION

Altered DC in the STG, MTG, IPL, and MFG were identified in depression groups. The DC values of these altered regions and their combinations presented good discriminative ability between HC, SD, and MDD. These findings could help to find effective biomarkers and reveal the potential mechanisms of depression.

Functional and effective connectivity analysis of drug-resistant epilepsy: a resting-state fMRI analysis

Objective

Epilepsy is considered as a neural network disorder. Seizure activity in epilepsy may disturb brain networks and damage brain functions. We propose using resting-state functional magnetic resonance imaging (rs-fMRI) data to characterize connectivity patterns in drug-resistant epilepsy.

Methods

This study enrolled 47 participants, including 28 with drug-resistant epilepsy and 19 healthy controls. Functional and effective connectivity was employed to assess drug-resistant epilepsy patients within resting state networks. The resting state functional connectivity (FC) analysis was performed to assess connectivity between each patient and healthy controls within the default mode network (DMN) and the dorsal attention network (DAN). In addition, dynamic causal modeling was used to compute effective connectivity (EC). Finally, a statistical analysis was performed to evaluate our findings.

Results

The FC analysis revealed significant connectivity changes in patients giving 64.3% (18/28) and 78.6% (22/28) for DMN and DAN, respectively. Statistical analysis of FC was significant between the medial prefrontal cortex, posterior cingulate cortex, and bilateral inferior parietal cortex for DMN. For DAN, it was significant between the left and the right intraparietal sulcus and the frontal eye field. For the DMN, the patient group showed significant EC connectivity in the right inferior parietal cortex and the medial prefrontal cortex for the DMN. There was also bilateral connectivity between the medial prefrontal cortex and the posterior cingulate cortex, as well as between the left and right inferior parietal cortex. For DAN, patients showed significant connectivity in the right frontal eye field and the right intraparietal sulcus. Bilateral connectivity was also found between the left frontal eye field and the left intraparietal sulcus, as well as between the right frontal eye field and the right intraparietal sulcus. The statistical analysis of the EC revealed a significant result in the medial prefrontal cortex and the right intraparietal cortex for the DMN. The DAN was found significant in the left frontal eye field, as well as the left and right intraparietal sulcus.

Conclusion

Our results provide preliminary evidence to support that the combination of functional and effective connectivity analysis of rs-fMRI can aid in diagnosing epilepsy in the DMN and DAN networks.

EMDS-7: Environmental microorganism image dataset seventh version for multiple object detection evaluation

Nowadays, the detection of environmental microorganism indicators is essential for us to assess the degree of pollution, but the traditional detection methods consume a lot of manpower and material resources. Therefore, it is necessary for us to make microbial data sets to be used in artificial intelligence. The Environmental Microorganism Image Dataset Seventh Version (EMDS-7) is a microscopic image data set that is applied in the field of multi-object detection of artificial intelligence. This method reduces the chemicals, manpower and equipment used in the process of detecting microorganisms. EMDS-7 including the original Environmental Microorganism (EM) images and the corresponding object labeling files in ".XML" format file. The EMDS-7 data set consists of 41 types of EMs, which has a total of 2,65 images and 13,216 labeled objects. The EMDS-7 database mainly focuses on the object detection. In order to prove the effectiveness of EMDS-7, we select the most commonly used deep learning methods (Faster-Region Convolutional Neural Network (Faster-RCNN), YOLOv3, YOLOv4, SSD, and RetinaNet) and evaluation indices for testing and evaluation. EMDS-7 is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/EMDS-7_DataSet/16869571.

CoT-XNet: contextual transformer with Xception network for diabetic retinopathy grading

Objective.Diabetic retinopathy (DR) grading is primarily performed by assessing fundus images. Many types of lesions, such as microaneurysms, hemorrhages, and soft exudates, are available simultaneously in a single image. However, their sizes may be small, making it difficult to differentiate adjacent DR grades even using deep convolutional neural networks (CNNs). Recently, a vision transformer has shown comparable or even superior performance to CNNs, and it also learns different visual representations from CNNs. Inspired by this finding, we propose a two-path contextual transformer with Xception network (CoT-XNet) to improve the accuracy of DR grading.Approach.The representations learned by CoT through one path and those by the Xception network through another path are concatenated before the fully connected layer. Meanwhile, the dedicated pre-processing, data resampling, and test time augmentation strategies are implemented. The performance of CoT-XNet is evaluated in the publicly available datasets of DDR, APTOS2019, and EyePACS, which include over 50 000 images. Ablation experiments and comprehensive comparisons with various state-of-the-art (SOTA) models have also been performed.Main results.Our proposed CoT-XNet shows better performance than available SOTA models, and the accuracy and Kappa are 83.10% and 0.8496, 84.18% and 0.9000 and 84.10% and 0.7684 respectively, in the three datasets (listed above). Class activation maps of CoT and Xception networks are different and complementary in most images.Significance.By concatenating the different visual representations learned by CoT and Xception networks, CoT-XNet can accurately grade DR from fundus images and present good generalizability. CoT-XNet will promote the application of artificial intelligence-based systems in the DR screening of large-scale populations.

Deep multiple instance learning for predicting chemotherapy response in non-small cell lung cancer using pretreatment CT images

The individual prognosis of chemotherapy is quite different in non-small cell lung cancer (NSCLC). There is an urgent need to precisely predict and assess the treatment response. To develop a deep multiple-instance learning (DMIL) based model for predicting chemotherapy response in NSCLC in pretreatment CT images. Two datasets of NSCLC patients treated with chemotherapy as the first-line treatment were collected from two hospitals. Dataset 1 (163 response and 138 nonresponse) was used to train, validate, and test the DMIL model and dataset 2 (22 response and 20 nonresponse) was used as the external validation cohort. Five backbone networks in the feature extraction module and three pooling methods were compared. The DMIL with a pre-trained VGG16 backbone and an attention mechanism pooling performed the best, with an accuracy of 0.883 and area under the curve (AUC) of 0.982 on Dataset 1. While using max pooling and convolutional pooling, the AUC was 0.958 and 0.931, respectively. In Dataset 2, the best DMIL model produced an accuracy of 0.833 and AUC of 0.940. Deep learning models based on the MIL can predict chemotherapy response in NSCLC using pretreatment CT images and the pre-trained VGG16 with attention mechanism pooling yielded better predictions.

Improving the level of autism discrimination with augmented data by GraphRNN

Datasets are the key to deep learning in autism disease research. However, due to the small quantity and heterogeneity of samples in current public datasets, for example Autism Brain Imaging Data Exchange (ABIDE), the recognition research is not sufficiently effective. Previous studies primarily focused on optimizing feature selection methods and data augmentation to improve recognition accuracy. This research is based on the latter, which learns the edge distribution of a real brain network through the graph recurrent neural network (GraphRNN) and generates synthetic data that have an incentive effect on the discriminant model. Experimental results show that the synthetic data greatly improves the classification ability of the subsequent classifiers, for example, it can improve the classification accuracy of a 50-layer ResNet by up to 30% compared with the case without synthetic data.

Automatic detection of stroke lesion from diffusion-weighted imaging via the improved YOLOv5

BACKGROUND AND OBJECTIVE

Stroke is the second most deadly disease globally and seriously endangers people's lives and health. The automatic detection of stroke lesions from diffusion-weighted imaging (DWI) can improve the diagnosis. Recently, automatic detection methods based on YOLOv5 have been utilized in medical images. However, most of them barely capture the stroke lesions because of their small size and fuzzy boundaries.

METHODS

To address this problem, a novel method for tracing the edge of the stroke lesion based on YOLOv5 (TE-YOLOv5) is proposed. Specifically, we constantly update the high-level features of the lesion using an aggregate pool (AP) module. Conversely, we feed the extracted feature into the reverse attention (RA) module to trace the edge relationship promptly. Overall, 1681 DWI images of 319 stroke patients have been collected, and experienced radiologists have marked the lesions. DWI images were randomly split into the training and test set at a ratio of 8:2. TE-YOLOv5 has been compared with the related models, and a detailed ablation analysis has been conducted to clarify the role of the RA and AP modules.

RESULTS

TE-YOLOv5 outperforms its counterparts and achieves competitive performance with a precision of 81.5%, a recall of 75.8%, and a mAP@0.5 of 80.7% (mean average precision while the intersection over union is 0.5) under the same backbone. At the patient level, the positive finding rate can reach 98.51%, while the confidence is set at 80.0%. After ablating RA, the mAP@0.5 decreases to 79.6%; after ablating RA and AP, the mAP@0.5 decreases to 78.1%.

CONCLUSIONS

The proposed TE-YOLOv5 can automatically and effectively detect stroke lesions from DWI images, especially for those with an extremely small size and blurred boundaries. AP and RA modules can aggregate multi-layer high-level features and concurrently track the edge relationship of stroke lesions. These detection methods might help radiologists improve stroke diagnosis and have great application potential in clinical practice.

Alterations of functional connectivity of the lateral habenula in subclinical depression and major depressive disorder

BACKGROUND

Major depressive disorder (MDD) is a common cause of disability and morbidity, affecting about 10% of the population worldwide. Subclinical depression (SD) can be understood as a precursor of MDD, and therefore provides an MDD risk indicator. The pathogenesis of MDD and SD in humans is still unclear, and the current diagnosis lacks accurate biomarkers and gold standards.

METHODS

A total of 40 MDD, 34 SD, and 40 healthy control (HC) participants matched by age, gender, and education were included in this study. Resting-state functional magnetic resonance images (rs-fMRI) were used to analyze the functional connectivity (FC) of the posterior parietal thalamus (PPtha), which includes the lateral habenula, as the region of interest. Analysis of variance with the post hoc t-test test was performed to find significant differences in FC and clarify the variations in FC among the HC, SD, and MDD groups.

RESULTS

Increased FC was observed between PPtha and the left inferior temporal gyrus (ITG) for MDD versus SD, and between PPtha and the right ITG for SD versus HC. Conversely, decreased FC was observed between PPtha and the right middle temporal gyrus (MTG) for MDD versus SD and MDD versus HC. The FC between PPtha and the middle frontal gyrus (MFG) in SD was higher than that in MDD and HC. Compared with the HC group, the FC of PPtha-ITG (left and right) increased in both the SD and MDD groups, PPtha-MTG (right) decreased in both the SD and MDD groups and PPtha-MFG (right) increased in the SD group and decreased in the MDD group.

CONCLUSION

Through analysis of FC measured by rs-fMRI, the altered FC between PPtha and several brain regions (right and left ITG, right MTG, and right MFG) has been identified in participants with SD and MDD. Different alterations in FC between PPtha and these regions were identified for patients with depression. These findings might provide insights into the potential pathophysiological mechanisms of SD and MDD, especially related to PPtha and the lateral habenula.

Prediction model of early biomarkers of massive cerebral infarction caused by anterior circulation occlusion: Establishment and evaluation

Objective

The purpose of this study is to establish and evaluate an early biomarker prediction model of massive cerebral infarction caused by anterior circulation occlusion.

Methods

One hundred thirty-four patients with acute cerebral infarction from January 2018 to October 2020 were selected to establish the development cohort for the internal test of the nomogram. Ninety-one patients with acute cerebral infarction hospitalized in our hospital from December 2020 to December 2021 were constituted the validation cohort for the external validation. All patients underwent baseline computed tomography (CT) scans within 12 h of onset and early imaging signs (hyperdense middle cerebral artery sign, obscuration of the lentiform nucleus, insular ribbon sign) of acute cerebral infarction were identified on CT by two neurologists. Based on follow-up CT images, patients were then divided into a massive cerebral infarction group and a non-massive cerebral infarction group. The nomogram model was constructed based on logistic regression analysis with R language. The nomogram was subsequently validated in an independent external validation cohort. Accuracy and discrimination of the prediction model were evaluated by a calibration chart, receiver operating characteristic (ROC) curve, and decision curve.

Results

The indicators, including insular ribbon sign, reperfusion therapy, National Institutes of Health Stroke Scale (NHISS) score, previous cerebral infarction, and atrial fibrillation, were entered into the prediction model through binary logistic regression analysis. The prediction model showed good predictive ability. The area under the ROC curve of the prediction model was 0.848. The specificity, sensitivity, and Youden index were 0.864, 0.733, and 0.597, respectively. This nomogram to the validation cohort also showed good discrimination (AUC = 0.940, 95% CI 0.894–0.985) and calibration.

Conclusion

Demonstrating favorable predictive efficacy and reproducibility, this study successfully established a prediction model of CT imaging signs and clinical data as early biomarkers of massive cerebral infarction caused by anterior circulation occlusion.

Iterative CT reconstruction based on ADMM using shearlet sparse regularization

The total variation (TV) method favors solutions with the piece-wise constant assumption of the desired image from sparse-view sampling, for example, simple geometric images with flat intensity. When the phantoms become more complex and contain complicated textures, for example, high-resolution phantom and lung CT images, the images reconstructed by TV regularization may lose their contrast and fine structures. One of the optimally sparse transforms for images, the shearlet transform, has C² without discontinuities on C² curves, giving excellent sensitive directional information as compared with other wavelet transform approaches. Here, we developed a Shearlet-Sparse Regularization (SSR) algorithm solved with the Alternating Direction Method of Multipliers (ADMM) to overcome this limitation. With the strengthened characteristics of SSR, we performed one simulation experiment and two real experiments using a NeuViz 64 X-ray CT scanning system to measure the performance and properties of proposed algorithm. The results demonstrate that the SSR method exhibits the advantage of providing high-quality directional information and contrast as compared with TV.

Predicting chemotherapy response in non-small-cell lung cancer via computed tomography radiomic features: Peritumoral, intratumoral, or combined?

Purpose

This study aims to evaluate the ability of peritumoral, intratumoral, or combined computed tomography (CT) radiomic features to predict chemotherapy response in non-small cell lung cancer (NSCLC).

Methods

After excluding subjects with incomplete data or other types of treatments, 272 (Dataset 1) and 43 (Dataset 2, external validation) NSCLC patients who were only treated with chemotherapy as the first-line treatment were enrolled between 2015 and 2019. All patients were divided into response and nonresponse based on the response evaluation criteria in solid tumors, version 1.1. By using 3D slicer and morphological operations in python, the intra- and peritumoral regions of lung tumors were segmented from pre-treatment CT images (unenhanced) and confirmed by two experienced radiologists. Then radiomic features (the first order, texture, shape, et al.) were extracted from the above regions of interest. The models were trained and tested in Dataset 1 and further validated in Dataset 2. The performance of models was compared using the area under curve (AUC), confusion matrix, accuracy, precision, recall, and F1-score.

Results

The radiomic model using features from the peritumoral region of 0–3 mm outperformed that using features from 3–6, 6–9, 9–12 mm peritumoral region, and intratumoral region (AUC: 0.95 versus 0.87, 0.86, 0.85, and 0.88). By the fusion of features from 0–3 and 3–6 mm peritumoral regions, the logistic regression model achieved the best performance, with an AUC of 0.97. This model achieved an AUC of 0.85 in the external cohort. Moreover, among the 20 selected features, seven features differed significantly between the two groups (p < 0.05).

Conclusions

CT radiomic features from both the peri- and intratumoral regions can predict chemotherapy response in NSCLC using machine learning models. Combined features from two peritumoral regions yielded better predictions.