Development of a Malignancy Potential Binary Prediction Model Based on Deep Learning for the Mitotic Count of Local Primary Gastrointestinal Stromal Tumors

Characterization of adrenal glands on computed tomography with a 3D V-Net-based model

OBJECTIVES

To evaluate the performance of a 3D V-Net-based segmentation model of adrenal lesions in characterizing adrenal glands as normal or abnormal.

METHODS

A total of 1086 CT image series with focal adrenal lesions were retrospectively collected, annotated, and used for the training of the adrenal lesion segmentation model. The dice similarity coefficient (DSC) of the test set was used to evaluate the segmentation performance. The other cohort, consisting of 959 patients with pathologically confirmed adrenal lesions (external validation dataset 1), was included for validation of the classification performance of this model. Then, another consecutive cohort of patients with a history of malignancy (N = 479) was used for validation in the screening population (external validation dataset 2). Parameters of sensitivity, accuracy, etc., were used, and the performance of the model was compared to the radiology report in these validation scenes.

RESULTS

The DSC of the test set of the segmentation model was 0.900 (0.810-0.965) (median (interquartile range)). The model showed sensitivities and accuracies of 99.7%, 98.3% and 87.2%, 62.2% in external validation datasets 1 and 2, respectively. It showed no significant difference comparing to radiology reports in external validation datasets 1 and lesion-containing groups of external validation datasets 2 (p = 1.000 and p > 0.05, respectively).

CONCLUSION

The 3D V-Net-based segmentation model of adrenal lesions can be used for the binary classification of adrenal glands.

CRITICAL RELEVANCE STATEMENT

A 3D V-Net-based segmentation model of adrenal lesions can be used for the detection of abnormalities of adrenal glands, with a high accuracy in the pre-surgical scene as well as a high sensitivity in the screening scene.

KEY POINTS

Adrenal lesions may be prone to inter-observer variability in routine diagnostic workflow. The study developed a 3D V-Net-based segmentation model of adrenal lesions with DSC 0.900 in the test set. The model showed high sensitivity and accuracy of abnormalities detection in different scenes.

Deep learning model combined with computed tomography features to preoperatively predicting the risk stratification of gastrointestinal stromal tumors

BACKGROUND

Gastrointestinal stromal tumors (GIST) are prevalent neoplasm originating from the gastrointestinal mesenchyme. Approximately 50% of GIST patients experience tumor recurrence within 5 years. Thus, there is a pressing need to accurately evaluate risk stratification preoperatively.

AIM

To assess the application of a deep learning model (DLM) combined with computed tomography features for predicting risk stratification of GISTs.

METHODS

Preoperative contrast-enhanced computed tomography (CECT) images of 551 GIST patients were retrospectively analyzed. All image features were independently analyzed by two radiologists. Quantitative parameters were statistically analyzed to identify significant predictors of high-risk malignancy. Patients were randomly assigned to the training (n = 386) and validation cohorts (n = 165). A DLM and a combined DLM were established for predicting the GIST risk stratification using convolutional neural network and subsequently evaluated in the validation cohort.

RESULTS

Among the analyzed CECT image features, tumor size, ulceration, and enlarged feeding vessels were identified as significant risk predictors (P < 0.05). In DLM, the overall area under the receiver operating characteristic curve (AUROC) was 0.88, with the accuracy (ACC) and AUROCs for each stratification being 87% and 0.96 for low-risk, 79% and 0.74 for intermediate-risk, and 84% and 0.90 for high-risk, respectively. The overall ACC and AUROC were 84% and 0.94 in the combined model. The ACC and AUROCs for each risk stratification were 92% and 0.97 for low-risk, 87% and 0.83 for intermediate-risk, and 90% and 0.96 for high-risk, respectively. Differences in AUROCs for each risk stratification between the two models were significant (P < 0.05).

CONCLUSION

A combined DLM with satisfactory performance for preoperatively predicting GIST stratifications was developed using routine computed tomography data, demonstrating superiority compared to DLM.

Performance of radiomics in preoperative determination of malignant potential and Ki-67 expression levels in gastrointestinal stromal tumors: a systematic review and meta-analysis

Empirical evidence for radiomics predicting the malignant potential and Ki-67 expression in gastrointestinal stromal tumors (GISTs) is lacking. The aim of this review article was to explore the preoperative discriminative performance of radiomics in assessing the malignant potential, mitotic index, and Ki-67 expression levels of GISTs. We systematically searched PubMed, EMBASE, Web of Science, and the Cochrane Library. The search was conducted up to 30 September 2023. Quality assessment was performed using the Radiomics Quality Score (RQS). A total of 35 original studies were included in the analysis. Among them, 26 studies focused on determining malignant potential, three studies on mitotic index discrimination, and six studies on Ki-67 discrimination. In the validation set, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of radiomics in the determination of high malignant potential were 0.74 (95% CI=0.69-0.78), 0.90 (95% CI=0.83-0.94), and 0.81 (95% CI=0.14-0.99), respectively. For moderately to highly malignant potential, the sensitivity, specificity, and AUC were 0.86 (95% CI=0.83-0.88), 0.73 (95% CI=0.67-0.78), and 0.88 (95% CI=0.27-0.99), respectively. Regarding the determination of high mitotic index, the sensitivity, specificity, and AUC of radiomics were 0.86 (95% CI=0.83-0.88), 0.73 (95% CI=0.67-0.78), and 0.88 (95% CI=0.27-0.99), respectively. When determining high Ki-67 expression, the combined sensitivity, specificity, and AUC were 0.74 (95% CI=0.65-0.81), 0.81 (95% CI=0.74-0.86), and 0.84 (95% CI=0.61-0.95), respectively. Radiomics demonstrates promising discriminative performance in the preoperative assessment of malignant potential, mitotic index, and Ki-67 expression levels in GISTs.

Deep Learning-Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging

PURPOSE

To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs).

METHODS

A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning-based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC).

RESULTS

Among the compared models, SegNeXt-ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively.

CONCLUSION

This two-stage SegNeXt-ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.

CT and MRI of Gastrointestinal Stromal Tumors: New Trends and Perspectives

Gastrointestinal stromal tumors (GISTs) are defined as mesenchymal tumors of the gastrointestinal tract that express positivity for CD117, which is a c-KIT proto-oncogene antigen. Expression of the c-KIT protein, a tyrosine kinase growth factor receptor, allows the distinction between GISTs and other mesenchymal tumors such as leiomyoma, leiomyosarcoma, schwannoma and neurofibroma. GISTs can develop anywhere in the gastrointestinal tract, as well as in the mesentery and omentum. Over the years, the management of GISTs has improved due to a better knowledge of their behaviors and risk or recurrence, the identification of specific mutations and the use of targeted therapies. This has resulted in a better prognosis for patients with GISTs. In parallel, imaging of GISTs has been revolutionized by tremendous progress in the field of detection, characterization, survival prediction and monitoring during therapy. Recently, a particular attention has been given to radiomics for the characterization of GISTs using analysis of quantitative imaging features. In addition, radiomics has currently many applications that are developed in conjunction with artificial intelligence with the aim of better characterizing GISTs and providing a more precise assessment of tumor burden. This article sums up recent advances in computed tomography and magnetic resonance imaging of GISTs in the field of image/data acquisition, tumor detection, tumor characterization, treatment response evaluation, and preoperative planning.

Reporting Quality of Research Studies on AI Applications in Medical Images According to the CLAIM Guidelines in a Radiology Journal With a Strong Prominence in Asia

OBJECTIVE

We aimed to evaluate the reporting quality of research articles that applied deep learning to medical imaging. Using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines and a journal with prominence in Asia as a sample, we intended to provide an insight into reporting quality in the Asian region and establish a journal-specific audit.

MATERIALS AND METHODS

A total of 38 articles published in the Korean Journal of Radiology between June 2018 and January 2023 were analyzed. The analysis included calculating the percentage of studies that adhered to each CLAIM item and identifying items that were met by ≤ 50% of the studies. The article review was initially conducted independently by two reviewers, and the consensus results were used for the final analysis. We also compared adherence rates to CLAIM before and after December 2020.

RESULTS

Of the 42 items in the CLAIM guidelines, 12 items (29%) were satisfied by ≤ 50% of the included articles. None of the studies reported handling missing data (item #13). Only one study respectively presented the use of de-identification methods (#12), intended sample size (#19), robustness or sensitivity analysis (#30), and full study protocol (#41). Of the studies, 35% reported the selection of data subsets (#10), 40% reported registration information (#40), and 50% measured inter and intrarater variability (#18). No significant changes were observed in the rates of adherence to these 12 items before and after December 2020.

CONCLUSION

The reporting quality of artificial intelligence studies according to CLAIM guidelines, in our study sample, showed room for improvement. We recommend that the authors and reviewers have a solid understanding of the relevant reporting guidelines and ensure that the essential elements are adequately reported when writing and reviewing the manuscripts for publication.

Use of a Convolutional Neural Network to Predict the Malignant Potential of Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Images: Visualization of the Focus of the Prediction Model

OBJECTIVE

We established a deep convolutional neural network (CNN) model based on ultrasound images (US-CNN) for predicting the malignant potential of gastrointestinal stromal tumors (GISTs).

METHODS

A total of 980 ultrasound images from 245 pathology-confirmed GIST patients after surgical operation were retrospectively collected and divided into a low (very-low-risk, low-risk) and a high (medium-risk, high-risk) malignant potential group. Eight pre-trained CNN models were used to extract the features. The CNN model with the highest accuracy in the test set was selected. The model's performance was evaluated by calculating accuracy, sensitivity, specificity, positive-predictive value (PPV), negative-predictive value (NPV) and the F1 score. Three radiologists with different experience levels also predicted the malignant potential of GISTs in the same test set. US-CNN and human assessments were compared. Subsequently, gradient-weighted class activation diagrams (Grad-CAMs) were used to visualize the model's final classification decisions.

RESULTS

Among the eight transfer learning-based CNNs, ResNet18 performed best. The accuracy, sensitivity, specificity, PPV, NPV and F1 score were 0.88, 0.86, 0.89, 0.82, 0.92 and 0.90, respectively, which were significantly better than those achieved by radiologists (resident doctor: 0.66, 0.55, 0.79, 0.74, 0.62 and 0.69; attending doctor: 0.68, 0.59, 0.78, 0.70, 0.69 and 0.73; professor: 0.69, 0.63, 0.72, 0.51, 0.80 and 0.76). Model interpretation with Grad-CAMs revealed that the activated areas mainly focused on cystic necrosis and margins.

CONCLUSION

The US-CNN model predicts GIST malignant potential well, which can assist in clinical treatment decision-making.

Development and Validation of Artificial-Intelligence-Based Radiomics Model Using Computed Tomography Features for Preoperative Risk Stratification of Gastrointestinal Stromal Tumors

BACKGROUND

preoperative risk assessment of gastrointestinal stromal tumors (GISTS) is required for optimal and personalized treatment planning. Radiomics features are promising tools to predict risk assessment. The purpose of this study is to develop and validate an artificial intelligence classification algorithm, based on CT features, to define GIST's prognosis as determined by the Miettinen classification.

METHODS

patients with histological diagnosis of GIST and CT studies were retrospectively enrolled. Eight morphologic and 30 texture CT features were extracted from each tumor and combined to obtain three models (morphologic, texture and combined). Data were analyzed using a machine learning classification (WEKA). For each classification process, sensitivity, specificity, accuracy and area under the curve were evaluated. Inter- and intra-reader agreement were also calculated.

RESULTS

52 patients were evaluated. In the validation population, highest performances were obtained by the combined model (SE 85.7%, SP 90.9%, ACC 88.8%, and AUC 0.954) followed by the morphologic (SE 66.6%, SP 81.8%, ACC 76.4%, and AUC 0.742) and texture (SE 50%, SP 72.7%, ACC 64.7%, and AUC 0.613) models. Reproducibility was high of all manual evaluations.

CONCLUSIONS

the AI-based radiomics model using a CT feature demonstrates good predictive performance for preoperative risk stratification of GISTs.

Deep learning and radiomics to predict the mitotic index of gastrointestinal stromal tumors based on multiparametric MRI

Introduction

Preoperative evaluation of the mitotic index (MI) of gastrointestinal stromal tumors (GISTs) represents the basis of individualized treatment of patients. However, the accuracy of conventional preoperative imaging methods is limited. The aim of this study was to develop a predictive model based on multiparametric MRI for preoperative MI prediction.

Methods

A total of 112 patients who were pathologically diagnosed with GIST were enrolled in this study. The dataset was subdivided into the development (n = 81) and test (n = 31) sets based on the time of diagnosis. With the use of T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) map, a convolutional neural network (CNN)-based classifier was developed for MI prediction, which used a hybrid approach based on 2D tumor images and radiomics features from 3D tumor shape. The trained model was tested on an internal test set. Then, the hybrid model was comprehensively tested and compared with the conventional ResNet, shape radiomics classifier, and age plus diameter classifier.

Results

The hybrid model showed good MI prediction ability at the image level; the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and accuracy in the test set were 0.947 (95% confidence interval [CI]: 0.927-0.968), 0.964 (95% CI: 0.930-0.978), and 90.8 (95% CI: 88.0-93.0), respectively. With the average probabilities from multiple samples per patient, good performance was also achieved at the patient level, with AUROC, AUPRC, and accuracy of 0.930 (95% CI: 0.828-1.000), 0.941 (95% CI: 0.792-1.000), and 93.6% (95% CI: 79.3-98.2) in the test set, respectively.

Discussion

The deep learning-based hybrid model demonstrated the potential to be a good tool for the operative and non-invasive prediction of MI in GIST patients.

Gastrointestinal stromal tumors: a comprehensive radiological review

Gastrointestinal stromal tumors (GISTs) originating from the interstitial cells of Cajal in the muscularis propria are the most common mesenchymal tumor of the gastrointestinal tract. Multiple modalities, including computed tomography (CT), magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography, ultrasonography, digital subtraction angiography, and endoscopy, have been performed to evaluate GISTs. CT is most frequently used for diagnosis, staging, surveillance, and response monitoring during molecularly targeted therapy in clinical practice. The diagnosis of GISTs is sometimes challenging because of the diverse imaging findings, such as anatomical location (esophagus, stomach, duodenum, small bowel, colorectum, appendix, and peritoneum), growth pattern, and enhancement pattern as well as the presence of necrosis, calcification, ulceration, early venous return, and metastasis. Imaging findings of GISTs treated with antineoplastic agents are quite different from those of other neoplasms (e.g. adenocarcinomas) because only subtle changes in size are seen even in responsive lesions. Furthermore, the recurrence pattern of GISTs is different from that of other neoplasms. This review discusses the advantages and disadvantages of each imaging modality, describes imaging findings obtained before and after treatment, presents a few cases of complicated GISTs, and discusses recent investigations performed using CT and MRI to predict histological risk grade, gene mutations, and patient outcomes.