Journal of Imaging Informatics in Medicine

Robust Radiomics Models for Predicting HIFU Prognosis in Uterine Fibroids Using SHAP Explanations: A Multicenter Cohort Study

This study sought to develop and validate different machine learning (ML) models that leverage non-contrast MRI radiomics to predict the degree of nonperfusion volume ratio (NVPR) of high-intensity focused ultrasound (HIFU) treatment for uterine fibroids, equipping clinicians with an early prediction tool for decision-making. This study conducted a retrospective analysis on 221 patients with uterine fibroids who received HIFU treatment and were divided into a training set (N = 117), internal validation (N = 49), and an external test set (N = 55). The 851 radiomics features were extracted from T2-weighted imaging (T2WI), and the max-relevance and min-redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection. Several ML models were constructed by logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM). These models underwent internal and external validation, and the best model's feature significance was assessed via the Shapley additive explanations (SHAP) method. Four significant non-contrast MRI radiomics features were identified, with the SVM model outperforming others in both internal and external validations, and the AUCs of the T2WI models were 0.860, 0.847, and 0.777, respectively. SHAP analysis highlighted five critical predictors of postoperative NVPR degree, encompassing two radiomics features from non-contrast MRI and three clinical data indicators. The SVM model combining radiomics features and clinical parameters effectively predicts NVPR degree post-HIFU, which enables timely and effective interventions of HIFU.

Application of TransUnet Deep Learning Model for Automatic Segmentation of Cervical Cancer in Small-Field T2WI Images

Effective segmentation of cervical cancer tissue from magnetic resonance (MR) images is crucial for automatic detection, staging, and treatment planning of cervical cancer. This study develops an innovative deep learning model to enhance the automatic segmentation of cervical cancer lesions. We obtained 4063 T2WI small-field sagittal, coronal, and oblique axial images from 222 patients with pathologically confirmed cervical cancer. Using this dataset, we employed a convolutional neural network (CNN) along with TransUnet models for segmentation training and evaluation of cervical cancer tissues. In this approach, CNNs are leveraged to extract local information from MR images, whereas Transformers capture long-range dependencies related to shape and structural information, which are critical for precise segmentation. Furthermore, we developed three distinct segmentation models based on coronal, axial, and sagittal T2WI within a small field of view using multidirectional MRI techniques. The dice similarity coefficient (DSC) and mean Hausdorff distance (AHD) were used to assess the performance of the models in terms of segmentation accuracy. The average DSC and AHD values obtained using the TransUnet model were 0.7628 and 0.8687, respectively, surpassing those obtained using the U-Net model by margins of 0.0033 and 0.3479, respectively. The proposed TransUnet segmentation model significantly enhances the accuracy of cervical cancer tissue delineation compared to alternative models, demonstrating superior performance in overall segmentation efficacy. This methodology can improve clinical diagnostic efficiency as an automated image analysis tool tailored for cervical cancer diagnosis.

Improving Ovarian Cancer Subtyping with Computer Vision Models on Tiled Histopathological Images

Ovarian cancer remains one of the most challenging cancers to diagnose due to its non-specific symptoms, lack of reliable screening tests, and the complexity of detecting abnormalities. Accurate subtype classification is crucial for personalised treatment and improved patient outcomes. In this study, we developed a machine learning pipeline fine-tuning pre-trained computer vision models to classify ovarian cancer subtypes from whole slide images (WSI). Using targeted tissue masks for necrosis, stroma, and tumour regions as a proof of concept, we demonstrated the efficacy of tiling masked regions to transform a complex detection-then-classification problem into a simpler classification task. Our method achieved high accuracy in tile-level classification, with a subsequent extension to subtype classification via majority voting on tiled images. Precision exceeds 90% across subtypes, which highlights the potential of scalable, automated systems to assist in ovarian cancer diagnostics. These findings contribute to the broader field of computational pathology, paving the way for enhanced diagnostic consistency and accessibility in clinical settings.

NETosis Genes and Pathomic Signature: A Novel Prognostic Marker for Ovarian Serous Cystadenocarcinoma

To evaluate the prognostic significance and molecular mechanism of NETosis markers in ovarian serous cystadenocarcinoma (OSC), we constructed a machine learning-based pathomic model utilizing hematoxylin and eosin (H&E) slides. We analyzed 333 patients with OSC from The Cancer Genome Atlas for prognostic-related neutrophil extracellular trap formation (NETosis) genes through bioinformatics analysis. Pathomic features were extracted from 54 cases with complete pathological images, genetic matrices, and clinical information. Two pathomic prognostic models were constructed using support vector machine (SVM) and logistic regression (LR) algorithms. Additionally, we established a predictive scoring system that integrated pathomic scores based on the NETcluster subtypes and clinical signature. We identified four NETosis genes significantly correlated with OSC prognosis, which were functionally associated with immune response, somatic mutations, tumor invasion, and metastasis. Five robust pathomic features were selected for overall survival prediction. The LR and SVM pathomic models demonstrated strong predictive performance for the NETcluster subtype classification through five-fold cross-validation. Time-dependent ROC analysis revealed excellent prognostic capability of the LR pathomic model's score for the overall survival (AUC values of 0.658, 0.761, and 0.735 at 36, 48, and 60 months, respectively), further validated by Kaplan-Meier analysis. The expression levels of NETosis genes greatly affected OSC patients' prognoses. The pathomic analysis of H&E slide pathological images provides an effective approach for predicting both NETcluster subtype and overall survival in OSC patients.

Analysis of Diagnostic Efficacy of the International Ovarian Tumor Analysis ADNEX Model and the ACR O-RADS US (Ovarian-Adnexal Reporting and Data System) for Benign and Malignant Ovarian Tumors: A Retrospective Study in a Tumor Center in Northeast China

This study is to analyze and compare the diagnostic efficacy of the ADNEX model and O-RADS in Northeast China for benign and malignant ovarian-adnexal tumors. From July 2020 to February 2022, ultrasound images of 312 ovarian-adnexal masses included in the study were analyzed retrospectively, and the properties of these masses were identified using the ADNEX model and O-RADS. The diagnostic efficiency of the ADNEX model and O-RADS was analyzed using a ROC curve, and the capacities of the two models in differentiating benign and malignant ovarian masses at the optimum cutoff value were compared, as well as the consistency of their diagnosis results was evaluated. The study included 312 ovarian-adnexal masses, including 145 malignant masses and 167 benign masses from 287 patients with an average age of (46.8 ± 11.3) years. The AUC of the ADNEX model was 0.974, and the optimum cutoff value was the risk value > 24.2%, with the corresponding sensitivity and specificity being 97.93 and 86.83, respectively. The AUC of the O-RADS was 0.956, and the optimum cutoff value was > O-RADS 3, with the corresponding sensitivity and specificity being 97.24 and 85.03, respectively. The AUCs of the two models were 0.924 and 0.911 at the optimum cutoff values, with no statistical differences between them (P = 0.284). Consistency analysis: the kappa values of the two models for the determination and pathological results of masses were 0.840 and 0.815, respectively, and that for the diagnostic outcomes was 0.910. Both the ADNEX model and O-RADS had good diagnostic performance in people from Northeast China. Their diagnostic capabilities were similar, and diagnostic results were highly consistent at the optimum cutoff values.

From CNN to Transformer: A Review of Medical Image Segmentation Models

Medical image segmentation is an important step in medical image analysis, especially as a crucial prerequisite for efficient disease diagnosis and treatment. The use of deep learning for image segmentation has become a prevalent trend. The widely adopted approach currently is U-Net and its variants. Moreover, with the remarkable success of pre-trained models in natural language processing tasks, transformer-based models like TransUNet have achieved desirable performance on multiple medical image segmentation datasets. Recently, the Segment Anything Model (SAM) and its variants have also been attempted for medical image segmentation. In this paper, we conduct a survey of the most representative seven medical image segmentation models in recent years. We theoretically analyze the characteristics of these models and quantitatively evaluate their performance on Tuberculosis Chest X-rays, Ovarian Tumors, and Liver Segmentation datasets. Finally, we discuss the main challenges and future trends in medical image segmentation. Our work can assist researchers in the related field to quickly establish medical segmentation models tailored to specific regions.

Predicting Mismatch Repair Deficiency Status in Endometrial Cancer through Multi-Resolution Ensemble Learning in Digital Pathology

For molecular classification of endometrial carcinoma, testing for mismatch repair (MMR) status is becoming a routine process. Mismatch repair deficiency (MMR-D) is caused by loss of expression in one or more of the 4 major MMR proteins: MLH1, MSH2, MSH6, PHS2. Over 30% of patients with endometrial cancer have MMR-D. Determining the MMR status holds significance as individuals with MMR-D are potential candidates for immunotherapy. Pathological whole slide image (WSI) of endometrial cancer with immunohistochemistry results of MMR proteins were gathered. Color normalization was applied to the tiles using a CycleGAN-based network. The WSI was divided into tiles at three different magnifications (2.5 × , 5 × , and 10 ×). Three distinct networks of the same architecture were employed to include features from all three magnification levels and were stacked for ensemble learning. Three architectures, InceptionResNetV2, EfficientNetB2, and EfficientNetB3 were employed and subjected to comparison. The per-tile results were gathered to classify MMR status in the WSI, and prediction accuracy was evaluated using the following performance metrics: AUC, accuracy, sensitivity, and specificity. The EfficientNetB2 was able to make predictions with an AUC of 0.821, highest among the three architectures, and an overall AUC range of 0.767 - 0.821 was reported across the three architectures. In summary, our study successfully predicted MMR classification from pathological WSIs in endometrial cancer through a multi-resolution ensemble learning approach, which holds the potential to facilitate swift decisions on tailored treatment, such as immunotherapy, in clinical settings.

A Comparative Study of Performance Between Federated Learning and Centralized Learning Using Pathological Image of Endometrial Cancer

Federated learning, an innovative artificial intelligence training method, offers a secure solution for institutions to collaboratively develop models without sharing raw data. This approach offers immense promise and is particularly advantageous for domains dealing with sensitive information, such as patient data. However, when confronted with a distributed data environment, challenges arise due to data paucity or inherent heterogeneity, potentially impacting the performance of federated learning models. Hence, scrutinizing the efficacy of this method in such intricate settings is indispensable. To address this, we harnessed pathological image datasets of endometrial cancer from four hospitals for training and evaluating the performance of a federated learning model and compared it with a centralized learning model. With optimal processing techniques (data augmentation, color normalization, and adaptive optimizer), federated learning exhibited lower precision but higher recall and Dice similarity coefficient (DSC) than centralized learning. Hence, considering the critical importance of recall in the context of medical image processing, federated learning is demonstrated as a viable and applicable approach in this field, offering advantages in terms of both performance and data security.

A Hybrid Model-Based Clinicopathological Features and Radiomics Based on Conventional MRI for Predicting Lymph Node Metastasis and DFS in Cervical Cancer

This study aimed to improve the accuracy of the diagnosis of lymph node metastasis (LNM) and prediction of patient prognosis in cervical cancer patients using a hybrid model based on MRI and clinical aspects. We retrospectively analyzed routine MR data from 485 patients with pathologically confirmed cervical cancer from January 2014 to June 2021. The data were divided into a training cohort (N = 261), internal cohort (N = 113), and external validation cohort (n = 111). A total of 2194 features were extracted from each ROI from T2WI and CE-T1WI. The clinical model (M1) was built with clinicopathological features including squamous cell carcinoma antigen, MRI-reported LNM, maximal tumor diameter (MTD). The radiomics model (M2) was built with four radiomics features. The hybrid model (M3) was constructed with squamous cell carcinoma antigen, MRI-reported LNM, MTD which consists of M1 and four radiomics features which consist of M2. GBDT algorithms were used to create the scores of M1 (clinical-score, C-score), M2 (radiomic score, R-score), and M3 (hybrid-score, H-score). M3 showed good performance in the training cohort (AUCs, M3 vs. M1 vs. M2, 0.917 vs. 0.830 vs. 0.788), internal validation cohorts (AUCs, M3 vs. M1 vs. M2, 0.872 vs. 0.750 vs. 0.739), and external validation cohort (AUCs, M3 vs. M1 vs. M2, 0.907 vs. 0.811 vs. 0.785). In addition, higher scores were significantly associated with worse disease-free survival (DFS) in the training cohort and the internal validation cohort (C-score, P = 0.001; R-score, P = 0.002; H-score, P = 0.006). Radiomics models can accurately predict LNM status in patients with cervical cancer. The hybrid model, which incorporates clinical and radiomics features, is a novel way to enhance diagnostic performance and predict the prognosis of cervical cancer.

Reliable Delineation of Clinical Target Volumes for Cervical Cancer Radiotherapy on CT/MR Dual-Modality Images

Accurate delineation of the clinical target volume (CTV) is a crucial prerequisite for safe and effective radiotherapy characterized. This study addresses the integration of magnetic resonance (MR) images to aid in target delineation on computed tomography (CT) images. However, obtaining MR images directly can be challenging. Therefore, we employ AI-based image generation techniques to "intelligentially generate" MR images from CT images to improve CTV delineation based on CT images. To generate high-quality MR images, we propose an attention-guided single-loop image generation model. The model can yield higher-quality images by introducing an attention mechanism in feature extraction and enhancing the loss function. Based on the generated MR images, we propose a CTV segmentation model fusing multi-scale features through image fusion and a hollow space pyramid module to enhance segmentation accuracy. The image generation model used in this study improves the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) from 14.87 and 0.58 to 16.72 and 0.67, respectively, and improves the feature distribution distance and learning-perception image similarity from 180.86 and 0.28 to 110.98 and 0.22, achieving higher quality image generation. The proposed segmentation method demonstrates high accuracy, compared with the FCN method, the intersection over union ratio and the Dice coefficient are improved from 0.8360 and 0.8998 to 0.9043 and 0.9473, respectively. Hausdorff distance and mean surface distance decreased from 5.5573 mm and 2.3269 mm to 4.7204 mm and 0.9397 mm, respectively, achieving clinically acceptable segmentation accuracy. Our method might reduce physicians' manual workload and accelerate the diagnosis and treatment process while decreasing inter-observer variability in identifying anatomical structures.