Protecting Prostate Cancer Classification From Rectal Artifacts via Targeted Adversarial Training.

Magnetic resonance imaging (MRI)-based deep neural networks (DNN) have been widely developed to perform prostate cancer (PCa) classification. However, in real-world clinical situations, prostate MRIs can be easily impacted by rectal artifacts, which have been found to lead to incorrect PCa classification. Existing DNN-based methods typically do not consider the interference of rectal artifacts on PCa classification, and do not design specific strategy to address this problem. In this study, we proposed a novel Targeted adversarial training with Proprietary Adversarial Samples (TPAS) strategy to defend the PCa classification model against the influence of rectal artifacts. Specifically, based on clinical prior knowledge, we generated proprietary adversarial samples with rectal artifact-pattern adversarial noise, which can severely mislead PCa classification models optimized by the ordinary training strategy. We then jointly exploited the generated proprietary adversarial samples and original samples to train the models. To demonstrate the effectiveness of our strategy, we conducted analytical experiments on multiple PCa classification models. Compared with ordinary training strategy, TPAS can effectively improve the single- and multi-parametric PCa classification at patient, slice and lesion level, and bring substantial gains to recent advanced models. In conclusion, TPAS strategy can be identified as a valuable way to mitigate the influence of rectal artifacts on deep learning models for PCa classification.

Correction to: Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Image.

Presents corrections to the paper, Multi-View Feature Transformation Based SVM+ for Computer-Aided Diagnosis of Liver Cancers With Ultrasound Image.

Multi-branch CNN and grouping cascade attention for medical image classification.

Visual Transformers(ViT) have made remarkable achievements in the field of medical image analysis. However, ViT-based methods have poor classification results on some small-scale medical image classification datasets. Meanwhile, many ViT-based models sacrifice computational cost for superior performance, which is a great challenge in practical clinical applications. In this paper, we propose an efficient medical image classification network based on an alternating mixture of CNN and Transformer tandem, which is called Eff-CTNet. Specifically, the existing ViT-based method still mainly relies on multi-head self-attention (MHSA). Among them, the attention maps of MHSA are highly similar, which leads to computational redundancy. Therefore, we propose a group cascade attention (GCA) module to split the feature maps, which are provided to different attention heads to further improves the diversity of attention and reduce the computational cost. In addition, we propose an efficient CNN (EC) module to enhance the ability of the model and extract the local detail information in medical images. Finally, we connect them and design an efficient hybrid medical image classification network, namely Eff-CTNet. Extensive experimental results show that our Eff-CTNet achieves advanced classification performance with less computational cost on three public medical image classification datasets.

Automated detection, labelling and radiological grading of clinical spinal MRIs.

Spinal magnetic resonance (MR) scans are a vital tool for diagnosing the cause of back pain for many diseases and conditions. However, interpreting clinically useful information from these scans can be challenging, time-consuming and hard to reproduce across different radiologists. In this paper, we alleviate these problems by introducing a multi-stage automated pipeline for analysing spinal MR scans. This pipeline first detects and labels vertebral bodies across several commonly used sequences (e.g. T1w, T2w and STIR) and fields of view (e.g. lumbar, cervical, whole spine). Using these detections it then performs automated diagnosis for several spinal disorders, including intervertebral disc degenerative changes in T1w and T2w lumbar scans, and spinal metastases, cord compression and vertebral fractures. To achieve this, we propose a new method of vertebrae detection and labelling, using vector fields to group together detected vertebral landmarks and a language-modelling inspired beam search to determine the corresponding levels of the detections. We also employ a new transformer-based architecture to perform radiological grading which incorporates context from multiple vertebrae and sequences, as a real radiologist would. The performance of each stage of the pipeline is tested in isolation on several clinical datasets, each consisting of 66 to 421 scans. The outputs are compared to manual annotations of expert radiologists, demonstrating accurate vertebrae detection across a range of scan parameters. Similarly, the model's grading predictions for various types of disc degeneration and detection of spinal metastases closely match those of an expert radiologist. To aid future research, our code and trained models are made publicly available.

Edge and dense attention U-net for atrial scar segmentation in LGE-MRI.

The segmentation of atrial scars in LGE-MRI images has huge potential value for clinical diagnosis and subsequent treatment. In clinical practice, atrial scars are usually manually calibrated by experienced experts, which is time-consuming and prone to errors. However, automatic segmentation also faces difficulties due to myocardial scars' small size and variable shape. The present study introduces a dual branch network, incorporating edge attention, and deep supervision strategy. Edge attention is introduced to fully utilize the spatial relationship between the scar and the atrium. Besides, dense attention is embedded in bottom layer to solve feature disappearance. At the same time, deep supervision accelerates the convergence of the model and improves segmentation accuracy. The experiments were conducted on the 2022 atrial and scar segmentation challenge dataset. The results demonstrate that the proposed method has achieved superior performance.

Computer-aided diagnosis system for grading brain tumor using histopathology images based on color and texture features.

BACKGROUND: Cancer pathology shows disease development and associated molecular features. It provides extensive phenotypic information that is cancer-predictive and has potential implications for planning treatment. Based on the exceptional performance of computational approaches in the field of digital pathogenic, the use of rich phenotypic information in digital pathology images has enabled us to identify low-level gliomas (LGG) from high-grade gliomas (HGG). Because the differences between the textures are so slight, utilizing just one feature or a small number of features produces poor categorization results. METHODS: In this work, multiple feature extraction methods that can extract distinct features from the texture of histopathology image data are used to compare the classification outcomes. The successful feature extraction algorithms GLCM, LBP, multi-LBGLCM, GLRLM, color moment features, and RSHD have been chosen in this paper. LBP and GLCM algorithms are combined to create LBGLCM. The LBGLCM feature extraction approach is extended in this study to multiple scales using an image pyramid, which is defined by sampling the image both in space and scale. The preprocessing stage is first used to enhance the contrast of the images and remove noise and illumination effects. The feature extraction stage is then carried out to extract several important features (texture and color) from histopathology images. Third, the feature fusion and reduction step is put into practice to decrease the number of features that are processed, reducing the computation time of the suggested system. The classification stage is created at the end to categorize various brain cancer grades. We performed our analysis on the 821 whole-slide pathology images from glioma patients in the Cancer Genome Atlas (TCGA) dataset. Two types of brain cancer are included in the dataset: GBM and LGG (grades II and III). 506 GBM images and 315 LGG images are included in our analysis, guaranteeing representation of various tumor grades and histopathological features. RESULTS: The fusion of textural and color characteristics was validated in the glioma patients using the 10-fold cross-validation technique with an accuracy equals to 95.8%, sensitivity equals to 96.4%, DSC equals to 96.7%, and specificity equals to 97.1%. The combination of the color and texture characteristics produced significantly better accuracy, which supported their synergistic significance in the predictive model. The result indicates that the textural characteristics can be an objective, accurate, and comprehensive glioma prediction when paired with conventional imagery. CONCLUSION: The results outperform current approaches for identifying LGG from HGG and provide competitive performance in classifying four categories of glioma in the literature. The proposed model can help stratify patients in clinical studies, choose patients for targeted therapy, and customize specific treatment schedules.

STC-UNet: renal tumor segmentation based on enhanced feature extraction at different network levels.

Renal tumors are one of the common diseases of urology, and precise segmentation of these tumors plays a crucial role in aiding physicians to improve diagnostic accuracy and treatment effectiveness. Nevertheless, inherent challenges associated with renal tumors, such as indistinct boundaries, morphological variations, and uncertainties in size and location, segmenting renal tumors accurately remains a significant challenge in the field of medical image segmentation. With the development of deep learning, substantial achievements have been made in the domain of medical image segmentation. However, existing models lack specificity in extracting features of renal tumors across different network hierarchies, which results in insufficient extraction of renal tumor features and subsequently affects the accuracy of renal tumor segmentation. To address this issue, we propose the Selective Kernel, Vision Transformer, and Coordinate Attention Enhanced U-Net (STC-UNet). This model aims to enhance feature extraction, adapting to the distinctive characteristics of renal tumors across various network levels. Specifically, the Selective Kernel modules are introduced in the shallow layers of the U-Net, where detailed features are more abundant. By selectively employing convolutional kernels of different scales, the model enhances its capability to extract detailed features of renal tumors across multiple scales. Subsequently, in the deeper layers of the network, where feature maps are smaller yet contain rich semantic information, the Vision Transformer modules are integrated in a non-patch manner. These assist the model in capturing long-range contextual information globally. Their non-patch implementation facilitates the capture of fine-grained features, thereby achieving collaborative enhancement of global-local information and ultimately strengthening the model's extraction of semantic features of renal tumors. Finally, in the decoder segment, the Coordinate Attention modules embedding positional information are proposed aiming to enhance the model's feature recovery and tumor region localization capabilities. Our model is validated on the KiTS19 dataset, and experimental results indicate that compared to the baseline model, STC-UNet shows improvements of 1.60%, 2.02%, 2.27%, 1.18%, 1.52%, and 1.35% in IoU, Dice, Accuracy, Precision, Recall, and F1-score, respectively. Furthermore, the experimental results demonstrate that the proposed STC-UNet method surpasses other advanced algorithms in both visual effectiveness and objective evaluation metrics.

Weakly Supervised Deep Learning in Radiology.

Deep learning (DL) is currently the standard artificial intelligence tool for computer-based image analysis in radiology. Traditionally, DL models have been trained with strongly supervised learning methods. These methods depend on reference standard labels, typically applied manually by experts. In contrast, weakly supervised learning is more scalable. Weak supervision comprises situations in which only a portion of the data are labeled (incomplete supervision), labels refer to a whole region or case as opposed to a precisely delineated image region (inexact supervision), or labels contain errors (inaccurate supervision). In many applications, weak labels are sufficient to train useful models. Thus, weakly supervised learning can unlock a large amount of otherwise unusable data for training DL models. One example of this is using large language models to automatically extract weak labels from free-text radiology reports. Here, we outline the key concepts in weakly supervised learning and provide an overview of applications in radiologic image analysis. With more fundamental and clinical translational work, weakly supervised learning could facilitate the uptake of DL in radiology and research workflows by enabling large-scale image analysis and advancing the development of new DL-based biomarkers.

Enhancing brain tumor segmentation in MRI images using the IC-net algorithm framework.

Brain tumors, often referred to as intracranial tumors, are abnormal tissue masses that arise from rapidly multiplying cells. During medical imaging, it is essential to separate brain tumors from healthy tissue. The goal of this paper is to improve the accuracy of separating tumorous regions from healthy tissues in medical imaging, specifically for brain tumors in MRI images which is difficult in the field of medical image analysis. In our research work, we propose IC-Net (Inverted-C), a novel semantic segmentation architecture that combines elements from various models to provide effective and precise results. The architecture includes Multi-Attention (MA) blocks, Feature Concatenation Networks (FCN), Attention-blocks which performs crucial tasks in improving brain tumor segmentation. MA-block aggregates multi-attention features to adapt to different tumor sizes and shapes. Attention-block is focusing on key regions, resulting in more effective segmentation in complex images. FCN-block captures diverse features, making the model more robust to various characteristics of brain tumor images. Our proposed architecture is used to accelerate the training process and also to address the challenges posed by the diverse nature of brain tumor images, ultimately leads to potentially improved segmentation performance. IC-Net significantly outperforms the typical U-Net architecture and other contemporary effective segmentation techniques. On the BraTS 2020 dataset, our IC-Net design obtained notable outcomes in Accuracy, Loss, Specificity, Sensitivity as 99.65, 0.0159, 99.44, 99.86 and DSC (core, whole, and enhancing tumors as 0.998717, 0.888930, 0.866183) respectively.

A semantic feature enhanced YOLOv5-based network for polyp detection from colonoscopy images.

Colorectal cancer (CRC) is a common digestive system tumor with high morbidity and mortality worldwide. At present, the use of computer-assisted colonoscopy technology to detect polyps is relatively mature, but it still faces some challenges, such as missed or false detection of polyps. Therefore, how to improve the detection rate of polyps more accurately is the key to colonoscopy. To solve this problem, this paper proposes an improved YOLOv5-based cancer polyp detection method for colorectal cancer. The method is designed with a new structure called P-C3 incorporated into the backbone and neck network of the model to enhance the expression of features. In addition, a contextual feature augmentation module was introduced to the bottom of the backbone network to increase the receptive field for multi-scale feature information and to focus on polyp features by coordinate attention mechanism. The experimental results show that compared with some traditional target detection algorithms, the model proposed in this paper has significant advantages for the detection accuracy of polyp, especially in the recall rate, which largely solves the problem of missed detection of polyps. This study will contribute to improve the polyp/adenoma detection rate of endoscopists in the process of colonoscopy, and also has important significance for the development of clinical work.

Potential Role of Generative Adversarial Networks in Enhancing Brain Tumors.

PURPOSE: Contrast enhancement is necessary for visualizing, diagnosing, and treating brain tumors. Through this study, we aimed to examine the potential role of general adversarial neural networks in generating artificial intelligence-based enhancement of tumors using a lightweight model. PATIENTS AND METHODS: A retrospective study was conducted on magnetic resonance imaging scans of patients diagnosed with brain tumors between 2020 and 2023. A generative adversarial neural network was built to generate images that would mimic the real contrast enhancement of these tumors. The performance of the neural network was evaluated quantitatively by VGG-16, ResNet, binary cross-entropy loss, mean absolute error, mean squared error, and structural similarity index measures. Regarding the qualitative evaluation, nine cases were randomly selected from the test set and were used to build a short satisfaction survey for experienced medical professionals. RESULTS: One hundred twenty-nine patients with 156 scans were identified from the hospital database. The data were randomly split into a training set and validation set (90%) and a test set (10%). The VGG loss function for training, validation, and test sets were 2,049.8, 2,632.6, and 4,276.9, respectively. Additionally, the structural similarity index measured 0.366, 0.356, and 0.3192, respectively. At the time of submitting the article, 23 medical professionals responded to the survey. The median overall satisfaction score was 7 of 10. CONCLUSION: Our network would open the door for using lightweight models in performing artificial contrast enhancement. Further research is necessary in this field to reach the point of clinical practicality.

Evaluating the efficacy of few-shot learning for GPT-4Vision in neurodegenerative disease histopathology: A comparative analysis with convolutional neural network model.

AIMS: Recent advances in artificial intelligence, particularly with large language models like GPT-4Vision (GPT-4V)-a derivative feature of ChatGPT-have expanded the potential for medical image interpretation. This study evaluates the accuracy of GPT-4V in image classification tasks of histopathological images and compares its performance with a traditional convolutional neural network (CNN). METHODS: We utilised 1520 images, including haematoxylin and eosin staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer's disease (AD), progressive supranuclear palsy (PSP) and corticobasal degeneration (CBD). We assessed GPT-4V's performance using multi-step prompts to determine how textual context influences image interpretation. We also employed few-shot learning to enhance improvements in GPT-4V's diagnostic performance in classifying three specific tau lesions-astrocytic plaques, neuritic plaques and tufted astrocytes-and compared the outcomes with the CNN model YOLOv8. RESULTS: GPT-4V accurately recognised staining techniques and tissue origin but struggled with specific lesion identification. The interpretation of images was notably influenced by the provided textual context, which sometimes led to diagnostic inaccuracies. For instance, when presented with images of the motor cortex, the diagnosis shifted inappropriately from AD to CBD or PSP. However, few-shot learning markedly improved GPT-4V's diagnostic capabilities, enhancing accuracy from 40% in zero-shot learning to 90% with 20-shot learning, matching the performance of YOLOv8, which required 100-shot learning to achieve the same accuracy. CONCLUSIONS: Although GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its performance. This approach is especially promising for neuropathology, where acquiring extensive labelled datasets is often challenging.

Intraindividual Comparison of Different Methods for Automated BPE Assessment at Breast MRI: A Call for Standardization.

Background The level of background parenchymal enhancement (BPE) at breast MRI provides predictive and prognostic information and can have diagnostic implications. However, there is a lack of standardization regarding BPE assessment. Purpose To investigate how well results of quantitative BPE assessment methods correlate among themselves and with assessments made by radiologists experienced in breast MRI. Materials and Methods In this pseudoprospective analysis of 5773 breast MRI examinations from 3207 patients (mean age, 60 years ± 10 [SD]), the level of BPE was prospectively categorized according to the Breast Imaging Reporting and Data System by radiologists experienced in breast MRI. For automated extraction of BPE, fibroglandular tissue (FGT) was segmented in an automated pipeline. Four different published methods for automated quantitative BPE extractions were used: two methods (A and B) based on enhancement intensity and two methods (C and D) based on the volume of enhanced FGT. The results from all methods were correlated, and agreement was investigated in comparison with the respective radiologist-based categorization. For surrogate validation of BPE assessment, how accurately the methods distinguished premenopausal women with (n = 50) versus without (n = 896) antihormonal treatment was determined. Results Intensity-based methods (A and B) exhibited a correlation with radiologist-based categorization of 0.56 ± 0.01 and 0.55 ± 0.01, respectively, and volume-based methods (C and D) had a correlation of 0.52 ± 0.01 and 0.50 ± 0.01 (P < .001). There were notable correlation differences (P < .001) between the BPE determined with the four methods. Among the four quantitation methods, method D offered the highest accuracy for distinguishing women with versus without antihormonal therapy (P = .01). Conclusion Results of different methods for quantitative BPE assessment agree only moderately among themselves or with visual categories reported by experienced radiologists; intensity-based methods correlate more closely with radiologists' ratings than volume-based methods. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Mann in this issue.

Review of speckle tracking analysis to measure the size, shape, and contractility of the fetal heart in fetuses with congenital heart defects.

Evaluation of the fetal heart involves two approaches. The first describes a screening protocol in which the heart is imaged in transverse planes that includes the four-chamber view (4CV), left and right outflow tracts, and the 3-vessel-tracheal view. The second approach is a fetal echocardiogram that requires additional cardiac images as well as evaluating ventricular function using diagnostic tools such as M-mode and pulsed Doppler ultrasound. Speckle tracking analysis of the ventricular and atrial endocardium of the fetal heart has focused primarily on computing longitudinal global strain. However, the technology enabling this measurement to occur has recently been adapted to enable the clinician to obtain numerous additional measurements of the size, shape, and contractility of the ventricles and atrial chambers. By using the increased number of measurements derived from speckle tracking analysis, we have reported the ability to screen for tetralogy of Fallot, D-transposition of the great arteries (D-TGA), and coarctation of the aorta by only imaging the 4CV. In addition, we have found that measurements derived from speckle tracking analysis of the ventricular and atrial chambers can be used to compute the risk for emergent neonatal balloon atrial septostomy in fetuses with D-TGA. The purpose of this review is to consolidate our experience in one source to provide perspective on the benefits of speckle tracking analysis to measure the size, shape, and contractility of the ventricles and atria imaged in the 4CV in fetuses with congenital heart defects.

Comparing Diagnostic Accuracy of Radiologists versus GPT-4V and Gemini Pro Vision Using Image Inputs from Diagnosis Please Cases.

Background The diagnostic abilities of multimodal large language models (LLMs) using direct image inputs and the impact of the temperature parameter of LLMs remain unexplored. Purpose To investigate the ability of GPT-4V and Gemini Pro Vision in generating differential diagnoses at different temperatures compared with radiologists using Radiology Diagnosis Please cases. Materials and Methods This retrospective study included Diagnosis Please cases published from January 2008 to October 2023. Input images included original images and captures of the textual patient history and figure legends (without imaging findings) from PDF files of each case. The LLMs were tasked with providing three differential diagnoses, repeated five times at temperatures 0, 0.5, and 1. Eight subspecialty-trained radiologists solved cases. An experienced radiologist compared generated and final diagnoses, considering the result correct if the generated diagnoses included the final diagnosis after five repetitions. Accuracy was assessed across models, temperatures, and radiology subspecialties, with statistical significance set at P < .007 after Bonferroni correction for multiple comparisons across the LLMs at the three temperatures and with radiologists. Results A total of 190 cases were included in neuroradiology (n = 53), multisystem (n = 27), gastrointestinal (n = 25), genitourinary (n = 23), musculoskeletal (n = 17), chest (n = 16), cardiovascular (n = 12), pediatric (n = 12), and breast (n = 5) subspecialties. Overall accuracy improved with increasing temperature settings (0, 0.5, 1) for both GPT-4V (41% [78 of 190 cases], 45% [86 of 190 cases], 49% [93 of 190 cases], respectively) and Gemini Pro Vision (29% [55 of 190 cases], 36% [69 of 190 cases], 39% [74 of 190 cases], respectively), although there was no evidence of a statistically significant difference after Bonferroni adjustment (GPT-4V, P = .12; Gemini Pro Vision, P = .04). The overall accuracy of radiologists (61% [115 of 190 cases]) was higher than that of Gemini Pro Vision at temperature 1 (T1) (P < .001), while no statistically significant difference was observed between radiologists and GPT-4V at T1 after Bonferroni adjustment (P = .02). Radiologists (range, 45%-88%) outperformed the LLMs at T1 (range, 24%-75%) in most subspecialties. Conclusion Using direct radiologic image inputs, GPT-4V and Gemini Pro Vision showed improved diagnostic accuracy with increasing temperature settings. Although GPT-4V slightly underperformed compared with radiologists, it nonetheless demonstrated promising potential as a supportive tool in diagnostic decision-making. © RSNA, 2024 See also the editorial by Nishino and Ballard in this issue.

DHAFormer: Dual-channel hybrid attention network with transformer for polyp segmentation.

The accurate early diagnosis of colorectal cancer significantly relies on the precise segmentation of polyps in medical images. Current convolution-based and transformer-based segmentation methods show promise but still struggle with the varied sizes and shapes of polyps and the often low contrast between polyps and their background. This research introduces an innovative approach to confronting the aforementioned challenges by proposing a Dual-Channel Hybrid Attention Network with Transformer (DHAFormer). Our proposed framework features a multi-scale channel fusion module, which excels at recognizing polyps across a spectrum of sizes and shapes. Additionally, the framework's dual-channel hybrid attention mechanism is innovatively conceived to reduce background interference and improve the foreground representation of polyp features by integrating local and global information. The DHAFormer demonstrates significant improvements in the task of polyp segmentation compared to currently established methodologies.

Deep Learning Reconstruction of Accelerated MRI: False-Positive Cartilage Delamination Inserted in MRI Arthrography Under Traction.

OBJECTIVES: The radiological imaging industry is developing and starting to offer a range of novel artificial intelligence software solutions for clinical radiology. Deep learning reconstruction of magnetic resonance imaging data seems to allow for the acceleration and undersampling of imaging data. Resulting reduced acquisition times would lead to greater machine utility and to greater cost-efficiency of machine operations. MATERIALS AND METHODS: Our case shows images from magnetic resonance arthrography under traction of the right hip joint from a 30-year-old, otherwise healthy, male patient. RESULTS: The undersampled image data when reconstructed by a deep learning tool can contain false-positive cartilage delamination and false-positive diffuse cartilage defects. CONCLUSIONS: In the future, precision of this novel technology will have to be put to thorough testing. Bias of systems, in particular created by the choice of training data, will have to be part of those assessments.