Lesion Contour Research Articles

Automated Detection of Drusenoid Pigment Epithelial Detachments From Spectral-Domain Optical Coherence Tomography in Patients With AMD.

This study aimed to develop an algorithm for automated detection of drusenoid pigment epithelial detachments (DPEDs) in optical coherence tomography (OCT) volumes of patients with age-related macular degeneration (AMD) and to compare its performance against traditional reading center grading on color-fundus photographs (CFPs). Eyes with a range of AMD severities, excluding neovascular disease, were imaged using spectral-domain OCT (SD-OCT) and paired CFPs and were followed annually for up to 5years. DPEDs were automatically identified by segmenting the retinal pigment epithelium (RPE) and Bruch's membrane (BM) layers from the SD-OCT volumes and imposing both a minimum RPE BM height (>75 µm) and a two-dimensional length requirement (>433 µm). Comparisons in detection rates and contoured areas were made between the algorithmic SD-OCT detections and manually graded and contoured CFPs. Of the 1602 visits for the 323 eyes, the automated OCT algorithm identified 139 visits (8.7%) from 50 eyes with DPED, but a reading center review of paired CFPs identified 23 visits (1.4%) from nine eyes as having DPEDs. Eyes identified with DPEDs on OCT received nine-step AMD severity scores ranging from 6 to 10, and those scores had occurrence ratios of 23/160 (14%), 89/226 (39%), 24/99 (24%), 2/63 (3%), and 1/29 (3%), respectively. On a subset of 25 visits that also underwent manual contouring of DPED lesions in CFP, the Pearson correlation coefficient for DPED areas observed by OCT and CFP was 0.85. Our analysis shows the feasibility of using OCT scans to objectively detect features that historically have been detected qualitatively by expert graders on CFPs. Automated detection and quantitation of high-risk features can facilitate screening patients for clinical-trial enrollment and could serve as an outcome metric [T1 (Translation-to-Humans) and T4 (Translation-to-Population-Health)].

NIMG-52. ARTIFICIAL INTELLIGENCE-BASED VOLUMETRIC KINETICS FOR EVALUATING TREATMENT RESPONSE IN IDH-MUTANT GLIOMA TREATED WITH IMMUNOTHERAPY

Abstract BACKGROUND Interpretating radiographic findings of glioma patients receiving immunotherapy is challenging. Repeated imaging is often required for clinical decisions, potentially delaying next line of treatment. Here we assess a glioma segmentation AI model to evaluate treatment response in IDH-mutant glioma patients receiving nivolumab. METHODS Clinical magnetic resonance imaging (MRI)s from twenty-nine patients enrolled in a clinical trial (NCT03718767) were retrospectively analyzed. All patients had at least two sequential MRIs, including baseline study. T2, T1 (pre/post-contrast), and T2 FLAIR MRI sequences were pre-processed using publicly available AI-based whole-brain segmentation models. Lesion contours were derived from a validated 4-class brain tumor segmentation AI model, distinguishing healthy brain parenchyma, peri-lesional edema, non-contrast enhancing volume (NEV), and contrast-enhancing volume (CEV). Total lesion burden volume (TLBV=NEV + CEV + Edema) was also calculated. Growth rates between responders (R) and non-responders (NR), defined as progression-free survival ≥ or < 6months, respectively, were compared using a Wilcoxon Rank Sum Test. RESULTS The R group displayed significantly lower median rates of change for CEV (R -35% vs. NR +142% p = 4.31e-04) and TLBV (R +6% vs NR +43% p = 1.55e-03), compared to NR from baseline to post-cycle 1-2. Additionally, similar trends persisted at post-cycle 3-4 for CEV (R -41% vs. NR +367% p = 3.03e-03) and TLBV (R +12% vs. NR +40% p = 7.74e-03). Although NR showed a higher average baseline TLBV, there was no discernible correlation detected between baseline TLBV and the rate of change during treatment. CONCLUSIONS AI-based volumetric analysis offers an objective response assessment, showing promise in tracking disease progression in IDH-mutant glioma patients on nivolumab, potentially enabling earlier identification of progressive disease and allowing for timely treatment adjustments. A larger prospective study is warranted to refine volumetric pattern analysis for early clinical decisions in immunotherapy.

Radiomics for Predicting Prognostic Factors in Breast Cancer: Insights from Contrast-Enhanced Mammography (CEM).

Objectives: To evaluate the correlation between radiomic features extracted from contrast-enhanced mammography (CEM) tumor lesions and peritumoral background with prognostic factors in breast cancer (BC). Methods: In this retrospective, single-center study, 134 women with histologically confirmed breast cancer underwent CEM examination. Radiomic features were extracted from manually segmented lesions and lesion contours were automatically delineated using PyRadiomics. The extracted features were categorized into seven classes: First-order Features, Shape Features (2D), Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), and Neighboring Gray Tone Difference Matrix (NGTDM). Histological examination assessed tumor type, grade, receptor structure (ER, PgR, HER2), Ki67 index, and lymph node involvement. Pearson correlation and multivariate regression were applied to evaluate associations between radiomic features and prognostic factors. Results: Significant correlations were found between First-order Features and prognostic factors such as ER, PgR, and Ki67 (p < 0.05). GLCM-based texture features showed strong associations with Ki67 and HER2 (p < 0.01). Radiomic features from peritumoral regions, especially shape and GLSZM metrics, were significantly correlated with Ki67 and lymph node involvement. Conclusions: Radiomic analysis of both tumor and peritumoral regions offers significant insights into BC prognosis. These findings support the integration of radiomics into personalized diagnostic and therapeutic strategies, potentially improving clinical decision making in BC management.

LesionMix data enhancement and entropy minimization for semi-supervised lesion segmentation of lung cancer

Determining the location and contour of the lesion is a crucial prerequisite for medical diagnosis, subsequent personalized treatment plan and prognostic prediction of lung cancer. Semi-supervised learning and data augmentation methods facilitate deep learning to be used in many fields of medical imaging. In this paper, we introduce a novel data enhancement technique called LesionMix. This method involves extracting and reusing lesions from a limited amount of labeled CT data, thereby enhancing the efficiency of utilizing those labeled data. Meanwhile, we propose a two-stage semi-supervised training strategy called Entropy Minimization LesionMix (EMLM). In the first stage, features containing lesion contour information are rapidly learned through LesionMix data augmentation. Entropy minimization strategy optimizes the model parameters to alleviate overfitting as much as possible in the second stage and improves prediction confidence. Our proposed method is validated on the public dataset LIDC-IDRI and the in-house dataset GDPHLUAD. Extensive experiments demonstrate that our method achieves promising performance and outperforms seven state-of-the-art semi-supervised models; Moreover, ablation experiments validate the effectiveness of various aspects of our approach.

RDAG U-Net: An Advanced AI Model for Efficient and Accurate CT Scan Analysis of SARS-CoV-2 Pneumonia Lesions.

Background/Objective: This study aims to utilize advanced artificial intelligence (AI) image recog-nition technologies to establish a robust system for identifying features in lung computed tomog-raphy (CT) scans, thereby detecting respiratory infections such as SARS-CoV-2 pneumonia. Spe-cifically, the research focuses on developing a new model called Residual-Dense-Attention Gates U-Net (RDAG U-Net) to improve accuracy and efficiency in identification. Methods: This study employed Attention U-Net, Attention Res U-Net, and the newly developed RDAG U-Net model. RDAG U-Net extends the U-Net architecture by incorporating ResBlock and DenseBlock modules in the encoder to retain training parameters and reduce computation time. The training dataset in-cludes 3,520 CT scans from an open database, augmented to 10,560 samples through data en-hancement techniques. The research also focused on optimizing convolutional architectures, image preprocessing, interpolation methods, data management, and extensive fine-tuning of training parameters and neural network modules. Result: The RDAG U-Net model achieved an outstanding accuracy of 93.29% in identifying pulmonary lesions, with a 45% reduction in computation time compared to other models. The study demonstrated that RDAG U-Net performed stably during training and exhibited good generalization capability by evaluating loss values, model-predicted lesion annotations, and validation-epoch curves. Furthermore, using ITK-Snap to convert 2D pre-dictions into 3D lung and lesion segmentation models, the results delineated lesion contours, en-hancing interpretability. Conclusion: The RDAG U-Net model showed significant improvements in accuracy and efficiency in the analysis of CT images for SARS-CoV-2 pneumonia, achieving a 93.29% recognition accuracy and reducing computation time by 45% compared to other models. These results indicate the potential of the RDAG U-Net model in clinical applications, as it can accelerate the detection of pulmonary lesions and effectively enhance diagnostic accuracy. Additionally, the 2D and 3D visualization results allow physicians to understand lesions' morphology and distribution better, strengthening decision support capabilities and providing valuable medical diagnosis and treatment planning tools.

Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment

PurposeRespiratory motion (RM) significantly impacts image quality in thoracoabdominal PET/CT imaging. This study introduces a unified data-driven respiratory motion correction (uRMC) method, utilizing deep learning neural networks, to solve all the major issues caused by RM, i.e., PET resolution loss, attenuation correction artifacts, and PET-CT misalignment.MethodsIn a retrospective study, 737 patients underwent [18F]FDG PET/CT scans using the uMI Panorama PET/CT scanner. Ninety-nine patients, who also had respiration monitoring device (VSM), formed the validation set. The remaining data of the 638 patients were used to train neural networks used in the uRMC. The uRMC primarily consists of three key components: (1) data-driven respiratory signal extraction, (2) attenuation map generation, and (3) PET-CT alignment. SUV metrics were calculated within 906 lesions for three approaches, i.e., data-driven uRMC (proposed), VSM-based uRMC, and OSEM without motion correction (NMC). RM magnitude of major organs were estimated.ResultsuRMC enhanced diagnostic capabilities by revealing previously undetected lesions, sharpening lesion contours, increasing SUV values, and improving PET-CT alignment. Compared to NMC, uRMC showed increases of 10% and 17% in SUVmax and SUVmean across 906 lesions. Sub-group analysis showed significant SUV increases in small and medium-sized lesions with uRMC. Minor differences were found between VSM-based and data-driven uRMC methods, with the SUVmax was found statistically marginal significant or insignificant between the two methods. The study observed varied motion amplitudes in major organs, typically ranging from 10 to 20 mm.ConclusionA data-driven solution for respiratory motion in PET/CT has been developed, validated and evaluated. To the best of our knowledge, this is the first unified solution that compensates for the motion blur within PET, the attenuation mismatch artifacts caused by PET-CT misalignment, and the misalignment between PET and CT.

PSMA PET/CT and mpMRI discrepancies in prostate cancer detection with whole-mount histopathology gold standard.

284 Background: Multiparametric MRI (mpMRI) and PSMA-PET are complementary imaging modalities used in the pre-surgical evaluation of patients with prostate cancer (PCa). The aim of this study was to evaluate the imaging and pathology parameters associated with PSMA-PET and mpMRI disagreement with each other and with gold standard histopathology. Methods: Patients undergoing radical prostatectomy (RP) with pre-surgical PSMA-PET and mpMRI were screened for inclusion in this retrospective analysis. Patients had the imaging scans done &lt;3 months from each other, and whole mount histopathology (WMHP) slides available. Two nuclear medicine physicians and 2 radiologists independently contoured PCa lesions on PSMA-PET and mpMRI, respectively. A consensus read was done with a third reader for each modality, and a majority rule was applied (2:1). Quantitative measures were extracted on a lesion-basis (SUVmean, SUVmax, tumor volume). A PET/MRI fusion was obtained, and agreement/disagreement was assessed visually, based on the overlapping lesion contours. WMHP slides were used to establish the disagreement of imaging-identified lesions with the gold standard pathology. Independent samples t-test and one-way ANOVA were used to assess group differences. Univariable and multivariable logistic regression models were used to assess the association of clinical, pathological, and imaging variables with PSMA-PET and mpMRI agreement/disagreement with each other and with pathology. Results: The cohort included 114 patients, and 175 pathology lesions were identified (ISUP 3, n=22; ISUP&gt;3, n=153). mpMRI and PSMA PET identified 138 and 170 lesions, respectively. Sensitivity for ISUP&gt;3 lesions was 79% and 87% for mpMRI and PSMA-PET, respectively. 115/153 (76%) ISUP&gt; 3 lesions were correctly identified, and 14/153 (9%) were missed by both imaging modalities, respectively. 5/153 (3%) were correctly identified by mpMRI and missed by PSMA-PET, 17/153 (11%) were correctly identified by PSMA-PET and missed by mpMRI. Lesion’s ISUP grade group and size on pathology were significantly lower in mpMRI- compared to mpMRI+ and in PET- compared to PET+ lesions. SUVmax and SUVmean were significantly higher in PET+/MRI+ than PET+/MRI- lesions. Lesion’s ISUP grade group and size were significantly correlated to PSMA-PET and mpMRI agreement, whereas PSMA-PET metrics were not. Logistic regression model showed that lesions with lower ISUP, smaller size, and lack of aggressive prostate cancer features on pathology (cribriform pattern and intraductal carcinoma) have higher likelihood of being missed by PET and mpMRI and of PET/MRI disagreement. Conclusions: Higher SUVmax, SUVmean, and tumor volume on PSMA-PET were associated with a TP finding on PSMA-PET, higher ISUP grade group and size on pathology were associated with a TP finding on both PSMA-PET and mpMRI, and with agreement between PSMA-PET and mpMRI.

A Comprehensive Study on the Digestive Endoscopic Technique and Narrow-Band Imaging for Early Gastric Cancer Screening

Objective: To explore the implementation of gastrointestinal endoscopy technology and endoscopic narrow-band imaging (NBI) in the early screening of gastric cancer and to observe and study their application effects. Methods: During the period from March 2023 to August 2023, 312 patients who received gastroscopy in the Kunming Guandu District People’s Hospital were selected, and they underwent both conventional gastroscopy and endoscopic NBI, with clinicopathological tissue biopsy serving as the gold standard. The application value for early screening of gastric cancer was observed and analyzed. Results: The scoring data showed that the clarity of gastric mucosal glandular tube structure, microvascular structure clarity, and lesion contour scoring data of conventional gastroscopy were lower than those of the NBI technology (P &lt; 0.05). The screening rate of pathological biopsy in 312 patients was 18.59% (58 cases). Conventional gastroscopy showed a screening rate of 11.53% (36 cases), while NBI technology examined a screening rate of 17.63% (55 cases), and the two-by-two comparison of the screening rate data of the three groups was not statistically significant (P &gt; 0.05). The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of conventional gastroscopy appeared to be lower than those of NBI technology (P &lt; 0.05). Conclusion: In the early screening of gastric cancer, endoscopic NBI technology can be applied to patients. Compared with conventional gastroscopy, it provides a clearer visualization of the structure of the gastric mucosal glandular structure and microvascular structure, with a certain screening rate. Additionally, its sensitivity, specificity, accuracy, positive predictive value, and negative predictive value are higher, demonstrating outstanding effectiveness.

Mono+ algorithm assessment of the diagnostic value of dual-energy CT for high-risk factors for colorectal cancer: a preliminary study.

Risk factors for colorectal cancer (CRC) affect the way patients are subsequently treated and their prognosis. Dual-energy computerized tomography (DECT) is an advanced imaging technique that enables the quantitative evaluation of lesions. This study aimed to evaluate the quality of DECT images based on the Mono+ algorithm in CRC, and based on this, to assess the value of DECT in the diagnosis of CRC risk factors. This prospective study was performed from 2021 to 2023. A dual-phase DECT protocol was established for consecutive patients with primary CRC. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), overall image quality, lesion delineation, and image noise of the dual-phase DECT images were assessed. Next, the optimal energy-level image was selected to analyze the iodine concentration (IC), normalized iodine concentration (NIC), effective atomic number, electron density, dual-energy index (DEI), and slope of the energy spectrum curve within the tumor for the high- and low-risk CRC groups. A multifactor binary logistic regression analysis was used to construct a differential diagnostic regression model for high- and low-risk CRC, receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC) was calculated to assess the diagnostic value of the model. A total of 74 patients were enrolled in this study, of whom 41 had high-risk factors and 33 had low-risk factors. The SNR and CNR were best at 40 keV virtual monoenergetic imaging (VMI) based on the Mono+ algorithm (VMI+) (SNR 8.79±1.27, P<0.001; CNR 14.89±1.77, P=0.027). The overall image quality and lesion contours were best at 60 keV VMI+ and 40 keV VMI+, respectively (P=0.001). Among all the DECT parameters, the arterial phase (AP)-IC, NIC, DEI, energy spectrum curve, and venous phase-NIC differed significantly between the two groups. The AP-IC was the optimal DECT parameter for predicting high- and low-risk CRC with AUC, sensitivity, specificity, and cut-off values of 0.96, 97.06%, 87.80%, and 2.94, respectively, and the 95% confidence interval (CI) of the AUC was 0.88-0.99. Integrating the clinical factors and DECT parameters, the AUC, sensitivity, specificity, and predictive accuracy of the model were 0.99, 100.00%, 92.68%, and 94.67%, respectively, and the 95% CI of the AUC was 0.93-1.00. The DECT parameters based on 40 keV noise-optimized VMI+ reconstruction images depicted the CRC tumors best, and the clinical DECT model may have significant implications for the preoperative prediction of high-risk factors in CRC patients.

TICT improved NIR emission and lysosome-specific functional dye visualizing viscosity in disease model

Since the dependence of ferroptosis on autophagy was discovered, the cross-linking between ferroptosis and autophagy has received much attention. Studies have shown that lysosomes are not only important participants in the autophagy process, but also iron storage hubs in organisms. Meanwhile, lysosome dysfunction has been shown to be one of the causes of ferroptosis. However, the connection between autophagy and ferroptosis is still obscure. Previous studies have revealed the relationships between viscosity and autophagy, as well as viscosity and ferroptosis, respectively. Therefore, viscosity may be a link between autophagy and ferroptosis. In this work, we developed a fluorescence probe (IG-Lyso) with the near infrared (emission wavelength of 825 nm) activated by viscosity, which was specifically captured by the lysosome through endocytosis. IG-Lyso was used to monitor lysosomal viscosity in the autophagy and ferroptosis processes. The experiment showed that autophagy was induced during ferroptosis, accompanied by an increase in viscosity. In addition, IG-Lyso had been successfully used to delineate the contours of tumor lesions by utilizing its high sensitivity to viscosity, thus achieving the purpose of tumor identification. We anticipate that this research not only provides a new idea to elucidate the connection between ferroptosis and autophagy, but also provides a new tool for direct navigation of tumor lesions in clinical applications.

Inter-Rater Variability of Prostate Lesion Segmentation on Multiparametric Prostate MRI.

External radiotherapy is a major treatment for localized prostate cancer (PCa). Dose escalation to the whole prostate gland increases biochemical relapse-free survival but also acute and late toxicities. Dose escalation to the dominant index lesion (DIL) only is of growing interest. It requires a robust delineation of the DIL. In this context, we aimed to evaluate the inter-observer variability of DIL delineation. Two junior radiologists and a senior radiation oncologist delineated DILs on 64 mpMRIs of patients with histologically confirmed PCa. For each mpMRI and each reader, eight individual DIL segmentations were delineated. These delineations were blindly performed from one another and resulted from the individual analysis of the T2, apparent diffusion coefficient (ADC), b2000, and dynamic contrast enhanced (DCE) sequences, as well as the analysis of combined sequences (T2ADC, T2ADCb2000, T2ADCDCE, and T2ADCb2000DCE). Delineation variability was assessed using the DICE coefficient, Jaccard index, Hausdorff distance measure, and mean distance to agreement. T2, ADC, T2ADC, b2000, T2 + ADC + b2000, T2 + ADC + DCE, and T2 + ADC + b2000 + DCE sequences obtained DICE coefficients of 0.51, 0.50, 0.54, 0.52, 0.54, 0.55, 0.53, respectively, which are significantly higher than the perfusion sequence alone (0.35, p < 0.001). The analysis of other similarity metrics lead to similar results. The tumor volume and PI-RADS classification were positively correlated with the DICE scores. Our study showed that the contours of prostatic lesions were more reproducible on certain sequences but confirmed the great variability of prostatic contours with a maximum DICE coefficient calculated at 0.55 (joint analysis of T2, ADC, and perfusion sequences).

Ultrasound Findings of Suspected Breast Cancer Lesions in Females Accessing Breast Ultrasound Services in Selected Hospitals in Lusaka, Zambia

Background: Breast cancer is the most common malignancy among women in Zambia. Ultrasound can be a useful tool for early diagnosis of breast cancer based on the breast lesions’ features. However, an overlap in the ultrasound features of malignant and benign breast tumours has been noticed together with a paucity of information on the ultrasound features that are more suggestive of breast cancer. Objective: The purpose of this study was to identify ultrasound features of suspected breast cancer lesions which may assist in ascertaining a high breast cancer or benign breast disease suspicion index, that may be used to prioritise patients requiring further and urgent management for breast cancer. Methods: Systematic random sampling was used for the selection of participants in this study. The selected patients first underwent an ultrasound scan in the Ultrasound department to obtain the breast lesion ultrasound features. The histology results for the same patients were then obtained from the University Teaching Hospital (UTH) histology laboratory or the histology report filed in the patient’s medical file. Results: Irregular shape of breast lesions, vertical orientation of breast lesions, hypoechogenicity of breast lesions, complex echo pattern of breast lesions, irregular or spiculated margin contours of breast lesions, compression of breast lesion surrounding tissue, absence of hyperechogenic spots in breast lesions and a breast lesion boundary with neither a hyperechoic halo nor thin capsule (None) were found to be associated with breast cancer. No breast lesion showed less than 3 ultrasound features suspicious for breast cancer. Hyperechoic spots in breast lesions were found to be associated with non-cancerous breast lesions. Conclusion: Low-resource countries, such as Zambia, where access to imaging diagnostic equipment such as Mammography and Magnetic Resonance Imaging machines (MRI), and histology examinations are scarce, the preceding ultrasound findings .......

Effect of differences in O-RADS lexicon interpretation between senior and junior sonologists on O-RADS classification and diagnostic performance

PurposeTo assess the consistency of Ovarian-Adnexal Reporting and Data System (O-RADS) lexicon interpretation between senior and junior sonologists and to investigate its impact on O-RADS classification and diagnostic performance.MethodsWe prospectively studied 620 patients with adnexal lesions, all of whom underwent transvaginal or transrectal ultrasound performed by a senior sonologist (R1) who selected the O-RADS lexicon description and O-RADS category for the lesion after the examination. Meanwhile, the junior sonologist (R2) analyzed the images retained by R1 and divided the lesion in the same way. Pathological findings were used as a reference standard. kappa (к) statistics were used to assess the interobserver agreement.ResultsOf the 620 adnexal lesions, 532 were benign and 88 were malignant. When using the O-RADS lexicon, R1 and R2 had almost perfect agreement regarding lesion category, external contour of solid lesions, presence of papillary inside cystic lesions, and fluid echogenicity (к: 0.81–1.00). Substantial agreement in solid components, acoustic shadow, vascularity and O-RADS categories (к: 0.61–0.80). Consistency in classifying classic benign lesions in the O-RADS category was only moderate (к = 0.535). No significant difference in diagnostic performance between them using O-RADS (P = 0.1211).ConclusionThere was good agreement between senior and junior sonologists in the interpretation of the O-RADS lexicon and in the classification of O-RADS, except for a moderate agreement in the interpretation and classification of classic benign lesions. Differences in O-RADS category delineation between sonologists had no significant effect on the diagnostic performance of O-RADS.

Enhanced grasshopper optimization‐based selection of ultrasound and elastography features for breast lesion classification

AbstractBreast cancer (BC) is the second leading cause of death in women worldwide, caused by the uncontrolled proliferation of malignant cells in the breast. It is very tough to differentiate cancer from non‐cancer cells because of their shape and structure. Therefore, early diagnosis and classification of breast tumors as benign is a hot research topic. However, existing methods for early diagnosis have shortcomings like high computational cost and low classification accuracy. To trounce those limitations, this paper presented a computer‐aided diagnosis (CAD) system employing metaheuristic algorithms and machine learning classifiers. The proposed system uses fused features of ultrasound (US) and elastography images to enhance classification accuracy. Firstly, both US and elastography images are separately preprocessed using an enhanced wavelet thresholding method to diminish speckle noise. Secondly, a new segmentation algorithm is proposed to extract the lesion region from the preprocessed US image. Then the contour of the segmented lesion is mapped on an elastography image to obtain the corresponding region of interest (ROI), and texture and morphology features are separately extracted and concatenated. Subsequently, the enhanced grasshopper optimization algorithm (EGOA) is adopted to select salient features and reduce the dimension. Finally, based on the selected features, two machine learning classifiers, linear discriminant analysis (LDA) and support vector machine (SVM), are employed to classify the lesions into benign and malignant. The effectiveness of the proposed method is validated on 520 tumor images, including both benign and malignant samples. The suggested performance has been assessed by computing the confusion matrix and receiver operating characteristic curve. The developed method, EGOA‐SVM, outperforms the other classifiers by reaching a higher classification rate of 99.4%, specificity of 100%, the sensitivity of 99.2%, and Matthew's coefficient of 0.979. The introduced method can improve the radiologist's performance in categorizing breast lesions with a good classification rate. It could be a promising tool for clinical use.

Accurate segmentation algorithm of acoustic neuroma in the cerebellopontine angle based on ACP-TransUNet.

Acoustic neuroma is one of the most common tumors in the cerebellopontine angle area. Patients with acoustic neuroma have clinical manifestations of the cerebellopontine angle occupying syndrome, such as tinnitus, hearing impairment and even hearing loss. Acoustic neuromas often grow in the internal auditory canal. Neurosurgeons need to observe the lesion contour with the help of MRI images, which not only takes a lot of time, but also is easily affected by subjective factors. Therefore, the automatic and accurate segmentation of acoustic neuroma in cerebellopontine angle on MRI is of great significance for surgical treatment and expected rehabilitation. In this paper, an automatic segmentation method based on Transformer is proposed, using TransUNet as the core model. As some acoustic neuromas are irregular in shape and grow into the internal auditory canal, larger receptive fields are thus needed to synthesize the features. Therefore, we added Atrous Spatial Pyramid Pooling to CNN, which can obtain a larger receptive field without losing too much resolution. Since acoustic neuromas often occur in the cerebellopontine angle area with relatively fixed position, we combined channel attention with pixel attention in the up-sampling stage so as to make our model automatically learn different weights by adding the attention mechanism. In addition, we collected 300 MRI sequence nuclear resonance images of patients with acoustic neuromas in Tianjin Huanhu hospital for training and verification. The ablation experimental results show that the proposed method is reasonable and effective. The comparative experimental results show that the Dice and Hausdorff 95 metrics of the proposed method reach 95.74% and 1.9476 mm respectively, indicating that it is not only superior to the classical models such as UNet, PANet, PSPNet, UNet++, and DeepLabv3, but also show better performance than the newly-proposed SOTA (state-of-the-art) models such as CCNet, MANet, BiseNetv2, Swin-Unet, MedT, TransUNet, and UCTransNet.

Prospective Evaluation of PI-RADS Version 2.1 for Prostate Cancer Detection and Investigation of Multiparametric MRI-derived Markers.

Background Data regarding the prospective performance of Prostate Imaging Reporting and Data System (PI-RADS) version 2.1 alone and in combination with quantitative MRI features for prostate cancer detection is limited. Purpose To assess lesion-based clinically significant prostate cancer (csPCa) rates in different PI-RADS version 2.1 categories and to identify MRI features that could improve csPCa detection. Materials and Methods This single-center prospective study included men with suspected or known prostate cancer who underwent multiparametric MRI and MRI/US-guided biopsy from April 2019 to December 2021. MRI scans were prospectively evaluated using PI-RADS version 2.1. Atypical transition zone (TZ) nodules were upgraded to category 3 if marked diffusion restriction was present. Lesions with an International Society of Urological Pathology (ISUP) grade of 2 or higher (range, 1-5) were considered csPCa. MRI features, including three-dimensional diameter, relative lesion volume (lesion volume divided by prostate volume), sphericity, and surface to volume ratio (SVR), were obtained from lesion contours delineated by the radiologist. Univariable and multivariable analyses were conducted at the lesion and participant levels to determine features associated with csPCa. Results In total, 454 men (median age, 67 years [IQR, 62-73 years]) with 838 lesions were included. The csPCa rates for lesions categorized as PI-RADS 1 (n = 3), 2 (n = 170), 3 (n = 197), 4 (n = 319), and 5 (n = 149) were 0%, 9%, 14%, 37%, and 77%, respectively. csPCa rates of PI-RADS 4 lesions were lower than PI-RADS 5 lesions (P < .001) but higher than PI-RADS 3 lesions (P < .001). Upgraded PI-RADS 3 TZ lesions were less likely to harbor csPCa compared with their nonupgraded counterparts (4% [one of 26] vs 20% [20 of 99], P = .02). Predictors of csPCa included relative lesion volume (odds ratio [OR], 1.6; P < .001), SVR (OR, 6.2; P = .02), and extraprostatic extension (EPE) scores of 2 (OR, 9.3; P < .001) and 3 (OR, 4.1; P = .02). Conclusion The rates of csPCa differed between consecutive PI-RADS categories of 3 and higher. MRI features, including lesion volume, shape, and EPE scores of 2 and 3, predicted csPCa. Upgrading of PI-RADS category 3 TZ lesions may result in unnecessary biopsies. ClinicalTrials.gov registration no. NCT03354416 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Goh in this issue.

An International Study of Factors Affecting Variability of Dosimetry Calculations, Part 2: Overall Variabilities in Absorbed Dose.

Dosimetry for personalized radiopharmaceutical therapy has gained considerable attention. Many methods, tools, and workflows have been developed to estimate absorbed dose (AD). However, standardization is still required to reduce variability of AD estimates across centers. One effort for standardization is the Society of Nuclear Medicine and Molecular Imaging 177Lu Dosimetry Challenge, which comprised 5 tasks (T1-T5) designed to assess dose estimate variability associated with the imaging protocol (T1 vs. T2 vs. T3), segmentation (T1 vs. T4), time integration (T4 vs. T5), and dose calculation (T5) steps of the dosimetry workflow. The aim of this work was to assess the overall variability in AD calculations for the different tasks. Methods: Anonymized datasets consisting of serial planar and quantitative SPECT/CT scans, organ and lesion contours, and time-integrated activity maps of 2 patients treated with 177Lu-DOTATATE were made available globally for participants to perform dosimetry calculations and submit their results in standardized submission spreadsheets. The data were carefully curated for formal mistakes and methodologic errors. General descriptive statistics for ADs were calculated, and statistical analysis was performed to compare the results of different tasks. Variability in ADs was measured using the quartile coefficient of dispersion. Results: ADs to organs estimated from planar imaging protocols (T2) were lower by about 60% than those from pure SPECT/CT (T1), and the differences were statistically significant. Importantly, the average differences in dose estimates when at least 1 SPECT/CT acquisition was available (T1, T3, T4, T5) were within ±10%, and the differences with respect to T1 were not statistically significant for most organs and lesions. When serial SPECT/CT images were used, the quartile coefficients of dispersion of ADs for organs and lesions were on average less than 20% and 26%, respectively, for T1; 20% and 18%, respectively, for T4 (segmentations provided); and 10% and 5%, respectively, for T5 (segmentation and time-integrated activity images provided). Conclusion: Variability in ADs was reduced as segmentation and time-integration data were provided to participants. Our results suggest that SPECT/CT-based imaging protocols generate more consistent and less variable results than planar imaging methods. Effort at standardizing segmentation and fitting should be made, as this may substantially reduce variability in ADs.

A Collaborative Learning Model for Skin Lesion Segmentation and Classification.

The automatic segmentation and classification of skin lesions are two essential tasks in computer-aided skin cancer diagnosis. Segmentation aims to detect the location and boundary of the skin lesion area, while classification is used to evaluate the type of skin lesion. The location and contour information of lesions provided by segmentation is essential for the classification of skin lesions, while the skin disease classification helps generate target localization maps to assist the segmentation task. Although the segmentation and classification are studied independently in most cases, we find meaningful information can be explored using the correlation of dermatological segmentation and classification tasks, especially when the sample data are insufficient. In this paper, we propose a collaborative learning deep convolutional neural networks (CL-DCNN) model based on the teacher-student learning method for dermatological segmentation and classification. To generate high-quality pseudo-labels, we provide a self-training method. The segmentation network is selectively retrained through classification network screening pseudo-labels. Specially, we obtain high-quality pseudo-labels for the segmentation network by providing a reliability measure method. We also employ class activation maps to improve the location ability of the segmentation network. Furthermore, we provide the lesion contour information by using the lesion segmentation masks to improve the recognition ability of the classification network. Experiments are carried on the ISIC 2017 and ISIC Archive datasets. The CL-DCNN model achieved a Jaccard of 79.1% on the skin lesion segmentation task and an average AUC of 93.7% on the skin disease classification task, which is superior to the advanced skin lesion segmentation methods and classification methods.

Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy

Small intestinal vascular malformations (angiodysplasias) are common causes of small intestinal bleeding. While capsule endoscopy has become the primary diagnostic method for angiodysplasia, manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload, which affects the accuracy of diagnosis. To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine, achieve automatic disease detection, and shorten the capsule endoscopy (CE) reading time. A convolutional neural network semantic segmentation model with a feature fusion method, which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour, thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions, was proposed. Resnet-50 was used as the skeleton network to design the fusion mechanism, fuse the shallow and depth features, and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia. The training set and test set were constructed and compared with PSPNet, Deeplab3+, and UperNet. The test set constructed in the study achieved satisfactory results, where pixel accuracy was 99%, mean intersection over union was 0.69, negative predictive value was 98.74%, and positive predictive value was 94.27%. The model parameter was 46.38 M, the float calculation was 467.2 G, and the time length to segment and recognize a picture was 0.6 s. Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

PI-RADSAI: introducing a new human-in-the-loop AI model for prostate cancer diagnosis based on MRI.

This study aims to develop and validate an artificial intelligence (AI)-aided Prostate Imaging Reporting and Data System (PI-RADSAI) for prostate cancer (PCa) diagnosis based on MRI. The deidentified MRI data of 1540 biopsy-naïve patients were collected from four centres. PI-RADSAI is a two-stage, human-in-the-loop AI capable of emulating the diagnostic acumen of subspecialists for PCa on MRI. The first stage uses a UNet-Seg model to detect and segment biopsy-candidate prostate lesions, whereas the second stage leverages UNet-Seg segmentation is trained specifically with subspecialist' knowledge-guided 3D-Resnet to achieve an automatic AI-aided diagnosis for PCa. In the independent test set, UNet-Seg identified 87.2% (628/720) of target lesions, with a Dice score of 44.9% (range, 22.8-60.2%) in segmenting lesion contours. In the ablation experiment, the model trained with the data from three centres was superior (kappa coefficient, 0.716 vs. 0.531) to that trained with single-centre data. In the internal and external tests, the triple-centre PI-RADSAI model achieved an overall agreement of 58.4% (188/322) and 60.1% (92/153) with a referential subspecialist in scoring target lesions; when one-point margin of error was permissible, the agreement rose to 91.3% (294/322) and 97.3% (149/153), respectively. In the paired test, PI-RADSAI outperformed 5/11 (45.5%) and matched the performance of 3/11 (27.3%) general radiologists in achieving a clinically significant PCa diagnosis (area under the curve, internal test, 0.801 vs. 0.770, p < 0.01; external test, 0.833 vs. 0.867, p = 0.309). Our closed-loop PI-RADSAI outperforms or matches the performance of more than 70% of general readers in the MRI assessment of PCa. This system might provide an alternative to radiologists and offer diagnostic benefits to clinical practice, especially where subspecialist expertise is unavailable.