Radiology Research Articles

LDCT lung cancer screening implementation in a Veterans Affairs hospital: A quality initiative.

e23238 Background: Lung cancer is the number one cause of cancer related deaths worldwide. United States Preventive Services Task Force (USPSTF) recommends annual Lung Cancer Screening (LCS) with Low Dose Computerized Tomography (LDCT) for adults who are current smokers aged 50 to 80 years with at least 20 pack year smoking history or have quit smoking within the past 15 years. Although LCS is a national initiative for Veteran Affairs (VA) Hospitals, there are several barriers in practice. Methods: The LCS program was established with a dedicated coordinator to provide better access to high-quality in-house screening, while reducing the dependance on expensive community care services and referrals. Smoking history in Tobacco Pack Years (TPY) is updated during a Primary Care Physician (PCP) visit, which triggers a clinical reminder in the electronic medical record for LCS. The LCS coordinator would then receive a consult. After shared decision-making with the patient, physician and coordinator, the patients are scheduled for LDCT. If the results are Lung-RADS 1 (negative), 2 or 3 (benign appearing nodules) the patients are notified of the findings and provided with subsequent follow ups. All Lung RADS 4 (suspicious findings) are discussed in the lung tumor board, which includes radiologist, oncologist, pulmonologist, pathologist, cardio-thoracic surgeon, and fellows in training. The committee determines the follow-up scan interval and/or additional investigations. Results: The performance of our LCS Program from June 2022 to January 2024 was reviewed. 5941 patients were assessed for TPY, of those 1127 patients were eligible for LCS scans and 1032 (93.3%) were enrolled into the LCS Program. 951 LDCT scans have been conducted thus far, this includes 598 annual initial screenings, the remaining are follow ups. 57 patients (6.81%) had Lung-RADS 3 findings and are undergoing nodule tracking. 16 patients (1.91%) required diagnostic work-up which includes a PET scan or biopsy. 14 patients (1.67%) have been diagnosed with cancer. Conclusions: Our LDCT Program showed a high acceptance rate of 93.3%, much of which can be attributed to the multiple layers of screening and shared decision-making processes. Patients received three phone calls and a letter as a reminder of their LDCT appointments. Our radiology department has four dedicated slots for LDCT screening each day which allows for further compliance. TPY documentation was identified as a limiting factor in this process. The LCS coordinator verified the TPY history with the patients which helped overcome this shortcoming. Overall a multidisciplinary team approach contributed to the success of our program.

Patent Foramen Ovale in Children: A Review of Recent Progress.

The support has been provided by clinical trials and guidelines for managing patent foramen ovale (PFO) in adults; however, the optimal approach is still unclear for treating PFO in pediatric patients. PFO and its associated clinical syndromes, imaging diagnosis, and management in pediatric patients were analyzed by a comprehensive analysis. Extensive research was performed using electronic databases, including PubMed, Cochrane, Web of Science, and EMBASE. This review includes the studies published until February 1st, 2024. A total of 583 articles were obtained, of which 54 were included in the comprehensive review. Numerous evidences have indicated that a right-to-left shunt through a PFO may be involved in cryptogenic stroke in children, although the connection between migraine and aura has not been substantiated by robust evidence. Children with sickle cell disease and a PFO were at higher risks of paradoxical embolization, rare syndromes caused by PFO could also occur in children such as platypnea-orthodeoxia syndrome, myocardial infarction, and decompression sickness. Contrast transthoracic echocardiography was deemed the most appropriate examination for children due to its favorable transthoracic windows, eliminating the need for anesthesia. This review suggested that the additional treatment was not needed as no evidence was provided for potential future complications linked to isolated PFO in children. For children facing unique circumstances related to PFO, a customized interdisciplinary consultation is essential prior to considering medical interventions.

Gender Estimation from Morphometric Measurements of Mandibular Lingula by Using Machine Learning Algorithms and Artificial Neural Networks

Background: Sex determination from the bones is of great importance for forensic medicine and anthropology. The mandible is highly valued because it is the strongest, largest and most dimorphic bone in the skull. Aim: Our aim in this study is gender estimation with morphometric measurements taken from mandibular lingula, an important structure on the mandible, by using machine learning algorithms and artificial neural networks. Methods: Cone beam computed tomography images of the mandibular lingula were obtained by retrospective scanning from the Picture Archiving Communication Systems of the Department of Oral, Dental and Maxillofacial Radiology, Faculty of Dentistry, İnönü University. Images scanned in Digital Imaging and Communications in Medicine (DICOM) format were transferred to RadiAnt DICOM Viewer (Version: 2020.2). The images were converted to 3-D format by using the 3D Volume Rendering console of the program. Eight anthropometric parameters were measured bilaterally from these 3-D images based on the mandibular lingula. Results: The results of the machine learning algorithms analyzed showed that the highest accuracy was 0.88 with Random Forest and Gaussian Naive Bayes algorithm. Accuracy rates of other parameters ranged between 0.78 and 0.88. Conclusions: As a result of the study, it is thought that mandibular lingula-centered morphometric measurements can be used for gender determination as well as bones such as the pelvis and skull as they were found to be highly accurate. This study also provides information on the anatomical position of the lingula according to gender in Turkish society. The results can be important for oral-dental surgeons, anthropologists, and forensic experts.

Transarterial chemoembolization combined with donafenib or lenvatinib as first-line treatment for unresectable hepatocellular carcinoma: A single-center real-world retrospective study.

e16137 Background: Combined Transarterial chemoembolization (TACE) with tyrosine kinase inhibitor (TKI) treatment has been proven to be beneficial. This study aimed to retrospectively compare the efficacy and safety of Donafenib (DON)-TACE versus Lenvatinib (LEN)-TACE as first-line treatment for unresectable hepatocellular carcinoma (uHCC). Methods: From May 2020 to May 2023, a retrospective analysis was conducted on the clinical data of 93 patients with previously untreated uHCC who underwent treatment at the department of Interventional Radiology of the Third Affiliated Hospital of Sun Yat-sen University. Among them, 49 were in the DON-TACE group and 44 in the LEN-TACE group. The primary endpoint was progression-free survival (PFS) according to mRECIST, and the secondary endpoints included objective response rate (ORR), disease control rate (DCR), and safety outcome. Results: As of the data cut-off date Aug 26, 2023, the median PFS was 221 days (95% CI 141–366) in the DON-TACE group and 173 days (95% CI 108–215) in the LEN-TACE group (HR = 0.783, 95% CI 0.462–1.325, P = 0.362).ORR and DCR of the DON-TACE group were 55.1% (95% CI 40.23–69.33) and 75.51% (95% CI 61.13–86.66), respectively, while those of the LEN-TACE group were 61.36% (95% CI 45.49–75.64) and 81.82% (95% CI 67.29–91.81). No significant difference was observed either in ORR(P = 0.689) or DCR(P = 0.627) between the two groups. The incidence rates of total adverse events for any grade (85.71% vs 100.00%, P = 0.027) and ≥Grade 3 (22.496% vs 45.45%, P = 0.019) were significantly lower in the DON-TACE group. In addition, the incidence rates of AST increased (27.27% vs 56.82%, P = 0.005), diarrhea (6.12% vs 25.00%, P = 0.011), vomiting (0% vs 40.91%, P < 0.001), proteinuria (0% vs 18.18%, P = 0.011), gastrointestinal hemorrhage (0% vs 13.64%, P = 0.048) and hypertension (2.04% vs 36.36%, P < 0.001) for any grade were also significantly lower in the DON-TACE group. Conclusions: DON-TACE and LEN-TACE showed comparable efficacy as first-line therapies for uHCC patients. DON-TACE demonstrated a lower incidence of severe adverse events.

Self-Trained Convolutional Neural Network (CNN) for Tuberculosis Diagnosis in Medical Imaging.

Background Tuberculosis (TB) is a serious infectious disease that primarily affects the lungs.Despite advancements in the medical industry, TBremains a significant global health challenge. Early and accurate detection of TB is crucial for effective treatment and reducing transmission. This article presents a deep learning approach using convolutional neural networks (CNNs) to improve TB detection in chest X-ray images. Methods For the dataset, we collected 7000 images from Kaggle.com, of which 3500 exhibit tuberculosis evidence and the remaining 3500 are normal. Preprocessing techniques such as wavelet transformation, contrast-limited adaptive histogram equalisation (CLAHE), and gamma correction were applied to enhance the image quality. Random flipping, random rotation, random resizing, and random rescaling were among the techniques employed to increase dataset variability and model robustness. Convolutional, max-pooling, flatten, and dense layers comprised the CNN model architecture. For binary classification, sigmoid activation was utilised in the output layer and rectified linear unit (ReLU) activation in the input and hidden layers. Results The CNN model achieved an accuracy of ~96.57% in detecting TB from chest X-ray images, demonstrating the effectiveness of deep learning, particularly CNNs, in this application. Self-trained CNNs have optimised the results as compared to the transfer learning of various pre-trained models. Conclusion This study shows how well deep learning-in particular, CNNs-performs in the identification of tuberculosis. Subsequent efforts have to give precedence to optimising the model by obtaining more extensive datasets from the local hospitals and localities, which are vulnerable to TB, and stress the possibility of augmenting diagnostic knowledge in medical imaging via machine learning methodologies.

Artificial intelligence solution to accelerate the acquisition of MRI images: Impact on the therapeutic care in oncology in radiology and radiotherapy departments

PurposeMRI is essential in the management of brain tumours. However, long waiting times reduce patient accessibility. Reducing acquisition time could improve access but at the cost of spatial resolution and diagnostic quality. A commercially available artificial intelligence (AI) solution, SubtleMR™, can increase the resolution of acquired images. The objective of this prospective study was to evaluate the impact of this algorithm that halves the acquisition time on the detectability of brain lesions in radiology and radiotherapy. Material and methodsThe T1/T2 MRI of 33 patients with brain metastases or meningiomas were analysed. Images acquired quickly have a matrix divided by two which halves the acquisition time. The visual quality and lesion detectability of the AI images were evaluated by radiologists and radiation oncologist as well as pixel intensity and lesions size. ResultsThe subjective quality of the image is lower for the AI images compared to the reference images. However, the analysis of lesion detectability shows a specificity of 1 and a sensitivity of 0.92 and 0.77 for radiology and radiotherapy respectively. Undetected lesions on the IA image are lesions with a diameter less than 4mm and statistically low average gadolinium-enhancement contrast. ConclusionIt is possible to reduce MRI acquisition times by half using the commercial algorithm to restore the characteristics of the image and obtain good specificity and sensitivity for lesions with a diameter greater than 4mm.

Outcomes of a program to improve breast cancer early detection in Cote d’Ivoire.

10553 Background: In Côte d'Ivoire >70% of women with breast cancer are diagnosed with Stage III/IV disease. Patients pay for all diagnosis and treatment costs. We evaluated the effect of provider education, patient navigation and financial support on time from presentation to diagnosis and treatment uptake. Methods: Setting. Five participating primary healthcare centers in Bouaké. Intervention: (1) Breast health training curricula for primary care providers (PCPs), community health workers (CHWs), and patient advocates/cancer survivors (PAs), based on findings from a qualitative assessment. Content included benign breast disease, cancer diagnosis and treatment (PCPs); raising awareness about breast cancer (CHWs); and patient navigation and treatment adherence support (PAs). 36 PCPs, 5 CHWs, and 2 cancer survivors were trained. (2) For indigent patients (almost all patients), the program paid for imaging and pathology diagnosis; for those diagnosed with cancer, costs of bloodwork, imaging, and chemotherapy. Participants: Women with breast symptoms presenting to health centers from December 2022-September 2023. Primary outcome: mean time from presentation to diagnostic resolution. Results: 223 women enrolled in the study. Mean age was 33.7 (st. dev 13.2). 195 (87.3%) were pre-menopausal. 16 (7.1%) had a family history of cancer. 96 (43%) had no formal education, 42 (18.8%) completed primary school or high school, while 85 (38.1%) completed college or university. Time from noticing symptoms to presenting to healthcare center was < 1 month for 96 (43%), 1-3 months for 33 (15%), 3-12 months for 28 (13%), and > 12 months for 62 (28%). The most common symptoms were breast pain in 150 (67.3%) and painless mass in 119 (53.3%). 175 (78.5%) were referred to the gynecology service at the University Teaching Hospital Bouaké for evaluation. 71 (31.8%) were treated with plan for follow-up as needed; 37 (16.6%) continued with surveillance; 90 (43.4%) were referred for breast ultrasound; 26 (11.7%) for mammography; 42 (18.8%) for breast biopsy; 2 receive antibiotics. Among 106 (91.4%) who had imaging, mean time from presentation to the healthcare center to imaging was 14.5 days (st. dev 15.6 days). Among 42 who had a breast biopsy, mean time from presentation to biopsy was 34.5 days (st. dev 27.4). Mean time from presentation to biopsy result was 64.7 days (st. dev 33.0 days). Seventeen (7.6%) patients were diagnosed with breast cancer. Five (29.4%) are undergoing treatment, one was lost to follow-up, and one died. Nine (52.9%) patients declined treatment despite many discussions with patient advocates, mainly citing fear of side-effects. Conclusions: Our program achieved the mean time of < 60 days from presenting to a healthcare center to diagnostic resolution either by imaging or biopsy recommended by the World Health Organization. Despite improving access to early diagnosis, program impact was limited due to suboptimal acceptance of treatment.

Primary central nervous system lymphomas: EHA-ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up.

This EHA-ESMO Clinical Practice Guideline provides key recommendations for managing primary DLBCL of the CNS.The guideline covers clinical, imaging and pathological diagnosis, staging and risk assessment, treatment and follow-up.Algorithms for first-line and salvage treatments are provided.The author group encompasses a multidisciplinary group of experts from different institutions and countries in Europe.Recommendations are based on available scientific data and the authors' collective expert opinion.

Advanced Sonographic Techniques in the Comprehensive Evaluation and Diagnosis of Male Infertility.

Background Infertility affects many couples, with male factors being responsible for over half of the cases. Male infertility can arise from various testicular illnesses, such as varicocele and cryptorchidism, as well as posttesticular disorders, like ejaculation abnormalities. Infertility is defined as the inability to conceive after 12 months of unprotected sexual activity or after six months for women over 35. Diagnostic techniques such as semen analysis and scrotal ultrasonography are done to evaluate conditions like varicocele and epididymo-orchitis. This study aims to assess the diagnostic utility of ultrasonography for male infertility and compare its findings with those from surgery and clinical care. Methodology All patients were referred to the Department of Radiology,Tertiary Care Hospital, South India, for transrectal and scrotal ultrasonography, using a high-frequency transducer with a frequency of 7.5 MHz and a color Doppler when necessary. The study included all male patients with infertility and abnormal semen analysis, as well as those with infertility accompanied by scrotal abnormalities detected during clinical examination. Patients were placed in the left lateral decubitus position for the transrectal ultrasonography examination. The testes and epididymis were thoroughly examined on both sides and compared regarding symmetry, size, texture, and vascularity. Results Varicocele was the most frequent anomaly detected by both clinical examination and ultrasonography. Ultrasound detected 30 cases of varicocele, whereas clinical examination diagnosed 15 cases. Hydrocele was identified in eight cases through clinical examination and in 15 cases through ultrasound. Epididymal cysts were found in five cases via clinical examination, while both clinical examination and ultrasonography discovered epididymitis in 10 cases. Overall, the number of anomalies detected by ultrasound was significantly higher than those found by physical examination, with a statistically significant p value of 0.001. Conclusion Transrectal ultrasound provides high-resolution imaging of the prostate, seminal vesicles, and distal vas deferens, which aids in diagnosing obstructive azoospermia. Imaging is a valuable supplement to clinical examination and laboratory studies for accurately identifying anatomy and abnormalities. Both transrectal and scrotal ultrasonography offer crucial information in diagnosing male infertility. Ultrasonography is more effective in identifying pathological abnormalities than clinical palpation.

Adjuvant chemotherapy in clinical local advanced CRC following preoperational therapies and pT0-3N0M0 diagnosis (CANWATCH).

TPS3645 Background: Adjuvant chemotherapy is often deemed unnecessary in pathological stage II colorectal cancer (CRC) following initial surgery without high-risk factors for recurrence. However, the efficacy of adjuvant chemotherapy for pT1-3N0M0 CRC following preoperative chemotherapy or chemoradiotherapy remains uncertain. Some cases of clinical locally advanced CRC (cTxN1-2M0), which are down-staged to pT0-3N0M0 after preoperative chemotherapy or chemoradiotherapy, may not truly require adjuvant chemotherapy due to the down-staging effects of preoperative treatments or false-positive imaging diagnosis of lymph nodes. Methods: CANWATCH is a multicenter, open-label, randomized, phase III study with a parallel design conducted in China. Patients were randomly assigned (1:1) to the wait-and-watch group or the adjuvant chemotherapy group. Enrollment and random assignment were performed using a computerized randomization management system. Patients in the wait-and-watch group did not receive adjuvant chemotherapy but were followed up periodically, while patients in the adjuvant chemotherapy group continued to receive adjuvant chemotherapy based on 5-FU or 5-FU analogues (mFOLFOX6 or Capeox). This study is the first prospective randomized controlled study to assess the necessity of adjuvant chemotherapy for patients with locally advanced CRC who received neoadjuvant therapy and achieved a down-staging to pT0-3N0M0. The study aims to provide precise clinical evidence for individualized precision treatment in locally advanced CRC patients. Key inclusion criteria included preoperative clinical tumor stage III (cTxN1-2M0) CRC, pathologically confirmed CRC adenocarcinoma by endoscopic biopsy, postoperative pathological stage T0-3N0M0 without high-risk factors for recurrence, and patient ability to understand and sign written informed consent. Main exclusion criteria were a history of other malignant tumors, complications requiring emergency surgery (occlusion, sub-occlusion, massive hemorrhage, and abscesses), colorectal tumor extension toward the abdominal wall and/or adjacent organs preventing immediate R0 resection of liver metastases, non-resectable lymph node metastasis, American Society of Anesthesiologists (ASA) grading ≥ IV, and/or Eastern Cooperative Oncology Group (ECOG) score ≥ 2. A total of 650 patients are planned to be enrolled in this study, and 301 patients have been enrolled as of February 6, 2024. The study is registered with ClinicalTrials.gov (NCT03748485) and is ongoing. Clinical trial information: NCT03748485 .

Venous Anomalies in Overgrowth Syndromes

Overgrowth syndromes, particularly within the PIK3CA-related overgrowth syndrome (PROS)spectrum, are commonly associated with venous anomalies. The anomalies include spongiform venous malformations and persistent embryonic veins, such as the lateral marginal vein (of Servelle). The anomalous veins pose a significant risk of thromboembolic disease and should be occluded, preferably earlier in life. A thorough understanding of the conditions, anatomy, and interdisciplinary treatment of these complex anomalies is essential for optimal management. This review explores the clinical and imaging diagnosis of overgrowth syndromes and techniques for assessing and treating associated venous anomalies, particularly the endovenous closure of anomalous veins

Isthmoceles - Accuracy of imaging diagnosis and clinical correlation with histology: A prospective cohort study.

Isthmoceles are a growing clinical concern. To evaluate the accuracy of diagnosis of isthmoceles by imaging and to correlate the dimensions with clinical symptoms and histopathology. Prospective study of women (n=60) with ≥1 C-section undergoing hysterectomy. Isthmoceles were measured by imaging before surgery and macroscopically on the specimen after hysterectomy, followed by histological analysis. Accuracy of isthmocele diagnosis, correlation with clinical symptoms, and histopathological findings. By imaging, isthmoceles were slightly deeper (P=0.0176) and shorter (P=0.0045) than macroscopic measurements. Differences were typically small (≤3mm). Defined as an indentation of ≥2 mm at site of C-section scar, imaging diagnosed 2 isthmoceles consequently not seen by histology and missed 3. Number of prior C-sections increased isthmocele severity but neither the incidence nor the remaining myometrial thickness (RMT) did. Severity correlated positively with symptoms and histology. However, clinical use was limited. Histological analysis revealed presence of thick wall vessels in 100%, elastosis in 40%, and adenomyosis in 38%. Isthmocele lining was asynchronous with the menstrual phase in 31%. Dimensions of isthmoceles by imaging were largely accurate with occasionally large differences observed. Number of C-sections did not increase isthmocele incidence, only severity. Indication for surgery remains clinical, considering dimensions and symptoms. Dimensions of isthmoceles should be confirmed before surgery since uterine contractions might change those dimensions. Symptoms increase with dimensions of isthmoceles but are not specific. Endometrial lining within the isthmocele can be asynchronous with the menstrual phase.

Automatic classification of temporomandibular joint disorders by magnetic resonance imaging and convolutional neural networks

Background/purposeIn this study, we utilized magnetic resonance imaging data of the temporomandibular joint, collected from the Division of Oral and Maxillofacial Surgery at Taipei Veterans General Hospital. Our research focuses on the classification and severity analysis of temporomandibular joint disease using convolutional neural networks. Materials and methodsIn gray-scale image series, the most critical features often lie within the articular disc cartilage, situated at the junction of the temporal bone and the condyles. To identify this region efficiently, we harnessed the power of You Only Look Once deep learning technology. This technology allowed us to pinpoint and crop the articular disc cartilage area. Subsequently, we processed the image by converting it into the HSV format, eliminating surrounding noise, and storing essential image information in the V value. To simplify age and left-right ear information, we employed linear discriminant analysis and condensed this data into the S and H values. ResultsWe developed the convolutional neural network with six categories to identify severe stages in patients with temporomandibular joint (TMJ) disease. Our model achieved an impressive prediction accuracy of 84.73%. ConclusionThis technology has the potential to significantly reduce the time required for clinical imaging diagnosis, ultimately improving the quality of patient care. Furthermore, it can aid clinical specialists by automating the identification of TMJ disorders.

Performance of traditional cardiovascular risk calculators Vs imaging diagnosis of atherosclerosis in patients with psoriatic arthritis

Performance of traditional cardiovascular risk calculators Vs imaging diagnosis of atherosclerosis in patients with psoriatic arthritis

DF-GAM: Cross-Domain Ultrasound Image High-Quality Reconstruction Using a Dual Frequency-Domain Guided Adaptation Model

ObjectiveTo enhance the quality of low-resolution (LR) ultrasound images and mitigate artifacts and speckle noise, which can impede accurate medical diagnosis, a novel method called the dual frequency-domain guided adaptation model (DF-GAM) is proposed. The method aims to achieve high-quality image reconstruction across diverse domains, including different ultrasound machines, diseases and phantom images. MethodsDF-GAM utilizes a dual-branch network architecture combined with frequency-domain self-adaptation and self-supervised edge regression. This approach enables cross-domain enhancement by focusing on the reconstruction of clear tissue structures and speckle patterns. The model is designed to adapt to various ultrasound imaging (USI) scenarios, ensuring its applicability in real-world clinical settings. ResultsExperimental evaluations of DF-GAM were conducted using five different datasets. The results demonstrated the method's effectiveness, with DF-GAM outperforming existing enhancement techniques. The average peak signal-to-noise ratio (PSNR) achieved was 34.62, and the structural similarity index (SSIM) was 0.91, indicating a significant improvement in image quality compared to other methods. ConclusionDF-GAM shows great potential in improving medical image diagnosis and interpretation. Its ability to enhance LR ultrasound images across various domains without the need for extensive training data makes it a valuable tool for clinical use. The high PSNR and SSIM scores validate the method's effectiveness, suggesting that DF-GAM could significantly contribute to the field of USI diagnostics.

Radiographic diagnosis of periodontal diseases - Current evidence versus innovations.

Accurate diagnosis of periodontal and peri-implant diseases relies significantly on radiographic examination, especially for assessing alveolar bone levels, bone defect morphology, and bone quality. This narrative review aimed to comprehensively outline the current state-of-the-art in radiographic diagnosis of alveolar bone diseases, covering both two-dimensional (2D) and three-dimensional (3D) modalities. Additionally, this review explores recent technological advances in periodontal imaging diagnosis, focusing on their potential integration into clinical practice. Clinical probing and intraoral radiography, while crucial, encounter limitations in effectively assessing complex periodontal bone defects. Recognizing these challenges, 3D imaging modalities, such as cone beam computed tomography (CBCT), have been explored for a more comprehensive understanding of periodontal structures. The significance of the radiographic assessment approach is evidenced by its ability to offer an objective and standardized means of evaluating hard tissues, reducing variability associated with manual clinical measurements and contributing to a more precise diagnosis of periodontal health. However, clinicians should be aware of challenges related to CBCT imaging assessment, including beam-hardening artifacts generated by the high-density materials present in the field of view, which might affect image quality. Integration of digital technologies, such as artificial intelligence-based tools in intraoral radiography software, the enhances the diagnostic process. The overarching recommendation is a judicious combination of CBCT and digital intraoral radiography for enhanced periodontal bone assessment. Therefore, it is crucial for clinicians to weigh the benefits against the risks associated with higher radiation exposure on a case-by-case basis, prioritizing patient safety and treatment outcomes.

Clinical application of novel mobile AI solution for real-time detection and differential diagnosis in breast ultrasound: The first prospective feasibility study.

574 Background: Existing artificial intelligence (AI) solutions for breast ultrasound faced limitations due to their non-real-time detection and server dependency. However, novel mobile real-time AI solution now enable on-device detection and differential diagnosis, aiding in immediate decision-making. This study aims to evaluate the feasibility and effectiveness of such a mobile AI solution in clinical settings, by comparing it against expert breast imaging diagnoses. Methods: From August to December 2023, a feasibility study was conducted in tertiary medical center of Taiwan using mobile AI solution (CadAI-B for breast, BeamWorks Inc., Korea). CadAI-B is connected via HDMI or DVI to an ultrasound equipment using tablet PC. It supports healthcare providers to detect suspicious breast lesions by highlighting suspicious area during breast ultrasound scanning, and to make a differential diagnosis by providing BI-RADS categories and malignancy score (0-100%). The rate of real-time detection in malignancies and area under the receiver operating characteristic curve (AUC) was calculated. Distribution of BI-RADS categorized by CadAI-B were compared with those by breast imaging experts on independent review. Results: The analysis included 33 patients with an average age of 47 years (IQR, 44 – 62). There were 14 malignancies, 17 benign lesions, and 2 normal cases, and 30 patients (90.9%) underwent biopsy. For patients with malignancies, CadAI-B successfully identified all malignancies. Overall diagnostic performance, as AUCs calculated by the malignancy score and BI-RADS, was 0.835 and 0.850, respectively. The per-patient sensitivity of CadAI-B was 100.0%, while the specificity was 52.6%. The BI-RADS distribution between CadAI-B and expert was the same in malignant cases. In benign cases, CadAI-B categorized 9 cases (50.0%) as C4A or C4B, while experts classified 13 cases (72.2%), indicating a potential reduction in the need for biopsy. Conclusions: This study demonstrates that real-time processing capabilities of CadAI-B enable the identification of critical lesions during breast ultrasound, helping to reduce unnecessary biopsy. These findings may be helpful in diagnostic decisions and training of non-experts in clinical settings and offer the potential to improve workflow efficiency. [Table: see text]

Development of IoT Based Power Facility Image Analysis and Diagnosis System

Development of IoT Based Power Facility Image Analysis and Diagnosis System

Solitary pulmonary capillary hemangioma – An underrecognized rare tumor. Report of 32 new cases with literature review

ObjectiveTo explore the clinical, imaging, pathologic characteristics and differential diagnosis of solitary pulmonary capillary hemangioma (SPCH). MethodsThirty two cases of SPCH were collected and studied, with literature review. ResultsThis study included 13 males and 19 females, with a male-to-female ratio of 1:1.5. The age ranged from 26 to 70 years (median age of 43 years). All patients were asymptomatic at presentation. Lung nodules were incidentally discovered during chest computed tomography (CT). Imaging features included 21 cases with partial solid nodules (PSN), 7 cases with ground-glass nodules (GGN), and 4 cases with solid nodules (SN). Eleven cases were in the left lung lower basal segment, 11 cases in the right lung lower basal segment, 6 cases in the right lung upper anterior segment, and 4 cases in the right lung middle lateral segment. The lower basal segments of the lungs were involved in 22 (11 in each lung) cases (22/32, 68 %). The tumors ranged from 6 to 18 mm (average 10 mm). Macroscopically, 16 cases had clear boundaries, while 16 cases had unclear boundaries, and gray-red or dark brown on cut surfaces. Intraoperative frozen section was performed in 27 cases, with diagnosis of SPCH in 12 and pneumonia or inflammatory lesion in 15. Microscopically, the nodules were composed of densely proliferated and dilated capillaries. The capillary walls were lined with a single layer of flat endothelial cells, without atypical features. Collapsed alveolar septa were replaced by a large number of capillaries. All cases showed proliferating capillaries spreading into the walls of small veins/arteries and bronchi, with 3 cases showing dilated capillaries protruding into the bronchiolar lumens as polyp-like structures. Twenty-six cases (26/32, 81 %) showed proliferating capillaries passed over the interlobular septa. Twenty-six cases (26/32, 81 %) showed irregular intimal thickening of small muscular arteries in the peripheral areas of the lesions, with the thickened intima being cellular or fibrous. In twenty-seven cases (27/32, 84 %) the lesions were located in the subpleura, with 6 cases involving the pleura. ConclusionSPCH is a rare benign lung tumor that mostly occurs in the lung lower basal segments with predominance in females. It usually appears as a ground-glass nodule on CT and is very similar to early-stage lung cancer. Accurate diagnosis requires collaboration of radiologists, surgeons, and pathologists. SPCH should be regarded as an important differential diagnosis of small incidental lung nodules.

Variation in the Branches of Arch of Aorta in Patients Undergoing Contrast Enhanced Multidetector Computed Tomography in a Tertiary Centre, Nepal.

Variations in the branching pattern of the Arch of Aorta (AoA) are common in patients undergoing contrast-enhanced Multidetector Computed Tomography, the identification of which is crucial in managing patients undergoing cardiovascular/neck surgeries and interventions. This prospective cross-sectional study involved 513 patients who were sent to the Department of Radiology for evaluation of various pathologies of chest and neck between August 2018 and July 2019. After approval from the Institutional Review Committee {Reference No: 11(6-11) E2/075/076}, contrast-enhanced computed tomography images were evaluated with variations in branches of the left-sided arch of the aorta and symptoms associated. Variations in branches of the arch of aorta were seen in 69 (13.45%; 95% CI: 10.60%-16.71%) of cases, left common carotid artery and brachiocephalic trunk having common origin or common trunk was 51(9.94%). The mean age was 52.4±20 years (Range 3 months to 92 years) with male to female ratio of 1.3:1. Contrast-enhanced computed tomography is the modality of choice for the detection of the variations in branches of AoA, recognition of which is crucial in vascular intervention and surgical procedures to reduce the postoperative morbidity and mortality of the patients.