Medical Imaging Research Articles

Reservoir Computing Based on Oxygen-Vacancy-Mediated X-ray Optical Synaptic Device for Medical CT Bone Diagnosis.

Recognition and judgment of X-ray computed tomography (CT) images play a crucial role in medical diagnosis and disease prevention. However, the storage and calculation of the X-ray imaging system applied in the traditional CT diagnosis is separate, and the pathological judgment is based on doctors' experience, which will affect the timeliness and accuracy of decision-making. In this paper, a simple-structured reservoir computing network (RC) is proposed based on Ga2O3 X-ray optical synaptic devices to recognize medical skeletal CT images with high accuracy. Through oxygen vacancy engineering, Ga2O3 X-ray optical synaptic devices with adjustable photocurrent gain and a persistent photoconductivity effect were obtained. By using the Ga2O3 X-ray optical synaptic device as a reservoir, we constructed an RC network for medical skeletal CT diagnosis and verified its image recognition capability using the MNIST data set with an accuracy of 78.08%. In the elbow skeletal CT image recognition task, the recognition rate is as high as 100%. This work constructs a simple-structured RC network for X-ray image recognition, which is of great significance in applications in medical fields.

PSFHS: Intrapartum ultrasound image dataset for AI-based segmentation of pubic symphysis and fetal head

During the process of labor, the intrapartum transperineal ultrasound examination serves as a valuable tool, allowing direct observation of the relative positional relationship between the pubic symphysis and fetal head (PSFH). Accurate assessment of fetal head descent and the prediction of the most suitable mode of delivery heavily rely on this relationship. However, achieving an objective and quantitative interpretation of the ultrasound images necessitates precise PSFH segmentation (PSFHS), a task that is both time-consuming and demanding. Integrating the potential of artificial intelligence (AI) in the field of medical ultrasound image segmentation, the development and evaluation of AI-based models rely significantly on access to comprehensive and meticulously annotated datasets. Unfortunately, publicly accessible datasets tailored for PSFHS are notably scarce. Bridging this critical gap, we introduce a PSFHS dataset comprising 1358 images, meticulously annotated at the pixel level. The annotation process adhered to standardized protocols and involved collaboration among medical experts. Remarkably, this dataset stands as the most expansive and comprehensive resource for PSFHS to date.

Abstract PO2-29-02: Towards Precision Medicine in Breast Imaging: A Novel Open Mammography Database with Tailor-Made 3D Image Retrieval for Artificial Intelligence and Teaching

Abstract Objectives: According to the World Health Organization (WHO), breast cancer is the most frequent malignant neoplasia and leading cause of cancer death among women worldwide. Low- and middle-income countries hold the worst survival rates mainly owing to a lack of access to appropriate diagnosis and treatment related resources. For proper early diagnosis, it is established that besides the physical structure itself (e.g., mammography units), there's a need for adequate interpretation of imaging and that might be a particularly major problem in low-income societies once there is a tendency of greater education setbacks. Mammography datasets can improve this resource-driven gap by enabling the development of artificial intelligence technologies (AI) which can make breast cancer diagnosis more accurate in a cost-effective and scalable way. We aim to create a new database of high quality digital mammography images suitable for AI development and education. Methods: Our mammography database was developed by means of retrospective selection of 100 exams performed by Hospital São Paulo - Federal University of São Paulo ranging from 2019 to 2023. The project is assumed to be safe, versatile, and usable, and required an extensive search for the appropriate tool. Ambra Health, an American company, has developed cloud-based software for medical image management and stood out as a viable alternative. Their platform meets international data security criteria, they also made the intended careful customization possible, in addition to the possibility of associating image and text attachments. The categories were created in accordance with the BI-RADS® descriptors, a wide range of clinical scenarios and additional materials available, and they served as the basis for the advanced search feature, which intuitively filters exams that meet the selected criteria simultaneously. The platform was integrated with an automatic anonymization system upon upload, ensuring data privacy. After submission, the exams are retained in a restricted area for anonymization verification, categorization, and attachment management, before being released to the end-user. So as to broaden geographic coverage, the descriptors were entered in American English, respecting the origin of the BI-RADS® lexicon, as for the website structure, automatic translation to the accessing browser standard language was selected. Results: Our website is active and available at http://mamografia.unifesp.br, with access granted upon a simple registration process. 941 mammography images from 100 anonymized cases, 62% of which include 3D images, can be filtered based on the combination of 113 clinical and imaging variables, as well as attachment availability. The language is adaptable to the user's native language, and categorized searches can be accessed directly from the browser or downloaded as customized datasets. Additionally, features such as saved searches or starred exams are also available. Conclusion: We have developed an online and free mammography database that is completely innovative by integrating various resources into a single platform. We provide high-resolution and 3D digital images that can be searched using an advanced search system. Moreover, we offer supplementary clinical information in various attachment formats, favoring a rich clinical correlation. In this way, we have achieved the ambivalence of our goal, which was to promote education and research. *"images speak louder than words" Database: https://mamografia.unifesp.br Tutorials: https://www.youtube.com/@Mamografiaunifesp e-mail: acesso@mamografia.unifesp.br password: acesso@mamografia12 (valid until dec/23) Citation Format: Natália Cordeiro, Gil Facina, Afonso Nazário, Vanessa Sanvido, Joaquim Araujo Neto, Morgana Silva, Simone Elias. Towards Precision Medicine in Breast Imaging: A Novel Open Mammography Database with Tailor-Made 3D Image Retrieval for Artificial Intelligence and Teaching [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-29-02.

High-performance computing in healthcare:an automatic literature analysis perspective

The adoption of high-performance computing (HPC) in healthcare has gained significant attention in recent years, driving advancements in medical research and clinical practice. Exploring the literature on HPC implementation in healthcare is valuable for decision-makers as it provides insights into potential areas for further investigation and investment. However, manually analyzing the vast number of scholarly articles is a challenging and time-consuming task. Fortunately, topic modeling techniques offer the capacity to process extensive volumes of scientific literature, identifying key trends within the field. This paper presents an automatic literature analysis framework based on a state-of-art vector-based topic modeling algorithm with multiple embedding techniques, unveiling the research trends surrounding HPC utilization in healthcare. The proposed pipeline consists of four phases: paper extraction, data preprocessing, topic modeling and outlier detection, followed by visualization. It enables the automatic extraction of meaningful topics, exploration of their interrelationships, and identification of emerging research directions in an intuitive manner. The findings highlight the transition of HPC adoption in healthcare from traditional numerical simulation and surgical visualization to emerging topics such as drug discovery, AI-driven medical image analysis, and genomic analysis, as well as correlations and interdisciplinary connections among application domains.

Automated Analysis of Split Kidney Function from CT Scans Using Deep Learning and Delta Radiomics.

Background: Differential kidney function assessment is an important part of preoperative evaluation of various urological interventions. It is obtained through dedicated nuclear medical imaging and is not yet implemented through conventional Imaging. Objective: We assess if differential kidney function can be obtained through evaluation of contrast-enhanced computed tomography(CT) using a combination of deep learning and (2D and 3D) radiomic features. Methods: All patients who underwent kidney nuclear scanning at Mayo Clinic sites between 2018-2022 were collected. CT scans of the kidneys were obtained within a 3-month interval before or after the nuclear scans were extracted. Patients who underwent a urological or radiological intervention within this time frame were excluded. A segmentation model was used to segment both kidneys. 2D and 3D radiomics features were extracted and compared between the two kidneys to compute delta radiomics and assess its ability to predict differential kidney function. Performance was reported using receiver operating characteristics, sensitivity, and specificity. Results: Studies from Arizona & Rochester formed our internal dataset (n = 1,159). Studies from Florida were separately processed as an external test set to validate generalizability. We obtained 323 studies from our internal sites and 39 studies from external sites. The best results were obtained by a random forest model trained on 3D delta radiomics features. This model achieved an area under curve (AUC) of 0.85 and 0.81 on internal and external test sets, while specificity and sensitivity were 0.84,0.68 on the internal set, 0.70, and 0.65 on the external set. Conclusion: This proposed automated pipeline can derive important differential kidney function information from contrast-enhanced CT and reduce the need for dedicated nuclear scans for early-stage differential kidney functional assessment. Clinical Impact: We establish a machine learning methodology for assessing differential kidney function from routine CT without the need for expensive and radioactive nuclear medicine scans.

Machine learning and deep learning algorithms in detecting COVID-19 utilizing medical images: a comprehensive review

Machine learning and deep learning algorithms in detecting COVID-19 utilizing medical images: a comprehensive review

Feasibility of acousto-electric tomography

Abstract In acousto-electric tomography (AET) the goal is to reconstruct the electric conductivity in a domain from electrostatic boundary measurements of corresponding currents and voltages, while the domain is perturbed by a time-dependent acoustic wave, thus taking advantage of the acousto-electric effect. We approach the AET reconstruction in two steps: First, the interior power density is obtained from boundary measurements by solving a linear inverse and ill-posed problem; second, the interior conductivity is reconstructed from the power density by solving a non-linear and well-posed problem. Mathematically these inverse problems are fairly well understood, and reconstruction methods work well on synthetic data. This is in contrast to experimental findings. An effect can indeed be observed and data can be collected. However, the acousto-electric coupling is very weak, and consequently, the change in the measured voltage due to the acoustic perturbation might be too small compared to the background noise for viable reconstructions. 

In this paper, we take one step towards understanding the feasibility of AET. We provide an in-silico model of the coupled physics scenario based on standard models for the individual phenomena. Moreover, we formulate and implement numerically a full reconstruction method for the inverse problem via the two steps. We perform computational experiments with realistically chosen parameters from the context of medical imaging. The focus is on understanding the role of the acousto-electric coupling parameter and the signal-to-noise ratio (SNR). The critical signal strength is analyzed and the omnipresent Johnson-Nyquist noise is estimated. We obtain both positive and negative findings; we can reconstruct features even under severe noise conditions, but we also find that the SNR one is likely to face in practice is too low to obtain useful reconstructions.

Deep Learning Approaches for Medical Image Analysis and Diagnosis

Deep Learning Approaches for Medical Image Analysis and Diagnosis

Abstract PO1-10-01: Racial/Ethnic Disparities in Rates of Pathological Complete Response and Survival in Patients with Inflammatory Breast Cancer

Abstract Radiation Therapy Toxicities and Survival Outcomes in Monoallelic ATM Variant Carriers with Non-Metastatic Breast Cancer: A Retrospective Analysis Rayan Bensenane1 MD, Arnaud Beddok1,2,3 MD, Nadine Andrieu4 PhD, Fabienne Lesueur4 PhD, Eve Cavaciuti 4 MSc, Dorothee Le Gal4 MSc, Eon-Marchais Severine4 PhD, Dominique Stoppa Lyonnet 5MD PhD, Youlia Kirova1 MD 1. Institut Curie, PSL Research University, Radiation Oncology Department, Paris/Saint-Cloud/Orsay, France. 2. Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, 125 Nashua St., Boston, MA, 02114, USA 3. Institut Curie, PSL Research University, University Paris Saclay, Inserm LITO U1288 Orsay, France 4. Inserm, U900, Institut Curie, PSL Research University, Mines ParisTech, Paris, France 5.Department of Genetics, Institut Curie; Inserm U830, Institut Curie; Paris-Cité University Abstract (characters: 2952; max 3400 characters, not include spaces) Background: The Ataxia-Telangiectasia Mutated (ATM) gene, involved in the repair of DNA double-strand breaks, can contribute to radiosensitivity when a bi-allelic variant is present and lead to Ataxia-Telangiectasia syndrome. Moreover, monoallelic ATM pathologic variant (PV) carriers, especially women, has an estimated occurrence rate of 0.5-1% globally and face a 2 to 3-fold increased risk of developing breast cancer. Despite evidence of in vitro radiosensitivity in cells derived from monoallelic variant carriers, there is a dearth of patient studies examining the risk of radiation-induced toxicity. This study aims to explore radiation therapy (RT) toxicities in non-metastatic breast cancer women carrying a germline monoallelic ATM variant, compared to non-carriers. Methods: A retrospective study was conducted on patients treated at Institut Curie, Paris from 1999 to 2014 and participating to CoF-AT (a French national study) and GENESIS database. ATM variant screenings encompassed both PV and non-PV, with toxicities evaluated using CTCAE v.5. Variants were classified as pathogenic, variant of unknown significance (VUS), or benign. Follow-up started from age/date at breast cancer to acute, late toxicities, disease recurrence or last news. Survival and toxicity comparisons were made using Kaplan-Meier survival analysis and Chi-square tests, respectively, with a significance level of α set at 0.05. Results: Among 50 patients, nine were ATM variant carriers (3 PV/5 VUS/1 benign), and 41 were non-carriers. Most patients had no smoking history (68%), and invasive ductal carcinoma was the predominant diagnosis (82%). The majority underwent breast-conservative surgery (80%), and the dominant RT techniques were 3D-Conformational Radiation Therapy (70%) and Isocentric Lateral Decubitus (30%). The median RT dose was 50 Gy over an average period of 36.5 days. With a median follow-up of 12 years post-diagnosis, no significant difference in acute dermatitis, esophagitis, lymphedema, cutaneous fibrosis, telangiectasia, or heart disease was observed between the groups. Analysis of overall survival (OS) showed a 5-year OS of 98%, decreasing to 89% at 10 years. For ATM variant carriers, the OS at 5, 10, and 15 years was 100%, 89%, and 89%, respectively, similar to non-carriers. Kaplan-Meier analysis revealed no significant differences in 5, 10, and 15-year overall survival, progression-free survival, local failure-specific survival, and contralateral breast cancer rates between the groups. Conclusion: In non-metastatic breast cancer patients, monoallelic ATM variant carrier status does not significantly influence acute or late RT toxicities and survival outcomes. These findings, derived from a small cohort, highlight the need for prospective studies for further validation. Table: Acute and Late Toxicities Post-Radiation Therapy in Monoallelic ATM Variant Carriers vs Non-Carriers Citation Format: Rebecca Zasloff, Samantha Thomas, Kendra Parrish, Astrid Botty van de Bruele, Gayle DiLalla, Maggie DiNome, Laura Rosenberger, Hannah Woriax, E Shelley Hwang, Jennifer Plichta, Akiko Chiba. Racial/Ethnic Disparities in Rates of Pathological Complete Response and Survival in Patients with Inflammatory Breast Cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-10-01.

May 2024 Medical Image of the Month: Hereditary Hemorrhagic Telangiectasia in a Patient on Veno-Arterial Extra-Corporeal Membrane Oxygenation

No abstract available. Manuscript truncated after 150 words. A 54-year-old man with a complex cardiac history, including Tetralogy of Fallot requiring Blalock-Taussig shunt in infancy, infundibular patch repair at age 7, and bioprosthetic tricuspid valve replacement at age 52, had ongoing frequent hospitalizations with decompensated right ventricular heart failure secondary to native pulmonary valve mixed stenosis plus regurgitation and left pulmonary artery stenosis. His case was further complicated by his history of hereditary hemorrhagic telangiectasia (HHT) with recurrent epistaxis and recent GI bleeds with multiple angiodysplastic lesions throughout the stomach, duodenum, and descending colon which were previously treated with argon plasma coagulation. The patient was admitted to our hospital in NYHA class IV heart failure receiving a continuous dopamine infusion and aggressive diuresis. Upon admission, a right heart catheterization demonstrated severe pulmonary valve regurgitation, left pulmonary artery stenosis, and systemic hypoxemia suggestive of an intrapulmonary shunt. Admission transthoracic echocardiogram demonstrated normal left ventricular ejection fraction of 55-60%, a …

Abstract PO1-23-05: Exploratory clinical trial of preoperative non-invasive localization before surgery in breast cancer patients using augmented reality technology

Abstract Purpose: A single-center, randomized, prospective exploratory clinical trial to assess the clinical efficacy of augmented reality(AR)-based breast cancer localization medical imaging solution in patients with breast cancer Methods: This prospective exploratory clinical trial enrolled 20 women who were diagnosed with invasive breast cancer between the ages of 19 and 70, had a single lesion or multifocal lesion with a lesion size of 5mm or more and 30mm or less, had no metastasis to other organs, and had not received prior chemotherapy. All patients underwent mammography, ultrasound, CT, and MRI for preoperative assessment. Patients were randomly assigned to US-guided skin marking (control) and SKIA-breast (AR localization) groups of 10 each. Result: Two surgeons performed breast-conserving surgery on twenty patients. Pathologic evaluation of all patients confirmed negative margins. Two independent pathologists evaluated marginal distance, and neither the two reader's estimates (R1, 6.20±4.37 vs. 5.04±3.47, p=0.519; R2, 5.10±4.31 vs. 4.10±2.38, p= 0.970) nor the two reader's average values (5.65±4.19 vs. 4.57±2.84, p= 0.509) showed any difference between the two groups. In comparing the tumor plane area ratio, there was no statistically significant difference between the two groups for the two readers (R1, 15.90±9.52 vs. 19.38±14.05, p=0.525; R2, 15.32±9.48 vs. 20.83±12.85, p=0.290) and the two reader's mean values (15.56±9.11 vs. 20.09±13.38, p=0.388). Based on the two surgeons' responses, convenience, safety, satisfaction, and reusability were all superior in the AR localization group (p=0.000). Conclusion: AR localization is an acceptable alternative to US-guided skin marking with no significant differences in surgical outcomes. Citation Format: Minah Lee, Jun Woo Lee, Woosung Lim, Joohyun Woo, Hyun-Goo Kim, Se Hyun Paek, SangHui Park, Ji Min Kim, Jin Chung, Jee Eun Lee, Jeoung Hyun Kim. Exploratory clinical trial of preoperative non-invasive localization before surgery in breast cancer patients using augmented reality technology [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-23-05.

Artificial intelligence for computer aided detection of pneumoconiosis: A succinct review since 1974

With the increasing availability of medical imaging data and advancements in artificial intelligence (AI) and computer vision (CV) techniques, computer aided diagnostic (CAD) systems have been consistently developed to help radiologists in the detection of pneumoconiosis. Pneumoconiosis is a respiratory disease caused by long term exposure of industrial dust. Pneumoconiosis has remained prevalent, even in countries with sophisticated healthcare systems and strict workplace measures. Consequently, this review article focuses on cascading the literature of existing CAD systems for pneumoconiosis diagnosis since 1974, providing a baseline for future research in this domain. For this purpose, 58 relevant articles were first selected after employing strict inclusion criteria, through 10 reliable databases and search engines, including Scopus, IEEE, Google Scholar, and PubMed etc. This review then systematically categorizes the selected CAD studies into two patterns, based on the employed methodology for pneumoconiosis diagnosis: texture-based and non-texture-based CAD systems. This study reveals that texture-based methods have been extensively adopted for pneumoconiosis diagnosis compared to non-texture-based methods (or deep learning based). However, deep learning approaches have shown superior performance thanks to the recent availability of large annotated CXR datasets and development of deep convolutional neural network (CNN) and transformer-based architectures. Finally, the analysis is concluded with a discussion on the shortcomings of current CAD systems and some suggested future directions for the development of effective diagnostic systems. Additionally, a number of benchmark datasets have also been discussed.

Abstract PO1-22-05: Radiation Therapy Toxicities and Survival Outcomes in Monoallelic ATM Variant Carriers with Non-Metastatic Breast Cancer: A Retrospective Analysis

Abstract Radiation Therapy Toxicities and Survival Outcomes in Monoallelic ATM Variant Carriers with Non-Metastatic Breast Cancer: A Retrospective Analysis Rayan Bensenane1 MD, Arnaud Beddok1,2,3 MD, Nadine Andrieu4 PhD, Fabienne Lesueur4 PhD, Eve Cavaciuti 4 MSc, Dorothee Le Gal4 MSc, Eon-Marchais Severine4 PhD, Dominique Stoppa Lyonnet 5MD PhD, Youlia Kirova1 MD 1. Institut Curie, PSL Research University, Radiation Oncology Department, Paris/Saint-Cloud/Orsay, France. 2. Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, 125 Nashua St., Boston, MA, 02114, USA 3. Institut Curie, PSL Research University, University Paris Saclay, Inserm LITO U1288 Orsay, France 4. Inserm, U900, Institut Curie, PSL Research University, Mines ParisTech, Paris, France Abstract (characters: 2952; max 3400 characters, not include spaces) Background: The Ataxia-Telangiectasia Mutated (ATM) gene, involved in the repair of DNA double-strand breaks, can contribute to radiosensitivity when a bi-allelic variant is present and lead to Ataxia-Telangiectasia syndrome. Moreover, monoallelic ATM pathologic variant (PV) carriers, especially women, has an estimated occurrence rate of 0.5-1% globally and face a 2 to 3-fold increased risk of developing breast cancer. Despite evidence of in vitro radiosensitivity in cells derived from monoallelic variant carriers, there is a dearth of patient studies examining the risk of radiation-induced toxicity. This study aims to explore radiation therapy (RT) toxicities in non-metastatic breast cancer women carrying a germline monoallelic ATM variant, compared to non-carriers. Methods: A retrospective study was conducted on patients treated at Institut Curie, Paris from 1999 to 2014 and participating to CoF-AT (a French national study) and GENESIS database. ATM variant screenings encompassed both PV and non-PV, with toxicities evaluated using CTCAE v.5. Variants were classified as pathogenic, variant of unknown significance (VUS), or benign. Follow-up started from age/date at breast cancer to acute, late toxicities, disease recurrence or last news. Survival and toxicity comparisons were made using Kaplan-Meier survival analysis and Chi-square tests, respectively, with a significance level of α set at 0.05. Results: Among 50 patients, nine were ATM variant carriers (3 PV/5 VUS/1 benign), and 41 were non-carriers. Most patients had no smoking history (68%), and invasive ductal carcinoma was the predominant diagnosis (82%). The majority underwent breast-conservative surgery (80%), and the dominant RT techniques were 3D-Conformational Radiation Therapy (70%) and Isocentric Lateral Decubitus (30%). The median RT dose was 50 Gy over an average period of 36.5 days. With a median follow-up of 12 years post-diagnosis, no significant difference in acute dermatitis, esophagitis, lymphedema, cutaneous fibrosis, telangiectasia, or heart disease was observed between the groups. Analysis of overall survival (OS) showed a 5-year OS of 98%, decreasing to 89% at 10 years. For ATM variant carriers, the OS at 5, 10, and 15 years was 100%, 89%, and 89%, respectively, similar to non-carriers. Kaplan-Meier analysis revealed no significant differences in 5, 10, and 15-year overall survival, progression-free survival, local failure-specific survival, and contralateral breast cancer rates between the groups. Conclusion: In non-metastatic breast cancer patients, monoallelic ATM variant carrier status does not significantly influence acute or late RT toxicities and survival outcomes. These findings, derived from a small cohort, highlight the need for prospective studies for further validation. Table: Acute and Late Toxicities Post-Radiation Therapy in Monoallelic ATM Variant Carriers vs Non-Carriers * Pearson/Chi2 test ; NS: non significant at α=0.05; ATM +/+: wild type for ATM; ATM +/- : ATM monoallelic germline variant carrier Citation Format: Rayan BENSENANE, Youlia Kirova, Arnaud BEDDOK, Andine ANDRIEU, Fabienne Lesueur, Eve CAVACIUTI, Dorothée Le GAL, Severine EON-MARCHAIS, Dominique STOPPA LYONNET. Radiation Therapy Toxicities and Survival Outcomes in Monoallelic ATM Variant Carriers with Non-Metastatic Breast Cancer: A Retrospective Analysis [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-22-05.

Which health conditions report the most spending on medical imaging? Evidence for Colombia

Medical imaging is essential for the proper diagnosis and treatment of many diseases. The literature has found that medical imaging generally accounts for a significant percentage of total healthcare spending. We analyzed a national database between 2013 and 2021, with more than 19 million patients on average, to review which health conditions account for the highest spending on medical imaging in the Colombian health system. We segmented the analysis by type of medical imaging, life cycles, health condition and sex. Our findings indicate that cardiac and mental illnesses account for the highest per capita spending on medical imaging, especially for the elderly. As a proportion of total expenditure, hypertension and tuberculosis are added, with special emphasis on the infancy-childhood life cycle.

A data augmentation approach that ensures the reliability of foregrounds in medical image segmentation

Medical image segmentation is an important task in medical imaging and diagnosis. Data augmentation can substantially improve the accuracy of medical image segmentation when the dataset has a small amount of medical images. However, the data augmentation methods for medical image are usually based on big models that require extensive search space. Furthermore, excessively complex models often have a heavy burden for the general healthcare organization or researcher. To address this problem, we propose a method of data augmentation that is simple to implement even for the general researcher and simple to transplant across various models. Here we introduce our new methods called KeepMask and KeepMix, which can be simply ported to a variety of models and provide high performance. These methods allow data augmentation without any effect on the target organ or lesion and can also be adapted to multi-class segmentation. KeepMask and KeepMix can not only perturb the background of an existing medical image but also add target organs that are not present to it and generate new images based on the image. In this paper, we performed our methods on both binary class datasets and multi-class datasets and obtained better performance. We conducted numerous experiments showing the predicted segmentation images using our proposed methods obtained more accurate boundaries.

Application of convolutional neural networks in medical images: a bibliometric analysis.

In the field of medical imaging, the rapid rise of convolutional neural networks (CNNs) has presented significant opportunities for conserving healthcare resources. However, with the wide spread application of CNNs, several challenges have emerged, such as enormous data annotation costs, difficulties in ensuring user privacy and security, weak model interpretability, and the consumption of substantial computational resources. The fundamental challenge lies in optimizing and seamlessly integrating CNN technology to enhance the precision and efficiency of medical diagnosis. This study sought to provide a comprehensive bibliometric overview of current research on the application of CNNs in medical imaging. Initially, bibliometric methods were used to calculate the frequency statistics, and perform the cluster analysis and the co-citation analysis of countries, institutions, authors, keywords, and references. Subsequently, the latent Dirichlet allocation (LDA) method was employed for the topic modeling of the literature. Next, an in-depth analysis of the topics was conducted, and the topics in the medical field, technical aspects, and trends in topic evolution were summarized. Finally, by integrating the bibliometrics and LDA results, the developmental trajectory, milestones, and future directions in this field were outlined. A data set containing 6,310 articles in this field published from January 2013 to December 2023 was complied. With a total of 55,538 articles, the United States led in terms of the citation count, while in terms of the publication volume, China led with 2,385 articles. Harvard University emerged as the most influential institution, boasting an average of 69.92 citations per article. Within the realm of CNNs, residual neural network (ResNet) and U-Net stood out, receiving 1,602 and 1,419 citations, respectively, which highlights the significant attention these models have received. The impact of coronavirus disease 2019 (COVID-19) was unmistakable, as reflected by the publication of 597 articles, making it a focal point of research. Additionally, among various disease topics, with 290 articles, brain-related research was the most prevalent. Computed tomography (CT) imaging dominated the research landscape, representing 73% of the 30 different topics. Over the past 11 years, CNN-related research in medical imaging has grown exponentially. The findings of the present study provide insights into the field's status and research hotspots. In addition, this article meticulously chronicled the development of CNNs and highlighted key milestones, starting with LeNet in 1989, followed by a challenging 20-year exploration period, and culminating in the breakthrough moment with AlexNet in 2012. Finally, this article explored recent advancements in CNN technology, including semi-supervised learning, efficient learning, trustworthy artificial intelligence (AI), and federated learning methods, and also addressed challenges related to data annotation costs, diagnostic efficiency, model performance, and data privacy.

3D-DGGAN: A Data-Guided Generative Adversarial Network for High Fidelity in Medical Image Generation.

Three-dimensional images are frequently used in medical imaging research for classification, segmentation, and detection. However, the limited availability of 3D images hinders research progress due to network training difficulties. Generative methods have been proposed to create medical images using AI techniques. Nevertheless, 2D approaches have difficulty dealing with 3D anatomical structures, which can result in discontinuities between slices. To mitigate these discontinuities, several 3D generative networks have been proposed. However, the scarcity of available 3D images makes training these networks with limited samples inadequate for producing high-fidelity 3D images. We propose a data-guided generative adversarial network to provide high fidelity in 3D image generation. The generator creates fake images with noise using reference code obtained by extracting features from real images. The generator also creates decoded images using reference code without noise. These decoded images are compared to the real images to evaluate fidelity in the reference code. This generation process can create high-fidelity 3D images from only a small amount of real training data. Additionally, our method employs three types of discriminator: volume (evaluates all the slices), slab (evaluates a set of consecutive slices), and slice (evaluates randomly selected slices). The proposed discriminator enhances fidelity by differentiating between real and fake images based on detailed characteristics. Results from our method are compared with existing methods by using quantitative analysis such as Fréchet inception distance and maximum mean discrepancy. The results demonstrate that our method produces more realistic 3D images than existing methods.

Individualized image region detection with total variation

AbstractMedical image data have emerged to be an indispensable component of modern medicine. Different from many general image problems that focus on outcome prediction or image recognition, medical image analysis pays more attention to model interpretation. For instance, given a list of medical images and corresponding labels of patients' health status, it is often of greater importance to identify the image regions that could differentiate the outcome status, compared to simply predicting labels of new images. Moreover, medical image data often demonstrate strong individual heterogeneity. In other words, the image regions associated with an outcome could be different across patients. As a consequence, the traditional one‐model‐fits‐all approach not only omits patient heterogeneity but also possibly leads to misleading or even wrong conclusions. In this article, we introduce a novel statistical framework to detect individualized regions that are associated with a binary outcome, that is, whether a patient has a certain disease or not. Moreover, we propose a total variation‐based penalization for individualized image region detection under a local label‐free scenario. Considering that local labeling is often difficult to obtain for medical image data, our approach may potentially have a wider range of applications in medical research. The effectiveness of our proposed approach is validated by two real histopathology databases: Colon Cancer and Camelyon16.

Efficient skin lesion segmentation with boundary distillation.

Medical image segmentation models are commonly known for their complex structures, which often render them impractical for use on edge computing devices and compromising efficiency in the segmentation process. In light of this, the industry has proposed the adoption of knowledge distillation techniques. Nevertheless, the vast majority of existing knowledge distillation methods are focused on the classification tasks of skin diseases. Specifically, for the segmentation tasks of dermoscopy lesion images, these knowledge distillation methods fail to fully recognize the importance of features in the boundary regions of lesions within medical images, lacking boundary awareness for skin lesions. This paper introduces pioneering medical image knowledge distillation architecture. The aim of this method is to facilitate the efficient transfer of knowledge from existing complex medical image segmentation networks to a more simplified student network. Initially, a masked boundary feature (MBF) distillation module is designed. By applying random masking to the periphery of skin lesions, the MBF distillation module obliges the student network to reproduce the comprehensive features of the teacher network. This process, in turn, augments the representational capabilities of the student network. Building on the MBF distillation module, this paper employs a cascaded combination approach to integrate the MBF distillation module into a multi-head boundary feature (M2BF) distillation module, further strengthening the student network's feature learning ability and enhancing the overall image segmentation performance of the distillation model. This method has been experimentally validated on the public datasets ISIC-2016 and PH2, with results showing significant performance improvements in the student network. Our findings highlight the practical utility of the lightweight network distilled using our approach, particularly in scenarios demanding high operational speed and minimal storage usage. This research offers promising prospects for practical applications in the realm of medical image segmentation.

Studying the History of Histopathology in Preclinical Medical Education as a Guide for the Uniform Integration of Radiology in Medical Education

Radiology and pathology, though distinct fields within medical education, share a common foundation in their essential roles for accurate diagnosis and understanding of diseases. While pathology, particularly histopathology, has long been integrated into preclinical medical education in the United States, radiology education has traditionally been less emphasized. This paper examines the historical development of histopathology training in medical education and its central role, contrasting it with the comparatively peripheral position of radiology education. We explore the historical context of medical education in the United States, tracing the integration of histopathology following the Flexner Report of 1910. In contrast, radiology, emerging later as a specialized field, has faced challenges in achieving comparable integration into medical curricula. Despite the increasing importance of medical imaging in diagnosis and treatment, radiology education remains variable and often lacking in standardization across medical schools. We highlight the need for greater emphasis on radiology education to better prepare medical students for modern clinical practice, where medical imaging plays an increasingly pivotal role. A call for a comprehensive assessment of radiology education and advocacy for its integration into preclinical curricula is made, emphasizing the importance of collaboration between the radiology profession and accrediting bodies to ensure competence in imaging across medical specialties. As medical imaging continues to advance and become more integral to healthcare, it is imperative that medical education reflects this evolution by establishing radiology as a fundamental component of preclinical training.