Comparing Commercial and Open-Source Large Language Models for Labeling Chest Radiograph Reports.

Background Rapid advances in large language models (LLMs) have led to the development of numerous commercial and open-source models. While recent publications have explored OpenAI's GPT-4 to extract information of interest from radiology reports, there has not been a real-world comparison of GPT-4 to leading open-source models. Purpose To compare different leading open-source LLMs to GPT-4 on the task of extracting relevant findings from chest radiograph reports. Materials and Methods Two independent datasets of free-text radiology reports from chest radiograph examinations were used in this retrospective study performed between February 2, 2024, and February 14, 2024. The first dataset consisted of reports from the ImaGenome dataset, providing reference standard annotations from the MIMIC-CXR database acquired between 2011 and 2016. The second dataset consisted of randomly selected reports created at the Massachusetts General Hospital between July 2019 and July 2021. In both datasets, the commercial models GPT-3.5 Turbo and GPT-4 were compared with open-source models that included Mistral-7B and Mixtral-8 × 7B (Mistral AI), Llama 2-13B and Llama 2-70B (Meta), and Qwen1.5-72B (Alibaba Group), as well as CheXbert and CheXpert-labeler (Stanford ML Group), in their ability to accurately label the presence of multiple findings in radiograph text reports using zero-shot and few-shot prompting. The McNemar test was used to compare F1 scores between models. Results On the ImaGenome dataset (n = 450), the open-source model with the highest score, Llama 2-70B, achieved micro F1 scores of 0.97 and 0.97 for zero-shot and few-shot prompting, respectively, compared with the GPT-4 F1 scores of 0.98 and 0.98 (P > .99 and < .001 for superiority of GPT-4). On the institutional dataset (n = 500), the open-source model with the highest score, an ensemble model, achieved micro F1 scores of 0.96 and 0.97 for zero-shot and few-shot prompting, respectively, compared with the GPT-4 F1 scores of 0.98 and 0.97 (P < .001 and > .99 for superiority of GPT-4). Conclusion Although GPT-4 was superior to open-source models in zero-shot report labeling, few-shot prompting with a small number of example reports closely matched the performance of GPT-4. The benefit of few-shot prompting varied across datasets and models. © RSNA, 2024 Supplemental material is available for this article.

Machine Learning for Adrenal Gland Segmentation and Classification of Normal and Adrenal Masses at CT.

Background Adrenal masses are common, but radiology reporting and recommendations for management can be variable. Purpose To create a machine learning algorithm to segment adrenal glands on contrast-enhanced CT images and classify glands as normal or mass-containing and to assess algorithm performance. Materials and Methods This retrospective study included two groups of contrast-enhanced abdominal CT examinations (development data set and secondary test set). Adrenal glands in the development data set were manually segmented by radiologists. Images in both the development data set and the secondary test set were manually classified as normal or mass-containing. Deep learning segmentation and classification models were trained on the development data set and evaluated on both data sets. Segmentation performance was evaluated with use of the Dice similarity coefficient (DSC), and classification performance with use of sensitivity and specificity. Results The development data set contained 274 CT examinations (251 patients; median age, 61 years; 133 women), and the secondary test set contained 991 CT examinations (991 patients; median age, 62 years; 578 women). The median model DSC on the development test set was 0.80 (IQR, 0.78-0.89) for normal glands and 0.84 (IQR, 0.79-0.90) for adrenal masses. On the development reader set, the median interreader DSC was 0.89 (IQR, 0.78-0.93) for normal glands and 0.89 (IQR, 0.85-0.97) for adrenal masses. Interreader DSC for radiologist manual segmentation did not differ from automated machine segmentation (P = .35). On the development test set, the model had a classification sensitivity of 83% (95% CI: 55, 95) and specificity of 89% (95% CI: 75, 96). On the secondary test set, the model had a classification sensitivity of 69% (95% CI: 58, 79) and specificity of 91% (95% CI: 90, 92). Conclusion A two-stage machine learning pipeline was able to segment the adrenal glands and differentiate normal adrenal glands from those containing masses. © RSNA, 2022 Online supplemental material is available for this article.

Utility of Normalized Body Composition Areas, Derived From Outpatient Abdominal CT Using a Fully Automated Deep Learning Method, for Predicting Subsequent Cardiovascular Events.

BACKGROUND. CT-based body composition (BC) measurements have historically been too resource intensive to analyze for widespread use and have lacked robust comparison with traditional weight metrics for predicting cardiovascular risk. OBJECTIVE. The aim of this study was to determine whether BC measurements obtained from routine CT scans by use of a fully automated deep learning algorithm could predict subsequent cardiovascular events independently from weight, BMI, and additional cardiovascular risk factors. METHODS. This retrospective study included 9752 outpatients (5519 women and 4233 men; mean age, 53.2 years; 890 patients self-reported their race as Black and 8862 self-reported their race as White) who underwent routine abdominal CT at a single health system from January 2012 through December 2012 and who were given no major cardiovascular or oncologic diagnosis within 3 months of undergoing CT. Using publicly available code, fully automated deep learning BC analysis was performed at the L3 vertebral body level to determine three BC areas (skeletal muscle area [SMA], visceral fat area [VFA], and subcutaneous fat area [SFA]). Age-, sex-, and race-normalized reference curves were used to generate z scores for the three BC areas. Subsequent myocardial infarction (MI) or stroke was determined from the electronic medical record. Multivariable-adjusted Cox proportional hazards models were used to determine hazard ratios (HRs) for MI or stroke within 5 years after CT for the three BC area z scores, with adjustment for normalized weight, normalized BMI, and additional cardiovascular risk factors (smoking status, diabetes diagnosis, and systolic blood pressure). RESULTS. In multivariable models, age-, race-, and sex-normalized VFA was associated with subsequent MI risk (HR of highest quartile compared with lowest quartile, 1.31 [95% CI, 1.03-1.67], p = .04 for overall effect) and stroke risk (HR of highest compared with lowest quartile, 1.46 [95% CI, 1.07-2.00], p = .04 for overall effect). In multivariable models, normalized SMA, SFA, weight, and BMI were not associated with subsequent MI or stroke risk. CONCLUSION. VFA derived from fully automated and normalized analysis of abdominal CT examinations predicts subsequent MI or stroke in Black and White patients, independent of traditional weight metrics, and should be considered an adjunct to BMI in risk models. CLINICAL IMPACT. Fully automated and normalized BC analysis of abdominal CT has promise to augment traditional cardiovascular risk prediction models.

National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence.

The remarkable advances of artificial intelligence (AI) technology are revolutionizing established approaches to the acquisition, interpretation, and analysis of biomedical imaging data. Development, validation, and continuous refinement of AI tools requires easy access to large high-quality annotated datasets, which are both representative and diverse. The National Cancer Institute (NCI) Imaging Data Commons (IDC) hosts large and diverse publicly available cancer image data collections. By harmonizing all data based on industry standards and colocalizing it with analysis and exploration resources, the IDC aims to facilitate the development, validation, and clinical translation of AI tools and address the well-documented challenges of establishing reproducible and transparent AI processing pipelines. Balanced use of established commercial products with open-source solutions, interconnected by standard interfaces, provides value and performance, while preserving sufficient agility to address the evolving needs of the research community. Emphasis on the development of tools, use cases to demonstrate the utility of uniform data representation, and cloud-based analysis aim to ease adoption and help define best practices. Integration with other data in the broader NCI Cancer Research Data Commons infrastructure opens opportunities for multiomics studies incorporating imaging data to further empower the research community to accelerate breakthroughs in cancer detection, diagnosis, and treatment. Published under a CC BY 4.0 license.

Multilevel Body Composition Analysis on Chest Computed Tomography Predicts Hospital Length of Stay and Complications After Lobectomy for Lung Cancer: A Multicenter Study.

OBJECTIVE: To investigate the impact of thoracic body composition on outcomes after lobectomy for lung cancer. SUMMARY AND BACKGROUND DATA: Preoperative identification of patients at risk for adverse outcomes permits treatment modification. The impact of body composition on lung resection outcomes has not been investigated in a multicenter setting. METHODS: A total of 958 consecutive patients undergoing lobectomy for lung cancer at 3 centers from 2014 to 2017 were retrospectively analyzed. Muscle and adipose tissue cross-sectional area at the fifth, eighth, and tenth thoracic vertebral body was quantified. Prospectively collected outcomes from a national database were abstracted to characterize the association between sums of muscle and adipose tissue and hospital length of stay (LOS), number of any postoperative complications, and number of respiratory postoperative complications using multivariate regression. A priori determined covariates were forced expiratory volume in 1 second and diffusion capacity of the lungs for carbon monoxide predicted, age, sex, body mass index, race, surgical approach, smoking status, Zubrod and American Society of Anesthesiologists scores. RESULTS: Mean patient age was 67 years, body mass index 27.4 kg/m2 and 65% had stage i disease. Sixty-three percent underwent minimally invasive lobectomy. Median LOS was 4 days and 34% of patients experienced complications. Muscle (using 30 cm2 increments) was an independent predictor of LOS (adjusted coefficient 0.972; P = 0.002), any postoperative complications (odds ratio 0.897; P = 0.007) and postoperative respiratory complications (odds ratio 0.860; P = 0.010). Sarcopenic obesity was also associated with LOS and adverse outcomes. CONCLUSIONS: Body composition on preoperative chest computed tomography is an independent predictor of LOS and postoperative complications after lobectomy for lung cancer.

Computed tomography-based body composition profile as a screening tool for geriatric frailty detection.

OBJECTIVE: To assess prevalence of CT imaging-derived sarcopenia, osteoporosis, and visceral obesity in clinically frail and prefrail patients and determine their association with the diagnosis of frailty. MATERIALS AND METHODS: This cross-sectional study was constructed using our institution's pelvic trauma registry and ambulatory database registry. The study included all elderly pelvic trauma patients and ambulatory outpatients between May 2016 and March 2020 who had a comprehensive geriatric assessment and CT abdomen/pelvis within 1 year from the date of the assessment. Patients were dichotomized in prefrail or frail groups. The study excluded patients with history of metastatic disease or malignancy requiring chemotherapy. RESULTS: The study cohort consisted of 151 elderly female and 65 male patients. Each gender population was subdivided into frail (114 female [75%], 51 male [78%]) and prefrail (37 female [25%], 14 male [22%]) patients. CT-imaging-derived diagnosis of osteoporosis (odds ratio, 2.5; 95% CI: 1.2-5.5) and sarcopenia (odds ratio, 2.6; 95% CI: 1.2-5.6) were associated with frailty in females, but did not reach statistical significance in males. BMI and subcutaneous adipose tissue at L3 level were statistically lower in the frail male group compared to the prefrail group. BMI showed strong correlation with the subcutaneous area at the L3 level in both genders (Spearman's coefficient of 0.8, p < 0.001). Hypoalbuminemia and visceral obesity were not associated with frailty in either gender. CONCLUSION: This proof-of-concept study demonstrates the feasibility of using CT-derived body-composition parameters as a screening tool for frailty, which can offer an opportunity for early medical intervention.

Highdicom: a Python Library for Standardized Encoding of Image Annotations and Machine Learning Model Outputs in Pathology and Radiology.

Machine learning (ML) is revolutionizing image-based diagnostics in pathology and radiology. ML models have shown promising results in research settings, but the lack of interoperability between ML systems and enterprise medical imaging systems has been a major barrier for clinical integration and evaluation. The DICOM® standard specifies information object definitions (IODs) and services for the representation and communication of digital images and related information, including image-derived annotations and analysis results. However, the complexity of the standard represents an obstacle for its adoption in the ML community and creates a need for software libraries and tools that simplify working with datasets in DICOM format. Here we present the highdicom library, which provides a high-level application programming interface (API) for the Python programming language that abstracts low-level details of the standard and enables encoding and decoding of image-derived information in DICOM format in a few lines of Python code. The highdicom library leverages NumPy arrays for efficient data representation and ties into the extensive Python ecosystem for image processing and machine learning. Simultaneously, by simplifying creation and parsing of DICOM-compliant files, highdicom achieves interoperability with the medical imaging systems that hold the data used to train and run ML models, and ultimately communicate and store model outputs for clinical use. We demonstrate through experiments with slide microscopy and computed tomography imaging, that, by bridging these two ecosystems, highdicom enables developers and researchers to train and evaluate state-of-the-art ML models in pathology and radiology while remaining compliant with the DICOM standard and interoperable with clinical systems at all stages. To promote standardization of ML research and streamline the ML model development and deployment process, we made the library available free and open-source at https://github.com/herrmannlab/highdicom .

Muscle Loss Is Associated with Overall Survival in Patients with Metastatic Colorectal Cancer Independent of Tumor Mutational Status and Weight Loss.

BACKGROUND: Survival in patients with metastatic colorectal cancer (mCRC) has been associated with tumor mutational status, muscle loss, and weight loss. We sought to explore the combined effects of these variables on overall survival. MATERIALS AND METHODS: We performed an observational cohort study, prospectively enrolling patients receiving chemotherapy for mCRC. We retrospectively assessed changes in muscle (using computed tomography) and weight, each dichotomized as >5% or ≤5% loss, at 3, 6, and 12 months after diagnosis of mCRC. We used regression models to assess relationships between tumor mutational status, muscle loss, weight loss, and overall survival. Additionally, we evaluated associations between muscle loss, weight loss, and tumor mutational status. RESULTS: We included 226 patients (mean age 59 ± 13 years, 53% male). Tumor mutational status included 44% wild type, 42% RAS-mutant, and 14% BRAF-mutant. Patients with >5% muscle loss at 3 and 12 months experienced worse survival controlling for mutational status and weight (3 months hazard ratio, 2.66; p < .001; 12 months hazard ratio, 2.10; p = .031). We found an association of >5% muscle loss with BRAF-mutational status at 6 and 12 months. Weight loss was not associated with survival nor mutational status. CONCLUSION: Increased muscle loss at 3 and 12 months may identify patients with mCRC at risk for decreased overall survival, independent of tumor mutational status. Specifically, >5% muscle loss identifies patients within each category of tumor mutational status with decreased overall survival in our sample. Our findings suggest that quantifying muscle loss on serial computed tomography scans may refine survival estimates in patients with mCRC. IMPLICATIONS FOR PRACTICE: In this study of 226 patients with metastatic colorectal cancer, it was found that losing >5% skeletal muscle at 3 and 12 months after the diagnosis of metastatic disease was associated with worse overall survival, independent of tumor mutational status and weight loss. Interestingly, results did not show a significant association between weight loss and overall survival. These findings suggest that muscle quantification on serial computed tomography may refine survival estimates in patients with metastatic colorectal cancer beyond mutational status.

Population-Scale CT-based Body Composition Analysis of a Large Outpatient Population Using Deep Learning to Derive Age-, Sex-, and Race-specific Reference Curves.

Background Although CT-based body composition (BC) metrics may inform disease risk and outcomes, obtaining these metrics has been too resource intensive for large-scale use. Thus, population-wide distributions of BC remain uncertain. Purpose To demonstrate the validity of fully automated, deep learning BC analysis from abdominal CT examinations, to define demographically adjusted BC reference curves, and to illustrate the advantage of use of these curves compared with standard methods, along with their biologic significance in predicting survival. Materials and Methods After external validation and equivalency testing with manual segmentation, a fully automated deep learning BC analysis pipeline was applied to a cross-sectional population cohort that included any outpatient without a cardiovascular disease or cancer who underwent abdominal CT examination at one of three hospitals in 2012. Demographically adjusted population reference curves were generated for each BC area. The z scores derived from these curves were compared with sex-specific thresholds for sarcopenia by using χ2 tests and used to predict 2-year survival in multivariable Cox proportional hazards models that included weight and body mass index (BMI). Results External validation showed excellent correlation (R = 0.99) and equivalency (P < .001) of the fully automated deep learning BC analysis method with manual segmentation. With use of the fully automated BC data from 12 128 outpatients (mean age, 52 years; 6936 [57%] women), age-, race-, and sex-normalized BC reference curves were generated. All BC areas varied significantly with these variables (P < .001 except for subcutaneous fat area vs age [P = .003]). Sex-specific thresholds for sarcopenia demonstrated that age and race bias were not present if z scores derived from the reference curves were used (P < .001). Skeletal muscle area z scores were significantly predictive of 2-year survival (P = .04) in combined models that included BMI. Conclusion Fully automated body composition (BC) metrics vary significantly by age, race, and sex. The z scores derived from reference curves for BC parameters better capture the demographic distribution of BC compared with standard methods and can help predict survival. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Summers in this issue.

Associations of Skeletal Muscle With Symptom Burden and Clinical Outcomes in Hospitalized Patients With Advanced Cancer.

BACKGROUND: Low muscle mass (quantity) is common in patients with advanced cancer, but little is known about muscle radiodensity (quality). We sought to describe the associations of muscle mass and radiodensity with symptom burden, healthcare use, and survival in hospitalized patients with advanced cancer. METHODS: We prospectively enrolled hospitalized patients with advanced cancer from September 2014 through May 2016. Upon admission, patients reported their physical (Edmonton Symptom Assessment System [ESAS]) and psychological (Patient Health Questionnaire-4 [PHQ-4]) symptoms. We used CT scans performed per routine care within 45 days before enrollment to evaluate muscle mass and radiodensity. We used regression models to examine associations of muscle mass and radiodensity with patients' symptom burden, healthcare use (hospital length of stay and readmissions), and survival. RESULTS: Of 1,121 patients enrolled, 677 had evaluable muscle data on CT (mean age, 62.86 ± 12.95 years; 51.1% female). Older age and female sex were associated with lower muscle mass (age: B, -0.16; P<.001; female: B, -6.89; P<.001) and radiodensity (age: B, -0.33; P<.001; female: B, -1.66; P=.014), and higher BMI was associated with higher muscle mass (B, 0.58; P<.001) and lower radiodensity (B, -0.61; P<.001). Higher muscle mass was significantly associated with improved survival (hazard ratio, 0.97; P<.001). Notably, higher muscle radiodensity was significantly associated with lower ESAS-Physical (B, -0.17; P=.016), ESAS-Total (B, -0.29; P=.002), PHQ-4-Depression (B, -0.03; P=.006), and PHQ-4-Anxiety (B, -0.03; P=.008) symptoms, as well as decreased hospital length of stay (B, -0.07; P=.005), risk of readmission or death in 90 days (odds ratio, 0.97; P<.001), and improved survival (hazard ratio, 0.97; P<.001). CONCLUSIONS: Although muscle mass (quantity) only correlated with survival, we found that muscle radiodensity (quality) was associated with patients' symptoms, healthcare use, and survival. These findings underscore the added importance of assessing muscle quality when seeking to address adverse muscle changes in oncology.

Traumatic cervical spine fracture patterns on CT: a retrospective analysis at a level 1 trauma center.

PURPOSE: The purpose of our study was to determine common acute traumatic cervical spine fracture patterns on CT cervical spine (CTCS). METHODS: We retrospectively reviewed 1091 CTCS positive for traumatic fractures performed over a 10-year period at a level 1 trauma center. Fractures were classified by vertebral level, laterality, and anatomic location (anterior/posterior arch, body, odontoid, pedicle, facet, lateral mass, lamina, spinous process, transverse foramina, and transverse processes). RESULTS: C2 was the most commonly fractured vertebra (38% of all studies), followed by C7 (32.4%). 48.7% of studies had upper cervical spine (C1 and/or C2) fractures. 39.7% of positive studies involved > 1 vertebral level. Conditioned on fractures at one cervical level, the probability of fracture was greatest at adjacent levels with a 50% chance of sustaining a C7 fracture with C6 fracture. However, 31.3% (136) of studies with multi-level fractures had non-contiguous fractures. The most common isolated vertebral process fracture was of the transverse process, seen in 89 (8.2%) studies at a single level, 27 (2.5%) studies at multiple levels. Subaxial spine vertebral process fractures outnumbered body fractures with progressive dominance of vertebral process fracture down the spine. CONCLUSION: C2 was the most commonly fractured vertebral level. Multi-level traumatic cervical spine fractures constituted 40% of our cohort, most commonly at C6/C7 and C1/C2. Although the conditional probability of concurrent fracture in studies with multi-level fractures was greatest in contiguous levels, nearly one-third of multi-level fractures involved non-contiguous fractures.

The Trials and Tribulations of Assembling Large Medical Imaging Datasets for Machine Learning Applications.

With vast interest in machine learning applications, more investigators are proposing to assemble large datasets for machine learning applications. We aim to delineate multiple possible roadblocks to exam retrieval that may present themselves and lead to significant time delays. This HIPAA-compliant, institutional review board-approved, retrospective clinical study required identification and retrieval of all outpatient and emergency patients undergoing abdominal and pelvic computed tomography (CT) at three affiliated hospitals in the year 2012. If a patient had multiple abdominal CT exams, the first exam was selected for retrieval (n=23,186). Our experience in attempting to retrieve 23,186 abdominal CT exams yielded 22,852 valid CT abdomen/pelvis exams and identified four major categories of challenges when retrieving large datasets: cohort selection and processing, retrieving DICOM exam files from PACS, data storage, and non-recoverable failures. The retrieval took 3 months of project time and at minimum 300 person-hours of time between the primary investigator (a radiologist), a data scientist, and a software engineer. Exam selection and retrieval may take significantly longer than planned. We share our experience so that other investigators can anticipate and plan for these challenges. We also hope to help institutions better understand the demands that may be placed on their infrastructure by large-scale medical imaging machine learning projects.

Using DICOM Metadata for Radiological Image Series Categorization: a Feasibility Study on Large Clinical Brain MRI Datasets.

The growing interest in machine learning (ML) in healthcare is driven by the promise of improved patient care. However, how many ML algorithms are currently being used in clinical practice? While the technology is present, as demonstrated in a variety of commercial products, clinical integration is hampered by a lack of infrastructure, processes, and tools. In particular, automating the selection of relevant series for a particular algorithm remains challenging. In this work, we propose a methodology to automate the identification of brain MRI sequences so that we can automatically route the relevant inputs for further image-related algorithms. The method relies on metadata required by the Digital Imaging and Communications in Medicine (DICOM) standard, resulting in generalizability and high efficiency (less than 0.4 ms/series). To support our claims, we test our approach on two large brain MRI datasets (40,000 studies in total) from two different institutions on two different continents. We demonstrate high levels of accuracy (ranging from 97.4 to 99.96%) and generalizability across the institutions. Given the complexity and variability of brain MRI protocols, we are confident that similar techniques could be applied to other forms of radiological imaging.

Diffusion tensor transformation for personalizing target volumes in radiation therapy.

Diffusion tensor imaging (DTI) is used in tumor growth models to provide information on the infiltration pathways of tumor cells into the surrounding brain tissue. When a patient-specific DTI is not available, a template image such as a DTI atlas can be transformed to the patient anatomy using image registration. This study investigates a model, the invariance under coordinate transform (ICT), that transforms diffusion tensors from a template image to the patient image, based on the principle that the tumor growth process can be mapped, at any point in time, between the images using the same transformation function that we use to map the anatomy. The ICT model allows the mapping of tumor cell densities and tumor fronts (as iso-levels of tumor cell density) from the template image to the patient image for inclusion in radiotherapy treatment planning. The proposed approach transforms the diffusion tensors to simulate tumor growth in locally deformed anatomy and outputs the tumor cell density distribution over time. The ICT model is validated in a cohort of ten brain tumor patients. Comparative analysis with the tumor cell density in the original template image shows that the ICT model accurately simulates tumor cell densities in the deformed image space. By creating radiotherapy target volumes as tumor fronts, this study provides a framework for more personalized radiotherapy treatment planning, without the use of additional imaging.

Integrating muscle fiber orientation from visible human data into radiotherapy target volumes.

Objective.A major challenge in treatment of tumors near skeletal muscle is defining the target volume for suspected tumor invasion into the muscle. This study develops a framework that generates radiation target volumes with muscle fiber orientation directly integrated into their definition. The framework is applied to nineteen sacral tumor patients with suspected infiltration into surrounding muscles.Approach.To compensate for the poor soft-tissue contrast of CT images, muscle fiber orientation is derived from cryo-images of two cadavers from the human visible project (VHP). The approach consists of (a) detecting image gradients in the cadaver images representative of muscle fibers, (b) mapping this information onto the patient image, and (c) embedding the muscle fiber orientation into an expansion method to generate patient-specific clinical target volumes (CTV). The validation tested the consistency of image gradient orientation across VHP subjects for the piriformis, gluteus maximus, paraspinal, gluteus medius, and gluteus minimus muscles. The model robustness was analyzed by comparing CTVs generated using different VHP subjects. The difference in shape between the new CTVs and standard CTV was analyzed for clinical impact.Main results.Good agreement was found between the image gradient orientation across VHP subjects, as the voxel-wise median cosine similarity was at least 0.86 (for the gluteus minimus) and up to 0.98 for the piriformis. The volume and surface similarity between the CTVs generating from different VHP subjects was on average at least 0.95 and 5.13 mm for the Dice Similarity Coefficient and the Hausdorff 95% Percentile Index, showing excellent robustness. Finally, compared to the standard CTV with different margins in muscle and non-muscle tissue, the new CTV margins are reduced in muscle tissue depending on the chosen clinical margins.Significance.This study implements a method to integrate muscle fiber orientation into the target volume without the need for additional imaging.

From Machine Learning to Patient Outcomes: A Comprehensive Review of AI in Pancreatic Cancer.

Pancreatic cancer is a highly aggressive and difficult-to-detect cancer with a poor prognosis. Late diagnosis is common due to a lack of early symptoms, specific markers, and the challenging location of the pancreas. Imaging technologies have improved diagnosis, but there is still room for improvement in standardizing guidelines. Biopsies and histopathological analysis are challenging due to tumor heterogeneity. Artificial Intelligence (AI) revolutionizes healthcare by improving diagnosis, treatment, and patient care. AI algorithms can analyze medical images with precision, aiding in early disease detection. AI also plays a role in personalized medicine by analyzing patient data to tailor treatment plans. It streamlines administrative tasks, such as medical coding and documentation, and provides patient assistance through AI chatbots. However, challenges include data privacy, security, and ethical considerations. This review article focuses on the potential of AI in transforming pancreatic cancer care, offering improved diagnostics, personalized treatments, and operational efficiency, leading to better patient outcomes.

The influence of anisotropy on the clinical target volume of brain tumor patients.

Objective.Current radiotherapy guidelines for glioma target volume definition recommend a uniform margin expansion from the gross tumor volume (GTV) to the clinical target volume (CTV), assuming uniform infiltration in the invaded brain tissue. However, glioma cells migrate preferentially along white matter tracts, suggesting that white matter directionality should be considered in an anisotropic CTV expansion. We investigate two models of anisotropic CTV expansion and evaluate their clinical feasibility.Approach.To incorporate white matter directionality into the CTV, a diffusion tensor imaging (DTI) atlas is used. The DTI atlas consists of water diffusion tensors that are first spatially transformed into local tumor resistance tensors, also known as metric tensors, and secondly fed to a CTV expansion algorithm to generate anisotropic CTVs. Two models of spatial transformation are considered in the first step. The first model assumes that tumor cells experience reduced resistance parallel to the white matter fibers. The second model assumes that the anisotropy of tumor cell resistance is proportional to the anisotropy observed in DTI, with an 'anisotropy weighting parameter' controlling the proportionality. The models are evaluated in a cohort of ten brain tumor patients.Main results.To evaluate the sensitivity of the model, a library of model-generated CTVs was computed by varying the resistance and anisotropy parameters. Our results indicate that the resistance coefficient had the most significant effect on the global shape of the CTV expansion by redistributing the target volume from potentially less involved gray matter to white matter tissue. In addition, the anisotropy weighting parameter proved useful in locally increasing CTV expansion in regions characterized by strong tissue directionality, such as near the corpus callosum.Significance.By incorporating anisotropy into the CTV expansion, this study is a step toward an interactive CTV definition that can assist physicians in incorporating neuroanatomy into a clinically optimized CTV.

CASCADE: Context-Aware Data-Driven AI for Streamlined Multidisciplinary Tumor Board Recommendations in Oncology.

This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise.

No code machine learning: validating the approach on use-case for classifying clavicle fractures.

PURPOSE: We created an infrastructure for no code machine learning (NML) platform for non-programming physicians to create NML model. We tested the platform by creating an NML model for classifying radiographs for the presence and absence of clavicle fractures. METHODS: Our IRB-approved retrospective study included 4135 clavicle radiographs from 2039 patients (mean age 52 ± 20 years, F:M 1022:1017) from 13 hospitals. Each patient had two-view clavicle radiographs with axial and anterior-posterior projections. The positive radiographs had either displaced or non-displaced clavicle fractures. We configured the NML platform to automatically retrieve the eligible exams using the series' unique identification from the hospital virtual network archive via web access to DICOM Objects. The platform trained a model until the validation loss plateaus. Once the testing was complete, the platform provided the receiver operating characteristics curve and confusion matrix for estimating sensitivity, specificity, and accuracy. RESULTS: The NML platform successfully retrieved 3917 radiographs (3917/4135, 94.7 %) and parsed them for creating a ML classifier with 2151 radiographs in the training, 100 radiographs for validation, and 1666 radiographs in testing datasets (772 radiographs with clavicle fracture, 894 without clavicle fracture). The network identified clavicle fracture with 90 % sensitivity, 87 % specificity, and 88 % accuracy with AUC of 0.95 (confidence interval 0.94-0.96). CONCLUSION: A NML platform can help physicians create and test machine learning models from multicenter imaging datasets such as the one in our study for classifying radiographs based on the presence of clavicle fracture.

Enrichment of lung cancer computed tomography collections with AI-derived annotations.

Public imaging datasets are critical for the development and evaluation of automated tools in cancer imaging. Unfortunately, many do not include annotations or image-derived features, complicating downstream analysis. Artificial intelligence-based annotation tools have been shown to achieve acceptable performance and can be used to automatically annotate large datasets. As part of the effort to enrich public data available within NCI Imaging Data Commons (IDC), here we introduce AI-generated annotations for two collections containing computed tomography images of the chest, NSCLC-Radiomics, and a subset of the National Lung Screening Trial. Using publicly available AI algorithms, we derived volumetric annotations of thoracic organs-at-risk, their corresponding radiomics features, and slice-level annotations of anatomical landmarks and regions. The resulting annotations are publicly available within IDC, where the DICOM format is used to harmonize the data and achieve FAIR (Findable, Accessible, Interoperable, Reusable) data principles. The annotations are accompanied by cloud-enabled notebooks demonstrating their use. This study reinforces the need for large, publicly accessible curated datasets and demonstrates how AI can aid in cancer imaging.