RESUMO
Early and accurate detection of cervical lymph nodes is essential for the optimal management and staging of patients with head and neck malignancies. Pilot studies have demonstrated the potential for radiomic and artificial intelligence (AI) approaches in increasing diagnostic accuracy for the detection and classification of lymph nodes, but implementation of many of these approaches in real-world clinical settings would necessitate an automated lymph node segmentation pipeline as a first step. In this study, we aim to develop a non-invasive deep learning (DL) algorithm for detecting and automatically segmenting cervical lymph nodes in 25,119 CT slices from 221 normal neck contrast-enhanced CT scans from patients without head and neck cancer. We focused on the most challenging task of segmentation of small lymph nodes, evaluated multiple architectures, and employed U-Net and our adapted spatial context network to detect and segment small lymph nodes measuring 5-10 mm. The developed algorithm achieved a Dice score of 0.8084, indicating its effectiveness in detecting and segmenting cervical lymph nodes despite their small size. A segmentation framework successful in this task could represent an essential initial block for future algorithms aiming to evaluate small objects such as lymph nodes in different body parts, including small lymph nodes looking normal to the naked human eye but harboring early nodal metastases.
RESUMO
BACKGROUND: Patients with oropharyngeal squamous cell carcinoma (OPSCC) treated with radiation-based therapy suffer from short- and long-term toxicities that affect quality of life (QOL). Transoral robotic surgery (TORS) has an established role in the management of early OPSCC but adjuvant treatment is often indicated postoperatively due to the high incidence of nodal metastasis associated with advanced human papillomavirus (HPV)-related OPSCC. To overcome the need for adjuvant radiation therapy (RT), neoadjuvant chemotherapy followed by TORS and neck dissection (ND) is proposed. This study aimed to assess if QOL in HPV-associated OPSCC receiving neoadjuvant chemotherapy followed by TORS and ND returns to baseline within 12 months of completing treatment. METHODS: A 12 month longitudinal study was carried out at McGill University Health Centre in Montreal, Canada, among a convenience sample of patients with American Joint Committee on Cancer Seventh Edition stage III and IVa HPV-related OPSCC who were treated with neoadjuvant chemotherapy followed by TORS and ND. QOL data were obtained pretreatment and at 1, 3, 6, and 12 months following treatment completion using the European Organisation for Research and Treatment of Cancer Core and Head and Neck extension modules. Paired t tests and mixed models for repeated measures analysis were used to assess changes in QOL from baseline to 12 months postoperatively and over time, respectively. RESULTS: Nineteen of 23 patients (median age 58 years) who received the study treatment fulfilled the eligibility criteria. OPSCC subsites were palatine tonsil (n = 12) and base of tongue (n = 7). All 19 patients were treated per protocol and none required adjuvant RT as per pathology review and protocol requirements at a postoperative multidisciplinary team tumor board discussion. No significant differences were found when comparing 12 month QOL follow-up scores to pretreatment scores in measures that would likely be affected by RT [eg, swallowing (P = .7), social eating (P = .8), xerostomia (P = .9)]. CONCLUSION: In HPV-related OPSCC, neoadjuvant chemotherapy followed by TORS and ND as definitive treatment is associated with excellent QOL outcomes. Postoperative QOL scores returned to baseline by 3 months and were maintained for all measures, indicating a return to normal function.
Assuntos
Terapia Neoadjuvante , Neoplasias Orofaríngeas , Infecções por Papillomavirus , Qualidade de Vida , Procedimentos Cirúrgicos Robóticos , Humanos , Masculino , Pessoa de Meia-Idade , Feminino , Neoplasias Orofaríngeas/terapia , Neoplasias Orofaríngeas/virologia , Neoplasias Orofaríngeas/cirurgia , Infecções por Papillomavirus/complicações , Idoso , Carcinoma de Células Escamosas/terapia , Carcinoma de Células Escamosas/cirurgia , Carcinoma de Células Escamosas/virologia , Estudos Longitudinais , Esvaziamento Cervical , Quimioterapia Adjuvante , Adulto , Papillomavirus HumanoRESUMO
Multiple sclerosis (MS) is a chronic inflammatory disease of the nervous system. MR imaging findings play an integral part in establishing diagnostic hallmarks of the disease during initial diagnosis and evaluating disease status. Multiple iterations of diagnostic criteria and consensus guidelines are put forth by various expert groups incorporating imaging of the brain and spine, and efforts have been made to standardize imaging protocols for MS. Emerging ancillary imaging findings have also attracted increasing interests and should be sought for on radiologic examination. In this paper, the authors review the clinical guidelines and approach to imaging of MS and related disorders, focusing on clinically impactful image interpretation and MR imaging reporting.
Assuntos
Esclerose Múltipla , Humanos , Esclerose Múltipla/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Encéfalo/diagnóstico por imagem , RadiografiaRESUMO
PURPOSE: To evaluate the association of primary tumor volume (TV) with overall survival (OS) and disease-free survival (DFS) in T3 N0-3M0 supraglottic cancers treated with intensity-modulated radiotherapy (IMRT). METHODS: This was a retrospective cohort study involving 239 patients diagnosed with T3 N0-3M0 supraglottic cancers between 2002 and 2018 from seven regional cancer centers in Canada. Clinical data were obtained from the patient records. Supraglottic TV was measured by neuroradiologists on diagnostic imaging. Kaplan-Meier method was used for survival probabilities, and a restricted cubic spline Cox proportional hazards regression analysis was used to analyze TV associations with OS and DFS. RESULTS: Mean (SD) of participants was 65.2 (9.4) years; 176 (73.6%) participants were male. 90 (38%) were N0, and 151 (64%) received concurrent systemic therapy. Mean TV (SD) was 11.37 (12.11) cm3 . With mean follow up (SD) of 3.28 (2.60) years, 2-year OS was 72.7% (95% CI 66.9%-78.9%) and DFS was 53.6% (47.4%-60.6%). Increasing TV was associated (per cm3 increase) with worse OS (HR, 1.01, 95% CI 1.00-1.02, p < 0.01) and DFS (HR, 1.01, 95% CI 1.00-1.02, p = 0.02). CONCLUSIONS: Increasing primary tumor volume is associated with worse OS and DFS in T3 supraglottic cancers treated with IMRT, with no clear threshold. The findings suggest that patients with larger tumors and poor baseline laryngeal function may benefit from upfront laryngectomy with adjuvant radiotherapy.
Assuntos
Carcinoma de Células Escamosas , Neoplasias Laríngeas , Humanos , Masculino , Feminino , Estudos Retrospectivos , Carcinoma de Células Escamosas/patologia , Carga Tumoral , Canadá , Neoplasias Laríngeas/patologia , Intervalo Livre de Doença , Estadiamento de NeoplasiasRESUMO
INTRODUCTION: Artificial intelligence (AI) has the potential to transform oncologic care. There have been significant developments in AI applications in medical imaging and increasing interest in multimodal models. These are likely to enable improved oncologic care through more precise diagnosis, increasingly in a more personalized and less invasive manner. In this review, we provide an overview of the current state and challenges that clinicians, administrative personnel and policy makers need to be aware of and mitigate for the technology to reach its full potential. AREAS COVERED: The article provides a brief targeted overview of AI, a high-level review of the current state and future potential AI applications in diagnostic radiology and to a lesser extent digital pathology, focusing on oncologic applications. This is followed by a discussion of emerging approaches, including multimodal models. The article concludes with a discussion of technical, regulatory challenges and infrastructure needs for AI to realize its full potential. EXPERT OPINION: There is a large volume of promising research, and steadily increasing commercially available tools using AI. For the most advanced and promising precision diagnostic applications of AI to be used clinically, robust and comprehensive quality monitoring systems and informatics platforms will likely be required.
Assuntos
Inteligência Artificial , Neoplasias , Humanos , Diagnóstico por Imagem , Oncologia , Previsões , Cuidados Paliativos , Neoplasias/diagnóstico por imagem , Neoplasias/terapiaRESUMO
PURPOSE: To evaluate the diagnostic performance of a natural language processing (NLP) model in detecting incidental lung nodules (ILNs) in unstructured chest computed tomography (CT) reports. METHODS: All unstructured consecutive reports of chest CT scans performed at a tertiary hospital between 2020 and 2021 were retrospectively reviewed (n = 21,542) to train the NLP tool. Internal validation was performed using reference readings by two radiologists of both CT scans and reports, using a different external cohort of 300 chest CT scans. Second, external validation was performed in a cohort of all random unstructured chest CT reports from 57 different hospitals conducted in May 2022. A review by the same thoracic radiologists was used as the gold standard. The sensitivity, specificity, and accuracy were calculated. RESULTS: Of 21,542 CT reports, 484 mentioned at least one ILN (mean age, 71 ± 17.6 [standard deviation] years; women, 52%) and were included in the training set. In the internal validation (n = 300), the NLP tool detected ILN with a sensitivity of 100.0% (95% CI, 97.6 to 100.0), a specificity of 95.9% (95% CI, 91.3 to 98.5), and an accuracy of 98.0% (95% CI, 95.7 to 99.3). In the external validation (n = 977), the NLP tool yielded a sensitivity of 98.4% (95% CI, 94.5 to 99.8), a specificity of 98.6% (95% CI, 97.5 to 99.3), and an accuracy of 98.6% (95% CI, 97.6 to 99.2). Twelve months after the initial reports, 8 (8.60%) patients had a final diagnosis of lung cancer, among which 2 (2.15%) would have been lost to follow-up without the NLP tool. CONCLUSION: NLP can be used to identify ILNs in unstructured reports with high accuracy, allowing a timely recall of patients and a potential diagnosis of early-stage lung cancer that might have been lost to follow-up.
Assuntos
Neoplasias Pulmonares , Processamento de Linguagem Natural , Humanos , Feminino , Pessoa de Meia-Idade , Idoso , Idoso de 80 Anos ou mais , Estudos Retrospectivos , Tomografia Computadorizada por Raios X/métodos , Neoplasias Pulmonares/diagnóstico por imagem , PulmãoRESUMO
OBJECTIVE: There is ongoing debate on the relative benefits and drawbacks of polyetheretherketone (PEEK) versus titanium (Ti) in generating a bone-to-implant surface microenvironment conducive to osseointegration. Micro- and nanoscale internal and topographic cage modifications have recently been posited to facilitate osseointegration and fusion, but human in vivo confirmation remains lacking. The authors of this study sought to directly compare early radiological outcomes in adults undergoing 1- and 2-level transforaminal lumbar interbody fusion (TLIF) procedures using either PEEK or nano-etched Ti interbody cages with an incorporated microlattice structure. METHODS: Patients were enrolled in a single academic center using a single-blind randomized controlled superiority design. Screening was undertaken from a pool of consecutive patients eligible for TLIF to undergo placement in a 1:1 ratio of either lordotic PEEK or activated Ti cages at each level of 1- or 2-level procedures. An a priori power analysis was performed and a preplanned interim analysis was undertaken once 50 of 70 patients were enrolled. Patient study data were collected perioperatively and uploaded to a Research Electronic Data Capture (REDCap) registry. Interbody fusion was assessed based on 6-month postoperative lumbar dual-energy CT (DECT) studies using the method of Brantigan and Steffee, as modified to describe the Fraser definition of locked pseudarthrosis (Brantigan-Steffee-Fraser [BSF] scale). RESULTS: In the final cohort of 50 patients, 40 interbody levels implanted with PEEK cages were compared with 34 interbody levels with activated Ti cages. The trial was stopped early given the results of an interim analysis with respect to the primary outcome. Surgical parameters including number of levels treated, average cage height, and position were not different between groups. For the PEEK and activated Ti groups, 20.6% versus 84.0% demonstrated BSF grade 3 fusion on 6-month postoperative DECT imaging (p < 0.001). Subsidence at 6 months on DECT was identified in 12 (41.4%) of PEEK levels versus 5 (20.8%) of activated Ti levels (p < 0.001). BSF-3 grading was predictive of segmental stability and numeric rating scale (NRS) leg pain improvement at 1 year postoperatively. Oswestry Disability Index and NRS back and leg pain scores all improved similarly in both cohorts at 1 year postoperatively. CONCLUSIONS: Activated Ti interbody cages mediate early fusion at significantly higher rates with lower rates of subsidence as compared with PEEK cages. These findings support the idea that interbody cage microscale properties, including surface topography, may play a primary role in facilitating osseointegration and fusion.
Assuntos
Fusão Vertebral , Titânio , Humanos , Adulto , Vértebras Lombares/diagnóstico por imagem , Vértebras Lombares/cirurgia , Método Simples-Cego , Fusão Vertebral/métodos , Polietilenoglicóis , Cetonas , Dor , Resultado do TratamentoRESUMO
Health informatics and artificial intelligence (AI) are expected to transform the healthcare enterprise and the future practice of radiology. There is an increasing body of literature on radiomics and deep learning/AI applications in medical imaging. There are also a steadily increasing number of FDA cleared AI applications in radiology. It is therefore essential for radiologists to have a basic understanding of these approaches, whether in academia or private practice. In this article, we will provide an overview of the field and familiarize the readers with the fundamental concepts behind these approaches.
Assuntos
Inteligência Artificial , Radiologia , Humanos , Radiologistas , Radiologia/métodos , Radiografia , PrevisõesRESUMO
There are many impactful applications of artificial intelligence (AI) in the electronic radiology roundtrip and the patient's journey through the healthcare system that go beyond diagnostic applications. These tools have the potential to improve quality and safety, optimize workflow, increase efficiency, and increase patient satisfaction. In this article, we review the role of AI for process improvement and workflow enhancement which includes applications beginning from the time of order entry, scan acquisition, applications supporting the image interpretation task, and applications supporting tasks after image interpretation such as result communication. These non-diagnostic workflow and process optimization tasks are an important part of the arsenal of potential AI tools that can streamline day to day clinical practice and patient care.
Assuntos
Inteligência Artificial , Radiologia , Humanos , Fluxo de Trabalho , Radiologia/métodosRESUMO
Artificial intelligence algorithms can learn by assimilating information from large datasets in order to decipher complex associations, identify previously undiscovered pathophysiological states, and construct prediction models. There has been tremendous interest and increased incorporation of artificial intelligence into various industries, including healthcare. As a result, there has been an exponential rise in the number of research articles and industry participants producing models intended for a variety of applications in medical imaging, which can be challenging to navigate for radiologists. In thoracic imaging, multiple applications are being evaluated for chest radiography and computed tomography and include applications for lung nodule evaluation and cancer imaging, quantifying diffuse lung disorders, and cardiac imaging, to name a few. This review aims to provide an overview of current clinical AI models, focusing on the most common clinical applications of AI in cardiothoracic imaging.
Assuntos
Algoritmos , Inteligência Artificial , Humanos , Tomografia Computadorizada por Raios X , RadiologistasRESUMO
There is a steadily increasing number of artificial intelligence (AI) tools available and cleared for use in clinical radiological practice. Radiologists will increasingly be faced with options provided by other radiologist colleagues, clinician colleagues, vendors, or other professionals for obtaining and deploying AI algorithms in clinical practice. It is important that radiologists are familiar with basic and practical aspects that need to be considered when assessing an AI tool for use in their practice, so that resources are properly allocated and there is an appropriate return on investment through enhancements in patient quality of care, safety, and/or process efficiency. In this review, we will discuss a potential approach for AI software assessment and practical points that should be considered when considering the acquisition and deployment of an AI tool in the radiology department.
Assuntos
Inteligência Artificial , Radiologia , Humanos , Algoritmos , RadiologistasRESUMO
Purpose: To investigate the impact of the following three methodological pitfalls on model generalizability: (a) violation of the independence assumption, (b) model evaluation with an inappropriate performance indicator or baseline for comparison, and (c) batch effect. Materials and Methods: The authors used retrospective CT, histopathologic analysis, and radiography datasets to develop machine learning models with and without the three methodological pitfalls to quantitatively illustrate their effect on model performance and generalizability. F1 score was used to measure performance, and differences in performance between models developed with and without errors were assessed using the Wilcoxon rank sum test when applicable. Results: Violation of the independence assumption by applying oversampling, feature selection, and data augmentation before splitting data into training, validation, and test sets seemingly improved model F1 scores by 71.2% for predicting local recurrence and 5.0% for predicting 3-year overall survival in head and neck cancer and by 46.0% for distinguishing histopathologic patterns in lung cancer. Randomly distributing data points for a patient across datasets superficially improved the F1 score by 21.8%. High model performance metrics did not indicate high-quality lung segmentation. In the presence of a batch effect, a model built for pneumonia detection had an F1 score of 98.7% but correctly classified only 3.86% of samples from a new dataset of healthy patients. Conclusion: Machine learning models developed with these methodological pitfalls, which are undetectable during internal evaluation, produce inaccurate predictions; thus, understanding and avoiding these pitfalls is necessary for developing generalizable models.Keywords: Random Forest, Diagnosis, Prognosis, Convolutional Neural Network (CNN), Medical Image Analysis, Generalizability, Machine Learning, Deep Learning, Model Evaluation Supplemental material is available for this article. Published under a CC BY 4.0 license.
RESUMO
Importance: The association of primary tumor volume with outcomes in T3 glottic cancers treated with radiotherapy with concurrent chemotherapy remains unclear, with some evidence suggesting worse locoregional control in larger tumors. Objective: To evaluate the association of primary tumor volume with oncologic outcomes in patients with T3 N0-N3 M0 glottic cancer treated with primary (chemo)radiotherapy in a large multi-institutional study. Design, Setting, and Participants: This multi-institutional retrospective cohort study involved 7 Canadian cancer centers from 2002 to 2018. Tumor volume was measured by expert neuroradiologists on diagnostic imaging. Clinical and outcome data were extracted from electronic medical records. Overall survival (OS) and disease-free survival (DFS) outcomes were assessed with marginal Cox regression. Laryngectomy-free survival (LFS) was modeled as a secondary analysis. Patients diagnosed with cT3 N0-N3 M0 glottic cancers from 2002 to 2018 and treated with curative intent intensity-modulated radiotherapy (IMRT) with or without chemotherapy. Overall, 319 patients met study inclusion criteria. Exposures: Tumor volume as measured on diagnostic imaging by expert neuroradiologists. Main Outcomes and Measures: Primary outcomes were OS and DFS; LFS was assessed as a secondary analysis, and late toxic effects as an exploratory analysis determined before start of the study. Results: The mean (SD) age of participants was 66 (12) years and 279 (88%) were men. Overall, 268 patients (84%) had N0 disease, and 150 (47%) received concurrent systemic therapy. The mean (SD) tumor volume was 4.04 (3.92) cm3. With a mean (SD) follow-up of 3.85 (3.04) years, there were 91 (29%) local, 35 (11%) regional, and 38 (12%) distant failures. Increasing tumor volume (per 1-cm3 increase) was associated with significantly worse adjusted OS (hazard ratio [HR], 1.07; 95% CI, 1.03-1.11) and DFS (HR, 1.04; 95% CI, 1.01-1.07). A total of 62 patients (19%) underwent laryngectomies with 54 (87%) of these within 800 days after treatment. Concurrent systemic therapy was associated with improved LFS (subdistribution HR, 0.63; 95% CI, 0.53-0.76). Conclusions and Relevance: Increasing tumor volumes in cT3 glottic cancers was associated with worse OS and DFS, and systemic therapy was associated with improved LFS. In absence of randomized clinical trial evidence, patients with poor pretreatment laryngeal function or those ineligible for systemic therapy may be considered for primary surgical resection with postoperative radiotherapy.
Assuntos
Carcinoma de Células Escamosas , Neoplasias Laríngeas , Neoplasias da Língua , Masculino , Humanos , Idoso , Feminino , Neoplasias Laríngeas/patologia , Carcinoma de Células Escamosas/patologia , Estudos Retrospectivos , Carga Tumoral , Canadá , Neoplasias da Língua/terapiaRESUMO
PURPOSE: Identifying optimal machine learning pipelines for computer-aided diagnosis is key for the development of robust, reproducible, and clinically relevant imaging biomarkers for endometrial carcinoma. The purpose of this study was to introduce the mathematical development of image descriptors computed from spherical harmonics (SPHARM) decompositions as well as the associated machine learning pipeline, and to evaluate their performance in predicting deep myometrial invasion (MI) and histopathological high-grade in preoperative multiparametric magnetic resonance imaging (MRI). PATIENTS AND METHODS: This retrospective study included 128 women with histopathology-confirmed endometrial carcinomas who underwent 1.5-T MRI before hysterectomy between January 2011 and July 2015. SPHARM descriptors of each tumor were computed on multiparametric MRI images (T2-weighted, diffusion-weighted, dynamic contrast-enhanced-MRI and apparent diffusion coefficient maps). Tensor-based logistic regression was used to classify two-dimensional SPHARM rotationally-invariant descriptors. Head-to-head comparisons with radiomics analyses were performed with DeLong tests with Bonferroni-Holm correction to compare diagnostic performances. RESULTS: With all MRI contrasts, SPHARM analysis resulted in area under the curve, sensitivity, specificity, and balanced accuracy values of 0.94 (95% confidence interval [CI]: 0.85, 1.00), 100% (95% CI: 100, 100), 74% (95% CI: 51, 92), 87% (95% CI: 78, 98), respectively, for predicting deep MI. For predicting high-grade tumor histology, the corresponding values for the same diagnostic metrics were 0.81 (95% CI: 0.64, 0.90), 93% (95% CI: 67, 100), 63% (95% CI: 45, 79) and 78% (95% CI: 64, 86). The corresponding values achieved via radiomics were 0.92 (95% CI: 0.82, 0.95), 82% (95% CI: 65, 93), 80% (95% CI: 51, 94), 81% (95% CI: 70, 91) for deep MI and 0.72 (95% CI: 0.58, 0.83), 93% (95% CI: 65, 100), 55% (95% CI: 41, 69), 74% (95% CI: 52, 88) for high-grade histology. The diagnostic performance of the SPHARM analysis was not significantly different (P = 0.62) from that of radiomics for predicting deep MI but was significantly higher (P = 0.044) for predicting high-grade histology. CONCLUSION: The proposed SPHARM analysis yields similar or higher diagnostic performance than radiomics in identifying deep MI and high-grade status in histology-proven endometrial carcinoma.