Foundation model for cancer imaging biomarkers

Foundation models in deep learning are characterized by a single large-scale model trained on vast amounts of data serving as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labelled datasets are often scarce. Here, we developed a foundation model for cancer imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of cancer imaging-based biomarkers. We found that it facilitated better and more efficient learning of imaging biomarkers and yielded task-specific models that significantly outperformed conventional supervised and other state-of-the-art pretrained implementations on downstream tasks, especially when training dataset sizes were very limited. Furthermore, the foundation model was more stable to input variations and showed strong associations with underlying biology. Our results demonstrate the tremendous potential of foundation models in discovering new imaging biomarkers that may extend to other clinical use cases and can accelerate the widespread translation of imaging biomarkers into clinical settings.

Foundation Models for Quantitative Biomarker Discovery in Cancer Imaging

Foundation models represent a recent paradigm shift in deep learning, where a single large-scale model trained on vast amounts of data can serve as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labeled datasets are often scarce. Here, we developed a foundation model for imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of imaging-based biomarkers. We found that they facilitated better and more efficient learning of imaging biomarkers and yielded task-specific models that significantly outperformed their conventional supervised counterparts on downstream tasks. The performance gain was most prominent when training dataset sizes were very limited. Furthermore, foundation models were more stable to input and inter-reader variations and showed stronger associations with underlying biology. Our results demonstrate the tremendous potential of foundation models in discovering novel imaging biomarkers that may extend to other clinical use cases and can accelerate the widespread translation of imaging biomarkers into clinical settings.

Antioxidant, antiapoptotic, and antifibrotic abilities of L-Arginine ameliorate the testicular dysfunction in diabetic rats

Testicular dysfunction and infertility are serious complications of diabetes mellitus (DM). L-Arginine (L-Arg) is a semi essential amino acid with various biological and metabolic functions. The molecular mechanisms of L-Arg on testicular dysfunction caused by DM remain elusive. This study aimed to assess the potential protective effect of L-Arg in diabetic testis and its possible mechanisms. 24 adult male Wistar albino rats were randomly divided into four groups: CON, L-Arg that received 1 g/kg body weight of L-Arg orally for 4 weeks, DM that fed a high fat diet followed by an injection of 30 mg/kg streptozotocin intraperitoneally, and L-Arg-treated DM that were diabetic and administered L-Arg. DM decreased relative testicular weight, reduced serum testosterone, and impaired semen parameters. Reduced total antioxidant capacity (TAC), superoxide dismutase (SOD), and glutathione peroxidase (GSH-Px), in addition to increased transforming growth factor B1 (TGF-β1) and nitric oxide (NO) levels, were found in the testicular tissue. This was associated with severe degenerative changes in the seminiferous tubules and interstitial cells of Leydig, reduction of Johnsen's score, significantly increased expression of both inducible nitric oxide synthase (iNOS) and caspase-3, and reduced zonula occludens (ZO)- 1 expression. Ultrastructurally, disrupted intercellular junctions and degeneration of interstitial cells of Leydig were observed. In contrast, treatment of diabetic animals with L-Arg increased TAC, SOD and GSH-Px, decreased TGF-β1 and NO levels, downregulated iNOS and caspase-3 expression, upregulated ZO-1 expression, and maintained the integrity of the Sertoli cell junctions. Hence, L-Arg restored the normal testicular structure and function via its antioxidant, antiapoptotic, and antifibrotic effects.

Clinical validation of deep learning algorithms for radiotherapy targeting of non-small-cell lung cancer: an observational study

BACKGROUND

Artificial intelligence (AI) and deep learning have shown great potential in streamlining clinical tasks. However, most studies remain confined to in silico validation in small internal cohorts, without external validation or data on real-world clinical utility. We developed a strategy for the clinical validation of deep learning models for segmenting primary non-small-cell lung cancer (NSCLC) tumours and involved lymph nodes in CT images, which is a time-intensive step in radiation treatment planning, with large variability among experts.

METHODS

In this observational study, CT images and segmentations were collected from eight internal and external sources from the USA, the Netherlands, Canada, and China, with patients from the Maastro and Harvard-RT1 datasets used for model discovery (segmented by a single expert). Validation consisted of interobserver and intraobserver benchmarking, primary validation, functional validation, and end-user testing on the following datasets: multi-delineation, Harvard-RT1, Harvard-RT2, RTOG-0617, NSCLC-radiogenomics, Lung-PET-CT-Dx, RIDER, and thorax phantom. Primary validation consisted of stepwise testing on increasingly external datasets using measures of overlap including volumetric dice (VD) and surface dice (SD). Functional validation explored dosimetric effect, model failure modes, test-retest stability, and accuracy. End-user testing with eight experts assessed automated segmentations in a simulated clinical setting.

FINDINGS

We included 2208 patients imaged between 2001 and 2015, with 787 patients used for model discovery and 1421 for model validation, including 28 patients for end-user testing. Models showed an improvement over the interobserver benchmark (multi-delineation dataset; VD 0·91 [IQR 0·83-0·92], p=0·0062; SD 0·86 [0·71-0·91], p=0·0005), and were within the intraobserver benchmark. For primary validation, AI performance on internal Harvard-RT1 data (segmented by the same expert who segmented the discovery data) was VD 0·83 (IQR 0·76-0·88) and SD 0·79 (0·68-0·88), within the interobserver benchmark. Performance on internal Harvard-RT2 data segmented by other experts was VD 0·70 (0·56-0·80) and SD 0·50 (0·34-0·71). Performance on RTOG-0617 clinical trial data was VD 0·71 (0·60-0·81) and SD 0·47 (0·35-0·59), with similar results on diagnostic radiology datasets NSCLC-radiogenomics and Lung-PET-CT-Dx. Despite these geometric overlap results, models yielded target volumes with equivalent radiation dose coverage to those of experts. We also found non-significant differences between de novo expert and AI-assisted segmentations. AI assistance led to a 65% reduction in segmentation time (5·4 min; p<0·0001) and a 32% reduction in interobserver variability (SD; p=0·013).

INTERPRETATION

We present a clinical validation strategy for AI models. We found that in silico geometric segmentation metrics might not correlate with clinical utility of the models. Experts' segmentation style and preference might affect model performance.

FUNDING

US National Institutes of Health and EU European Research Council.

Contribution of interleukin 27 serum level to pathogenesis and prognosis in children with immune thrombocytopenia

Concepts surrounding the mechanisms of thrombocytopenia in ITP have shifted from the traditional view of autoantibody mediated platelet destruction to more complex mechanisms in which impaired platelet production, T-cell-mediated effects, and disturbed cytokine profiles play a role. Interleukin 27 (IL-27) plays pleiotropic roles in immunomodulation and autoimmune diseases.We aimed to determine the level of IL-27 in patients with ITP and its relationship to patient and disease characteristics as well as disease chronicity and response to treatment.Sixty childrens with primary immune thrombocytopenia were consequetively enrolled in this study as well as 20 age and sex matched healthy controls.ITP patients had significantly higher levels of IL-27 than controls (770.6 and 373.8 pg/ml, respectively). Patients with acute ITP had the highest levels of IL-27 among patient groups, while patients in remission had the lowest IL-27 levels (860.1and 622.9 pg/ml, respectively). Patients who received IVIG and combined steroids plus IVIG had significantly higher IL-27 levels than others. Patients who received Eltrombopag had significantly lower IL-27 levels than others.IL-27 seems to play a role in pathogenesis of childhood ITP. IL-27 can be used as a predictor for disease occurrence as well as responsiveness to treatment.

Primary headache disorders in epileptic adults

Background

Epilepsy and primary headache disorders are two relatively common neurological disorders and their relationship is still a matter of debate. We aimed to estimate the prevalence and clinical features of primary headache disorders in patients with epilepsy.

Methods

62 subjects aged ≥ 18 years were recruited from the hospital’s neurology outpatient clinic in the period from January to April 2018. The subjects were further divided into two equal groups, epileptics and non-epileptics. They underwent a semi-structured interview including the ILAE 2017 epilepsy classification and the ICHD III-beta criteria for headache. Patients' demographic data and clinical characteristics of epilepsy and headache and temporal relationships between them were assessed. Patients who experienced headaches were grouped based on the type of headaches and on whether their headaches occurred in the pre-ictal, post-ictal or inter-ictal period.

Results

Primary headache disorders were more common in epileptic group (61.3%) than the non-epileptic group (32.2%) (p = 0.021). The tension-type headache was the most common (45.2%) followed by migraine-type headache (12.9%) in the epileptic group. Post-ictal headache was the most common type (29%). Inter-ictal headaches were significantly related to "focal to bilateral tonic–clonic" seizures (p = 0.046). The prevalence of headache among patients on polytherapy (69.2%) was higher than that of patients on monotherapy (52.9%).

Conclusions

In this study, headache was more common in epileptic patients. TTH was the most represented type of headache in patients with epilepsy. Headache occurred in patients with epilepsy most frequently during the post-ictal period.

Deep Learning-based Detection of Intravenous Contrast Enhancement on CT Scans

Identifying the presence of intravenous contrast material on CT scans is an important component of data curation for medical imaging-based artificial intelligence model development and deployment. Use of intravenous contrast material is often poorly documented in imaging metadata, necessitating impractical manual annotation by clinician experts. Authors developed a convolutional neural network (CNN)-based deep learning platform to identify intravenous contrast enhancement on CT scans. For model development and validation, authors used six independent datasets of head and neck (HN) and chest CT scans, totaling 133 480 axial two-dimensional sections from 1979 scans, which were manually annotated by clinical experts. Five CNN models were trained first on HN scans for contrast enhancement detection. Model performances were evaluated at the patient level on a holdout set and external test set. Models were then fine-tuned on chest CT data and externally validated. This study found that Digital Imaging and Communications in Medicine metadata tags for intravenous contrast material were missing or erroneous for 1496 scans (75.6%). An EfficientNetB4-based model showed the best performance, with areas under the curve (AUCs) of 0.996 and 1.0 in HN holdout (n = 216) and external (n = 595) sets, respectively, and AUCs of 1.0 and 0.980 in the chest holdout (n = 53) and external (n = 402) sets, respectively. This automated, scan-to-prediction platform is highly accurate at CT contrast enhancement detection and may be helpful for artificial intelligence model development and clinical application. Keywords: CT, Head and Neck, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN), Machine Learning Algorithms, Contrast Material Supplemental material is available for this article. © RSNA, 2022.

End-to-End Non-Small-Cell Lung Cancer Prognostication Using Deep Learning Applied to Pretreatment Computed Tomography

PURPOSE

Clinical TNM staging is a key prognostic factor for patients with lung cancer and is used to inform treatment and monitoring. Computed tomography (CT) plays a central role in defining the stage of disease. Deep learning applied to pretreatment CTs may offer additional, individualized prognostic information to facilitate more precise mortality risk prediction and stratification.

METHODS

We developed a fully automated imaging-based prognostication technique (IPRO) using deep learning to predict 1-year, 2-year, and 5-year mortality from pretreatment CTs of patients with stage I-IV lung cancer. Using six publicly available data sets from The Cancer Imaging Archive, we performed a retrospective five-fold cross-validation using pretreatment CTs of 1,689 patients, of whom 1,110 were diagnosed with non-small-cell lung cancer and had available TNM staging information. We compared the association of IPRO and TNM staging with patients' survival status and assessed an Ensemble risk score that combines IPRO and TNM staging. Finally, we evaluated IPRO's ability to stratify patients within TNM stages using hazard ratios (HRs) and Kaplan-Meier curves.

RESULTS

IPRO showed similar prognostic power (concordance index [C-index] 1-year: 0.72, 2-year: 0.70, 5-year: 0.68) compared with that of TNM staging (C-index 1-year: 0.71, 2-year: 0.71, 5-year: 0.70) in predicting 1-year, 2-year, and 5-year mortality. The Ensemble risk score yielded superior performance across all time points (C-index 1-year: 0.77, 2-year: 0.77, 5-year: 0.76). IPRO stratified patients within TNM stages, discriminating between highest- and lowest-risk quintiles in stages I (HR: 8.60), II (HR: 5.03), III (HR: 3.18), and IV (HR: 1.91).

CONCLUSION

Deep learning applied to pretreatment CT combined with TNM staging enhances prognostication and risk stratification in patients with lung cancer.

Artificial intelligence for clinical oncology

Clinical oncology is experiencing rapid growth in data that are collected to enhance cancer care. With recent advances in the field of artificial intelligence (AI), there is now a computational basis to integrate and synthesize this growing body of multi-dimensional data, deduce patterns, and predict outcomes to improve shared patient and clinician decision making. While there is high potential, significant challenges remain. In this perspective, we propose a pathway of clinical cancer care touchpoints for narrow-task AI applications and review a selection of applications. We describe the challenges faced in the clinical translation of AI and propose solutions. We also suggest paths forward in weaving AI into individualized patient care, with an emphasis on clinical validity, utility, and usability. By illuminating these issues in the context of current AI applications for clinical oncology, we hope to help advance meaningful investigations that will ultimately translate to real-world clinical use.

Improvement of sexual dysfunction in patients after treatment of hepatitis C virus using directly acting antivirals

OBJECTIVE

The impact on male and female sexual dysfunction of treating hepatitis C virus (HCV) using direct-acting antiviral agents (DAAs) has not been sufficiently studied. The aim of this study was to assess the impact of HCV clearance with DAAs on sexual dysfunction (SD) in both sexes.

METHODS

In chronic HCV patients who were eligible for DAAs, 100 sexually active men completed the Arabic version of the international index of erectile function questionnaire (IIEF-5), and the same number of sexually active women completed Female Sexual Function Index (FSFI), before, at the end of, and 3 months after, treatment for HCV.

RESULT

The mean of the IIEF-5 scores for male patients was 16.29 ±.07 before treatment, 16.88 ± 3.63 3 months after treatment (p < .01), and was significantly higher, at 19.06 ± 3.31 6 months after treatment cessation (p < .01). In female patients, the mean total FSFI score at baseline was 19.22 ± 2.40 and after 3 months of treatment was 21.61 ± 3.45 (p < .01), with a significant increase (25.09 ± 4.52) after 6 months (p < .01). No difference in the improvement of sexual function was reported either after 3 months or at the end of treatment between males and females (p > .05).

CONCLUSIONS

Significant improvement in SD associated with HCV infection in both sexes was recorded following viral clearance using DAAs treatment.

Deep learning classification of lung cancer histology using CT images

Tumor histology is an important predictor of therapeutic response and outcomes in lung cancer. Tissue sampling for pathologist review is the most reliable method for histology classification, however, recent advances in deep learning for medical image analysis allude to the utility of radiologic data in further describing disease characteristics and for risk stratification. In this study, we propose a radiomics approach to predicting non-small cell lung cancer (NSCLC) tumor histology from non-invasive standard-of-care computed tomography (CT) data. We trained and validated convolutional neural networks (CNNs) on a dataset comprising 311 early-stage NSCLC patients receiving surgical treatment at Massachusetts General Hospital (MGH), with a focus on the two most common histological types: adenocarcinoma (ADC) and Squamous Cell Carcinoma (SCC). The CNNs were able to predict tumor histology with an AUC of 0.71(p = 0.018). We also found that using machine learning classifiers such as k-nearest neighbors (kNN) and support vector machine (SVM) on CNN-derived quantitative radiomics features yielded comparable discriminative performance, with AUC of up to 0.71 (p = 0.017). Our best performing CNN functioned as a robust probabilistic classifier in heterogeneous test sets, with qualitatively interpretable visual explanations to its predictions. Deep learning based radiomics can identify histological phenotypes in lung cancer. It has the potential to augment existing approaches and serve as a corrective aid for diagnosticians.

Abstract IA-05: Deep learning radiomics in cancer imaging

Radiographic medical images contain a vast wealth of information allowing for accurate non-invasive tumor characterization and ultimately improving cancer care. Radiomics enables the extraction of mineable high-dimensional features from images, quantification of tumor phenotypes for survival, recurrence, and treatment response prediction, and ultimately better patient stratification. Recent advances in AI, deep learning in particular, has allowed for the automated extraction of imaging features without the need for pre-definition. In this talk, we will be exploring deep learning radiomics applications in cancer patients from both single time point and longitudinal imaging data. We will also be identifying challenges regarding the stability, reproducibility, and transparency of such approaches.

Citation Format: Ahmed Hosny. Deep learning radiomics in cancer imaging [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr IA-05.

Transparency and reproducibility in artificial intelligence

Breakthroughs in artificial intelligence (AI) hold enormous potential as it can automate complex tasks and go even beyond human performance. In their study, McKinney et al. showed the high potential of AI for breast cancer screening. However, the lack of methods’ details and algorithm code undermines its scientific value. Here, we identify obstacles hindering transparent and reproducible AI research as faced by McKinney et al., and provide solutions to these obstacles with implications for the broader field.

Erectile dysfunction in patients with first-episode psychosis

Sexual dysfunction is more prevalent in psychotic patients than in the nonpsychotic population. The objective of this study was to identify correlations between serum prolactin levels, testosterone levels and erectile dysfunction in patients with first-episode psychosis (n = 40) compared to age-matched healthy controls (n = 40). All subjects underwent clinical evaluation, international index of erectile function (IIEF5) score assessment and measurement of serum prolactin and total testosterone levels. In first-episode psychotic patients, the IIEF-5 score and total testosterone levels were significantly lower, while serum prolactin levels were higher. We concluded that men with first-episode psychosis are at an increased risk for development of erectile dysfunction, and increased duration of untreated psychosis leads to a higher incidence of erectile dysfunction and hyperprolactinemia.

Neurobehavioral, testicular and erectile impairments of chronic ketamine administration: Pathogenesis and ameliorating effect of N-acetyl cysteine

Ketamine, a dissociative anesthetic, recently has spread as a recreational drug. Its abuse lead to neurobehavioral disturbance in addition to toxic effects on other body organs. To evaluate the toxic effects of chronic administration of low ketamine doses on the memory, testicles, and erection, explore its pathophysiology through oxidative stress mechanism and examine the ameliorating effect of N-acetyl cysteine (NAC). A total of 40 male albino rats were assigned to control, vehicle, ketamine only I.P. (10 mg/kg), and ketamine (10 mg/kg) + NAC (150 mg/kg) groups. Assessment of memory affection and erectile function by Passive Avoidance, Novel Object Recognition, and copulatory tests were performed. Estimation of malondialdehyde (MDA), catalase (CAT), and total antioxidant capacity (TAC) in serum and prefrontal & hippocampal homogenate, and luteinizing hormone (LH), testosterone in serum were done. Prefrontal cortex, hippocampus, and testes were collected for histopathology. Chronic ketamine administration induced significant memory deficits (P < 0.05), reduced erectile function (P < 0.05), severe hypospermatogenesis, increased MDA, reduced CAT, TAC levels in serum, and tissue homogenate (P < 0.05) and reduction of LH, and testosterone (P < 0.05). Treatment with NAC resulted in significant improvement of memory function, improved erectile function, and decrease in oxidative injury in both serum and tissue homogenates. Testosterone and LH levels exhibited significant difference between treatment groups and controls (P < 0.05). NAC reduced the deleterious histopathological changes. These data suggest that long-term ketamine affects short and long memory, induces erectile and testicular dysfunction through oxidative stress. Co-administration with NAC ameliorates these toxic effects.

Impact of irregular marital cohabitation on quality of life and sexual dysfunction in infertile men from upper Egypt

OBJECTIVE

Irregular patterns of marital cohabitation are a common problem in upper Egypt due to employment conditions. The objective of this study was to investigate the effect of irregular marital cohabitation on the quality of life and sexual function of infertile men.

METHODS

In total, 208 infertile men were included and divided into two groups. The first group included 134 infertile men with an irregular pattern of marital cohabitation and the second group included 74 infertile men with a regular pattern of marital cohabitation. All subjects were assessed through a clinical evaluation, conventional semen analysis, the fertility quality of life (FertiQoL) questionnaire, the International Index of Erectile Function (IIEF-5) score, and the premature ejaculation diagnostic tool (PMEDT).

RESULTS

The two groups were compared in terms of conventional semen parameters, FertiQoL, IIEF-5 score, and PMEDT. Infertile men with an irregular pattern of marital cohabitation had significantly lower subscale and total FertiQoL and IIEF-5 scores. Additionally, they had significantly higher PMEDT scores. Erectile dysfunction and premature ejaculation were more common in them than in infertile men with a regular pattern of marital cohabitation.

CONCLUSION

Irregular patterns of marital cohabitation had an adverse effect on quality of life and sexual function in infertile men.

Bioinspired design of flexible armor based on chiton scales

Man-made armors often rely on rigid structures for mechanical protection, which typically results in a trade-off with flexibility and maneuverability. Chitons, a group of marine mollusks, evolved scaled armors that address similar challenges. Many chiton species possess hundreds of small, mineralized scales arrayed on the soft girdle that surrounds their overlapping shell plates. Ensuring both flexibility for locomotion and protection of the underlying soft body, the scaled girdle is an excellent model for multifunctional armor design. Here we conduct a systematic study of the material composition, nanomechanical properties, three-dimensional geometry, and interspecific structural diversity of chiton girdle scales. Moreover, inspired by the tessellated organization of chiton scales, we fabricate a synthetic flexible scaled armor analogue using parametric computational modeling and multi-material 3D printing. This approach allows us to conduct a quantitative evaluation of our chiton-inspired armor to assess its orientation-dependent flexibility and protection capabilities.

3D printing and intraoperative neuronavigation tailoring for skull base reconstruction after extended endoscopic endonasal surgery: proof of concept

OBJECTIVE

Endoscopic endonasal approaches are increasingly performed for the surgical treatment of multiple skull base pathologies. Preventing postoperative CSF leaks remains a major challenge, particularly in extended approaches. In this study, the authors assessed the potential use of modern multimaterial 3D printing and neuronavigation to help model these extended defects and develop specifically tailored prostheses for reconstructive purposes.

METHODS

Extended endoscopic endonasal skull base approaches were performed on 3 human cadaveric heads. Pre-Preprocedure and intraprocedure CT scans were completed and were used to segment and design extended and tailored skull base models. Multimaterial models with different core/edge interfaces were 3D printed for implantation trials. A novel application of the intraoperative landmark acquisition method was used to transfer the navigation, helping to tailor the extended models.

RESULTS

Prostheses were created based on preoperative and intraoperative CT scans. The navigation transfer offered sufficiently accurate data to tailor the preprinted extended skull base defect prostheses. Successful implantation of the skull base prostheses was achieved in all specimens. The progressive flexibility gradient of the models’ edges offered the best compromise for easy intranasal maneuverability, anchoring, and structural stability. Prostheses printed based on intraprocedure CT scans were accurate in shape but slightly undersized.

CONCLUSIONS

Preoperative 3D printing of patient-specific skull base models is achievable for extended endoscopic endonasal surgery. The careful spatial modeling and the use of a flexibility gradient in the design helped achieve the most stable reconstruction. Neuronavigation can help tailor preprinted prostheses.

Deep Learning to Assess Long-term Mortality From Chest Radiographs

Importance

Chest radiography is the most common diagnostic imaging test in medicine and may also provide information about longevity and prognosis.

Objective

To develop and test a convolutional neural network (CNN) (named CXR-risk) to predict long-term mortality, including noncancer death, from chest radiographs.

Design, Setting, and Participants

In this prognostic study, CXR-risk CNN development (n = 41 856) and testing (n = 10 464) used data from the screening radiography arm of the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO) (n = 52 320), a community cohort of asymptomatic nonsmokers and smokers (aged 55-74 years) enrolled at 10 US sites from November 8, 1993, through July 2, 2001. External testing used data from the screening radiography arm of the National Lung Screening Trial (NLST) (n = 5493), a community cohort of heavy smokers (aged 55-74 years) enrolled at 21 US sites from August 2002, through April 2004. Data analysis was performed from January 1, 2018, to May 23, 2019.

Exposure

Deep learning CXR-risk score (very low, low, moderate, high, and very high) based on CNN analysis of the enrollment radiograph.

Main Outcomes and Measures

All-cause mortality. Prognostic value was assessed in the context of radiologists' diagnostic findings (eg, lung nodule) and standard risk factors (eg, age, sex, and diabetes) and for cause-specific mortality.

Results

Among 10 464 PLCO participants (mean [SD] age, 62.4 [5.4] years; 5405 men [51.6%]; median follow-up, 12.2 years [interquartile range, 10.5-12.9 years]) and 5493 NLST test participants (mean [SD] age, 61.7 [5.0] years; 3037 men [55.3%]; median follow-up, 6.3 years [interquartile range, 6.0-6.7 years]), there was a graded association between CXR-risk score and mortality. The very high-risk group had mortality of 53.0% (PLCO) and 33.9% (NLST), which was higher compared with the very low-risk group (PLCO: unadjusted hazard ratio [HR], 18.3 [95% CI, 14.5-23.2]; NLST: unadjusted HR, 15.2 [95% CI, 9.2-25.3]; both P < .001). This association was robust to adjustment for radiologists' findings and risk factors (PLCO: adjusted HR [aHR], 4.8 [95% CI, 3.6-6.4]; NLST: aHR, 7.0 [95% CI, 4.0-12.1]; both P < .001). Comparable results were seen for lung cancer death (PLCO: aHR, 11.1 [95% CI, 4.4-27.8]; NLST: aHR, 8.4 [95% CI, 2.5-28.0]; both P ≤ .001) and for noncancer cardiovascular death (PLCO: aHR, 3.6 [95% CI, 2.1-6.2]; NLST: aHR, 47.8 [95% CI, 6.1-374.9]; both P < .001) and respiratory death (PLCO: aHR, 27.5 [95% CI, 7.7-97.8]; NLST: aHR, 31.9 [95% CI, 3.9-263.5]; both P ≤ .001).

Conclusions and Relevance

In this study, the deep learning CXR-risk score stratified the risk of long-term mortality based on a single chest radiograph. Individuals at high risk of mortality may benefit from prevention, screening, and lifestyle interventions.

Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging

PURPOSE

Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non-small cell lung cancer (NSCLC).Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans).

RESULTS

Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17-17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016).

CONCLUSIONS

We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.

Artificial intelligence in cancer imaging: Clinical challenges and applications

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study

BACKGROUND

Non-small-cell lung cancer (NSCLC) patients often demonstrate varying clinical courses and outcomes, even within the same tumor stage. This study explores deep learning applications in medical imaging allowing for the automated quantification of radiographic characteristics and potentially improving patient stratification.

METHODS AND FINDINGS

We performed an integrative analysis on 7 independent datasets across 5 institutions totaling 1,194 NSCLC patients (age median = 68.3 years [range 32.5-93.3], survival median = 1.7 years [range 0.0-11.7]). Using external validation in computed tomography (CT) data, we identified prognostic signatures using a 3D convolutional neural network (CNN) for patients treated with radiotherapy (n = 771, age median = 68.0 years [range 32.5-93.3], survival median = 1.3 years [range 0.0-11.7]). We then employed a transfer learning approach to achieve the same for surgery patients (n = 391, age median = 69.1 years [range 37.2-88.0], survival median = 3.1 years [range 0.0-8.8]). We found that the CNN predictions were significantly associated with 2-year overall survival from the start of respective treatment for radiotherapy (area under the receiver operating characteristic curve [AUC] = 0.70 [95% CI 0.63-0.78], p < 0.001) and surgery (AUC = 0.71 [95% CI 0.60-0.82], p < 0.001) patients. The CNN was also able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy (p < 0.001) and surgery (p = 0.03) datasets. Additionally, the CNN was found to significantly outperform random forest models built on clinical parameters-including age, sex, and tumor node metastasis stage-as well as demonstrate high robustness against test-retest (intraclass correlation coefficient = 0.91) and inter-reader (Spearman's rank-order correlation = 0.88) variations. To gain a better understanding of the characteristics captured by the CNN, we identified regions with the most contribution towards predictions and highlighted the importance of tumor-surrounding tissue in patient stratification. We also present preliminary findings on the biological basis of the captured phenotypes as being linked to cell cycle and transcriptional processes. Limitations include the retrospective nature of this study as well as the opaque black box nature of deep learning networks.

CONCLUSIONS

Our results provide evidence that deep learning networks may be used for mortality risk stratification based on standard-of-care CT images from NSCLC patients. This evidence motivates future research into better deciphering the clinical and biological basis of deep learning networks as well as validation in prospective data.

A Novel Mixed Reality Navigation System for Laparoscopy Surgery

OBJECTIVE

To design and validate a novel mixed reality head-mounted display for intraoperative surgical navigation.

DESIGN

A mixed reality navigation for laparoscopic surgery (MRNLS) system using a head mounted display (HMD) was developed to integrate the displays from a laparoscope, navigation system, and diagnostic imaging to provide context-specific information to the surgeon. Further, an immersive auditory feedback was also provided to the user. Sixteen surgeons were recruited to quantify the differential improvement in performance based on the mode of guidance provided to the user (laparoscopic navigation with CT guidance (LN-CT) versus mixed reality navigation for laparoscopic surgery (MRNLS)). The users performed three tasks: (1) standard peg transfer, (2) radiolabeled peg identification and transfer, and (3) radiolabeled peg identification and transfer through sensitive wire structures.

RESULTS

For the more complex task of peg identification and transfer, significant improvements were observed in time to completion, kinematics such as mean velocity, and task load index subscales of mental demand and effort when using the MRNLS (p < 0.05) compared to the current standard of LN-CT. For the final task of peg identification and transfer through sensitive structures, time taken to complete the task and frustration were significantly lower for MRNLS compared to the LN-CT approach.

CONCLUSIONS

A novel mixed reality navigation for laparoscopic surgery (MRNLS) has been designed and validated. The ergonomics of laparoscopic procedures could be improved while minimizing the necessity of additional monitors in the operating room.

Data Analysis Strategies in Medical Imaging

Radiographic imaging continues to be one of the most effective and clinically useful tools within oncology. Sophistication of artificial intelligence has allowed for detailed quantification of radiographic characteristics of tissues using predefined engineered algorithms or deep learning methods. Precedents in radiology as well as a wealth of research studies hint at the clinical relevance of these characteristics. However, critical challenges are associated with the analysis of medical imaging data. Although some of these challenges are specific to the imaging field, many others like reproducibility and batch effects are generic and have already been addressed in other quantitative fields such as genomics. Here, we identify these pitfalls and provide recommendations for analysis strategies of medical imaging data, including data normalization, development of robust models, and rigorous statistical analyses. Adhering to these recommendations will not only improve analysis quality but also enhance precision medicine by allowing better integration of imaging data with other biomedical data sources. Clin Cancer Res; 24(15); 3492-9. ©2018 AACR.

Artificial intelligence in radiology

Artificial intelligence (AI) algorithms, particularly deep learning, have demonstrated remarkable progress in image-recognition tasks. Methods ranging from convolutional neural networks to variational autoencoders have found myriad applications in the medical image analysis field, propelling it forward at a rapid pace. Historically, in radiology practice, trained physicians visually assessed medical images for the detection, characterization and monitoring of diseases. AI methods excel at automatically recognizing complex patterns in imaging data and providing quantitative, rather than qualitative, assessments of radiographic characteristics. In this Opinion article, we establish a general understanding of AI methods, particularly those pertaining to image-based tasks. We explore how these methods could impact multiple facets of radiology, with a general focus on applications in oncology, and demonstrate ways in which these methods are advancing the field. Finally, we discuss the challenges facing clinical implementation and provide our perspective on how the domain could be advanced.

Artificial intelligence in radiology

Artificial intelligence (AI) algorithms, particularly deep learning, have demonstrated remarkable progress in image-recognition tasks. Methods ranging from convolutional neural networks to variational autoencoders have found myriad applications in the medical image analysis field, propelling it forward at a rapid pace. Historically, in radiology practice, trained physicians visually assessed medical images for the detection, characterization and monitoring of diseases. AI methods excel at automatically recognizing complex patterns in imaging data and providing quantitative, rather than qualitative, assessments of radiographic characteristics. In this Opinion article, we establish a general understanding of AI methods, particularly those pertaining to image-based tasks. We explore how these methods could impact multiple facets of radiology, with a general focus on applications in oncology, and demonstrate ways in which these methods are advancing the field. Finally, we discuss the challenges facing clinical implementation and provide our perspective on how the domain could be advanced.

Making data matter: Voxel printing for the digital fabrication of data across scales and domains

We present a multimaterial voxel-printing method that enables the physical visualization of data sets commonly associated with scientific imaging. Leveraging voxel-based control of multimaterial three-dimensional (3D) printing, our method enables additive manufacturing of discontinuous data types such as point cloud data, curve and graph data, image-based data, and volumetric data. By converting data sets into dithered material deposition descriptions, through modifications to rasterization processes, we demonstrate that data sets frequently visualized on screen can be converted into physical, materially heterogeneous objects. Our approach alleviates the need to postprocess data sets to boundary representations, preventing alteration of data and loss of information in the produced physicalizations. Therefore, it bridges the gap between digital information representation and physical material composition. We evaluate the visual characteristics and features of our method, assess its relevance and applicability in the production of physical visualizations, and detail the conversion of data sets for multimaterial 3D printing. We conclude with exemplary 3D-printed data sets produced by our method pointing toward potential applications across scales, disciplines, and problem domains.

Predictors of Mortality in Living Donor Liver Transplantation

BACKGROUND

Egypt has the highest prevalence of the world hepatitis C virus (HCV) load. Hence, the problem of end-stage liver disease (ESLD) is considered a huge burden on the community. Living donor liver transplantation (LDLT) is the only source of donation in Egypt till now. Survival rates had shown significant improvement in the past decades. This study provides analysis of the mortality rates and possible predictors of mortality following LDLT. It also aids in developing a practical and easy-to-apply risk index for prediction of early mortality.

PATIENTS AND METHODS

This study is a retrospective study that was designed to analyze data from 128 adult patients with ESLD who underwent LDLT in the Liver Transplantation Unit at Faculty of Medicine, Cairo University. Early and late mortality were identified. All potential risk factors were tested using univariate regression for association with early and late mortality. Significant variables were then entered into a multivariable logistic regression model for identifying the predictors for mortality.

RESULTS

Sepsis was the most common cause of early mortality. Early mortality and 1-year mortality were 29 (23%) and 23 (18%), respectively. Model for End-Stage Liver Disease (MELD) score, intraoperative packed red blood corpuscles (RBCs), and duration of intensive care unit (ICU) stay were found to be independently associated with early mortality.

CONCLUSION

A MELD score >20, intraoperative transfusion >8 units of packed RBCs, and ICU stay >9 days are three independent predictors of early mortality. Their incorporation into a combined Risk Index can be used to improve outcomes of LDLT.

Silent cerebral MRI findings in lupus nephritis patients: Is it clinically significant?

Lupus nephritis (LN) carries high morbidity and mortality and whenever added to neuropsychiatric manifestations lead to more unfavorable prognosis. Though silent brain MRI findings in systemic lupus erythematosus (SLE) had been widely studied, the current work focused on LN patients comparing them to those without kidney affection, studying their cerebral MRI and its correlation with the histopathological classes of LN and disease activity. This may enable us to know more about early brain affection in LN patients for better follow up, management, and prognosis of this serious comorbidity. Cerebral MRI and MRA were studied in 40 SLE patients without neuropsychiatric manifestations; 20 LN patients with different histopathological classes and 20 patients without kidney affection. Disease activity was assessed for all patients using SLE disease activity index (SLEDAI). Abnormal MRI brain findings were more common in LN patients “though non significant” (P = 0.9). The most common lesions were white matter hyperintense lesions (WMHLs). Number and size of such lesions were significantly higher in LN patients (1.8 fold that of non nephritis, P = 0.003 and 0.03, respectively) and positively correlated with urea, creatinine, urinary albumin/creatinine ratio, SLEDAI, ESR, CRP, and grades of renal biopsy and negatively correlated with C3 and C4. Cortical atrophy and prepontine space dilatation were also significantly higher in LN patients (P = 0.01). Asymptomatic MRI brain lesions whenever present in LN patients, they are usually clinically significant and well correlate to laboratory parameters of LN, grades of renal biopsy, and disease activity independent to age, sex and hypertension.

Computational Radiomics System to Decode the Radiographic Phenotype

Radiomics aims to quantify phenotypic characteristics on medical imaging through the use of automated algorithms. Radiomic artificial intelligence (AI) technology, either based on engineered hard-coded algorithms or deep learning methods, can be used to develop noninvasive imaging-based biomarkers. However, lack of standardized algorithm definitions and image processing severely hampers reproducibility and comparability of results. To address this issue, we developed PyRadiomics, a flexible open-source platform capable of extracting a large panel of engineered features from medical images. PyRadiomics is implemented in Python and can be used standalone or using 3D Slicer. Here, we discuss the workflow and architecture of PyRadiomics and demonstrate its application in characterizing lung lesions. Source code, documentation, and examples are publicly available at www.radiomics.io With this platform, we aim to establish a reference standard for radiomic analyses, provide a tested and maintained resource, and to grow the community of radiomic developers addressing critical needs in cancer research. Cancer Res; 77(21); e104-7. ©2017 AACR.

Different Score Systems to Predict Mortality in Living Donor Liver Transplantation: Which Is the Winner? The Experience of an Egyptian Center for Living Donor Liver Transplantation

INTRODUCTION

Many scoring systems have been proposed to predict the outcome of deceased donor liver transplantation. However, their impact on the outcome in living donor liver transplantation (LDLT) has not yet been elucidated. This study sought to assess performance of preoperative Model for End-Stage Liver Disease (MELD) score in predicting postoperative mortality in LDLT and to compare it with other scores: MELDNa, United Kingdom End-Stage Liver Disease (UKELD), MELD to serum sodium ratio (MESO), updated MELD, donor age-MELD (D-MELD) and integrated MELD (iMELD).

METHODS

We retrospectively analyzed data from 86 adult Egyptian patients who underwent LDLT in a single center. Preoperative MELD, MELDNa, MESO, UKELD, updated MELD, D-MELD, and iMELD were calculated. Receiver-operator characteristic (ROC) curves and area under the curve (AUC) were used to assess the performance of MELD and other scores in predicting postoperative mortality at 3 months (early) and 12 months.

RESULTS

Among the 86 patients, mean age 48 ± 7 years, 76 (88%) were of male sex and 27 (31.4%) had died. Preoperative MELD failed to predict early mortality (AUC = 0.63; P = .066). Comparing preoperative MELD with other scores, all other scores had better predictive ability (P < .05), with D-MELD on the top of the list (AUC = 0.68, P = .016), followed closely by UKELD (AUC = 0.67, P = .025). After that were iMELD, MESO, and MELDNa with the same predictive performance (AUC = 0.65; P < .05); updated MELD had the lowest prediction (AUC = 0.640; P = .04). Moreover, all scores failed to predict mortality at 12 months (P > .05).

CONCLUSIONS

Preoperative MELD failed to predict either early or 1-year mortality after LDLT. D-MELD, UKELD, MELDNa, iMELD, and MESO could be used as better predictors of early mortality than MELD; however, we need to develop an effective score system to predict mortality after LDLT.

Intra-operative Ultrasound-guided Thrombectomy and Thrombolysis for Post-operative Portal Vein Thrombosis in Living Liver Donors

There are few reports of portal vein thrombosis among living donor liver transplant donors and no published data on the management of this event. In this report, we present our experience in the diagnosis and management of this rare complication in two living donor liver transplantation donors who developed post-operative portal vein thrombosis. Both cases were successfully managed with intra-operative ultrasound-guided thrombectomy, vein patch venoplasty, and catheter-directed thrombolysis. The two donors are symptom-free two years after the event.

Microencapsulation Approach for Orally Extended Delivery of Glipizide: In vitro and in vivo Evaluation

Glipizide is an effective antidiabetic agent, however, it suffers from relatively short biological half-life. To solve this encumbrance, it is a prospective candidate for fabricating glipizide extended release microcapsules. Microencapsulation of glipizde with a coat of alginate alone or in combination with chitosan or carbomer 934P was prepared employing ionotropic gelation process. The prepared microcapsules were evaluated in vitro by microscopical examination, determination of the particle size, yield and microencapsulation efficiency. The filled capsules were assessed for content uniformity and drug release characteristics. Stability study of the optimised formulas was carried out at three different temperatures over 12 weeks. In vivo bioavailability study and hypoglycemic activity of C9 microcapsules were done on albino rabbits. All formulas achieved high yield, microencapsulation efficiency and extended t_1/2. C9 and C19 microcapsules attained the most optimised results in all tests and complied with the dissolution requirements for extended release dosage forms. These two formulas were selected for stability studies. C9 exhibited longer shelf-life and hence was chosen for in vivo studies. C9 microcapsules showed an improvement in the drug bioavailability and significant hypoglycemic activity compared to immediate release tablets (Minidiab^® 5 mg). The optimised microcapsule formulation developed was found to produce extended antidiabetic activity.

Outcome of living donor liver transplantation for Egyptian patients with hepatitis C (genotype 4)-related cirrhosis

BACKGROUND

Hepatitis C virus (HCV) recurrence after living donor liver transplantation (LDLT) represents a challenging issue due to universal viral recurrence and invasion into the graft, although the incidence of histological recurrence, risk factors, and survival rates are still controversial.

PATIENTS AND METHODS

Recurrence of HCV was studied in 38 of 53 adult patients who underwent LDLT.

RESULTS

Recipient and graft survivals were 86.6% at the end of the follow-up which was comparable to literature reports for deceased donor liver transplantation (DDLT). Clinical HCV recurrence was observed in 10/38 patients (26.3%). Four patients developed mild fibrosis with a mean fibrosis score of 0.6 and mean grade of histological activity index (HAI) of 7.1. None of the recipients developed allograft cirrhosis during the mean follow-up period of 16 +/- 8.18 months (range, 4-35 months). Estimated and actual graft volumes were negatively correlated with the incidence and early clinical HCV recurrence. None of the other risk factors were significantly correlated with clinical HCV recurrence: gender, donor and recipient ages, pretransplantation Child-Pugh or model for end-stage liver disease (MELD) scores, pre- and postoperative viremia, immunosuppressive drugs, pulse steroid therapy, and preoperative anti-HBc status.

CONCLUSIONS

Postoperative patient and graft survival rates for HCV (genotype 4)-related cirrhosis were more or less comparable to DDLT reported in the literature. Clinical HCV recurrence after LDLT in our study was low. Small graft volume was a significant risk factor for HCV recurrence. A longer follow-up and a larger number of patients are required to clarify these issues.

A new system for the assessment of diabetic foot planter pressure

Most skin injuries in neuropathy-type diabetic foot patients occur on the planter soft tissue at sites of abnormally high pressure values. If not detected and treated early enough, these localized sites are likely to develop skin breakdown and ulceration, which puts the patient at higher risks including the need for amputation. Current diagnostic techniques, such as CT and MRI, are primarily used for assessing later stage patients but are not used for screening. In this work, we report a new system for the assessment of planter pressure distribution. The system is easy to use, inexpensive, and may provide the needed accuracy to become a screening and ulceration risk assessment device. The method used is based on the "blanching" effect of tissue that occurs when it is under pressure. Using a standard optical scanner, we acquire the footprint under body weight and map the resulting blanching to different intensity levels. Different intensity levels are mapped to different color codes to obtain pressure distribution maps. These maps can be used by the clinician to identify high risk sites to help prescribe the necessary intervention. Initial testing of the system has demonstrated encouraging preliminary results.