AI-based improvement in lung cancer detection on chest radiographs: results of a multi-reader study in NLST dataset.

OBJECTIVE: Assess if deep learning-based artificial intelligence (AI) algorithm improves reader performance for lung cancer detection on chest X-rays (CXRs). METHODS: This reader study included 173 images from cancer-positive patients (n = 98) and 346 images from cancer-negative patients (n = 196) selected from National Lung Screening Trial (NLST). Eight readers, including three radiology residents, and five board-certified radiologists, participated in the observer performance test. AI algorithm provided image-level probability of pulmonary nodule or mass on CXRs and a heatmap of detected lesions. Reader performance was compared with AUC, sensitivity, specificity, false-positives per image (FPPI), and rates of chest CT recommendations. RESULTS: With AI, the average sensitivity of readers for the detection of visible lung cancer increased for residents, but was similar for radiologists compared to that without AI (0.61 [95% CI, 0.55-0.67] vs. 0.72 [95% CI, 0.66-0.77], p = 0.016 for residents, and 0.76 [95% CI, 0.72-0.81] vs. 0.76 [95% CI, 0.72-0.81, p = 1.00 for radiologists), while false-positive findings per image (FPPI) was similar for residents, but decreased for radiologists (0.15 [95% CI, 0.11-0.18] vs. 0.12 [95% CI, 0.09-0.16], p = 0.13 for residents, and 0.24 [95% CI, 0.20-0.29] vs. 0.17 [95% CI, 0.13-0.20], p < 0.001 for radiologists). With AI, the average rate of chest CT recommendation in patients positive for visible cancer increased for residents, but was similar for radiologists (54.7% [95% CI, 48.2-61.2%] vs. 70.2% [95% CI, 64.2-76.2%], p < 0.001 for residents and 72.5% [95% CI, 68.0-77.1%] vs. 73.9% [95% CI, 69.4-78.3%], p = 0.68 for radiologists), while that in cancer-negative patients was similar for residents, but decreased for radiologists (11.2% [95% CI, 9.6-13.1%] vs. 9.8% [95% CI, 8.0-11.6%], p = 0.32 for residents and 16.4% [95% CI, 14.7-18.2%] vs. 11.7% [95% CI, 10.2-13.3%], p < 0.001 for radiologists). CONCLUSIONS: AI algorithm can enhance the performance of readers for the detection of lung cancers on chest radiographs when used as second reader. KEY POINTS: • Reader study in the NLST dataset shows that AI algorithm had sensitivity benefit for residents and specificity benefit for radiologists for the detection of visible lung cancer. • With AI, radiology residents were able to recommend more chest CT examinations (54.7% vs 70.2%, p < 0.001) for patients with visible lung cancer. • With AI, radiologists recommended significantly less proportion of unnecessary chest CT examinations (16.4% vs. 11.7%, p < 0.001) in cancer-negative patients.

Quantitative Framework for Risk Stratification of Thyroid Nodules With Ultrasound: A Step Toward Automated Triage of Thyroid Cancer.

OBJECTIVE. The purpose of this study was to explore whether a quantitative framework can be used to sonographically differentiate benign and malignant thyroid nodules at a level comparable to that of experts. MATERIALS AND METHODS. A dataset of ultrasound images of 92 biopsy-confirmed nodules was collected retrospectively. The nodules were delineated and annotated by two expert radiologists using the standardized Thyroid Imaging Reporting and Data System lexicon of the American College of Radiology. In the framework studied, quantitative features of echogenicity, texture, edge sharpness, and margin curvature properties of thyroid nodules were analyzed in a regularized logistic regression model to predict malignancy of a nodule. The framework was validated by leave-one-out cross-validation technique, and ROC AUC, sensitivity, and specificity were used to compare with those obtained with six expert annotation-based classifiers. RESULTS. The AUC of the proposed method was 0.828 (95% CI, 0.715-0.942), which was greater than or comparable to that of the expert classifiers, for which the AUC values ranged from 0.299 to 0.829 (p = 0.99). Use of the proposed framework could have avoided biopsy of 20 of 46 benign nodules in a curative strategy (at sensitivity of 1, statistically significantly higher than three expert classifiers) or helped identify 10 of 46 malignancies in a conservative strategy (at specificity of 1, statistically significantly higher than five expert classifiers). CONCLUSION. When the proposed quantitative framework was used, thyroid nodule malignancy was predicted at the level of expert classifiers. Such a framework may ultimately prove useful as the basis for a fully automated system of thyroid nodule triage.

Colony stimulating factor-1 receptor is a central component of the foreign body response to biomaterial implants in rodents and non-human primates.

Host recognition and immune-mediated foreign body response to biomaterials can compromise the performance of implanted medical devices. To identify key cell and cytokine targets, here we perform in-depth systems analysis of innate and adaptive immune system responses to implanted biomaterials in rodents and non-human primates. While macrophages are indispensable to the fibrotic cascade, surprisingly neutrophils and complement are not. Macrophages, via CXCL13, lead to downstream B cell recruitment, which further potentiated fibrosis, as confirmed by B cell knockout and CXCL13 neutralization. Interestingly, colony stimulating factor-1 receptor (CSF1R) is significantly increased following implantation of multiple biomaterial classes: ceramic, polymer and hydrogel. Its inhibition, like macrophage depletion, leads to complete loss of fibrosis, but spares other macrophage functions such as wound healing, reactive oxygen species production and phagocytosis. Our results indicate that targeting CSF1R may allow for a more selective method of fibrosis inhibition, and improve biomaterial biocompatibility without the need for broad immunosuppression.

Diagnostic Performance of Margin Features in Thyroid Nodules in Prediction of Malignancy.

OBJECTIVE: The purpose of this study was to evaluate thyroid nodule margins for specific morphologic features and determine the diagnostic performance of these features in differentiating papillary carcinoma from benign thyroid nodules. MATERIALS AND METHODS: Nodules measuring 1-3 cm in largest diameter that had been evaluated with high-resolution ultrasound (12-18 MHz) and ultrasound-guided biopsy with definitive pathologic diagnosis were analyzed. Three blinded board-certified readers evaluated high-resolution images of each nodule for jagged edges, lobulated borders, and curved borders along their margins. Reader interpretations were correlated with the pathologic diagnosis to determine the diagnostic performance of each feature. A board-certified pathologist analyzed 10 randomly selected nodules with jagged edges by slide review to evaluate for structural correlation with the imaging finding. RESULTS: The diagnostic performance of jagged edges in papillary carcinoma of the thyroid was 67.4% sensitive and 78.3% specific (odds ratio, 7.44; p < 0.001) for malignancy. Jagged edges correlated with infiltrative variant expansion at slide review. Lobulated borders had sensitivity of 76.1% and specificity of 60.9% for papillary carcinoma (odds ratio, 4.95; p = 0.001) for malignancy. Curved borders were not a significant predictor of papillary carcinoma. CONCLUSION: Jagged edges and lobulated borders of thyroid nodule margins are statistically significant predictors of papillary carcinoma of the thyroid. Jagged edges correlate with infiltrative-type expansion and may be useful predictors of more aggressive papillary carcinomas.

Size- and shape-dependent foreign body immune response to materials implanted in rodents and non-human primates.

The efficacy of implanted biomedical devices is often compromised by host recognition and subsequent foreign body responses. Here, we demonstrate the role of the geometry of implanted materials on their biocompatibility in vivo. In rodent and non-human primate animal models, implanted spheres 1.5 mm and above in diameter across a broad spectrum of materials, including hydrogels, ceramics, metals and plastics, significantly abrogated foreign body reactions and fibrosis when compared with smaller spheres. We also show that for encapsulated rat pancreatic islet cells transplanted into streptozotocin-treated diabetic C57BL/6 mice, islets prepared in 1.5-mm alginate capsules were able to restore blood-glucose control for up to 180 days, a period more than five times longer than for transplanted grafts encapsulated within conventionally sized 0.5-mm alginate capsules. Our findings suggest that the in vivo biocompatibility of biomedical devices can be significantly improved simply by tuning their spherical dimensions.

Implantable, multifunctional, bioresorbable optics.

Advances in personalized medicine are symbiotic with the development of novel technologies for biomedical devices. We present an approach that combines enhanced imaging of malignancies, therapeutics, and feedback about therapeutics in a single implantable, biocompatible, and resorbable device. This confluence of form and function is accomplished by capitalizing on the unique properties of silk proteins as a mechanically robust, biocompatible, optically clear biomaterial matrix that can house, stabilize, and retain the function of therapeutic components. By developing a form of high-quality microstructured optical elements, improved imaging of malignancies and of treatment monitoring can be achieved. The results demonstrate a unique family of devices for in vitro and in vivo use that provide functional biomaterials with built-in optical signal and contrast enhancement, demonstrated here with simultaneous drug delivery and feedback about drug delivery with no adverse biological effects, all while slowly degrading to regenerate native tissue.

Acoustic Patterning of Growth Factor for Three-Dimensional Tissue Engineering.

Temporal and spatial presentations of biological cues are critical for tissue engineering. There is a great need in improving the incorporation of bioagent(s) (specifically growth factor(s) [GF(s)]) onto three-dimensional scaffolds. In this study, we developed a process to combine additive manufacturing (AM) technology with acoustic droplet ejection (ADE) technology to control GF distribution. More specifically, we implemented ADE to control the distribution of recombinant human bone morphogenetic protein-2 (rhBMP-2) onto polycaprolactone (PCL)-based tissue engineering constructs (TECs). Three substrates were used in this study: (1) succinimide-terminated PCL (PCL-N-hydroxysuccinimide [NHS]) as model material, (2) alkali-treated PCL (PCL-NaOH) as first control material, and (3) fibrin-coated PCL (PCL-Fibrin) as second control material. It was shown that our process enables a pattern of BMP-2 spots of ∼250 µm in diameter with ∼700 µm center-to-center spacing. An initial concentration of BMP-2 higher than 300 µg/L was required to retain a detectable amount of GF on the substrate after a wash with phosphate-buffered solution. However, to obtain detectable osteogenic differentiation of C2C12 cells, the initial concentration of BMP-2 higher than 750 µg/L was needed. The cells on PCL-NHS samples showed spatial alkaline phosphatase staining correlating with local patterns of BMP-2, although the intensity was lower than the controls (PCL-NaOH and PCL-Fibrin). Our results have demonstrated that the developed AM-ADE process holds great promise in creating TECs with highly controlled GF patterning. Impact statement The combined process of additive manufacturing with acoustic droplet ejection to control growth factor (GF) distribution across three-dimensional (3D) porous scaffolds that is presented in this study enables creating 3D tissue engineering constructs with highly controlled GF patterning. Such constructs enable temporal and spatial presentations of biological cues for enhancing cell migration and differentiation and eventually the formation of targeted tissues in vitro and in vivo.

Central echogenic areas in thyroid nodules: Diagnostic performance in prediction of papillary cancer.

PURPOSE: To determine the diagnostic performance of the "central echogenic area" sonographic finding in differentiating papillary carcinomas from benign nodules and to how this finding may be used to improve fine needle aspiration(FNA) technique/utilization. MATERIALS AND METHODS: We retrospectively analyzed ultrasound guided FNAs of thyroid nodules between 1 and 3 cm for central echogenic areas. 92 patients (evenly distributed benign vs papillary carcinoma) were evaluated by a blinded reader for areas of non-shadowing homogenously echogenic centers within the nodules and correlated with FNA proven pathologic diagnosis. A selection of nodules with the central echogenic area finding were selected for further slide review to establish a pathologic basis for the finding. RESULTS: Diagnostic performance of the "central echogenic area" feature in papillary thyroid cancers was 52.2% sensitive and 91.3% specific for papillary thyroid carcinoma with a PPV of 85.7% and NPV of 65.6%. There was a significant correlation with a p < 0.01 between the central echogenic area finding and papillary carcinoma. On pathologic slide review, nodules with central echogenic areas consistently demonstrated a central scar with conglomerate fibrosis and very few viable cells. CONCLUSION: Despite its relatively low sensitivity, the central echogenic area finding is highly specific for papillary carcinoma of the thyroid and can be a useful sonographic finding in decisions regarding FNA. Additionally, due to the paucity of cells and high density of conglomerate fibrosis, central echogenic areas should be avoided during FNA to decrease the chance of an inadequate sample collection.

Toward Automated Pre-Biopsy Thyroid Cancer Risk Estimation in Ultrasound.

We propose a computational framework for automated cancer risk estimation of thyroid nodules visualized in ultrasound (US) images. Our framework estimates the probability of nodule malignancy using random forests on a rich set of computational features. An expert radiologist annotated thyroid nodules in 93 biopsy-confirmed patients using semantic image descriptors derived from standardized lexicon. On our dataset, the AUC of the proposed method was 0.70, which was comparable to five baseline expert annotation-based classifiers with AUC values from 0.72 to 0.81. Moreover, the use of the framework for decision making on nodule biopsy could have spared five out of 46 benign nodule biopsies at no cost to the health of patients with malignancies. Our results confirm the feasibility of computer-aided tools for noninvasive malignancy risk estimation in patients with thyroid nodules that could help to decrease the number of unnecessary biopsies and surgeries.

Combinatorial hydrogel library enables identification of materials that mitigate the foreign body response in primates.

The foreign body response is an immune-mediated reaction that can lead to the failure of implanted medical devices and discomfort for the recipient. There is a critical need for biomaterials that overcome this key challenge in the development of medical devices. Here we use a combinatorial approach for covalent chemical modification to generate a large library of variants of one of the most widely used hydrogel biomaterials, alginate. We evaluated the materials in vivo and identified three triazole-containing analogs that substantially reduce foreign body reactions in both rodents and, for at least 6 months, in non-human primates. The distribution of the triazole modification creates a unique hydrogel surface that inhibits recognition by macrophages and fibrous deposition. In addition to the utility of the compounds reported here, our approach may enable the discovery of other materials that mitigate the foreign body response.

Neutrophil Responses to Sterile Implant Materials.

In vivo implantation of sterile materials and devices results in a foreign body immune response leading to fibrosis of implanted material. Neutrophils, one of the first immune cells to be recruited to implantation sites, have been suggested to contribute to the establishment of the inflammatory microenvironment that initiates the fibrotic response. However, the precise numbers and roles of neutrophils in response to implanted devices remains unclear. Using a mouse model of peritoneal microcapsule implantation, we show 30-500 fold increased neutrophil presence in the peritoneal exudates in response to implants. We demonstrate that these neutrophils secrete increased amounts of a variety of inflammatory cytokines and chemokines. Further, we observe that they participate in the foreign body response through the formation of neutrophil extracellular traps (NETs) on implant surfaces. Our results provide new insight into neutrophil function during a foreign body response to peritoneal implants which has implications for the development of biologically compatible medical devices.

Silk-based conformal, adhesive, edible food sensors.

An array of passive metamaterial antennas fabricated on all protein-based silk substrates were conformally transferred and adhered to the surface of an apple. This process allows the opportunity for intimate contact of micro- and nanostructures that can probe, and accordingly monitor changes in, their surrounding environment. This provides in situ monitoring of food quality. It is to be noted that this type of sensor consists of all edible and biodegradable components, holding utility and potential relevance for healthcare and food/consumer products and markets.