Artificial intelligence-based diagnosis of asbestosis: analysis of a database with applicants for asbestosis state aid.

OBJECTIVES: In many countries, workers who developed asbestosis due to their occupation are eligible for government support. Based on the results of clinical examination, a team of pulmonologists determine the eligibility of patients to these programs. In this Dutch cohort study, we aim to demonstrate the potential role of an artificial intelligence (AI)-based system for automated, standardized, and cost-effective evaluation of applications for asbestosis patients. METHODS: A dataset of n = 523 suspected asbestosis cases/applications from across the Netherlands was retrospectively collected. Each case/application was reviewed, and based on the criteria, a panel of three pulmonologists would determine eligibility for government support. An AI system is proposed, which uses thoracic CT images as input, and predicts the assessment of the clinical panel. Alongside imaging, we evaluated the added value of lung function parameters. RESULTS: The proposed AI algorithm reached an AUC of 0.87 (p < 0.001) in the prediction of accepted versus rejected applications. Diffusion capacity (DLCO) also showed comparable predictive value (AUC = 0.85, p < 0.001), with little correlation between the two parameters (r-squared = 0.22, p < 0.001). The combination of the imaging AI score and DLCO achieved superior performance (AUC = 0.95, p < 0.001). Interobserver variability between pulmonologists on the panel was estimated at alpha = 0.65 (Krippendorff's alpha). CONCLUSION: We developed an AI system to support the clinical decision-making process for the application to the government support for asbestosis. A multicenter prospective validation study is currently ongoing to examine the added value and reliability of this system alongside the clinic panel. KEY POINTS: • Artificial intelligence can detect imaging patterns of asbestosis in CT scans in a cohort of patients applying for state aid. • Combining the AI prediction with the diffusing lung function parameter reaches the highest diagnostic performance. • Specific cases with fibrosis but no asbestosis were correctly classified, suggesting robustness of the AI system, which is currently under prospective validation.

Colonoscopy with robotic steering and automated lumen centralization: a feasibility study in a colon model.

BACKGROUND AND STUDY AIMS: We introduced a new platform for performing colonoscopy with robotic steering and automated lumen centralization (RS-ALC) and evaluated its technical feasibility. PARTICIPANTS AND METHODS: Expert endoscopists (n = 8) and endoscopy-naive novices (n = 10) used conventional steering and RS-ALC to perform colonoscopy in a validated colon model with simulated polyps (n = 21). The participants were randomized to which modality they were to use first. End points were the cecal intubation time, number of detected polyps, and subjective evaluation of the platform. RESULTS: Novices were able to intubate the cecum faster with RS-ALC (median 8 minutes [min] 56 seconds [s], interquartile range [IQR] 6  min 46  s - 16  min 34  s vs. median 11  min 47  s, IQR 8  min 19  s - 15  min 33  s, P = 0.65), whereas experts were faster with conventional steering (median 2  min 9  s, IQR 1  min 13 s - 7  min 28  s vs. median 13  min 1  s, IQR 5  min 9 s - 16  min 54  s, P = 0.12). Novices detected more polyps with RS-ALC (median 88.1 %, IQR 79.8 % - 95.2 % vs. median 78.6 %, IQR 75.0 % - 91.7 %, P = 0.17), whereas experts detected more polyps with conventional steering (median 80.9 %, IQR 76.2 % - 85.7 % vs. median 69.0 %, IQR 61.0 % - 75.0 %, P = 0.03). Novices were more positive than experts about the new platform (P = 0.02), noting an easier and faster introduction of the colonoscope with RS-ALC than with conventional steering. CONCLUSIONS: Colonoscopy with RS-ALC is technically feasible and appears to be easier and more intuitive than conventional steering for endoscopy-naive novices.

Artificial Intelligence-based Quantification of Pleural Plaque Volume and Association With Lung Function in Asbestos-exposed Patients.

PURPOSE: Pleural plaques (PPs) are morphologic manifestations of long-term asbestos exposure. The relationship between PP and lung function is not well understood, whereas the time-consuming nature of PP delineation to obtain volume impedes research. To automate the laborious task of delineation, we aimed to develop automatic artificial intelligence (AI)-driven segmentation of PP. Moreover, we aimed to explore the relationship between pleural plaque volume (PPV) and pulmonary function tests. MATERIALS AND METHODS: Radiologists manually delineated PPs retrospectively in computed tomography (CT) images of patients with occupational exposure to asbestos (May 2014 to November 2019). We trained an AI model with a no-new-UNet architecture. The Dice Similarity Coefficient quantified the overlap between AI and radiologists. The Spearman correlation coefficient ( r ) was used for the correlation between PPV and pulmonary function test metrics. When recorded, these were vital capacity (VC), forced vital capacity (FVC), and diffusing capacity for carbon monoxide (DLCO). RESULTS: We trained the AI system on 422 CT scans in 5 folds, each time with a different fold (n = 84 to 85) as a test set. On these independent test sets combined, the correlation between the predicted volumes and the ground truth was r = 0.90, and the median overlap was 0.71 Dice Similarity Coefficient. We found weak to moderate correlations with PPV for VC (n = 80, r = -0.40) and FVC (n = 82, r = -0.38), but no correlation for DLCO (n = 84, r = -0.09). When the cohort was split on the median PPV, we observed statistically significantly lower VC ( P = 0.001) and FVC ( P = 0.04) values for the higher PPV patients, but not for DLCO ( P = 0.19). CONCLUSION: We successfully developed an AI algorithm to automatically segment PP in CT images to enable fast volume extraction. Moreover, we have observed that PPV is associated with loss in VC and FVC.

An improved camera model for oblique-viewing laparoscopes: high reprojection accuracy independent of telescope rotation.

Objective. Oblique-viewing laparoscopes are popular in laparoscopic surgeries where the target anatomy is located in narrow areas. Their viewing direction can be shifted by telescope rotation without changing the laparoscope pose. This rotation also changes laparoscope camera parameters that are estimated by camera calibration to be able to reproject an anatomical model onto the laparoscopic view, creating augmented reality (AR). The aim of this study was to develop a camera model that accounts for these changes, achieving high reprojection accuracy for any telescope rotation.Approach. Camera parameters were acquired by calibrations encompassing a wide telescope rotation range. For those parameters showing periodic changes upon rotation, interpolation models were created and used to establish an updatable camera model. With this model, corner points of a tracked checkerboard were reprojected onto the checkerboard laparoscopic images, at random rotation angles. Root-mean-square reprojection errors (RMSEs) were calculated between the reprojected and imaged corner points.Main results. Reprojection RMSEs were low and approximately independent on telescope rotation angle, over a wide rotation range of 320°. The mean reprojection RMSE was 2.8±0.7 pixels for a conventional laparoscope and 3.6±0.7 pixels for a chip-on-the-tip (COTT) laparoscope, corresponding to 0.3±0.1 mm and 0.4±0.1 mm in world coordinates respectively. Worst-case reprojection errors were about 9 pixels (0.8 mm) for both laparoscopes.Significance. The camera model developed in this study improves on existing models for oblique-viewing laparoscopes because it provides high reprojection accuracy independent of the telescope rotation angle and is applicable for conventional and chip-on-a-tip oblique-viewing laparoscopes. The work presented here is an important step towards creating accurate AR in image-guided interventions where oblique-viewing laparoscopes are used while simultaneously providing the surgeon the flexibility to rotate the telescope to any desired rotation angle.Acronyms. CC: camera coordinates; CCToolbox: camera calibration toolbox; COTT: chip-on-the-tip; CS: camera sensor; DD: decentering distortion; FL: focal length; OTS: optical tracking system; PP: principal point; RD: radial distortion; SI: supplementary information;tHE:hand-eye translation component.

Artificial CT images can enhance variation of case images in diagnostic radiology skills training.

OBJECTIVES: We sought to investigate if artificial medical images can blend with original ones and whether they adhere to the variable anatomical constraints provided. METHODS: Artificial images were generated with a generative model trained on publicly available standard and low-dose chest CT images (805 scans; 39,803 2D images), of which 17% contained evidence of pathological formations (lung nodules). The test set (90 scans; 5121 2D images) was used to assess if artificial images (512 × 512 primary and control image sets) blended in with original images, using both quantitative metrics and expert opinion. We further assessed if pathology characteristics in the artificial images can be manipulated. RESULTS: Primary and control artificial images attained an average objective similarity of 0.78 ± 0.04 (ranging from 0 [entirely dissimilar] to 1[identical]) and 0.76 ± 0.06, respectively. Five radiologists with experience in chest and thoracic imaging provided a subjective measure of image quality; they rated artificial images as 3.13 ± 0.46 (range of 1 [unrealistic] to 4 [almost indistinguishable to the original image]), close to their rating of the original images (3.73 ± 0.31). Radiologists clearly distinguished images in the control sets (2.32 ± 0.48 and 1.07 ± 0.19). In almost a quarter of the scenarios, they were not able to distinguish primary artificial images from the original ones. CONCLUSION: Artificial images can be generated in a way such that they blend in with original images and adhere to anatomical constraints, which can be manipulated to augment the variability of cases. CRITICAL RELEVANCE STATEMENT: Artificial medical images can be used to enhance the availability and variety of medical training images by creating new but comparable images that can blend in with original images. KEY POINTS: • Artificial images, similar to original ones, can be created using generative networks. • Pathological features of artificial images can be adjusted through guiding the network. • Artificial images proved viable to augment the depth and broadening of diagnostic training.

Radiation-free 3D head shape and volume evaluation after endoscopically assisted strip craniectomy followed by helmet therapy for trigonocephaly.

INTRODUCTION: Radiation-free 3D post-operative sequential follow-up in craniosynostosis is hindered by the lack of consistent markers restricting evaluation to subjective comparison. However, using the computed cranial focal point (CCFP), it is possible to perform correct sequential image superposition and objective evaluation. We used this technique for mean volume and shape change evaluation of the head utilizing 3D photos after endoscopically assisted trigonocephaly surgery. METHODS: We performed a mean head shape and volume evaluation on age grouped 3D photos (n = 86) of children who underwent endoscopically assisted strip craniectomy with helmet therapy. We used CT-scans of healthy children as reference. We performed a mean shape evolution analysis and calculated the anterior fossa to total volume ratio (A/T-ratio). The volume- and A/T-ratio pattern were compared with the reference group. RESULTS: The mean anterior fossa volume evolved from 336 ml (33.4% A/T-ratio) pre-surgery to 664 ml (36.0% A/T-ratio) at 37-48 months post-surgery. Both groups have a near similar volume- and A/T-ratio pattern over time. The first 18 months show a predominant growth around the resected metopic suture. Between 18 and 24 months we observed mostly anterior orbital rim growth. From 24 months till 36-48 months the head grows predominantly at the temporal area. The least outward growth was observed at the temporal bones. CONCLUSION: Using a novel technique we were able to objectively evaluate head shape and volume using stereophotogrammetry after endoscopically assisted strip craniectomy. The A/T-ratio and volume growth pattern of endoscopically treated patients is near identical to that of the normal reference group.

Automatic detection of diabetic foot complications with infrared thermography by asymmetric analysis.

Early identification of diabetic foot complications and their precursors is essential in preventing their devastating consequences, such as foot infection and amputation. Frequent, automatic risk assessment by an intelligent telemedicine system might be feasible and cost effective. Infrared thermography is a promising modality for such a system. The temperature differences between corresponding areas on contralateral feet are the clinically significant parameters. This asymmetric analysis is hindered by (1) foot segmentation errors, especially when the foot temperature and the ambient temperature are comparable, and by (2) different shapes and sizes between contralateral feet due to deformities or minor amputations. To circumvent the first problem, we used a color image and a thermal image acquired synchronously. Foot regions, detected in the color image, were rigidly registered to the thermal image. This resulted in 97.8% ± 1.1% sensitivity and 98.4% ± 0.5% specificity over 76 high-risk diabetic patients with manual annotation as a reference. Nonrigid landmark-based registration with B-splines solved the second problem. Corresponding points in the two feet could be found regardless of the shapes and sizes of the feet. With that, the temperature difference of the left and right feet could be obtained.

Diagnostic values for skin temperature assessment to detect diabetes-related foot complications.

BACKGROUND: Skin temperature assessment is a promising modality for early detection of diabetic foot problems, but its diagnostic value has not been studied. Our aims were to investigate the diagnostic value of different cutoff skin temperature values for detecting diabetes-related foot complications such as ulceration, infection, and Charcot foot and to determine urgency of treatment in case of diagnosed infection or a red-hot swollen foot. MATERIALS AND METHODS: The plantar foot surfaces of 54 patients with diabetes visiting the outpatient foot clinic were imaged with an infrared camera. Nine patients had complications requiring immediate treatment, 25 patients had complications requiring non-immediate treatment, and 20 patients had no complications requiring treatment. Average pixel temperature was calculated for six predefined spots and for the whole foot. We calculated the area under the receiver operating characteristic curve for different cutoff skin temperature values using clinical assessment as reference and defined the sensitivity and specificity for the most optimal cutoff temperature value. Mean temperature difference between feet was analyzed using the Kruskal-Wallis tests. RESULTS: The most optimal cutoff skin temperature value for detection of diabetes-related foot complications was a 2.2°C difference between contralateral spots (sensitivity, 76%; specificity, 40%). The most optimal cutoff skin temperature value for determining urgency of treatment was a 1.35°C difference between the mean temperature of the left and right foot (sensitivity, 89%; specificity, 78%). CONCLUSIONS: Detection of diabetes-related foot complications based on local skin temperature assessment is hindered by low diagnostic values. Mean temperature difference between two feet may be an adequate marker for determining urgency of treatment.

Infrared thermal imaging for automated detection of diabetic foot complications.

BACKGROUND: Although thermal imaging can be a valuable technology in the prevention and management of diabetic foot disease, it is not yet widely used in clinical practice. Technological advancement in infrared imaging increases its application range. The aim was to explore the first steps in the applicability of high-resolution infrared thermal imaging for noninvasive automated detection of signs of diabetic foot disease. METHODS: The plantar foot surfaces of 15 diabetes patients were imaged with an infrared camera (resolution, 1.2 mm/pixel): 5 patients had no visible signs of foot complications, 5 patients had local complications (e.g., abundant callus or neuropathic ulcer), and 5 patients had diffuse complications (e.g., Charcot foot, infected ulcer, or critical ischemia). Foot temperature was calculated as mean temperature across pixels for the whole foot and for specified regions of interest (ROIs). RESULTS: No differences in mean temperature >1.5 °C between the ipsilateral and the contralateral foot were found in patients without complications. In patients with local complications, mean temperatures of the ipsilateral and the contralateral foot were similar, but temperature at the ROI was >2 °C higher compared with the corresponding region in the contralateral foot and to the mean of the whole ipsilateral foot. In patients with diffuse complications, mean temperature differences of >3 °C between ipsilateral and contralateral foot were found. CONCLUSIONS: With an algorithm based on parameters that can be captured and analyzed with a high-resolution infrared camera and a computer, it is possible to detect signs of diabetic foot disease and to discriminate between no, local, or diffuse diabetic foot complications. As such, an intelligent telemedicine monitoring system for noninvasive automated detection of signs of diabetic foot disease is one step closer. Future studies are essential to confirm and extend these promising early findings.

Statistical analysis of spectral data: a methodology for designing an intelligent monitoring system for the diabetic foot.

Early detection of (pre-)signs of ulceration on a diabetic foot is valuable for clinical practice. Hyperspectral imaging is a promising technique for detection and classification of such (pre-)signs. However, the number of the spectral bands should be limited to avoid overfitting, which is critical for pixel classification with hyperspectral image data. The goal was to design a detector/classifier based on spectral imaging (SI) with a small number of optical bandpass filters. The performance and stability of the design were also investigated. The selection of the bandpass filters boils down to a feature selection problem. A dataset was built, containing reflectance spectra of 227 skin spots from 64 patients, measured with a spectrometer. Each skin spot was annotated manually by clinicians as "healthy" or a specific (pre-)sign of ulceration. Statistical analysis on the data set showed the number of required filters is between 3 and 7, depending on additional constraints on the filter set. The stability analysis revealed that shot noise was the most critical factor affecting the classification performance. It indicated that this impact could be avoided in future SI systems with a camera sensor whose saturation level is higher than 106, or by postimage processing.