This guest editorial introduces the special section on Advances in Breast Imaging.

A program devoted to performing the first in vivo synchrotron radiation (SR) breast computed tomography (BCT) is ongoing at the Elettra facility. Using the high spatial coherence of SR, phase-contrast (PhC) imaging techniques can be used. The latest high-resolution BCT acquisitions of breast specimens, obtained with the propagation-based PhC approach, are herein presented as part of the SYRMA-3D collaboration effort toward the clinical exam. Images are acquired with a 60-μm pixel dead-time-free single-photon-counting CdTe detector. The samples are imaged at 32 and 38 keV in a continuous rotating mode, delivering 5 to 20 mGy of mean glandular dose. Contrast-to-noise ratio (CNR) and spatial resolution performances are evaluated for both PhC and phase-retrieved images, showing that by applying the phase-retrieval algorithm a five-time CNR increase can be obtained with a minor loss in spatial resolution across soft tissue interfaces. It is shown that, despite having a poorer CNR, PhC images can provide a sharper visualization of microcalcifications, thus being complementary to phase-retrieved images. Furthermore, the first full-volume scan of a mastectomy sample (9  ×  9  ×  3  cm³) is reported. This investigation into surgical specimens indicates that SR BCT in terms of CNR, spatial resolution, scan duration, and scan volume is feasible.

Enhancing quality using the inspection program (EQUIP) augments the FDA/MQSA program ensuring image quality review and implementation of corrective processes. We compared technical recalls between digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM). Prospectively recorded technical recalls of consecutive screening mammograms (10/2013 – 12/2017) were compared for imaging modality [FFDM, DBT + FFDM, DBT + synthesized mammography (SynM)], images requested, and indication(s) (motion, positioning, technical/artifact). Chi-squared tests evaluated statistical significance between proportions. Of 48,324 screening mammograms, 277 (0.57%) patients were recalled for 360 indications with 371 repeated views. DBT exams had significantly less recalls compared to FFDM (X²  =  25.239; p  =  0  <  0.001). 98 (27.2%) recalls were for motion, 192 (53.3%) positioning, and 70 (19.4%) technique/artifacts. Theses indications for technical recall were compared for FFDM, DBT + FFDM, and DBT + SynM. There were significant differences in the indications for technical recall prior to and after implementing DBT + SynM (X²  =  18.719; p  <  0.001). Technical recalls declined significantly with the inclusion of DBT (SynM/FFDM) compared to FFDM alone. Recalls for motion demonstrated the greatest decrease. Positioning remains a dominant factor for technical recall regardless of modality, supporting the opportunity for continued technologist education in positioning to decrease technical recalls.

Fiber-like features are an important aspect of breast imaging. Vessels and ducts are present in all breast images, and spiculations radiating from a mass can indicate malignancy. Accordingly, fiber objects are one of the three types of signals used in the American College of Radiology digital mammography (ACR-DM) accreditation phantom. Our work focuses on the image properties of fiber-like structures in digital breast tomosynthesis (DBT) and how image reconstruction can affect their appearance. The impact of DBT image reconstruction algorithm and regularization strength on the conspicuity of fiber-like signals of various orientations is investigated in simulation. A metric is developed to characterize this orientation dependence and allow for quantitative comparison of algorithms and associated parameters in the context of imaging fiber signals. The imaging properties of fibers, characterized in simulation, are then demonstrated in detail with physical DBT data of the ACR-DM phantom. The characterization of imaging of fiber signals is used to explain features of an actual clinical DBT case. For the algorithms investigated, at low regularization setting, the results show a striking variation in conspicuity as a function of orientation in the viewing plane. In particular, the conspicuity of fibers nearly aligned with the plane of the x-ray source trajectory is decreased relative to more obliquely oriented fibers. Increasing regularization strength mitigates this orientation dependence at the cost of increasing depth blur of these structures.

Mammographic density is an important risk factor for breast cancer. In recent research, percentage density assessed visually using visual analogue scales (VAS) showed stronger risk prediction than existing automated density measures, suggesting readers may recognize relevant image features not yet captured by hand-crafted algorithms. With deep learning, it may be possible to encapsulate this knowledge in an automatic method. We have built convolutional neural networks (CNN) to predict density VAS scores from full-field digital mammograms. The CNNs are trained using whole-image mammograms, each labeled with the average VAS score of two independent readers. Each CNN learns a mapping between mammographic appearance and VAS score so that at test time, they can predict VAS score for an unseen image. Networks were trained using 67,520 mammographic images from 16,968 women and for model selection we used a dataset of 73,128 images. Two case-control sets of contralateral mammograms of screen detected cancers and prior images of women with cancers detected subsequently, matched to controls on age, menopausal status, parity, HRT and BMI, were used for evaluating performance on breast cancer prediction. In the case-control sets, odd ratios of cancer in the highest versus lowest quintile of percentage density were 2.49 (95% CI: 1.59 to 3.96) for screen-detected cancers and 4.16 (2.53 to 6.82) for priors, with matched concordance indices of 0.587 (0.542 to 0.627) and 0.616 (0.578 to 0.655), respectively. There was no significant difference between reader VAS and predicted VAS for the prior test set (likelihood ratio chi square, p  =  0.134). Our fully automated method shows promising results for cancer risk prediction and is comparable with human performance.

Assessment of breast density at the point of mammographic examination could lead to optimized breast cancer screening pathways. The onsite breast density information may offer guidance of when to recommend supplemental imaging for women in a screening program. A software application (Insight BD, Siemens Healthcare GmbH) for fast onsite quantification of volumetric breast density is evaluated. The accuracy of the method is assessed using breast tissue equivalent phantom experiments resulting in a mean absolute error of 3.84%. Reproducibility of measurement results is analyzed using 8427 exams in total, comparing for each exam (if available) the densities determined from left and right views, from cranio-caudal and medio-lateral oblique views, from full-field digital mammograms (FFDM) and digital breast tomosynthesis (DBT) data and from two subsequent exams of the same breast. Pearson correlation coefficients of 0.937, 0.926, 0.950, and 0.995 are obtained. Consistency of the results is demonstrated by evaluating the dependency of the breast density on women’s age. Furthermore, the agreement between breast density categories computed by the software with those determined visually by 32 radiologists is shown by an overall percentage agreement of 69.5% for FFDM and by 64.6% for DBT data. These results demonstrate that the software delivers accurate, reproducible, and consistent measurements that agree well with the visual assessment of breast density by radiologists.

Contrast-enhanced digital mammography (CEDM) reveals neovasculature of breast lesions in a two-dimensional contrast enhancement map. Contrast-enhanced digital breast tomosynthesis (CEDBT) provides contrast enhancement in three dimensions, which may improve lesion characterization and localization. We aim to compare CEDM and CEDBT for lesion assessment. Women with breast imaging-reporting and data system 4 or 5 suspicious breast lesion(s) were recruited in our study and were imaged with CEDM and CEDBT in succession under one breast compression. Two radiologists assessed CEDM and CEDBT with both images displayed side-by-side and compared (1) contrast enhancement of lesions and (2) lesion margin using a five-point scale ranging from −2 (CEDM much better) to +2 (CEDBT much better). Biopsy identified 19 malignant lesions with contrast enhancement. Our results show that CEDBT provides better lesion margins than CEDM with limited reduction in contrast enhancement. CEDBT delivers less radiation dose compared to CEDM + DBT. Synthetic CEDM can be generated from CEDBT data and provides lesion contrast enhancement comparable to CEDM. CEDBT has potential for clinical applications, such as treatment response monitoring and guidance for biopsy.

Radiomic features extracted from magnetic resonance (MR) images have potential for diagnosis and prognosis of breast cancer. However, presentation of lesions on images may be affected by biopsy. Thirty-four nonsize features were extracted from 338 dynamic contrast-enhanced MR images of benign lesions and luminal A cancers (80 benign/34 luminal A prebiopsy; 46 benign/178 luminal A postbiopsy). Feature value distributions were compared by biopsy condition using the Kolmogorov–Smirnov test. Classification performance was assessed by biopsy condition in the task of distinguishing between lesion types using the area under the receiver operating characteristic curve (AUCROC) as performance metric. Superiority and equivalence testing of differences in AUCROC between biopsy conditions were conducted using Bonferroni–Holm-adjusted significance levels. Distributions for most nonsize features for each lesion type failed to show a statistically significant difference between biopsy conditions. Fourteen features outperformed random guessing in classification. Their differences in AUCROC by biopsy condition failed to reach statistical significance, but we were unable to prove equivalence using a margin of ΔAUCROC  =    ±  0.10. However, classification performance for lesions imaged either prebiopsy or postbiopsy appears to be similar when taking into account biopsy condition.

With recent advances in the field of deep learning, the use of convolutional neural networks (CNNs) in medical imaging has become very encouraging. The aim of our paper is to propose a patch-based CNN method for automated mass detection in full-field digital mammograms (FFDM). In addition to evaluating CNNs pretrained with the ImageNet dataset, we investigate the use of transfer learning for a particular domain adaptation. First, the CNN is trained using a large public database of digitized mammograms (CBIS-DDSM dataset), and then the model is transferred and tested onto the smaller database of digital mammograms (INbreast dataset). We evaluate three widely used CNNs (VGG16, ResNet50, InceptionV3) and show that the InceptionV3 obtains the best performance for classifying the mass and nonmass breast region for CBIS-DDSM. We further show the benefit of domain adaptation between the CBIS-DDSM (digitized) and INbreast (digital) datasets using the InceptionV3 CNN. Mass detection evaluation follows a fivefold cross-validation strategy using free-response operating characteristic curves. Results show that the transfer learning from CBIS-DDSM obtains a substantially higher performance with the best true positive rate (TPR) of 0.98  ±  0.02 at 1.67 false positives per image (FPI), compared with transfer learning from ImageNet with TPR of 0.91  ±  0.07 at 2.1 FPI. In addition, the proposed framework improves upon mass detection results described in the literature on the INbreast database, in terms of both TPR and FPI.

Digital breast tomosynthesis (DBT) is an imaging technique created to visualize 3-D mammary structures for the purpose of diagnosing breast cancer. This imaging technique is based on the principle of computed tomography. Due to the use of a dangerous ionizing radiation, the “as low as reasonably achievable” (ALARA) principle should be respected, aiming at minimizing the radiation dose to obtain an adequate examination. Thus, a noise filtering method is a fundamental step to achieve the ALARA principle, as the noise level of the image increases as the radiation dose is reduced, making it difficult to analyze the image. In our work, a double denoising approach for DBT is proposed, filtering in both projection (prereconstruction) and image (postreconstruction) domains. First, in the prefiltering step, methods were used for filtering the Poisson noise. To reconstruct the DBT projections, we used the filtered backprojection algorithm. Then, in the postfiltering step, methods were used for filtering Gaussian noise. Experiments were performed on simulated data generated by open virtual clinical trials (OpenVCT) software and on a physical phantom, using several combinations of methods in each domain. Our results showed that double filtering (i.e., in both domains) is not superior to filtering in projection domain only. By investigating the possible reason to explain these results, it was found that the noise model in DBT image domain could be better modeled by a Burr distribution than a Gaussian distribution. Finally, this important contribution can open a research direction in the DBT denoising problem.

The convolutional neural network (CNN) is a promising technique to detect breast cancer based on mammograms. Training the CNN from scratch, however, requires a large amount of labeled data. Such a requirement usually is infeasible for some kinds of medical image data such as mammographic tumor images. Because improvement of the performance of a CNN classifier requires more training data, the creation of new training images, image augmentation, is one solution to this problem. We applied the generative adversarial network (GAN) to generate synthetic mammographic images from the digital database for screening mammography (DDSM). From the DDSM, we cropped two sets of regions of interest (ROIs) from the images: normal and abnormal (cancer/tumor). Those ROIs were used to train the GAN, and the GAN then generated synthetic images. For comparison with the affine transformation augmentation methods, such as rotation, shifting, scaling, etc., we used six groups of ROIs [three simple groups: affine augmented, GAN synthetic, real (original), and three mixture groups of any two of the three simple groups] for each to train a CNN classifier from scratch. And, we used real ROIs that were not used in training to validate classification outcomes. Our results show that, to classify the normal ROIs and abnormal ROIs from DDSM, adding GAN-generated ROIs in the training data can help the classifier prevent overfitting, and on validation accuracy, the GAN performs about 3.6% better than affine transformations for image augmentation. Therefore, GAN could be an ideal augmentation approach. The images augmented by GAN or affine transformation cannot substitute for real images to train CNN classifiers because the absence of real images in the training set will cause over-fitting.

Recent advances in thin film transistor array technology have enabled the possibility of “back-irradiated” (BI) indirect active-matrix flat-panel imagers (AMFPIs), in which x-rays first expose the scintillator through the optical sensor, and “dual-screen” AMFPIs, in which two scintillating screens are sandwiched around a bidirectional active matrix. We developed a theoretical treatment of such detectors. The theory is used to investigate possible imaging performance improvements over conventional “front-irradiation” (FI) AMFPIs, where the active matrix is opposite the x-ray entrance surface. Simple expressions for the modulation transfer function, normalized noise power spectrum, Swank factor (A_s), Lubberts function L  (  f  )  , and spatial frequency-dependent detective quantum efficiency DQE  (  f  )   are derived and used to compute these quantities for a variety of FI, BI, and dual-screen detector configurations. DQE  (  f  )   is used as the figure of merit for optimizing and comparing the performance of the various configurations. Large performance improvements over FI single-screen systems are found possible with BI. Further improvements are found possible with dual-screen configurations. The ratio of the thicknesses of the two screens that optimizes DQE is generally asymmetric, with the thinner screen facing the incident flux. The optimum ratio depends on the x-ray attenuation length in the screen.

We describe the development and verification of an optical, powder-free, intraoral scanner based on a chromatic confocal imaging system, which has been realized in a single-shot multifocal approach. The system is based on a combination of micro-optical and dispersion optical elements. The methodology of recording and analyzing the acquired data are discussed in detail. A proof of concept with the application in intraoral scanning is provided. According to the current findings, the measurement uncertainty, scan speed, and overall performance of the device can well compete with the state-of-the-art of commercially available intraoral scanners.

Texture is a key radiomics measurement for quantification of disease and disease progression. The sensitivity of the measurements to image acquisition, however, is uncertain. We assessed bias and variability of computed tomography (CT) texture feature measurements across many clinical image acquisition settings and reconstruction algorithms. Diverse, anatomically informed textures (texture A, B, and C) were simulated across 1188 clinically relevant CT imaging conditions representing four in-plane pixel sizes (0.4, 0.5, 0.7, and 0.9 mm), three slice thicknesses (0.625, 1.25, and 2.5 mm), three dose levels (CTDI_vol 1.90, 3.75, and 7.50 mGy), and 33 reconstruction kernels. Imaging conditions corresponded to noise and resolution properties representative of five commercial scanners (GE LightSpeed VCT, GE Discovery 750 HD, GE Revolution, Siemens Definition Flash, and Siemens Force) in filtered backprojection and iterative reconstruction. About 21 texture features were calculated and compared between the ground-truth phantom (i.e., preimaging) and its corresponding images. Each feature was measured with four unique volumes of interest (VOIs) sizes (244, 579, 1000, and 1953  mm³. To characterize the bias, the percentage relative difference [PRD(%)] in each feature was calculated between the imaged scenario and the ground truth for all VOI sizes. Feature variability was assessed in terms of (1) σ_PRD  (    %    )   indicating the variability between the ground truth and simulated image scenario based on the PRD(%), (2) COV_f indicating the simulation-based variability, and (3) COV_T indicating the natural variability present in the ground-truth phantom. The PRD ranged widely from −97  %   to 1220%, with an underlying variability (σ) of up to 241%. Features such as gray-level nonuniformity, texture entropy, sum average, and homogeneity exhibited low susceptibility to reconstruction kernel effects (PRD  <  3  %  ) with relatively small σ_PRD  (    %    )   (≤5  %  ) across imaging conditions. The dynamic range of results indicates that image acquisition and reconstruction conditions of in-plane pixel sizes, slice thicknesses, dose levels, and reconstruction kernels can lead to significant bias and variability in feature measurements.

Volume-of-interest (VOI) imaging is a strategy in computed tomography (CT) that restricts x-ray fluence to particular anatomical targets via dynamic beam modulation. This permits dose reduction while retaining image quality within the VOI. VOI-CT implementation has been challenged, in part, by a lack of hardware solutions for tailoring the incident fluence to the patient and anatomical site, as well as difficulties involving interior tomography reconstruction of truncated projection data. We propose a general VOI-CT imaging framework using multiple aperture devices (MADs), an emerging beam filtration scheme based on two binary x-ray filters. Location of the VOI is prescribed using two scout views at anterior–posterior (AP) and lateral perspectives. Based on a calibration of achievable fluence field patterns, MAD motion trajectories were designed using an optimization objective that seeks to maximize the relative fluence in the VOI subject to minimum fluence constraints. A modified penalized-likelihood method is developed for reconstruction of heavily truncated data using the full-field scout views to help solve the interior tomography problem. Physical experiments were conducted to show the feasibility of noncentered and elliptical VOI in two applications—spine and lung imaging. Improved dose utilization and retained image quality are validated with respect to standard full-field protocols. We observe that the contrast-to-noise ratio (CNR) is 40% higher compared with low-dose full-field scans at the same dose. The total dose reduction is 50% for equivalent image quality (CNR) within the VOI.

Wilms’ tumor is one of the most frequent malignant solid tumors in childhood. Accurate segmentation of tumor tissue is a key step during therapy and treatment planning. Since it is difficult to obtain a comprehensive set of tumor data of children, there is no benchmark so far allowing evaluation of the quality of human or computer-based segmentations. The contributions in our paper are threefold: (i) we present the first heterogeneous Wilms’ tumor benchmark data set. It contains multisequence MRI data sets before and after chemotherapy, along with ground truth annotation, approximated based on the consensus of five human experts. (ii) We analyze human expert annotations and interrater variability, finding that the current clinical practice of determining tumor volume is inaccurate and that manual annotations after chemotherapy may differ substantially. (iii) We evaluate six computer-based segmentation methods, ranging from classical approaches to recent deep-learning techniques. We show that the best ones offer a quality comparable to human expert annotations.

Most of the current state-of-the-art methods for tumor segmentation are based on machine learning models trained manually on segmented images. This type of training data is particularly costly, as manual delineation of tumors is not only time-consuming but also requires medical expertise. On the other hand, images with a provided global label (indicating presence or absence of a tumor) are less informative but can be obtained at a substantially lower cost. We propose to use both types of training data (fully annotated and weakly annotated) to train a deep learning model for segmentation. The idea of our approach is to extend segmentation networks with an additional branch performing image-level classification. The model is jointly trained for segmentation and classification tasks to exploit the information contained in weakly annotated images while preventing the network from learning features that are irrelevant for the segmentation task. We evaluate our method on the challenging task of brain tumor segmentation in magnetic resonance images from the Brain Tumor Segmentation 2018 Challenge. We show that the proposed approach provides a significant improvement in segmentation performance compared to the standard supervised learning. The observed improvement is proportional to the ratio between weakly annotated and fully annotated images available for training.

We propose a pipeline to acquire a scalar tapering measurement from the carina to the most distal point of an individual airway visible on computed tomography (CT). We show the applicability of using tapering measurements on clinically acquired data by quantifying the reproducibility of the tapering measure. We generate a spline from the centerline of an airway to measure the area and arclength at contiguous intervals. The tapering measurement is the gradient of the linear regression between area in log space and arclength. The reproducibility of the measure was assessed by analyzing different radiation doses, voxel sizes, and reconstruction kernel on single timepoint and longitudinal CT scans and by evaluating the effect of airway bifurcations. Using 74 airways from 10 CT scans, we show a statistical difference, p  =  3.4  ×  10^−  4, in tapering between healthy airways (n  =  35) and those affected by bronchiectasis (n  =  39). The difference between the mean of the two populations is 0.011  mm^−  1, and the difference between the medians of the two populations was 0.006  mm^−  1. The tapering measurement retained a 95% confidence interval of ±0.005  mm^−  1 in a simulated 25 mAs scan and retained a 95% confidence of ±0.005  mm^−  1 on simulated CTs up to 1.5 times the original voxel size. We have established an estimate of the precision of the tapering measurement and estimated the effect on precision of the simulated voxel size and CT scan dose. We recommend that the scanner calibration be undertaken with the phantoms as described, on the specific CT scanner, radiation dose, and reconstruction algorithm that are to be used in any quantitative studies.

A color fundus image is an image of the inner wall of the eyeball taken with a fundus camera. Doctors can observe retinal vessel changes in the image, and these changes can be used to diagnose many serious diseases such as atherosclerosis, glaucoma, and age-related macular degeneration. Automated segmentation of retinal vessels can facilitate more efficient diagnosis of these diseases. We propose an improved U-net architecture to segment retinal vessels. Multiscale input layer and dense block are introduced into the conventional U-net, so that the network can make use of richer spatial context information. The proposed method is evaluated on the public dataset DRIVE, achieving 0.8199 in sensitivity and 0.9561 in accuracy. Especially for thin blood vessels, which are difficult to detect because of their low contrast with the background pixels, the segmentation results have been improved.

We present a skin lesion diagnosis system that segments the lesion and classifies it as melanoma or nonmelanoma. The proposed system is capable to deal with skin lesion images acquired by standard consumer-grade cameras and dermascopes. In order to suppress the image artifacts and enhance the lesion area, we propose an illumination correction strategy which consists of filtering in frequency and spatial domains. We introduce a hybrid model for lesion segmentation, which forms texture segments of the illumination corrected image using a factorization technique. Then based on the texture distinctiveness of the corrected and the texture segmented images, the saliency maps are computed, which are combined to decide lesion texture segments. In order to classify the segmented lesion, we propose a multimodal feature set composed of texture-, shape-, and color-based features. Classification performance of the multimodal features is evaluated using support vector machine, decision trees, and Mahalanobis distance classifiers. We evaluate the performance of the proposed system qualitatively and quantitatively. For the consumer-grade camera skin images dataset and ISIC 2017 dermascopic images dataset, the average segmentation accuracies are 98.4% and 95.4%, respectively; the classification accuracies are 98.06% and 93.95%, respectively.

The purpose of this study was to evaluate breast MRI radiomics in predicting, prior to any treatment, the response to neoadjuvant chemotherapy (NAC) in patients with invasive lymph node (LN)-positive breast cancer for two tasks: (1) prediction of pathologic complete response and (2) prediction of post-NAC LN status. Our study included 158 patients, with 19 showing post-NAC complete pathologic response (pathologic TNM stage T0,N0,MX) and 139 showing incomplete response. Forty-two patients were post-NAC LN-negative, and 116 were post-NAC LN-positive. We further analyzed prediction of response by hormone receptor subtype of the primary cancer (77 hormone receptor-positive, 39 HER2-enriched, 38 triple negative, and 4 cancers with unknown receptor status). Only pre-NAC MRIs underwent computer analysis, initialized by an expert breast radiologist indicating index cancers and metastatic axillary sentinel LNs on DCE-MRI images. Forty-nine computer-extracted radiomics features were obtained, both for the primary cancers and for the metastatic sentinel LNs. Since the dataset contained MRIs acquired at 1.5 T and at 3.0 T, we eliminated features affected by magnet strength using the Mann–Whitney U-test with the null-hypothesis that 1.5 T and 3.0 T samples were selected from populations having the same distribution. Bootstrapping and ROC analysis were used to assess performance of individual features in the two classification tasks. Eighteen features appeared unaffected by magnet strength. Pre-NAC tumor features generally appeared uninformative in predicting response to therapy. In contrast, some pre-NAC LN features were able to predict response: two pre-NAC LN features were able to predict pathologic complete response (area under the ROC curve (AUC) up to 0.82 [0.70; 0.88]), and another two were able to predict post-NAC LN-status (AUC up to 0.72 [0.62; 0.77]), respectively. In the analysis by a hormone receptor subtype, several potentially useful features were identified for predicting response to therapy in the hormone receptor-positive and HER2-enriched cancers.

Twin-to-twin transfusion syndrome is a condition in which identical twins share a certain pattern of vascular connections in the placenta. This leads to an imbalance in the blood flow that, if not treated, may result in a fatal outcome for both twins. To treat this condition, a surgeon explores the placenta with a fetoscope to find and photocoagulate all intertwin vascular connections. However, the reduced field of view of the fetoscope complicates their localization and general overview. A much more effective exploration could be achieved with an online mosaic created at exploration time. Currently, accurate, globally consistent algorithms such as bundle adjustment cannot be used due to their offline nature, while online algorithms lack sufficient accuracy. We introduce two pruning strategies facilitating the use of bundle adjustment in a sequential fashion: (1) a technique that efficiently exploits the potential of using an electromagnetic tracking system to avoid unnecessary matching attempts between spatially inconsistent image pairs, and (2) an aggregated representation of images, which we refer to as superframes, that allows decreasing the computational complexity of a globally consistent approach. Quantitative and qualitative results on synthetic and phantom-based datasets demonstrate a better trade-off between efficiency and accuracy.

Conventional optical tracking systems use cameras sensitive to near-infrared (NIR) light and NIR illuminated/active-illuminating markers to localize instrumentation and the patient in the operating room (OR) physical space. This technology is widely used within the neurosurgical theater and is a staple in the standard of care for craniotomy planning. To accomplish, planning is largely conducted at the time of the procedure in the OR with the patient in a fixed head orientation. We propose a framework to achieve this in the OR without conventional tracking technology, i.e., a “trackerless” approach. Briefly, we investigate an extension of the 3D Slicer which combines surgical planning and craniotomy designation. While taking advantage of the well-developed 3D Slicer platform, we implement advanced features to aid the neurosurgeon in planning the location of the anticipated craniotomy relative to the preoperatively imaged tumor in a physical-to-virtual setup, and then subsequently aid the true physical procedure by correlating that physical-to-virtual plan with an intraoperative magnetic resonance imaging-to-physical registered field-of-view display. These steps are done such that the craniotomy can be designated without the use of a conventional optical tracking technology. To test this approach, four experienced neurosurgeons performed experiments on five different surgical cases using our 3D Slicer module as well as the conventional procedure for comparison. The results suggest that our planning system provides a simple, cost-efficient, and reliable solution for surgical planning and delivery without the use of conventional tracking technologies. We hypothesize that the combination of this craniotomy planning approach and our past developments in cortical surface registration and deformation tracking using stereo-pair data from the surgical microscope may provide a fundamental realization of an integrated trackerless surgical guidance platform.

We propose a deformable registration algorithm for prostate-specific membrane antigen (PSMA) PET/CT and transrectal ultrasound (TRUS) fusion. Accurate registration of PSMA PET to intraoperative TRUS will allow physicians to customize dose planning based on the regions involved. The inputs to the registration algorithm are the PET/CT and TRUS volumes as well as the prostate segmentations. PET/CT and TRUS volumes are first rigidly registered by maximizing the overlap between the segmented prostate binary masks. Three-dimensional anatomical landmarks are then automatically extracted from the boundary as well as within the prostate. Then, a deformable registration is performed using a regularized thin plate spline where the landmark localization error is optimized between the extracted landmarks that are in correspondence. The proposed algorithm was evaluated on 25 prostate cancer patients treated with low-dose-rate brachytherapy. We registered the postimplant CT to TRUS using the proposed algorithm and computed target registration errors (TREs) by comparing implanted seed locations. Our approach outperforms state-of-the-art methods, with significantly lower (mean  ±  standard deviation) TRE of 1.96  ±  1.29  mm while being computationally efficient (mean computation time of 38 s). The proposed landmark-based PET/CT-TRUS deformable registration algorithm is simple, computationally efficient, and capable of producing quality registration of the prostate boundary as well as the internal gland.

Head and neck squamous cell carcinoma (SCC) is primarily managed by surgical cancer resection. Recurrence rates after surgery can be as high as 55%, if residual cancer is present. Hyperspectral imaging (HSI) is evaluated for detection of SCC in ex-vivo surgical specimens. Several machine learning methods are investigated, including convolutional neural networks (CNNs) and a spectral–spatial classification framework based on support vector machines. Quantitative results demonstrate that additional data preprocessing and unsupervised segmentation can improve CNN results to achieve optimal performance. The methods are trained in two paradigms, with and without specular glare. Classifying regions that include specular glare degrade the overall results, but the combination of the CNN probability maps and unsupervised segmentation using a majority voting method produces an area under the curve value of 0.81 [0.80, 0.83]. As the wavelengths of light used in HSI can penetrate different depths into biological tissue, cancer margins may change with depth and create uncertainty in the ground truth. Through serial histological sectioning, the variance in the cancer margin with depth is investigated and paired with qualitative classification heat maps using the methods proposed for the testing group of SCC patients. The results determined that the validity of the top section alone as the ground truth may be limited to 1 to 2 mm. The study of specular glare and margin variation provided better understanding of the potential of HSI for the use in the operating room.

The channelized-Hotelling observer (CHO) was investigated as a surrogate of human observers in task-based image quality assessment. The CHO with difference-of-Gaussian (DoG) channels has shown potential for the prediction of human detection performance in digital mammography (DM) images. However, the DoG channels employ parameters that describe the shape of each channel. The selection of these parameters influences the performance of the DoG CHO and needs further investigation. The detection performance of the DoG CHO was calculated and correlated with the detection performance of three humans who evaluated DM images in 2-alternative forced-choice experiments. A set of DM images of an anthropomorphic breast phantom with and without calcification-like signals was acquired at four different dose levels. For each dose level, 200 square regions-of-interest (ROIs) with and without signal were extracted. Signal detectability was assessed on ROI basis using the CHO with various DoG channel parameters and it was compared to that of the human observers. It was found that varying these DoG parameter values affects the correlation (r²) of the CHO with human observers for the detection task investigated. In conclusion, it appears that the the optimal DoG channel sets that maximize the prediction ability of the CHO might be dependent on the type of background and signal of ROIs investigated.

Raman spectroscopy mapping was used to study ex vivo fresh lung tissues and compare to histology sections. The Raman mapping measurements revealed differences in the molecular composition of normal lung tissue, adenocarcinoma, and squamous cell carcinoma (SCC). Molecular heterogeneity of the tissue samples was well captured by the k-means clustering analysis of the Raman datasets, as confirmed by the correlation with the adjacent haematoxylin and eosin (H&E) stained tissue sections. The results indicate that the fluorescence background varies considerably even in samples that appear structurally uniform in the H&E images, both for normal and tumor tissue. The results show that characteristic Raman bands can be used to discriminate between tumorous and nontumorous lung tissues and between adenocarcinoma and SCC tissues. These results indicate the potential to develop Raman classifications models for lung tissues based on the Raman spectral differences at the microscopic level, which can be used for tissue diagnosis or treatment stratification.

Simulations of acoustic wave propagation, including both the forward and the backward propagations of the wave (also known as full-wave simulations), are increasingly utilized in ultrasound imaging due to their ability to more accurately model important acoustic phenomena. Realistic anatomic models, particularly those of the abdominal wall, are needed to take full advantage of the capabilities of these simulation tools. We describe a method for converting fat–water-separated magnetic resonance imaging (MRI) volumes to anatomical models for ultrasound simulations. These acoustic models are used to map acoustic imaging parameters, such as speed of sound and density, to grid points in an ultrasound simulation. The tissues of these models are segmented from the MRI volumes into five primary classes of tissue in the human abdominal wall (skin, fat, muscle, connective tissue, and nontissue). This segmentation is achieved using an unsupervised machine learning algorithm, fuzzy c-means clustering (FCM), on a multiscale feature representation of the MRI volumes. We describe an automated method for utilizing FCM weights to produce a model that achieves ∼90  %   agreement with manual segmentation. Two-dimensional (2-D) and three-dimensional (3-D) full-wave nonlinear ultrasound simulations are conducted, demonstrating the utility of realistic 3-D abdominal wall models over previously available 2-D abdominal wall models.

This abstract corrects an error in the article, “Back-irradiated and dual-screen sandwich detector configurations for radiography,” by A. R. Lubinsky et al.

This erratum corrects the spelling of an author’s name.

This erratum corrects an error in the article, “Prostate cancer detection from multi-institution multiparametric MRIs using deep convolutional neural networks system,” by Y. Sumathipala et al.