Recurrent attention U-Net for segmentation and quantification of breast arterial calcifications on synthesized 2D mammograms.

Breast arterial calcifications (BAC) are a type of calcification commonly observed on mammograms and are generally considered benign and not associated with breast cancer. However, there is accumulating observational evidence of an association between BAC and cardiovascular disease, the leading cause of death in women. We present a deep learning method that could assist radiologists in detecting and quantifying BAC in synthesized 2D mammograms. We present a recurrent attention U-Net model consisting of encoder and decoder modules that include multiple blocks that each use a recurrent mechanism, a recurrent mechanism, and an attention module between them. The model also includes a skip connection between the encoder and the decoder, similar to a U-shaped network. The attention module was used to enhance the capture of long-range dependencies and enable the network to effectively classify BAC from the background, whereas the recurrent blocks ensured better feature representation. The model was evaluated using a dataset containing 2,000 synthesized 2D mammogram images. We obtained 99.8861% overall accuracy, 69.6107% sensitivity, 66.5758% F-1 score, and 59.5498% Jaccard coefficient, respectively. The presented model achieved promising performance compared with related models.

Multimodal Spatiotemporal Deep Learning Framework to Predict Response of Breast Cancer to Neoadjuvant Systemic Therapy.

Current approaches to breast cancer therapy include neoadjuvant systemic therapy (NST). The efficacy of NST is measured by pathologic complete response (pCR). A patient who attains pCR has significantly enhanced disease-free survival progress. The accurate prediction of pCR in response to a given treatment regimen could increase the likelihood of achieving pCR and prevent toxicities caused by treatments that are not effective. Th early prediction of response to NST can increase the likelihood of survival and help with decisions regarding breast-conserving surgery. An automated NST prediction framework that is able to precisely predict which patient undergoing NST will achieve a pathological complete response (pCR) at an early stage of treatment is needed. Here, we propose an end-to-end efficient multimodal spatiotemporal deep learning framework (deep-NST) framework to predict the outcome of NST prior or at an early stage of treatment. The deep-NST model incorporates imaging data captured at different timestamps of NST regimens, a tumor's molecular data, and a patient's demographic data. The efficacy of the proposed work is validated on the publicly available ISPY-1 dataset, in terms of accuracy, area under the curve (AUC), and computational complexity. In addition, seven ablation experiments were carried out to evaluate the impact of each design module in the proposed work. The experimental results show that the proposed framework performs significantly better than other recent methods.

PIPE-Net: A pyramidal-input-parallel-encoding network for the segmentation of corneal layer interfaces in OCT images.

Segmentation of corneal layer interfaces in optical coherence tomography (OCT) images is necessary to generate thickness maps used for cornea diagnosis. In this paper, we propose PIPE-Net, a fully convolutional neural network with a pyramidal input, parallel encoders, and a densely connected decoder to segment four corneal layer interfaces. The pyramidal input is encoded using parallel encoders, which allows the network to process a larger receptive field. The encoders are connected level-wise to the decoder through residual summations. The decoder is densely connected using residual summations between its levels to enhance the gradient flow. We use a linear growth rate for the number of feature maps to limit the network parameters, which allows the network to be trained using a small dataset. A dataset of 295 OCT images was obtained and manually segmented by experienced and trained operators. We implemented other related networks in the literature for comparison with our proposed network. We performed k-fold cross-validation to evaluate all the networks, and their performance was evaluated using precision-recall curves and average precision. PIPE-Net outperformed the other networks with an average precision of 0.95. The layer interfaces were detected and smoothed using the Savitzky-Golay filter, and they were closer to the expert.

Towards a better understanding of annotation tools for medical imaging: a survey.

Medical imaging refers to several different technologies that are used to view the human body to diagnose, monitor, or treat medical conditions. It requires significant expertise to efficiently and correctly interpret the images generated by each of these technologies, which among others include radiography, ultrasound, and magnetic resonance imaging. Deep learning and machine learning techniques provide different solutions for medical image interpretation including those associated with detection and diagnosis. Despite the huge success of deep learning algorithms in image analysis, training algorithms to reach human-level performance in these tasks depends on the availability of large amounts of high-quality training data, including high-quality annotations to serve as ground-truth. Different annotation tools have been developed to assist with the annotation process. In this survey, we present the currently available annotation tools for medical imaging, including descriptions of graphical user interfaces (GUI) and supporting instruments. The main contribution of this study is to provide an intensive review of the popular annotation tools and show their successful usage in annotating medical imaging dataset to guide researchers in this area.

The Influence of Age and Gender Information on the Diagnosis of Diabetic Retinopathy: Based on Neural Networks.

This paper proposes the importance of age and gender information in the diagnosis of diabetic retinopathy. We utilized Deep Residual Neural Networks (ResNet) and Densely Connected Convolutional Networks (DenseNet), which are proven effective on image classification problems and the diagnosis of diabetic retinopathy using the retinal fundus images. We used the ensemble of several classical networks and decentralized the training so that the network was simple and avoided overfitting. To observe whether the age and gender information could help enhance the performance, we added the information before the dense layer and compared the results with the results that did not add age and gender information. We found that the test accuracy of the network with age and gender information was 2.67% higher than that of the network without age and gender information. Meanwhile, compared with gender information, age information had a better help for the results.Clinical Relevance- The additional information in the dataset (such as age, gender, time of illness, etc.) can improve the accuracy of automatic diagnosis. Therefore, we strongly recommend that researchers add these different kinds of additional information when creating the dataset.

A Novel Network With Parallel Resolution Encoders for the Diagnosis of Corneal Diseases.

OBJECTIVE: To propose a deep-learning network for the diagnosis of two corneal diseases: Fuchs' endothlelial dystrophy and keratoconus, based on optical coherence tomography (OCT) images of the cornea. METHODS: In this paper, we propose a novel network with parallel resolution-specific encoders and composite classification features to directly diagnose Fuchs' endothelial dystrophy and keratoconus using OCT images. Our proposed network consists of a multi-resolution input, multiple parallel encoders, and a composite of convolutional and dense features for classification. The purpose of using parallel resolution-specific encoders is to perform multi-resolution feature fusion. Also, using composite classification features enhances the dense feature learning. We implemented other related networks for comparison with our network and performed k-fold cross-validation on a dataset of 16,721 OCT images. We used saliency maps and sensitivity analysis to visualize our proposed network. RESULTS: The proposed network outperformed other networks with an image classification accuracy of 0.91 and a scan classification accuracy of 0.94. The visualizations show that our network learned better features than other networks. SIGNIFICANCE: The proposed methods can potentially be a step towards the early diagnosis of corneal diseases, which is necessary to prevent their progression, hence, prevent loss of vision.

DV-DCNN: Dual-view deep convolutional neural network for matching detected masses in mammograms.

BACKGROUND AND OBJECTIVE: Mammography is an X-ray imaging technique used for breast cancer screening. Each breast is usually screened at two different angles generating two views known as mediolateral oblique (MLO) and craniocaudal (CC), which are clinically used by radiologists to detect suspicious masses and diagnose breast cancer. Previous studies applied deep learning models to process each view separately and concatenate the features from the two views to detect and classifying masses. However, direct concatenation is not enough to uncover the relationship between the masses that appear in the two views because they can substantially vary in terms of shape, size, and texture. The relationship between the two views should be established by matching correspondence between their extracted masses. This paper presents a dual-view deep convolutional neural network (DV-DCNN) model for matching masses detected from the two views by establishing correspondence between their extracted patches, which leads to more robust mass detection. METHODS: Given a pair of patches as input, the presented model determines whether these patches represent the same mass or not. The network contains two parts: a feature extraction part using tied dense blocks, and a neighborhood patch matching part with three consecutive layers, i.e., a cross-input neighborhood differences layer to find the relationship between the two patches, a patch summary features layer to define a summary of the neighborhood differences and an across-patch features layer to learn a higher-level representation across neighborhood differences. RESULTS: To evaluate the model's performance in diverse cases, several experimental scenarios were followed for training and testing using two public datasets, i.e., CBIS-DDSM and INbreast. We also evaluate the contribution of our mass-matching model within a mass detection framework. Experiments show that DV-DCNN outperforms other related deep learning models and demonstrate that the detection results improve when using our model. CONCLUSIONS: Matching potential masses between two different views of the same breast leads to more robust mass detection. Experimental results demonstrate the efficacy of a dual-view deep learning model in matching masses, which helps in increasing the accuracy of mass detection and decreasing the false positive rates.

Multidisease Deep Learning Neural Network for the Diagnosis of Corneal Diseases.

PURPOSE: To report a multidisease deep learning diagnostic network (MDDN) of common corneal diseases: dry eye syndrome (DES), Fuchs endothelial dystrophy (FED), and keratoconus (KCN) using anterior segment optical coherence tomography (AS-OCT) images. STUDY DESIGN: Development of a deep learning neural network diagnosis algorithm. METHODS: A total of 158,220 AS-OCT images from 879 eyes of 478 subjects were used to develop and validate a classification deep network. After a quality check, the network was trained and validated using 134,460 images. We tested the network using a test set of consecutive patients involving 23,760 AS-OCT images of 132 eyes of 69 patients. The area under receiver operating characteristic curve (AUROC), area under precision-recall curve (AUPRC), and F1 score and 95% confidence intervals (CIs) were computed. RESULTS: The MDDN achieved eye-level AUROCs >0.99 (95% CI: 0.90, 1.0), AUPRCs > 0.96 (95% CI: 0.90, 1.0), and F1 scores > 0.90 (95% CI: 0.81, 1.0) for DES, FED, and KCN, respectively. CONCLUSIONS: MDDN is a novel diagnostic tool for corneal diseases that can be used to automatically diagnose KCN, FED, and DES using only AS-OCT images.

Convolutional neural networks for breast cancer detection in mammography: A survey.

Despite its proven record as a breast cancer screening tool, mammography remains labor-intensive and has recognized limitations, including low sensitivity in women with dense breast tissue. In the last ten years, Neural Network advances have been applied to mammography to help radiologists increase their efficiency and accuracy. This survey aims to present, in an organized and structured manner, the current knowledge base of convolutional neural networks (CNNs) in mammography. The survey first discusses traditional Computer Assisted Detection (CAD) and more recently developed CNN-based models for computer vision in mammography. It then presents and discusses the literature on available mammography training datasets. The survey then presents and discusses current literature on CNNs for four distinct mammography tasks: (1) breast density classification, (2) breast asymmetry detection and classification, (3) calcification detection and classification, and (4) mass detection and classification, including presenting and comparing the reported quantitative results for each task and the pros and cons of the different CNN-based approaches. Then, it offers real-world applications of CNN CAD algorithms by discussing current Food and Drug Administration (FDA) approved models. Finally, this survey highlights the potential opportunities for future work in this field. The material presented and discussed in this survey could serve as a road map for developing CNN-based solutions to improve mammographic detection of breast cancer further.

Correcting Higher Order Aberrations Using Image Processing.

Higher Order Aberrations (HOAs) are complex refractive errors in the human eye that cannot be corrected by regular lens systems. Researchers have developed numerous approaches to analyze the effect of these refractive errors; the most popular among these approaches use Zernike polynomial approximation to describe the shape of the wavefront of light exiting the pupil after it has been altered by the refractive errors. We use this wavefront shape to create a linear imaging system that simulates how the eye perceives source images at the retina. With phase information from this system, we create a second linear imaging system to modify source images so that they would be perceived by the retina without distortion. By modifying source images, the visual process cascades two optical systems before the light reaches the retina, a technique that counteracts the effect of the refractive errors. While our method effectively compensates for distortions induced by HOAs, it also introduces blurring and loss of contrast; a problem that we address with Total Variation Regularization. With this technique, we optimize source images so that they are perceived at the retina as close as possible to the original source image. To measure the effectiveness of our methods, we compute the Euclidean error between the source images and the images perceived at the retina. When comparing our results with existing corrective methods that use deconvolution and total variation regularization, we achieve an average of 50% reduction in error with lower computational costs.

3DCD: Scene Independent End-to-End Spatiotemporal Feature Learning Framework for Change Detection in Unseen Videos.

Change detection is an elementary task in computer vision and video processing applications. Recently, a number of supervised methods based on convolutional neural networks have reported high performance over the benchmark dataset. However, their success depends upon the availability of certain proportions of annotated frames from test video during training. Thus, their performance on completely unseen videos or scene independent setup is undocumented in the literature. In this work, we present a scene independent evaluation (SIE) framework to test the supervised methods in completely unseen videos to obtain generalized models for change detection. In addition, a scene dependent evaluation (SDE) is also performed to document the comparative analysis with the existing approaches. We propose a fast (speed-25 fps) and lightweight (0.13 million parameters, model size-1.16 MB) end-to-end 3D-CNN based change detection network (3DCD) with multiple spatiotemporal learning blocks. The proposed 3DCD consists of a gradual reductionist block for background estimation from past temporal history. It also enables motion saliency estimation, multi-schematic feature encoding-decoding, and finally foreground segmentation through several modular blocks. The proposed 3DCD outperforms the existing state-of-the-art approaches evaluated in both SIE and SDE setup over the benchmark CDnet 2014, LASIESTA and SBMI2015 datasets. To the best of our knowledge, this is a first attempt to present results in clearly defined SDE and SIE setups in three change detection datasets.

Pathological-Corneas Layer Segmentation and Thickness Measurement in OCT Images.

Purpose: The purpose of this study was to propose a new algorithm for the segmentation and thickness measurement of pathological corneas with irregular layers using a two-stage graph search and ray tracing. Methods: In the first stage, a graph, with only gradient edge-cost, is used to segment the air-epithelium and endothelium-aqueous boundaries. In the second stage, a graph, with gradient, directional, and multiplier edge-cost, is used to correct segmentation. The optical coherence tomography (OCT) image is flattened using the air-epithelium boundary and a graph search is used to segment the epithelium-Bowman's and Bowman's-stroma boundaries. Then, the OCT image is flattened using the endothelium-aqueous boundary and a graph search is used to segment the Descemet's membrane. Ray tracing is used to correct the inter-boundary distances, then the thickness is measured using the shortest distance. The proposed algorithm was trained and evaluated using 190 OCT images manually segmented by trained operators. Results: The mean and standard deviation of the unsigned errors of the algorithm-operator and inter-operator were 0.89 ± 1.03 and 0.77 ± 0.68 pixels in segmentation and 3.62 ± 3.98 and 2.95 ± 2.52 µm in thickness measurement. Conclusions: Our proposed algorithm can produce accurate segmentation and thickness measurements compared with the manual operators. Translational Relevance: Our algorithm could be potentially useful in the clinical practice.

DU-Net: Convolutional Network for the Detection of Arterial Calcifications in Mammograms.

Breast arterial calcifications (BACs) are part of several benign findings present on some mammograms. Previous studies have indicated that BAC may provide evidence of general atherosclerotic vascular disease, and potentially be a useful marker of cardiovascular disease (CVD). Currently, there is no technique in use for the automatic detection of BAC in mammograms. Since a majority of women over the age of 40 already undergo breast cancer screening with mammography, detecting BAC may offer a method to screen women for CVD in a way that is effective, efficient, and broad reaching, at no additional cost or radiation. In this paper, we present a deep learning approach for detecting BACs in mammograms. Inspired by the promising results achieved using the U-Net model in many biomedical segmentation problems and the DenseNet in semantic segmentation, we extend the U-Net model with dense connectivity to automatically detect BACs in mammograms. The presented model helps to facilitate the reuse of computation and improve the flow of gradients, leading to better accuracy and easier training of the model. We evaluate the performance using a set of full-field digital mammograms collected and prepared for this task from a publicly available dataset. Experimental results demonstrate that the presented model outperforms human experts as well as the other related deep learning models. This confirms the effectiveness of our model in the BACs detection task, which is a promising step in providing a cost-effective risk assessment tool for CVD.

Expansion of Peripheral Visual Field with Novel Virtual Reality Digital Spectacles.

PURPOSE: To examine an image remapping method for peripheral visual field (VF) expansion with novel virtual reality digital spectacles (DSpecs) to improve visual awareness in glaucoma patients. DESIGN: Prospective case series. METHODS: Monocular peripheral VF defects were measured and defined with a head-mounted display diagnostic algorithm. The monocular VF was used to calculate remapping parameters with a customized algorithm to relocate and resize unseen peripheral targets within the remaining VF. The sequence of monocular VF was tested and customized image remapping was carried out in 23 patients with typical glaucomatous defects. Test images demonstrating roads and cars were used to determine increased awareness of peripheral hazards while wearing the DSpecs. Patients' scores in identifying and counting peripheral objects with the remapped images were the main outcome measurements. RESULTS: The diagnostic monocular VF testing algorithm was comparable to standard automated perimetric determination of threshold sensitivity based on point-by-point assessment. Eighteen of 23 patients (78%) could identify safety hazards with the DSpecs that they could not previously. The ability to identify peripheral objects improved with the use of the DSpecs (P = 0.024, chi-square test). Quantification of the number of peripheral objects improved with the DSpecs (P = 0.0026, Wilcoxon rank sum test). CONCLUSIONS: These novel spectacles may enhance peripheral objects awareness by enlarging the functional field of view in glaucoma patients.

Toward Improving the Mobility of Patients with Peripheral Visual Field Defects with Novel Digital Spectacles.

PURPOSE: To assess the efficacy of novel Digital spectacles (DSpecs) to improve mobility of patients with peripheral visual field (VF) loss. DESIGN: Prospective case series. METHODS: Binocular VF defects were quantified with the DSpecs testing strategy. An algorithm was implemented that generated personalized visual augmentation profiles based on the measured VF. These profiles were achieved by relocating and resizing video signals to fit within the remaining VF in real time. Twenty patients with known binocular VF defects were tested using static test images, followed by dynamic walking simulations to determine if they could identify objects and avoid obstacles in an environment mimicking a real-life situation. The effect of the DSpecs were assessed for visual/hand coordination with object-grasping tests. Patients performed these tests with and without the DSpecs correction profile. RESULTS: The diagnostic binocular VF testing with the DSpecs was comparable to the integrated monocular standard automated perimetry based on point-by-point assessment with a mismatch error of 7.0%. Eighteen of 20 patients (90%) could identify peripheral objects in test images with the DSpecs that they could not previously. Visual/hand coordination was successful for 17 patients (85%) from the first trial. The object-grasping performance improved to 100% by the third trial. Patient performance, judged by finding and identifying objects in the periphery in a simulated walking environment, was significantly better with the DSpecs (P = 0.02, Wilcoxon rank sum test). CONCLUSIONS: DSpecs may improve mobility by facilitating the ability of patients to better identify moving peripheral hazardous objects.

Automatic Segmentation of Corneal Microlayers on Optical Coherence Tomography Images.

PURPOSE: To propose automatic segmentation algorithm (AUS) for corneal microlayers on optical coherence tomography (OCT) images. METHODS: Eighty-two corneal OCT scans were obtained from 45 patients with normal and abnormal corneas. Three testing data sets totaling 75 OCT images were randomly selected. Initially, corneal epithelium and endothelium microlayers are estimated using a corneal mask and locally refined to obtain final segmentation. Flat-epithelium and flat-endothelium images are obtained and vertically projected to locate inner corneal microlayers. Inner microlayers are estimated by translating epithelium and endothelium microlayers to detected locations then refined to obtain final segmentation. Images were segmented by trained manual operators (TMOs) and by the algorithm to assess repeatability (i.e., intraoperator error), reproducibility (i.e., interoperator and segmentation errors), and running time. A random masked subjective test was conducted by corneal specialists to subjectively grade the segmentation algorithm. RESULTS: Compared with the TMOs, the AUS had significantly less mean intraoperator error (0.53 ± 1.80 vs. 2.32 ± 2.39 pixels; P < 0.0001), it had significantly different mean segmentation error (3.44 ± 3.46 vs. 2.93 ± 3.02 pixels; P < 0.0001), and it had significantly less running time per image (0.19 ± 0.07 vs. 193.95 ± 194.53 seconds; P < 0.0001). The AUS had insignificant subjective grading for microlayer-segmentation grading (4.94 ± 0.32 vs. 4.96 ± 0.24; P = 0.5081), but it had significant subjective grading for regional-segmentation grading (4.96 ± 0.26 vs. 4.79 ± 0.60; P = 0.025). CONCLUSIONS: The AUS can reproduce the manual segmentation of corneal microlayers with comparable accuracy in almost real-time and with significantly better repeatability. TRANSLATIONAL RELEVANCE: The AUS can be useful in clinical settings and can aid the diagnosis of corneal diseases by measuring thickness of segmented corneal microlayers.

Evaluation of endothelial/Descemet membrane complex of eye bank donor corneas using enhanced depth imaging optical coherence tomography.

Objective: We present a novel method for screening eye bank donor corneas using high definition optical coherence tomography (HD-OCT). This technology allows for the quantification of endothelial/Descemet membrane (En/DM) complex thickness ex vivo. Design: Prospective interventional study. Participants: Fifty-two corneal grafts from 27 donors were included in this study. Twenty additional control eyes and 11 eyes with Fuchs' endothelial corneal dystrophy were also evaluated for comparison. Methods: A custom built, high speed HD-OCT device (Envisu R2210, Bioptigen, Buffalo Grove, IL, USA) was used to obtain images, and custom-made graph-based segmentation software was used to automatically deconstruct corneal images into micro-layers. HD-OCT imaging was used to scan through the sealed sterile case of donor corneas stored in McCarey-Kaufman medium to image their En/DM complex through the center of the cornea. Results: This technology allowed for quantification of En/DM complex thickness in all donor corneas through the sealed sterile container used to transport graft tissue. Mean En/DM complex thickness of donor corneas was 17±4 µm. The difference between donor cornea En/DM thickness and that of control subjects (16±2 µm) was not statistically significant (p=0.3), suggesting that the transport container and media do not affect measurements. There was a significant difference between En/DM thickness of Fuchs' endothelial corneal dystrophy eyes (25±5 µm) and both donor corneas (p<0.0001) and control subjects (p<0.0001). Conclusions: We have described a new technique to measure En/DM complex thickness in eye bank donor corneas stored in a sealed sterile case. This may represent a novel adjunctive approach to screen corneal grafts for early endothelial disease.

Novel chitosan-ZnO based nanocomposites as luminescent tags for cellulosic materials.

Novel chitosan-ZnO composites have been synthesized as luminescent taggants for cellulosic materials. The synthesized chitosan-ZnO nanospheres (CS-ZnO NS), chitosan-ZnO-oleic acid quantum dots (CS-ZnO-oleic QD) and chitosan-ZnO-oleic acid:Eu(3+) doped nanorods (CS-ZnO-oleic:Eu(3+) NR) were characterized by X-ray diffraction, photoluminescence spectroscopy, FTIR spectroscopy and transmission electron microscopy. The prepared luminescent CS-ZnO composites were used in printing paste and applied to different types of papers and textiles by using screen printing technique. The colorimetric values of the printed CS-ZnO-oleic acid and CS-ZnO-oleic:Eu(3+) showed that printing caused slightly change in color values. Scanning electron microscopy images and color values of the printed surface showed that CS-ZnO-oleic QD and highly luminescence CS-ZnO-olic:Eu(3+) NR are suitable for use as a printed security feature.

Formation principles and ligand dynamics of nanoassemblies of CdSe quantum dots and functionalised dye molecules.

Functional dye molecules, such as porphyrins, attached to CdSe quantum dots (QDs) through anchoring meso-pyridyl substituents, form quasi-stable nanoassemblies. This fact results in photoluminescence (PL) quenching of the QDs both due to Förster resonance energy transfer (FRET) and the formation of non-radiative surface states under conditions of quantum confinement (non-FRET). The formation process is in competition with the ligand dynamics. At least two timescales are found for the formation of the assemblies: 1) one faster than 60 s attributed to saturation of empty attachment sites and 2) one slower than 600 s, which is attributed to a reorganisation of the tri-n-octylphosphine oxide (TOPO) ligand shell. Finally, this process results in almost complete exchange of the TOPO shell by porphyrin dye molecules. Following a Stern-Volmer analysis, we established a microscopic description of PL quenching and assembly formation. Based on this formalism, we determined the equilibrium constant for assembly formation between QDs and the pyridyl-functionalised dye molecules to be K ≈ 10(5) - 10(7) M(-1), which is several orders of magnitude larger than that of the TOPO ligands. Our results give additional insights into the non-FRET PL quenching processes involved and show that the QD surface is inhomogeneous with respect to the involved attachment and detachment processes. In comparison with other methods, such as NMR spectroscopy, the advantage of our approach is that ligand dynamics can be investigated at extremely low ratios of dye molecules to QDs.

Identification of different donor-acceptor structures via Förster Resonance Energy Transfer (FRET) in quantum-dot-perylene bisimide assemblies.

Nanoassemblies are formed via self-assembly of ZnS capped CdSe quantum dots (QD) and perylene bisimide (PBI) dyes. Upon assembly formation the QD photoluminescence is quenched, as can be detected both via single particle detection and ensemble experiments in solution. Quenching has been assigned to FRET and NON-FRET processes. Analysis of FRET allows for a distinction between different geometries of the QD dye assemblies. Time-resolved single molecule spectroscopy reveals intrinsic fluctuations of the PBI fluorescence lifetime and spectrum, caused by rearrangement of the phenoxy side groups. The distribution of such molecular conformations and their changed dynamics upon assembly formation are discussed in the scope of FRET efficiency and surface ligand density.