Thomas Wittenberg

Background: The non-invasive 3D-imaging and successive 3D-segmentation of plant root systems has gained interest within fundamental plant research and selectively breeding resilient crops. Currently the state of the art consists of computed tomography (CT) scans and reconstruction followed by an adequate 3D-segmentation process.
Challenge: Generating an exact 3D-segmentation of the roots becomes challenging due to inhomogeneous soil composition, as well as high scale variance in the root… Mehr anzeigen

Background: The non-invasive 3D-imaging and successive 3D-segmentation of plant root systems has gained interest within fundamental plant research and selectively breeding resilient crops. Currently the state of the art consists of computed tomography (CT) scans and reconstruction followed by an adequate 3D-segmentation process.
Challenge: Generating an exact 3D-segmentation of the roots becomes challenging due to inhomogeneous soil composition, as well as high scale variance in the root structures themselves.
Approach: (1) We address the challenge by combining deep convolutional neural networks (DCNNs) with a weakly supervised learning paradigm. Furthermore, (2) we apply a spatial pyramid pooling (SPP) layer to cope with the scale variance of roots. (3) We generate a fine-tuned training data set with a specialized sub-labeling technique. (4) Finally, to yield fast and high-quality segmentations, we propose a specialized iterative inference algorithm, which locally adapts the field of view (FoV) for the network.
Experiments: We compare our segmentation results against an analytical reference algorithm for root segmentation (RootForce) on a set of roots from Cassava plants and show qualitatively that an increased amount of root voxels and root branches can be segmented.
Results: Our findings show that with the proposed DCNN approach combined with the dynamic inference, much more, and especially fine, root structures can be detected than with a classical analytical reference method.
Conclusion: We show that the application of the proposed DCNN approach leads to better and more robust root segmentation, especially for very small and thin roots. Weniger anzeigen

Abstract:When documenting colonoscopic examinations,the challenge arises, that the exact location of the detected le-sions (such as polyps) can usually only be determined withlow precision. In order to improve the image-based documen-tation of such lesions with respect to their location and context,a system is currently investigated and developed, allowing thecreation of a panoramic map of the interior of the colon’s lu-men during an endoscopic examination. To evaluate the pro-posed… Mehr anzeigen

Abstract:When documenting colonoscopic examinations,the challenge arises, that the exact location of the detected le-sions (such as polyps) can usually only be determined withlow precision. In order to improve the image-based documen-tation of such lesions with respect to their location and context,a system is currently investigated and developed, allowing thecreation of a panoramic map of the interior of the colon’s lu-men during an endoscopic examination. To evaluate the pro-posed algorithms, a 3D-printed colon phantom with knowngeometry has been developed. Furthermore, to obtain imagesequences with precise and known motion during a simulatedexamination for test purposes, a robot was used to performthe insertion and withdrawal of the endoscope with constantspeed and a steady viewing angle. The thus obtained imagedata is used to generate an ideal panoramic map using our theproposed stitching algorithm. Hence, it is possible to obtainreference maps of the phantom, which can be used to evaluatethe quality of the algorithm. Weniger anzeigen

Introduction:Early detection of adenomas andpolyps is one central goal of colonoscopic screening programs.As the adenoma detection rate (ADR) depends on the experi-ence of the endoscopist, AI-based polyp detection systems canbe used for real-time assistance. Hence, to support the physi-cians such AI-based systems using deep-convolutional neuralnetworks (DCNNS) have been introduced in the past years.One disadvantage of these techniques is the need of a hugeamount of labeled training… Mehr anzeigen

Introduction:Early detection of adenomas andpolyps is one central goal of colonoscopic screening programs.As the adenoma detection rate (ADR) depends on the experi-ence of the endoscopist, AI-based polyp detection systems canbe used for real-time assistance. Hence, to support the physi-cians such AI-based systems using deep-convolutional neuralnetworks (DCNNS) have been introduced in the past years.One disadvantage of these techniques is the need of a hugeamount of labeled training data.Method: We investigate a"human-in-the-loop approach" to minimize the required timeto generate labeled training data. The approach is evaluatedwithin the training a YOLOv4 neural network to detect polypsin colonoscopic image data. The performance metrics of theneural network are evaluated on three public datasets.Results:The performance of the YOLO network increased from a pre-cision of 0.88, recall of 0.83,F1score of 0.86, and aF2scoreof 0.86 to a precision of 0.91, recall of 0.87,F1= of 0.89, andF2= of 0.88. The interactive labelling of 1,000 images onlytakes one hours.Conclusion: The proposed "human-in-the-loop approach" is capable of generating labelled image data ina minimum of time while increasing the performance metricsas well. For higher performance increase more data can nowbe labeled within this new approach. Weniger anzeigen

Infective endocarditis(IE) is an infection of the en-docardium, and the heart valves associated with high morbi-dity and mortality. Fluorescence in situ Hybridization (FISH) is a molecular imaging technique used for diagnosis of IE ba-sed on histological heart valve tissue sections. FISH allows de-tection and identification of microorganisms and gives infor-mation about their quantity and spatial distribution. This infor-mation is important to guide appropriate antibiotic treatment. However, as… Mehr anzeigen

Infective endocarditis(IE) is an infection of the en-docardium, and the heart valves associated with high morbi-dity and mortality. Fluorescence in situ Hybridization (FISH) is a molecular imaging technique used for diagnosis of IE ba-sed on histological heart valve tissue sections. FISH allows de-tection and identification of microorganisms and gives infor-mation about their quantity and spatial distribution. This infor-mation is important to guide appropriate antibiotic treatment. However, as manual FISH image analysis is time- and cost-expensive, an automated image analysis pipeline (consisting of tissue segmentation, bacteria detection, and spot detection modules) is proposed toassist locating potential regions with microorganisms. The proposed approach was evaluated in a study, where fiveobservers manually assessed a set of 171 fields-of-view (FoVs) captured in 400-fold magnification from 10 randomly chosen WSI for the presence of microorganisms, morphologi-cally detected by the nucleic acid stain DAPI. The task of the observers was to mark the presented image using a 2-class sco-re (‘positive/questionable’ or ‘negative’). The human assess-ment was compared to the results suggested by the algorithm.The proposed algorithm locates and ranks potential regions with microorganisms in heart valve sections so that experts can validate them in higher power FoVs for the presence of bacte-ria and identify their species. The automated system for pre-selectingand recommending adequate FoVs is thus a starting point to support experts and save human resources.It is now ready to be further developed for the detection of bacteria by FISH. Weniger anzeigen

Currently, various AI-based systems for computer-assisted adenoma- and polyp-detection during colonoscopy have been brought to the market and are under clinical investi-gation. With these systems available to be used during routine screening colonoscopy and first results published about ex-periments and findings, it has become of interest how and to which extend such systems are used during the examination. Specifically, similarly to automotive navigation, it is of inte-rest of how… Mehr anzeigen

Currently, various AI-based systems for computer-assisted adenoma- and polyp-detection during colonoscopy have been brought to the market and are under clinical investi-gation. With these systems available to be used during routine screening colonoscopy and first results published about ex-periments and findings, it has become of interest how and to which extend such systems are used during the examination. Specifically, similarly to automotive navigation, it is of inte-rest of how much visual focus is put onto the augmented image of the above-mentioned devices, signalling possible hypothe-sis of adenomas or polyps, and how much time-of-attention remains on the original colonoscopic video data. Thus, within a study, N = 36 participants using a prototype of a polyp -detection system have been observed with an eye-tracker-sys-tem, to capture and evaluate the relative time of attention with respect to the original and augmented video data and dif feren-tiate these values between various sub-groups based on expe-rience, education and gender. T- tests were conducted to iden-tify potential significant differences. Based on the obtained data, the augmented video data is used with a very high at-tention (up to 75%) depending on the regarded sub-group. Ex-perienced as well as less-experienced users (with > 500 colo-noscopies) both preferred looking at the original data. In con-trast, gastroenterologists (in contrast to nurses, students, en-gineers) were more interested in the outcome of the novel AI-system. The female group preferred looking at the un-obstructed data, while the male group was highly interested in the AI-based data. Weniger anzeigen

Computed X-ray tomography (CTX) is a high-end nondestructive approach for the visual assessment of root architecture in soil. Nevertheless, in order to evaluate high-resolution CTX data of root architectures, manual segmentation of the depicted root systems from large-scale volume data is currently necessary, which is time consuming & error prone. The duration of such a segmentation is of importance, especially for time-resolved growth analysis, where several instances of a plant need to be… Mehr anzeigen

Computed X-ray tomography (CTX) is a high-end nondestructive approach for the visual assessment of root architecture in soil. Nevertheless, in order to evaluate high-resolution CTX data of root architectures, manual segmentation of the depicted root systems from large-scale volume data is currently necessary, which is time consuming & error prone. The duration of such a segmentation is of importance, especially for time-resolved growth analysis, where several instances of a plant need to be segmented & evaluated. Specifically, in our application, the contrast between soil and root data varies due to different growth stages and watering situations at the time of scanning. Additionally, the root system itself is expanding in length and in the diameter of individual roots. For semiautomated & robust root system segmentation from CTX data, we propose 'RootForce', which is an extension of Frangi’s multi-scale vesselness method and integrates a 3D local variance. It allows precise delineation of roots with diameters down to several μm in pots with varying diameters. Additionally, RootForce is not limited to the segmentation of small below-ground organs, but is also able to handle storage roots with a diameter > 40 voxels. Using CTX volume data of full-grown bean plants as well as time-resolved growth studies of cassava plants, RootForce produces similar results compared to manual segmentation of the regarded root architectures. Furthermore, RootForce enables the user to obtain traits not possible to be calculated before, such as total root volume & length, volume over depth and more. The proposed tool can provide a higher efficiency for the semiautomatic high-throughput assessment of the root architectures of different types of plants from large-scale CTX. Furthermore, for all datasets within a growth experiment, only a single set of parameters is needed. Thus, the proposed tool can be used for a wide range of growth experiments in the field of plant phenotyping. Weniger anzeigen

Adenoma detection is a highly personalized task that differs markedly among endoscopists. Technical advances are therefore desirable for the improvement of the adenoma detection rate (ADR). An automated computer-driven technology would offer the chance to objectively assess the presence of colorectal polyps during colonoscopy. We present here the application of a real-time automated polyp detection software (APDS) under routine colonoscopy conditions.
METHODS:

This was a prospective… Mehr anzeigen

Adenoma detection is a highly personalized task that differs markedly among endoscopists. Technical advances are therefore desirable for the improvement of the adenoma detection rate (ADR). An automated computer-driven technology would offer the chance to objectively assess the presence of colorectal polyps during colonoscopy. We present here the application of a real-time automated polyp detection software (APDS) under routine colonoscopy conditions.
METHODS:

This was a prospective study at a university hospital in Germany. A prototype of a novel APDS ("KoloPol," Fraunhofer IIS, Erlangen, Germany) was used for automated image-based polyp detection. The software functions by highlighting structures of possible polyp lesions in a color-coded manner during real-time colonoscopy procedures. Testing the feasibility of APDS deployment under real-time conditions was the primary goal of the study. APDS polyp detection rates (PDRs) were defined as secondary endpoints provided that endoscopists' detection served as criterion standard.
RESULTS:

The APDS was applied in 55 routine colonoscopies without the occurrence of any clinically relevant adverse events. Endoscopists' PDRs and ADRs were 56.4% and 30.9%, respectively. The PDRs and ADRs of the APDS were 50.9% and 29.1%, respectively. The APDS detected 55 of 73 polyps (75.3%). Smaller polyp size and flat polyp morphology were correlated with insufficient polyp detection by the APDS.
CONCLUSION:

Computer-assisted automated low-delay polyp detection is feasible during real-time colonoscopy. Efforts should be undertaken to improve the APDS with respect to smaller and flat shaped polyps. (Clinical trial registration number: NCT02838888.). Weniger anzeigen

OBJECTIVE: To develop a standardized digital reporting tool for cystoscopy of the urinary bladder using panoramic imaging.
MATERIALS AND METHODS:
An image processing and stitching software (Endorama) was developed to generate panoramic images from cystoscopy data. In a processing phase, algorithms were modulated and refined by reference to cystoscopy sequences (n = 30). Subsequently, standard systematic cystoscopies (n = 12) were recorded in patients undergoing transurethral resection of… Mehr anzeigen

OBJECTIVE: To develop a standardized digital reporting tool for cystoscopy of the urinary bladder using panoramic imaging.
MATERIALS AND METHODS:
An image processing and stitching software (Endorama) was developed to generate panoramic images from cystoscopy data. In a processing phase, algorithms were modulated and refined by reference to cystoscopy sequences (n = 30). Subsequently, standard systematic cystoscopies (n = 12) were recorded in patients undergoing transurethral resection of a bladder tumor to create panoramic images.
RESULTS All sequences were applicable for the development and refinements of the software. Processing increasingly allowed the creation of images illustrating large parts of the bladder and relevant anatomic landmarks in different locations. The pathway covered by the endoscope during the intervention was illustrated as a route in the respective digital image. During the application phase, panoramic images were successfully created in 10 out of 12 cases. The resolution of the images was 4096 × 2048 pixels and the images required a median digital memory of 3.9 MB (3.4-5.7). The panoramic images illustrated 22 relevant findings of which 7 were papillary tumors.
CONCLUSION: High-quality digital panoramic maps of the urinary bladder were created using specifically processed data of videocystoscopy. In this preliminary series, relevant findings were illustrated in the respective image. Our tool may help improve standardization of cystoscopy reports and reduce interobserver variability. Weniger anzeigen

Endoscopic procedures form part of routine clinical practice for minimally invasive examinations and interventions. While they are beneficial for the patient, reducing surgical trauma and making convalescence times shorter, they make orientation and manipulation more challenging for the physician, due to the limited field of view through the endoscope. However, this drawback can be reduced by means of medical image processing and computer vision, using image stitching and surface reconstruction… Mehr anzeigen

Endoscopic procedures form part of routine clinical practice for minimally invasive examinations and interventions. While they are beneficial for the patient, reducing surgical trauma and making convalescence times shorter, they make orientation and manipulation more challenging for the physician, due to the limited field of view through the endoscope. However, this drawback can be reduced by means of medical image processing and computer vision, using image stitching and surface reconstruction methods to expand the field of view. This paper provides a comprehensive overview of the current state of the art in endoscopic image stitching and surface reconstruction. The literature in the relevant fields of application and algorithmic approaches is surveyed. The technological maturity of the methods and current challenges and trends are analyzed. Weniger anzeigen

An increasing number of free software tools have been made available for the evaluation of fluorescence cell micrographs. The main users are biologists and related life scientists with no or little knowledge of image processing. In this review, we give an overview of available tools and guidelines about which tools the users should use to segment fluorescence micrographs. We selected 15 free tools and divided them into stand-alone, Matlab-based, ImageJ-based, free demo versions of commercial… Mehr anzeigen

An increasing number of free software tools have been made available for the evaluation of fluorescence cell micrographs. The main users are biologists and related life scientists with no or little knowledge of image processing. In this review, we give an overview of available tools and guidelines about which tools the users should use to segment fluorescence micrographs. We selected 15 free tools and divided them into stand-alone, Matlab-based, ImageJ-based, free demo versions of commercial tools and data sharing tools. The review consists of two parts: First, we developed a criteria catalogue and rated the tools regarding structural requirements, functionality (flexibility, segmentation and image processing filters) and usability (documentation, data management, usability and visualization). Second, we performed an image processing case study with four representative fluorescence micrograph segmentation tasks with figure-ground and cell separation. The tools display a wide range of functionality and usability. In the image processing case study, we were able to perform figure-ground separation in all micrographs using mainly thresholding. Cell separation was not possible with most of the tools, because cell separation methods are provided only by a subset of the tools and are difficult to parametrize and to use. Most important is that the usability matches the functionality of a tool. To be usable, specialized tools with less functionality need to fulfill less usability criteria, whereas multipurpose tools need a well-structured menu and intuitive graphical user interface. Weniger anzeigen

Mammography is the central diagnostic method for clinical diagnostics of breast cancer and the breast cancer screening program. In the clinical routine complementary methods, such as ultrasound, tomosynthesis and optional magnetic resonance imaging (MRI) are already combined for the diagnostic procedure. Future developments will utilize investigative procedures either as a hybrid (combination of several different imaging modalities in one instrument) or as a fusion method (the technical fusion… Mehr anzeigen

Mammography is the central diagnostic method for clinical diagnostics of breast cancer and the breast cancer screening program. In the clinical routine complementary methods, such as ultrasound, tomosynthesis and optional magnetic resonance imaging (MRI) are already combined for the diagnostic procedure. Future developments will utilize investigative procedures either as a hybrid (combination of several different imaging modalities in one instrument) or as a fusion method (the technical fusion of two or more of these methods) to implement fusion imaging into diagnostic algorithms. For screening there are reasonable hypotheses to aim for studies that individualize the diagnostic process within the screening procedure. Individual breast cancer risk prediction and individualized knowledge about sensitivity and specificity for certain diagnostic methods could be tested. The clinical implementation of these algorithms is not yet in sight. Weniger anzeigen

Introduction: Although mammographic density is an established risk factor for breast cancer, its use is limited in clinical practice because of a lack of automated and standardized measurement methods. The aims of this study were to evaluate a variety of automated texture features in mammograms as risk factors for breast cancer and to compare them with the percentage mammographic density (PMD) by using a case-control study design.

Methods: A case-control study including 864 cases and 418… Mehr anzeigen

Introduction: Although mammographic density is an established risk factor for breast cancer, its use is limited in clinical practice because of a lack of automated and standardized measurement methods. The aims of this study were to evaluate a variety of automated texture features in mammograms as risk factors for breast cancer and to compare them with the percentage mammographic density (PMD) by using a case-control study design.

Methods: A case-control study including 864 cases and 418 controls was analyzed automatically. Four hundred seventy features were explored as possible risk factors for breast cancer. These included statistical features, moment-based features, spectral-energy features, and form-based features. An elaborate variable selection process using logistic regression analyses was performed to identify those features that were associated with case-control status. In addition, PMD was assessed and included in the regression model.

Results: Of the 470 image-analysis features explored, 46 remained in the final logistic regression model. An area under the curve of 0.79, with an odds ratio per standard deviation change of 2.88 (95% CI, 2.28 to 3.65), was obtained with validation data. Adding the PMD did not improve the final model.

Conclusions: Using texture features to predict the risk of breast cancer appears feasible. PMD did not show any additional value in this study. With regard to the features assessed, most of the analysis tools appeared to reflect mammographic density, although some features did not correlate with PMD. It remains to be investigated in larger case-control studies whether these features can contribute to increased prediction accuracy.
Weniger anzeigen

Interpreting images from fluorescence microscopy is often a time-consuming task with poor reproducibility. Various image processing routines that can help investigators evaluate the images are therefore useful. The critical aspect for a reliable automatic image analysis system is a robust segmentation algorithm that can perform accurate segmentation for different cell types. In this study, several image segmentation methods were therefore compared and evaluated in order to identify the most… Mehr anzeigen

Interpreting images from fluorescence microscopy is often a time-consuming task with poor reproducibility. Various image processing routines that can help investigators evaluate the images are therefore useful. The critical aspect for a reliable automatic image analysis system is a robust segmentation algorithm that can perform accurate segmentation for different cell types. In this study, several image segmentation methods were therefore compared and evaluated in order to identify the most appropriate segmentation schemes that are usable with little new parameterization and robustly with different types of fluorescence-stained cells for various biological and biomedical tasks. The study investigated, compared, and enhanced four different methods for segmentation of cultured epithelial cells. The maximum-intensity linking (MIL) method, an improved MIL, a watershed method, and an improved watershed method based on morphological reconstruction were used. Three manually annotated datasets consisting of 261, 817, and 1,333 HeLa or L929 cells were used to compare the different algorithms. The comparisons and evaluations showed that the segmentation performance of methods based on the watershed transform was significantly superior to the performance of the MIL method. The results also indicate that using morphological opening by reconstruction can improve the segmentation of cells stained with a marker that exhibits the dotted surface of cells.

Weniger anzeigen