Search

Simple Summary Pathology is a cornerstone in cancer diagnostics, and digital pathology and artificial intelligence-driven image analysis could potentially save time and enhance diagnostic accuracy. For clinical implementation of artificial intelligence, a major question is whether the computer models maintain high performance when applied to new settings. We tested the generalizability of a highly accurate deep learning model for breast cancer metastasis detection in sentinel lymph nodes from, firstly, unseen sentinel node data and, secondly, data with a small change in surgical indication, in this case lymph nodes from axillary dissections. Model performance dropped in both settings, particularly on axillary dissection nodes. Retraining of the model was needed to mitigate the performance drop. The study highlights the generalization challenge of clinical implementation of AI models, and the possibility that retraining might be necessary. Poor generalizability is a major barrier to clinical implementation of artificial intelligence in digital pathology. The aim of this study was to test the generalizability of a pretrained deep learning model to a new diagnostic setting and to a small change in surgical indication. A deep learning model for breast cancer metastases detection in sentinel lymph nodes, trained on CAMELYON multicenter data, was used as a base model, and achieved an AUC of 0.969 (95% CI 0.926-0.998) and FROC of 0.838 (95% CI 0.757-0.913) on CAMELYON16 test data. On local sentinel node data, the base model performance dropped to AUC 0.929 (95% CI 0.800-0.998) and FROC 0.744 (95% CI 0.566-0.912). On data with a change in surgical indication (axillary dissections) the base model performance indicated an even larger drop with a FROC of 0.503 (95%CI 0.201-0.911). The model was retrained with addition of local data, resulting in about a 4% increase for both AUC and FROC for sentinel nodes, and an increase of 11% in AUC and 49% in FROC for axillary nodes. Patho, Funding Agencies|Vinnova [2017-02447]

Automated detection of cancer metastases in lymph nodes has the potential to improve assessment of prognosis for patients. To enable fair comparison between the algorithms for this purpose, we set up the CAMELYON17 challenge in conjunction with the IEEE International Symposium on Biomedical Imaging 2017 conference in Melbourne. Over 300 participants registered on the challenge website, of which 23 teams submitted a total of 37 algorithms before the initial deadline. Participants were provided with 899 whole-slide images for developing their algorithms. The developed algorithms were evaluated based on the test set encompassing 100 patients and 500 whole-slide images. The evaluation metric used was a quadratic weighted Cohen’s kappa. We discuss the algorithmic details of the ten best pre-conference and two post-conference submissions. All these participants used convolutional neural networks in combination with pre-and postprocessing steps. Algorithms differed mostly in neural network architecture, training strategy and pre-and postprocessing methodology. Overall, the kappa metric ranged from 0.89 to -0.13 across all submissions. The best results were obtained with pre-trained architectures such as ResNet. Confusion matrix analysis revealed that all participants struggled with reliably identifying isolated tumor cells, the smallest type of metastasis, with detection rates below 40%. Qualitative inspection of the results of the top participants showed categories of false positives, such as nerves or contamination, which could be targets for further optimization. Last, we show that simple combinations of the top algorithms result in higher kappa metric values than any algorithm individually, with 0.93 for the best combination.

Táto bakalárska práca popisuje konštrukciu aktívnej zóny jadrového reaktora VVER 1000 a zaoberá sa spracovaním výsledkov z výpočtov neutrónového kódu PARCS v rozhraní SNAP. V dnešnej dobe je pri návrhu alebo zmenách na jadrovom reaktore dôležité vopred si overiť správanie budúceho nového alebo zmeneného zariadenia. Na to slúžia rôzne výpočtové programy určené špeciálne na tieto výpočty. Na prácu s nimi je ale potrebné rozumieť konštrukcii aktívnej zóny, aby používateľ vedel, čo sa počíta a porozumel výsledkom výpočtu. Tie môžu byť buď vo forme textových súborov, alebo je ich možné spracovať do podoby grafov alebo animácií pomocou rôznych aplikácií, v prípade tejto práce v rozhraní SNAP., This bachelor thesis describes core design of nuclear reactor VVER 1000 and deals with processing of results calculated by neutronics code PARCS in SNAP application suite. Nowadays, while designing or modifying nuclear reactor, it is very important to verify behavior of newly designed or modified parts in anticipation. For this purpose there are various computing programmes designed especially for these computations. However, to work with them is necessary to be familiar with the construction of the reactor core, because it is important to understand the results of the calculations. These can be shown either in form of text files or or processed into form of graphs and animations using various applications, in this case in SNAP application suite.

Táto bakalárska práca popisuje konštrukciu aktívnej zóny jadrového reaktora VVER 1000 a zaoberá sa spracovaním výsledkov z výpočtov neutrónového kódu PARCS v rozhraní SNAP. V dnešnej dobe je pri návrhu alebo zmenách na jadrovom reaktore dôležité vopred si overiť správanie budúceho nového alebo zmeneného zariadenia. Na to slúžia rôzne výpočtové programy určené špeciálne na tieto výpočty. Na prácu s nimi je ale potrebné rozumieť konštrukcii aktívnej zóny, aby používateľ vedel, čo sa počíta a porozumel výsledkom výpočtu. Tie môžu byť buď vo forme textových súborov, alebo je ich možné spracovať do podoby grafov alebo animácií pomocou rôznych aplikácií, v prípade tejto práce v rozhraní SNAP., This bachelor thesis describes core design of nuclear reactor VVER 1000 and deals with processing of results calculated by neutronics code PARCS in SNAP application suite. Nowadays, while designing or modifying nuclear reactor, it is very important to verify behavior of newly designed or modified parts in anticipation. For this purpose there are various computing programmes designed especially for these computations. However, to work with them is necessary to be familiar with the construction of the reactor core, because it is important to understand the results of the calculations. These can be shown either in form of text files or or processed into form of graphs and animations using various applications, in this case in SNAP application suite.

Táto bakalárska práca popisuje konštrukciu aktívnej zóny jadrového reaktora VVER 1000 a zaoberá sa spracovaním výsledkov z výpočtov neutrónového kódu PARCS v rozhraní SNAP. V dnešnej dobe je pri návrhu alebo zmenách na jadrovom reaktore dôležité vopred si overiť správanie budúceho nového alebo zmeneného zariadenia. Na to slúžia rôzne výpočtové programy určené špeciálne na tieto výpočty. Na prácu s nimi je ale potrebné rozumieť konštrukcii aktívnej zóny, aby používateľ vedel, čo sa počíta a porozumel výsledkom výpočtu. Tie môžu byť buď vo forme textových súborov, alebo je ich možné spracovať do podoby grafov alebo animácií pomocou rôznych aplikácií, v prípade tejto práce v rozhraní SNAP., This bachelor thesis describes core design of nuclear reactor VVER 1000 and deals with processing of results calculated by neutronics code PARCS in SNAP application suite. Nowadays, while designing or modifying nuclear reactor, it is very important to verify behavior of newly designed or modified parts in anticipation. For this purpose there are various computing programmes designed especially for these computations. However, to work with them is necessary to be familiar with the construction of the reactor core, because it is important to understand the results of the calculations. These can be shown either in form of text files or or processed into form of graphs and animations using various applications, in this case in SNAP application suite.

Táto bakalárska práca popisuje konštrukciu aktívnej zóny jadrového reaktora VVER 1000 a zaoberá sa spracovaním výsledkov z výpočtov neutrónového kódu PARCS v rozhraní SNAP. V dnešnej dobe je pri návrhu alebo zmenách na jadrovom reaktore dôležité vopred si overiť správanie budúceho nového alebo zmeneného zariadenia. Na to slúžia rôzne výpočtové programy určené špeciálne na tieto výpočty. Na prácu s nimi je ale potrebné rozumieť konštrukcii aktívnej zóny, aby používateľ vedel, čo sa počíta a porozumel výsledkom výpočtu. Tie môžu byť buď vo forme textových súborov, alebo je ich možné spracovať do podoby grafov alebo animácií pomocou rôznych aplikácií, v prípade tejto práce v rozhraní SNAP., This bachelor thesis describes core design of nuclear reactor VVER 1000 and deals with processing of results calculated by neutronics code PARCS in SNAP application suite. Nowadays, while designing or modifying nuclear reactor, it is very important to verify behavior of newly designed or modified parts in anticipation. For this purpose there are various computing programmes designed especially for these computations. However, to work with them is necessary to be familiar with the construction of the reactor core, because it is important to understand the results of the calculations. These can be shown either in form of text files or or processed into form of graphs and animations using various applications, in this case in SNAP application suite.

Diplomová práca je zameraná na tvorbu projektovej dokumentácie používanej v elektroenergetike, konkrétne tvorbu schém v oblasti sekundárnej techniky. Zaoberá sa základmi značenia používaného prevádzkovateľmi distribučných sústav v Českej republike, stupňami dokumentácie potrebnými pri výstavbe alebo rekonštrukcii samotných elektrických zariadení. Cieľom diplomovej práce navrhnúť rozvádzač ochrán dvomi projekčnými riešeniami s využitím dvoch rôznych typov softvérov. Použité softvéry budú Autocad LT ako zástupca CAD systému a Ruplan EVU ako CAE softvér. Na základe skúseností získaných pri projektovaní a vopred určených hľadísk určiť softvér vhodnejší pre projektovanie., The master’s thesis is aimed at creation of project documentation used in power engineering, specifically the creation of schemes in the field of secondary technology. It deals with the basics of marking used by distribution system operators in the Czech Republic, the levels of documentation necessary for the construction or reconstruction of the electrical equipment itself. The aim of this master’s thesis is to design the switchboard with two design solutions using two different types of software. Used software will be Autocad LT as a representative of the CAD system and Ruplan EVU as CAE software. Based on the experience gained in designing and pre-defined aspects, at the end of thesis determine software that is more suited to designing.