diff --git a/diag.bib b/diag.bib index bbd126e..aac6a2e 100644 --- a/diag.bib +++ b/diag.bib @@ -14028,21 +14028,20 @@ @article{Hänt24a gscites = {0}, } -@article{Höpp24, - author = {H\"{o}, - title = {Classifying histopathological growth patterns for resected colorectal liver metastasis with a deep learning analysis}, - doi = {10.1093/bjsopen/zrae127}, - year = {2024}, - abstract = {Abstract Background Histopathological growth patterns are one of the strongest prognostic factors in patients with resected colorectal liver metastases. Development of an efficient, objective and ideally automated histopathological growth pattern scoring method can substantially help the implementation of histopathological growth pattern assessment in daily practice and research. This study aimed to develop and validate a deep-learning algorithm, namely neural image compression, to distinguish desmoplastic from non-desmoplastic histopathological growth patterns of colorectal liver metastases based on digital haematoxylin and eosin-stained slides. Methods The algorithm was developed using digitalized whole-slide images obtained in a single-centre (Erasmus MC Cancer Institute, the Netherlands) cohort of patients who underwent first curative intent resection for colorectal liver metastases between January 2000 and February 2019. External validation was performed on whole-slide images of patients resected between October 2004 and December 2017 in another institution (Radboud University Medical Center, the Netherlands). The outcomes of interest were the automated classification of dichotomous hepatic growth patterns, distinguishing between desmoplastic hepatic growth pattern and non-desmoplatic growth pattern by a deep-learning model; secondary outcome was the correlation of these classifications with overall survival in the histopathology manual-assessed histopathological growth pattern and those assessed using neural image compression. Results Nine hundred and thirty-two patients, corresponding to 3.641 whole-slide images, were reviewed to develop the algorithm and 870 whole-slide images were used for external validation. Median follow-up for the development and the validation cohorts was 43 and 29 months respectively. The neural image compression approach achieved significant discriminatory power to classify 100% desmoplastic histopathological growth pattern with an area under the curve of 0.93 in the development cohort and 0.95 upon external validation. Both the histopathology manual-scored histopathological growth pattern and neural image compression-classified histopathological growth pattern achieved a similar multivariable hazard ratio for desmoplastic versus non-desmoplastic growth pattern in the development cohort (histopathology manual score: 0.63 versus neural image compression: 0.64) and in the validation cohort (histopathology manual score: 0.40 versus neural image compression: 0.48). Conclusions The neural image compression approach is suitable for pathology-based classification tasks of colorectal liver metastases.}, - url = {http://dx.doi.org/10.1093/bjsopen/zrae127}, - file = {Hopp24.pdf:pdf\\Hopp24.pdf:PDF}, - optnote = {DIAG, RADIOLOGY}, - journal = {BJS Open}, - automatic = {yes}, - all_ss_ids = {['1d7145807115961dc21da9e42128f12629934295']}, - volume = {8}, - ,}, - pmid = {39471410}, +@Article{Höpp24, + author = {H\"{o}ppener, Diederik J and Aswolinskiy, Witali and Qian, Zhen and Tellez, David and Nierop, Pieter M H and Starmans, Martijn and Nagtegaal, Iris D and Doukas, Michail and de Wilt, Johannes H W and Gr\"{u}nhagen, Dirk J and van der Laak, Jeroen A W M and Vermeulen, Peter and Ciompi, Francesco and Verhoef, Cornelis}, + title = {Classifying histopathological growth patterns for resected colorectal liver metastasis with a deep learning analysis}, + doi = {10.1093/bjsopen/zrae127}, + url = {http://dx.doi.org/10.1093/bjsopen/zrae127}, + volume = {8}, + abstract = {Abstract Background Histopathological growth patterns are one of the strongest prognostic factors in patients with resected colorectal liver metastases. Development of an efficient, objective and ideally automated histopathological growth pattern scoring method can substantially help the implementation of histopathological growth pattern assessment in daily practice and research. This study aimed to develop and validate a deep-learning algorithm, namely neural image compression, to distinguish desmoplastic from non-desmoplastic histopathological growth patterns of colorectal liver metastases based on digital haematoxylin and eosin-stained slides. Methods The algorithm was developed using digitalized whole-slide images obtained in a single-centre (Erasmus MC Cancer Institute, the Netherlands) cohort of patients who underwent first curative intent resection for colorectal liver metastases between January 2000 and February 2019. External validation was performed on whole-slide images of patients resected between October 2004 and December 2017 in another institution (Radboud University Medical Center, the Netherlands). The outcomes of interest were the automated classification of dichotomous hepatic growth patterns, distinguishing between desmoplastic hepatic growth pattern and non-desmoplatic growth pattern by a deep-learning model; secondary outcome was the correlation of these classifications with overall survival in the histopathology manual-assessed histopathological growth pattern and those assessed using neural image compression. Results Nine hundred and thirty-two patients, corresponding to 3.641 whole-slide images, were reviewed to develop the algorithm and 870 whole-slide images were used for external validation. Median follow-up for the development and the validation cohorts was 43 and 29 months respectively. The neural image compression approach achieved significant discriminatory power to classify 100% desmoplastic histopathological growth pattern with an area under the curve of 0.93 in the development cohort and 0.95 upon external validation. Both the histopathology manual-scored histopathological growth pattern and neural image compression-classified histopathological growth pattern achieved a similar multivariable hazard ratio for desmoplastic versus non-desmoplastic growth pattern in the development cohort (histopathology manual score: 0.63 versus neural image compression: 0.64) and in the validation cohort (histopathology manual score: 0.40 versus neural image compression: 0.48). Conclusions The neural image compression approach is suitable for pathology-based classification tasks of colorectal liver metastases.}, + all_ss_ids = {['1d7145807115961dc21da9e42128f12629934295']}, + automatic = {yes}, + file = {Hopp24.pdf:pdf\\Hopp24.pdf:PDF}, + journal = {BJS Open}, + optnote = {DIAG, RADIOLOGY}, + pmid = {39471410}, + year = {2024}, } @article{Igle09, @@ -14065,20 +14064,21 @@ @article{Igle09 all_ss_ids = {['b5efadc7ed85042a5af820dfc430993a08ba00af']}, } -@article{Ilié24, - author = {Ili\'{e}, - title = {Standardization through education of molecular pathology: a spotlight on the European Masters in Molecular Pathology}, - doi = {10.1007/s00428-024-03933-2}, - year = {2024}, - abstract = {Despite advancements in precision medicine, many cancer patients globally, particularly those in resource-constrained environments, face significant challenges in accessing high-quality molecular testing and targeted therapies. The considerable heterogeneity in molecular testing highlights the urgent need to harmonize practices across Europe and beyond, establishing a more standardized and consistent approach in MP laboratories. Professionals, especially molecular pathologists, must move beyond traditional education to cope with this heterogeneity. This perspective addresses critical issues in molecular pathology (MP), such as limited access to high-quality molecular testing, leading to disparities in cancer treatment, and the consequences of inconsistent practices. Recognizing the necessity for a standardized framework for education to address these issues, educational programs play a pivotal role in updating professionals' skills to achieve standardization in MP. European experts from the Steering Committee, the Pathology Section of the European Union of Medical Specialists, and the European Society of Pathology have proposed creating a comprehensive Master's degree program called the "European Masters in Molecular Pathology" (EMMP). This program emerges as a strategic response to the demand for a specialized and standardized framework for education in MP, catering to professionals who concurrently work and study. The program's design aligns with evidence-based education methods, ensuring effective learning and engagement while integrating computational pathology to analyze complex molecular data, enhance diagnostic accuracy, and improve treatment outcomes. EMMP's structured curriculum, strategic partnerships, and regular updates underscore its significance in standardizing MP practices. Exploring future developments, this perspective delves into technology integration and interdisciplinary collaboration, anticipating ongoing advances and harmonization. Challenges and future directions in MP education are discussed, emphasizing the necessity for dynamic curriculum updates, seamless technology integration, and interdisciplinary cooperation. This perspective underscores EMMP's pivotal role in preparing pathologists for this dynamic field, advocating continuous advancements in education and training to uphold excellence in MP practices and maintain the highest patient care standards.}, - url = {http://dx.doi.org/10.1007/s00428-024-03933-2}, - file = {Ilie24.pdf:pdf\\Ilie24.pdf:PDF}, - optnote = {DIAG, RADIOLOGY}, - journal = {Virchows Archiv}, - automatic = {yes}, - all_ss_ids = {['2fdd3b9f1bd87dddab7f7c090673e653608cfb1f']}, - ,}, - pmid = {39354109}, +@Article{Ilié24, + author = {Ili\'{e}, Marius and Lake, Vivien and de Alava, Enrique and Bonin, Serena and Chlebowski, Sandra and Delort, Aur\'{e}lie and Dequeker, Elisabeth and Al-Dieri, Raed and Diepstra, Arjan and Carp\'{e}n, Olli and Eloy, Catarina and Fassina, Ambrogio and Fend, Falko and Fernandez, Pedro L. and Gorkiewicz, Gregor and Heeke, Simon and Henrique, Rui and Hoefler, Gerald and Huertas, Pablo and Hummel, Michael and Kashofer, Karl and van der Laak, Jeroen and de Pablos, Rocio Martinez and Schmitt, Fernando and Schuuring, Ed and Stanta, Giorgio and Timens, Wim and Westphalen, Benedikt and Hofman, Paul}, + title = {Standardization through education of molecular pathology: a spotlight on the European Masters in Molecular Pathology}, + doi = {10.1007/s00428-024-03933-2}, + pages = {761-775}, + url = {http://dx.doi.org/10.1007/s00428-024-03933-2}, + volume = {485}, + abstract = {Despite advancements in precision medicine, many cancer patients globally, particularly those in resource-constrained environments, face significant challenges in accessing high-quality molecular testing and targeted therapies. The considerable heterogeneity in molecular testing highlights the urgent need to harmonize practices across Europe and beyond, establishing a more standardized and consistent approach in MP laboratories. Professionals, especially molecular pathologists, must move beyond traditional education to cope with this heterogeneity. This perspective addresses critical issues in molecular pathology (MP), such as limited access to high-quality molecular testing, leading to disparities in cancer treatment, and the consequences of inconsistent practices. Recognizing the necessity for a standardized framework for education to address these issues, educational programs play a pivotal role in updating professionals� skills to achieve standardization in MP. European experts from the Steering Committee, the Pathology Section of the European Union of Medical Specialists, and the European Society of Pathology have proposed creating a comprehensive Master�s degree program called the �European Masters in Molecular Pathology� (EMMP). This program emerges as a strategic response to the demand for a specialized and standardized framework for education in MP, catering to professionals who concurrently work and study. The program�s design aligns with evidence-based education methods, ensuring effective learning and engagement while integrating computational pathology to analyze complex molecular data, enhance diagnostic accuracy, and improve treatment outcomes. EMMP�s structured curriculum, strategic partnerships, and regular updates underscore its significance in standardizing MP practices. Exploring future developments, this perspective delves into technology integration and interdisciplinary collaboration, anticipating ongoing advances and harmonization. Challenges and future directions in MP education are discussed, emphasizing the necessity for dynamic curriculum updates, seamless technology integration, and interdisciplinary cooperation. This perspective underscores EMMP�s pivotal role in preparing pathologists for this dynamic field, advocating continuous advancements in education and training to uphold excellence in MP practices and maintain the highest patient care standards.}, + all_ss_ids = {['']}, + automatic = {yes}, + citation-count = {0}, + file = {Ili�24a.pdf:pdf\\Ili�24a.pdf:PDF}, + journal = {Virchows Archiv}, + optnote = {DIAG, RADIOLOGY}, + year = {2024}, } @article{Isgu03, @@ -23721,21 +23721,20 @@ @article{Nist24 year = {2024}, } -@article{Nist24a, - author = {van Nistelrooij, Niels and Chaves, Eduardo Trota and Cenci, Maximiliano Sergio and Cao, Lingyun and Loomans, Bas A.C. and Xi, Tong and El-Ghoul, Khalid and Romero, Vitor Henrique Digmayer and Lima, Giana Silveira and Fl\"{u}, - title = {Deep learning-based algorithm for staging secondary caries in bitewings}, - doi = {10.1159/000542289}, - year = {2024}, - abstract = {Introduction: Despite the notable progress in developing artificial intelligence (AI)-based tools for caries detection in bitewings, limited research has addressed the detection and staging of secondary caries. Therefore, we aimed to develop a Convolutional neural network (CNN)-based algorithm for these purposes using a novel approach for determining lesion severity. Methods: We used a dataset from a Dutch dental practice-based research network containing 2,612 restored teeth in 413 bitewings from 383 patients aged 15 to 88 years and trained the Mask R-CNN architecture with a Swin Transformer backbone. Two-stage training fine-tuned caries detection accuracy and severity assessment. Annotations of caries around restorations were made by two evaluators and checked by two other experts. Aggregated accuracy metrics (mean +- Standard Deviation - SD) in detecting teeth with secondary caries were calculated considering two thresholds: detecting all lesions and dentine lesions. The correlation between the lesion severity scores obtained with the algorithm and the annotators' consensus was determined using the Pearson correlation coefficient and Bland-Altman plots. Results: Our refined algorithm showed high specificity in detecting all lesions (0.966 +- 0.025) and dentine lesions (0.964 +- 0.019). Sensitivity values were lower: 0.737 +- 0.079 for all lesions and 0.808 +- 0.083 for dentine lesions. The areas under ROC curves (SD) were 0.940 (0.025) for all lesions and 0.946 (0.023) for dentine lesions. The correlation coefficient for severity scores was 0.802. Conclusion: We developed an improved algorithm to support clinicians in detecting and staging secondary caries in bitewing, incorporating an innovative approach for annotation, considering the lesion severity as a continuous outcome.}, - url = {http://dx.doi.org/10.1159/000542289}, - file = {Nist24a.pdf:pdf\\Nist24a.pdf:PDF}, - optnote = {DIAG, RADIOLOGY}, - journal = {Caries Research}, - automatic = {yes}, - all_ss_ids = {['281ba311f4b859d9b05f0107f456cc84d1b0d87b']}, - pages = {1-21}, - ,}, - pmid = {39471790}, +@Article{Nist24a, + author = {van Nistelrooij, Niels and Chaves, Eduardo Trota and Cenci, Maximiliano Sergio and Cao, Lingyun and Loomans, Bas A.C. and Xi, Tong and El-Ghoul, Khalid and Romero, Vitor Henrique Digmayer and Lima, Giana Silveira and Fl\"{u}gge, Tabea and van Ginneken, Bram and Huysmans, Marie-Charlotte and Vinayahalingam, Shankeeth and Mendes, Fausto Medeiros}, + title = {Deep learning-based algorithm for staging secondary caries in bitewings}, + doi = {10.1159/000542289}, + pages = {1-21}, + url = {http://dx.doi.org/10.1159/000542289}, + abstract = {Introduction: Despite the notable progress in developing artificial intelligence (AI)-based tools for caries detection in bitewings, limited research has addressed the detection and staging of secondary caries. Therefore, we aimed to develop a Convolutional neural network (CNN)-based algorithm for these purposes using a novel approach for determining lesion severity. Methods: We used a dataset from a Dutch dental practice-based research network containing 2,612 restored teeth in 413 bitewings from 383 patients aged 15 to 88 years and trained the Mask R-CNN architecture with a Swin Transformer backbone. Two-stage training fine-tuned caries detection accuracy and severity assessment. Annotations of caries around restorations were made by two evaluators and checked by two other experts. Aggregated accuracy metrics (mean � Standard Deviation - SD) in detecting teeth with secondary caries were calculated considering two thresholds: detecting all lesions and dentine lesions. The correlation between the lesion severity scores obtained with the algorithm and the annotators� consensus was determined using the Pearson correlation coefficient and Bland-Altman plots. Results: Our refined algorithm showed high specificity in detecting all lesions (0.966 � 0.025) and dentine lesions (0.964 � 0.019). Sensitivity values were lower: 0.737 � 0.079 for all lesions and 0.808 � 0.083 for dentine lesions. The areas under ROC curves (SD) were 0.940 (0.025) for all lesions and 0.946 (0.023) for dentine lesions. The correlation coefficient for severity scores was 0.802. Conclusion: We developed an improved algorithm to support clinicians in detecting and staging secondary caries in bitewing, incorporating an innovative approach for annotation, considering the lesion severity as a continuous outcome.}, + all_ss_ids = {['']}, + automatic = {yes}, + citation-count = {0}, + file = {Nist24b.pdf:pdf\\Nist24b.pdf:PDF}, + journal = {Caries Research}, + optnote = {DIAG, RADIOLOGY}, + year = {2024}, } @article{Noor19, @@ -32714,20 +32713,19 @@ @conference{Twil23c optnote = {DIAG, RADIOLOGY}, } -@article{Twil24, - author = {Twilt, Jasper J. and Saha, Anindo and Bosma, Joeran S. and van Ginneken, Bram and Bjartell, Anders and Padhani, Anwar R. and Bonekamp, David and Villeirs, Geert and Salomon, Georg and Giannarini, Gianluca and Kalpathy-Cramer, Jayashree and Barentsz, Jelle and Maier-Hein, Klaus H. and Rusu, Mirabela and Rouvi\`{e}, - title = {Evaluating Biparametric Versus Multiparametric Magnetic Resonance Imaging for Diagnosing Clinically Significant Prostate Cancer: An International, Paired, Noninferiority, Confirmatory Observer Study}, - doi = {10.1016/j.eururo.2024.09.035}, - year = {2024}, - abstract = {Abstract unavailable}, - url = {http://dx.doi.org/10.1016/j.eururo.2024.09.035}, - file = {Twil24.pdf:pdf\\Twil24.pdf:PDF}, - optnote = {DIAG, RADIOLOGY}, - journal = {European Urology}, - automatic = {yes}, - all_ss_ids = {['cbf45a7e21376e31b51488b84c421932c85bb3fc']}, - ,}, - pmid = {39438187}, +@Article{Twil24, + author = {Twilt, Jasper J. and Saha, Anindo and Bosma, Joeran S. and van Ginneken, Bram and Bjartell, Anders and Padhani, Anwar R. and Bonekamp, David and Villeirs, Geert and Salomon, Georg and Giannarini, Gianluca and Kalpathy-Cramer, Jayashree and Barentsz, Jelle and Maier-Hein, Klaus H. and Rusu, Mirabela and Rouvi\`{e}}, + title = {Evaluating Biparametric Versus Multiparametric Magnetic Resonance Imaging for Diagnosing Clinically Significant Prostate Cancer: An International, Paired, Noninferiority, Confirmatory Observer Study}, + doi = {10.1016/j.eururo.2024.09.035}, + url = {http://dx.doi.org/10.1016/j.eururo.2024.09.035}, + abstract = {Abstract unavailable}, + all_ss_ids = {['cbf45a7e21376e31b51488b84c421932c85bb3fc']}, + automatic = {yes}, + file = {Twil24.pdf:pdf\\Twil24.pdf:PDF}, + journal = {European Urology}, + optnote = {DIAG, RADIOLOGY}, + pmid = {39438187}, + year = {2024}, } @conference{Uden15, diff --git a/scripts/bib_handling_code/processbib.py b/scripts/bib_handling_code/processbib.py index 68be453..9c0ea6c 100644 --- a/scripts/bib_handling_code/processbib.py +++ b/scripts/bib_handling_code/processbib.py @@ -268,15 +268,14 @@ def read_bibfile(filename, full_path=None): fp.close() return entries - def parse_bibtex_string(bibtex_string: str) -> BibEntry: # Create a new BibEntry instance bib_entry = BibEntry() - # Remove newline characters for easier parsing - bibtex_string = bibtex_string.replace("\n", " ").strip() + # Remove leading/trailing spaces and ensure proper formatting + bibtex_string = bibtex_string.strip() - # Use regex to extract the BibTeX entry type (e.g., article) and key (e.g., Jurg24a) + # Use regex to extract the BibTeX entry type (e.g., article) and key (e.g., Hopp24a) type_and_key_match = re.match(r"@(\w+)\{([^,]+),", bibtex_string) if not type_and_key_match: raise ValueError("Invalid BibTeX entry format") @@ -287,13 +286,37 @@ def parse_bibtex_string(bibtex_string: str) -> BibEntry: # Now we remove the entry type and key from the string, leaving just the fields fields_string = bibtex_string[type_and_key_match.end():].strip() - # Extract individual fields using a regex - field_matches = re.findall(r"(\w+)\s*=\s*\{([^}]+)\}", fields_string) - - # Populate the BibEntry fields - for field, value in field_matches: - value = unidecode(value.strip()) # Ensure values are properly formatted - bib_entry.fields[field.strip().lower()] = f"{{{value}}}" + # A recursive function to parse fields with nested braces + def parse_fields(fields_str): + fields = {} + stack = [] + key, value, brace_level = None, "", 0 + + for i, char in enumerate(fields_str): + if char == "=" and brace_level == 0 and not key: + key = fields_str[:i].strip() # Capture the key + stack.append("=") + elif char == "{" and stack and stack[-1] == "=": + brace_level += 1 + value += char + elif char == "}": + brace_level -= 1 + value += char + if brace_level == 0: + fields[key] = value.strip() + stack.pop() # Remove "=" + remainder = fields_str[i + 1:].lstrip(", ") + if remainder: + fields.update(parse_fields(remainder)) # Parse the remaining fields + break + elif brace_level > 0: + value += char + + return fields + + # Extract individual fields, properly handling nested braces + fields = parse_fields(fields_string) + bib_entry.fields = {k.strip().lower(): v.strip() for k, v in fields.items()} return bib_entry