RESUMEN
Quantitative evaluation of image segmentation algorithms is crucial in the field of bioimage analysis. The most common assessment scores, however, are often misinterpreted and multiple definitions coexist with the same name. Here we present the ambiguities of evaluation metrics for segmentation algorithms and show how these misinterpretations can alter leaderboards of influential competitions. We also propose guidelines for how the currently existing problems could be tackled.
Asunto(s)
Algoritmos , Procesamiento de Imagen Asistido por Computador , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
PURPOSE: Confocal Laser Endomicroscopy (CLE) is an imaging tool, that has demonstrated potential for intraoperative, real-time, non-invasive, microscopical assessment of surgical margins of oropharyngeal squamous cell carcinoma (OPSCC). However, interpreting CLE images remains challenging. This study investigates the application of OpenAI's Generative Pretrained Transformer (GPT) 4.0 with Vision capabilities for automated classification of CLE images in OPSCC. METHODS: CLE Images of histological confirmed SCC or healthy mucosa from a database of 12 809 CLE images from 5 patients with OPSCC were retrieved and anonymized. Using a training data set of 16 images, a validation set of 139 images, comprising SCC (83 images, 59.7%) and healthy normal mucosa (56 images, 40.3%) was classified using the application programming interface (API) of GPT4.0. The same set of images was also classified by CLE experts (two surgeons and one pathologist), who were blinded to the histology. Diagnostic metrics, the reliability of GPT and inter-rater reliability were assessed. RESULTS: Overall accuracy of the GPT model was 71.2%, the intra-rater agreement was κ = 0.837, indicating an almost perfect agreement across the three runs of GPT-generated results. Human experts achieved an accuracy of 88.5% with a substantial level of agreement (κ = 0.773). CONCLUSIONS: Though limited to a specific clinical framework, patient and image set, this study sheds light on some previously unexplored diagnostic capabilities of large language models using few-shot prompting. It suggests the model`s ability to extrapolate information and classify CLE images with minimal example data. Whether future versions of the model can achieve clinically relevant diagnostic accuracy, especially in uncurated data sets, remains to be investigated.
Asunto(s)
Neoplasias de Cabeza y Cuello , Humanos , Reproducibilidad de los Resultados , Microscopía Confocal/métodos , Carcinoma de Células Escamosas de Cabeza y Cuello , Rayos LáserRESUMEN
OBJECTIVES: Confocal laser endomicroscopy (CLE) is an optical method that enables microscopic visualization of oral mucosa. Previous studies have shown that it is possible to differentiate between physiological and malignant oral mucosa. However, differences in mucosal architecture were not taken into account. The objective was to map the different oral mucosal morphologies and to establish a "CLE map" of physiological mucosa as baseline for further application of this powerful technology. MATERIALS AND METHODS: The CLE database consisted of 27 patients. The following spots were examined: (1) upper lip (intraoral) (2) alveolar ridge (3) lateral tongue (4) floor of the mouth (5) hard palate (6) intercalary line. All sequences were examined by two CLE experts for morphological differences and video quality. RESULTS: Analysis revealed clear differences in image quality and possibility of depicting tissue morphologies between the various localizations of oral mucosa: imaging of the alveolar ridge and hard palate showed visually most discriminative tissue morphology. Labial mucosa was also visualized well using CLE. Here, typical morphological features such as uniform cells with regular intercellular gaps and vessels could be clearly depicted. Image generation and evaluation was particularly difficult in the area of the buccal mucosa, the lateral tongue and the floor of the mouth. CONCLUSION: A physiological "CLE map" for the entire oral cavity could be created for the first time. CLINICAL RELEVANCE: This will make it possible to take into account the existing physiological morphological features when differentiating between normal mucosa and oral squamous cell carcinoma in future work.
Asunto(s)
Microscopía Confocal , Mucosa Bucal , Humanos , Microscopía Confocal/métodos , Mucosa Bucal/diagnóstico por imagen , Mucosa Bucal/citología , Masculino , Femenino , Persona de Mediana Edad , Neoplasias de la Boca/patología , Neoplasias de la Boca/diagnóstico por imagenRESUMEN
Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training, n = 245 whole-slide images (WSIs), validation (n = 35 WSIs), and test sets (n = 70 WSIs). Full annotations included the 7 tumor classes and 6 normal skin structures. The data set was used to train a convolutional neural network (CNN) for the automatic segmentation of tumor and nontumor classes. Subsequently, the detected tumor regions were classified patch-wise into 1 of the 7 tumor classes. A majority of patches-approach led to a tumor classification accuracy of the network on the slide-level of 95% (133/140 WSIs), with a patch-level precision of 85%. The same 140 WSIs were provided to 6 experienced pathologists for diagnosis, who achieved a similar slide-level accuracy of 98% (137/140 correct majority votes). Our results highlight the feasibility of artificial intelligence-based methods as a support tool in diagnostic oncologic pathology with future applications in other species and tumor types.
Asunto(s)
Aprendizaje Profundo , Enfermedades de los Perros , Neoplasias Cutáneas , Animales , Perros , Inteligencia Artificial , Eosina Amarillenta-(YS) , Hematoxilina , Reproducibilidad de los Resultados , Neoplasias Cutáneas/diagnóstico , Neoplasias Cutáneas/veterinaria , Aprendizaje Automático , Enfermedades de los Perros/diagnósticoRESUMEN
Exercise-induced pulmonary hemorrhage (EIPH) is a relevant respiratory disease in sport horses, which can be diagnosed by examination of bronchoalveolar lavage fluid (BALF) cells using the total hemosiderin score (THS). The aim of this study was to evaluate the diagnostic accuracy and reproducibility of annotators and to validate a deep learning-based algorithm for the THS. Digitized cytological specimens stained for iron were prepared from 52 equine BALF samples. Ten annotators produced a THS for each slide according to published methods. The reference methods for comparing annotator's and algorithmic performance included a ground truth dataset, the mean annotators' THSs, and chemical iron measurements. Results of the study showed that annotators had marked interobserver variability of the THS, which was mostly due to a systematic error between annotators in grading the intracytoplasmatic hemosiderin content of individual macrophages. Regarding overall measurement error between the annotators, 87.7% of the variance could be reduced by using standardized grades based on the ground truth. The algorithm was highly consistent with the ground truth in assigning hemosiderin grades. Compared with the ground truth THS, annotators had an accuracy of diagnosing EIPH (THS of < or ≥ 75) of 75.7%, whereas, the algorithm had an accuracy of 92.3% with no relevant differences in correlation with chemical iron measurements. The results show that deep learning-based algorithms are useful for improving reproducibility and routine applicability of the THS. For THS by experts, a diagnostic uncertainty interval of 40 to 110 is proposed. THSs within this interval have insufficient reproducibility regarding the EIPH diagnosis.
Asunto(s)
Aprendizaje Profundo , Enfermedades de los Caballos , Enfermedades Pulmonares , Animales , Líquido del Lavado Bronquioalveolar , Hemorragia/diagnóstico , Hemorragia/veterinaria , Hemosiderina , Enfermedades de los Caballos/diagnóstico , Caballos , Hierro , Enfermedades Pulmonares/diagnóstico , Enfermedades Pulmonares/veterinaria , Reproducibilidad de los ResultadosRESUMEN
The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intraobserver discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying or classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, computer-assisted review by pathologists may ensure reliability. In the present study, we compared partial (MC-ROI preselection) and full (additional visualization of MF candidates and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole-slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MFs, and improving classification against imposters. The interobserver consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected hotspot MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38%. The results of this study demonstrate that computer assistance may lead to more reproducible and accurate MCs in ccMCTs.
Asunto(s)
Aprendizaje Profundo , Algoritmos , Animales , Inteligencia Artificial , Perros , Humanos , Patólogos , Reproducibilidad de los ResultadosRESUMEN
PURPOSE: Confocal laser endomicroscopy (CLE) allows surface imaging of the laryngeal and pharyngeal mucosa in vivo at a thousand-fold magnification. This study aims to compare irregular blood vessels and intraepithelial capillary loops in healthy mucosa and squamous cell carcinoma (SCC) via CLE. MATERIALS AND METHODS: We included ten patients with confirmed SCC and planned total laryngectomy in this study between March 2020 and February 2021. CLE images of these patients were collected and compared with the corresponding histology in hematoxylin and eosin staining. We analyzed the characteristic endomicroscopic patterns of blood vessels and intraepithelial capillary loops for the diagnosis of SCC. RESULTS: In a total of 54 sequences, we identified 243 blood vessels which were analyzed regarding structure, diameter, and Fluorescein leakage, confirming that irregular, corkscrew-like vessels (24.4% vs. 1.3%; P < .001), dilated intraepithelial capillary loops (90.8% vs. 28.7%; P < .001), and increased capillary leakage (40.7% vs. 2.5%; P < .001), are significantly more frequently detected in SCC compared to the healthy epithelium. We defined a vessel diameter of 30 µm in capillary loops as a cut-off value, obtaining a sensitivity, specificity, PPV, and NPV and accuracy of 90.6%, 71.3%, 57.4%, 94.7%, and 77.1%, respectively, for the detection of malignancy based solely on capillary architecture. CONCLUSION: Capillaries within malignant lesions are fundamentally different from those in healthy mucosa regions. The capillary architecture is a significant feature aiding the identification of malignant mucosa areas during in-vivo, real-time CLE examination.
Asunto(s)
Capilares , Neoplasias de Cabeza y Cuello , Capilares/diagnóstico por imagen , Humanos , Rayos Láser , Microscopía Confocal/métodos , Carcinoma de Células Escamosas de Cabeza y CuelloRESUMEN
PURPOSE: Confocal laser endomicroscopy (CLE) allows imaging of the laryngeal mucosa in a thousand-fold magnification. This study analyzes differences in tissue homogeneity between healthy mucosa and squamous cell carcinoma (SCC) via CLE. MATERIALS AND METHODS: We included five SCC patients with planned total laryngectomy in this study between October 2020 and February 2021. We captured CLE scans of the tumor and healthy mucosa. Analysis of image homogeneity to diagnose SCC was performed by measuring the signal intensity in four regions of interest (ROI) in each frame in a total of 60 sequences. Each sequence was assigned to the corresponding histological pattern, derived from hematoxylin and eosin staining. In addition, we recorded the subjective evaluation of seven investigators regarding tissue homogeneity. RESULTS: Out of 3600 images, 1620 (45%) correlated with benign mucosa and 1980 (55%) with SCC. ROIs of benign mucosa and SCC had a mean and standard deviation (SD) of signal intensity of, respectively, 232.1 ± 3.34 and 467.3 ± 9.72 (P < 0.001). The mean SD between the four different ROIs was 39.1 ± 1.03 for benign and 101.5 ± 2.6 for SCC frames (P < 0.001). In addition, homogeneity yielded a sensitivity and specificity of 81.8% and 86.2%, respectively, regarding the investigator-dependent analysis. CONCLUSIONS: SCC shows a significant tissue inhomogeneity in comparison to the healthy epithelium. The results support this feature's importance in identifying malignant mucosa areas during CLE examination. However, the examiner-dependent evaluation emphasizes that homogeneity is a sub-criterion that must be considered in a broad context.
Asunto(s)
Carcinoma de Células Escamosas , Neoplasias de Cabeza y Cuello , Carcinoma de Células Escamosas/diagnóstico por imagen , Carcinoma de Células Escamosas/patología , Humanos , Rayos Láser , Microscopía Confocal/métodos , Carcinoma de Células Escamosas de Cabeza y CuelloRESUMEN
Counting mitotic figures (MF) in hematoxylin and eosin-stained histologic sections is an integral part of the diagnostic pathologist's tumor evaluation. The mitotic count (MC) is used alone or as part of a grading scheme for assessment of prognosis and clinical decisions. Determining MCs is subjective, somewhat laborious, and has interobserver variation. Proposals for standardizing this parameter in the veterinary field are limited to terminology (use of the term MC) and area (MC is counted in an area measuring 2.37 mm2). Digital imaging techniques are now commonplace and widely used among veterinary pathologists, and field of view area can be easily calculated with digital imaging software. In addition to standardizing the methods of counting MF, the morphologic characteristics of MF and distinguishing atypical mitotic figures (AMF) versus mitotic-like figures (MLF) need to be defined. This article provides morphologic criteria for MF identification and for distinguishing normal phases of MF from AMF and MLF. Pertinent features of digital microscopy and application of computational pathology (CPATH) methods are discussed. Correct identification of MF will improve MC consistency, reproducibility, and accuracy obtained from manual (glass slide or whole-slide imaging) and CPATH approaches.
Asunto(s)
Programas Informáticos , Animales , Eosina Amarillenta-(YS) , Hematoxilina , Índice Mitótico/veterinaria , Reproducibilidad de los ResultadosRESUMEN
Standardization of tumor assessment lays the foundation for validation of grading systems, permits reproducibility of oncologic studies among investigators, and increases confidence in the significance of study results. Currently, there is minimal methodological standardization for assessing tumors in veterinary medicine, with few attempts to validate published protocols and grading schemes. The current article attempts to address these shortcomings by providing standard guidelines for tumor assessment parameters and protocols for evaluating specific tumor types. More detailed information is available in the Supplemental Files, the intention of which is 2-fold: publication as part of this commentary, but more importantly, these will be available as "living documents" on a website (www.vetcancerprotocols.org), which will be updated as new information is presented in the peer-reviewed literature. Our hope is that veterinary pathologists will agree that this initiative is needed, and will contribute to and utilize this information for routine diagnostic work and oncologic studies. Journal editors and reviewers can utilize checklists to ensure publications include sufficient detail and standardized methods of tumor assessment. To maintain the relevance of the guidelines and protocols, it is critical that the information is periodically updated and revised as new studies are published and validated with the intent of providing a repository of this information. Our hope is that this initiative (a continuation of efforts published in this journal in 2011) will facilitate collaboration and reproducibility between pathologists and institutions, increase case numbers, and strengthen clinical research findings, thus ensuring continued progress in veterinary oncologic pathology and improving patient care.
Asunto(s)
Neoplasias , Patología Veterinaria , Animales , Neoplasias/diagnóstico , Neoplasias/veterinaria , Reproducibilidad de los ResultadosRESUMEN
PURPOSE: This pilot study aimed to assess the feasibility of intraoperative assessment of safe margins with confocal laser endomicroscopy (CLE) during oropharyngeal squamous cell carcinoma (OPSCC) surgery. METHODS: We included five consecutive patients confirmed OPSCC and planned tumor resection in September and October 2020. Healthy appearing mucosa in the marginal zone, and the tumor margin, were examined with CLE and biopsy during tumor resection. A total of 12,809 CLE frames were correlated with the gold standard of hematoxylin and eosin staining. Three head and neck surgeons and one pathologist were asked to identify carcinoma in a sample of 169 representative images, blinded to the histological results. RESULTS: Healthy mucosa showed epithelium with uniform size and shape with distinct cytoplasmic membranes and regular vessel architecture. CLE optical biopsy of OPSCC demonstrated a disorganized arrangement of variable cellular morphology. We calculated an accuracy, sensitivity, specificity, PPV, and NPV of 86%, 90%, 79%, 88%, and 82%, respectively, with inter-rater reliability and κ-value of 0.60. CONCLUSION: CLE can be easily integrated into the intraoperative setting, generate real-time, in-vivo microscopic images of the oropharynx for evaluation and demarcation of cancer. It can eventually contribute to a less radical approach by enabling a more precise evaluation of the cancer margin.
Asunto(s)
Neoplasias de Cabeza y Cuello , Humanos , Rayos Láser , Microscopía Confocal , Proyectos Piloto , Reproducibilidad de los Resultados , Carcinoma de Células Escamosas de Cabeza y Cuello/diagnóstico por imagen , Carcinoma de Células Escamosas de Cabeza y Cuello/cirugíaRESUMEN
Mitotic count (MC) is an important element for grading canine cutaneous mast cell tumors (ccMCTs) and is determined in 10 consecutive high-power fields with the highest mitotic activity. However, there is variability in area selection between pathologists. In this study, the MC distribution and the effect of area selection on the MC were analyzed in ccMCTs. Two pathologists independently annotated all mitotic figures in whole-slide images of 28 ccMCTs (ground truth). Automated image analysis was used to examine the ground truth distribution of the MC throughout the tumor section area, which was compared with the manual MCs of 11 pathologists. Computerized analysis demonstrated high variability of the MC within different tumor areas. There were 6 MCTs with consistently low MCs (MC<7 in all tumor areas), 13 cases with mostly high MCs (MC ≥7 in ≥75% of 10 high-power field areas), and 9 borderline cases with variable MCs around 7, which is a cutoff value for ccMCT grading. There was inconsistency among pathologists in identifying the areas with the highest density of mitotic figures throughout the 3 ccMCT groups; only 51.9% of the counts were consistent with the highest 25% of the ground truth MC distribution. Regardless, there was substantial agreement between pathologists in detecting tumors with MC ≥7. Falsely low MCs below 7 mainly occurred in 4 of 9 borderline cases that had very few ground truth areas with MC ≥7. The findings of this study highlight the need to further standardize how to select the region of the tumor in which to determine the MC.
Asunto(s)
Enfermedades de los Perros/patología , Técnicas Histológicas/veterinaria , Neoplasias Cutáneas/veterinaria , Animales , Recuento de Células/veterinaria , Perros , Procesamiento de Imagen Asistido por Computador , Mastocitos/patología , Índice Mitótico/veterinaria , Clasificación del Tumor/veterinaria , Variaciones Dependientes del Observador , Patólogos , Neoplasias Cutáneas/patología , Programas InformáticosRESUMEN
OBJECTIVE: Confocal laser endomicroscopy (CLE) is an optical imaging technique that allows in vivo, real-time, microscope-like assessment of superficial lesions. Although there is substantial data on CLE use in the upper GI tract, there is limited information regarding its application in the nasal cavity and paranasal sinuses. This study aims to assess the feasibility and diagnostic metrics of CLE in the nasal cavity and paranasal sinuses regarding differentiation between healthy/benign and malignant tissue. These structures show, however, a wider variety of frequent and concomitant benign and malignant pathologies, which could pose an increased challenge for optical biopsy by CLE. METHODS: We performed CLE on a case series of six patients with various findings in the nose (three chronic rhinosinusitis, adenocarcinoma, meningoenzephalozele, esthesionneuroblastoma). Forty-two sequences (3792 images) from various structures in the nasal cavity and/or paranasal sinuses were acquired. Biopsies were taken at corresponding locations and analyzed in hematoxylin and eosin staining as a standard of reference. Three independent examiners blinded to the histopathology assessed the sequences. RESULTS: Healthy and inflamed mucosa could be distinguished from malignant lesions with an accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 84.1%, 85.4%, 83.1%, 72.5%, and 92.1%, respectively, with a substantial agreement between raters (Fleiss κ = 0.62). CONCLUSION: This technique shows, despite its limitations, potential as an adjunctive imaging technique during sinus surgery; however, the creation of a scoring system based on reproducible and defined characteristics in a larger more diverse population should be the focus of further research to improve its diagnostic value and clinical utility. LEVEL OF EVIDENCE: NA Laryngoscope, 2024.
RESUMEN
The integration of deep learning-based tools into diagnostic workflows is increasingly prevalent due to their efficiency and reproducibility in various settings. We investigated the utility of automated nuclear morphometry for assessing nuclear pleomorphism (NP), a criterion of malignancy in the current grading system in canine pulmonary carcinoma (cPC), and its prognostic implications. We developed a deep learning-based algorithm for evaluating NP (variation in size, i.e., anisokaryosis and/or shape) using a segmentation model. Its performance was evaluated on 46 cPC cases with comprehensive follow-up data regarding its accuracy in nuclear segmentation and its prognostic ability. Its assessment of NP was compared to manual morphometry and established prognostic tests (pathologists' NP estimates (n = 11), mitotic count, histological grading, and TNM-stage). The standard deviation (SD) of the nuclear area, indicative of anisokaryosis, exhibited good discriminatory ability for tumor-specific survival, with an area under the curve (AUC) of 0.80 and a hazard ratio (HR) of 3.38. The algorithm achieved values comparable to manual morphometry. In contrast, the pathologists' estimates of anisokaryosis resulted in HR values ranging from 0.86 to 34.8, with slight inter-observer reproducibility (k = 0.204). Other conventional tests had no significant prognostic value in our study cohort. Fully automated morphometry promises a time-efficient and reproducible assessment of NP with a high prognostic value. Further refinement of the algorithm, particularly to address undersegmentation, and application to a larger study population are required.
RESUMEN
Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking.
Asunto(s)
Laboratorios , Mitosis , Humanos , Animales , Gatos , Algoritmos , Procesamiento de Imagen Asistido por Computador/métodos , Estándares de ReferenciaRESUMEN
The success of immuno-oncology treatments promises long-term cancer remission for an increasing number of patients. The response to checkpoint inhibitor drugs has shown a correlation with the presence of immune cells in the tumor and tumor microenvironment. An in-depth understanding of the spatial localization of immune cells is therefore critical for understanding the tumor's immune landscape and predicting drug response. Computer-aided systems are well suited for efficiently quantifying immune cells in their spatial context. Conventional image analysis approaches are often based on color features and therefore require a high level of manual interaction. More robust image analysis methods based on deep learning are expected to decrease this reliance on human interaction and improve the reproducibility of immune cell scoring. However, these methods require sufficient training data and previous work has reported low robustness of these algorithms when they are tested on out-of-distribution data from different pathology labs or samples from different organs. In this work, we used a new image analysis pipeline to explicitly evaluate the robustness of marker-labeled lymphocyte quantification algorithms depending on the number of training samples before and after being transferred to a new tumor indication. For these experiments, we adapted the RetinaNet architecture for the task of T-lymphocyte detection and employed transfer learning to bridge the domain gap between tumor indications and reduce the annotation costs for unseen domains. On our test set, we achieved human-level performance for almost all tumor indications with an average precision of 0.74 in-domain and 0.72-0.74 cross-domain. From our results, we derive recommendations for model development regarding annotation extent, training sample selection, and label extraction for the development of robust algorithms for immune cell scoring. By extending the task of marker-labeled lymphocyte quantification to a multi-class detection task, the pre-requisite for subsequent analyses, e.g., distinguishing lymphocytes in the tumor stroma from tumor-infiltrating lymphocytes, is met.
RESUMEN
Histopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users' trust in computer-assisted image classification.
Asunto(s)
Enfermedades de los Gatos , Aprendizaje Profundo , Enfermedades de los Perros , Linfoma , Animales , Perros , Gatos , Inteligencia Artificial , Reproducibilidad de los Resultados , Enfermedades de los Gatos/diagnóstico por imagen , Enfermedades de los Perros/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Linfoma/diagnóstico por imagen , Linfoma/veterinariaRESUMEN
The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species.